Recognizing highly occluded objects is believed to arises from the interaction between the brain's vision and cognition controlling areas, although supporting neuroimaging data is currently limited. To explore the neural mechanism during this activity, we conducted an occlusion object recognition experiment using functional magnetic resonance imaging (fMRI). During magnet resonance examinations, 66 subjects engaged in object recognition tasks with three different occlusion degrees. Generalized linear model (GLM) analysis showed that the activation degree of occipital lobe (inferior occipital gyrus, middle occipital gyrus, and occipital fusiform gyrus) and dorsal anterior cingulate cortex (dACC) was related to the occlusion degree of the objects. Multivariate pattern analysis (MVPA) further unearthed a considerable surge in classification precision when dACC activation was incorporated as a feature. This suggested the combined role of dACC and occipital lobe in occluded object recognition tasks. Moreover, psychophysiological interaction (PPI) analysis disclosed that functional connectivity (FC) between the dACC and the occipital lobe was enhanced with increased occlusion, highlighting the necessity of FC between these two brain regions in effectively identifying exceedingly occluded objects. In conclusion, these findings contribute to understanding the neural mechanisms of highly occluded objects recognition, augmenting our appreciation of how the brain manages incomplete visual data.

Indoor scene recognition and semantic information can be helpful for social robots. Recently, in the field of indoor scene recognition, researchers have incorporated object-level information and shown improved performances. This paper demonstrates that scene recognition can be performed solely using object-level information in line with these advances. A state-of-the-art object detection model was trained to detect objects typically found in indoor environments and then used to detect objects in scene data. These predicted objects were then used as features to predict room categories. This paper successfully combines approaches conventionally used in computer vision (YOLO) and Term Frequency-Inverse Document Frequency (TF-IDF). These approaches could be further helpful in the field of embodied research and dynamic scene classification, which we elaborate on.

In the context of Shared Autonomous Vehicles, the need to monitor the environment inside the car will be crucial. This article focuses on the application of deep learning algorithms to detect objects, namely lost/forgotten items to inform the passengers, and aggressive items to monitoring if violent actions may arise between passengers. For object detection algorithms was used public datasets (COCO and TAO) to train state-of-the-art algorithms, such as YOLOv5. For violent action detection was used the MoLa InCar dataset to train on state-of-the-art algorithms such as I3D, R(2+1)D, SlowFast, TSN and TSM. At the end an embedded automotive solution was used to demonstrate both methods running in real-time.

A single water pollution by dyes is a huge environmental problem; there is a necessity to produce new decolorization methods that are effective, cost-attractive, and suitable in industrial use. Magnetic chitosan polymers offer the advantage of easy separation from the dye solution. In this work, a Chitosan-Fe polymer was synthesized, characterized, and tested for removal of the azo dye Direct Red 83:1 from water. The polymer was characterized in terms of surface morphology (SEM), elemental analysis (EA), differential scanning calorimetry (DSC), thermal gravimetric analysis (TGA), infrared spectrophotometry (IR), X-ray powder diffraction (XRD) and density functional theory (DFT). The reported results hint that 1 g and pH 7.0 were the best conditions to carry out both kinetic and isotherm models. To understand the adsorption behavior of Direct Red 83:1 onto the polymers, adsorption rate and maximum adsorption capacity were calculated using kinetic tests and isotherm curves respectively. The kinetic data and mechanism of the adsorption process were analyzed by three models and the equilibrium data by three adsorption isotherms. The results indicated that the adsorption process follows a pseudo-second-order kinetics (R2= 0.999) and fits the Temkin isotherm (R2= 0.946), indicating that the adsorption occurred on heterogeneous surfaces. The newly synthesized Chitosan-Fe polymer exhibited good adsorption properties and easy separation of cleaned water.

This paper provides a methodology for the production of synthetic images for training neural networks to recognise shapes and objects. There are many scenarios in which it is difficult, expensive and even dangerous to produce a set of images that is satisfactory for the training of a neural network. The development of 3D modelling software has nowadays reached such a level of realism and ease of use that it seemed natural to explore this innovative path and to give an answer regarding the reliability of this method that bases the training of the neural network on synthetic images. The results obtained in the two proposed use cases, that of the recognition of a pictorial style and that of the recognition of migrants at sea, leads us to support the validity of the approach, provided that the work is conducted in a very scrupulous and rigorous manner, exploiting the full potential of the modelling software. The code produced, which automatically generates the transformations necessary for the data augmentation of each image, and the generation of random environmental conditions in the case of Blender and Unity3D software, is available under the GPL licence on GitHub. The results obtained lead us to affirm that through the good practices presented in the article, we have defined a simple, reliable, economic and safe method to feed the training phase of a neural network dedicated to the recognition of objects and features, to be applied to various contexts.

The objective of person re-identification (ReID) tasks is to match a specific individual across different times, locations, or camera viewpoints. The prevalent issue of occlusion in real-world scenarios affects image information, rendering the affected features unreliable. The difficulty and core challenge lie in how to effectively discern and extract visual features from human images under various complex conditions, including cluttered backgrounds, diverse postures, and the presence of occlusions. Some works have employed pose estimation or human keypoint detection to construct graph-structured information to counteract the effects of occlusions. However, this approach introduces new noise due to issues such as the invisibility of keypoints. Our proposed module, in contrast, does not require the use of additional feature extractors. Our module employs multi-scale graph attention for the reweighting of feature importance. This allows features to concentrate on areas genuinely pertinent to the re-identification task, thereby enhancing the model's robustness against occlusions. To address these problems, a model that employs multi-scale graph attention to re-weight the importance of features is proposed in this study, significantly enhancing the model’s robustness against occlusions. Our experimental results demonstrate that, compared to baseline models, the method proposed herein achieves a notable improvement in mAP on occluded data sets, with increases of 0.5%, 31.5%, and 12.3% in mAP scores.

RFID based technology innovated a new field of wireless sensing, which has been applied in posture recognition, object localization and the other sensing fields, the existing sensing methods often require tags to be attached to dynamic targets (because RFID signals are more sensitive to moving target), significantly limiting their applications. It is a challenging task to sensing a static target without tag attached in NLOS (Non-Line-of-Sight). We utilized RFID technologies to sense the static foreign objects in agricultural products, and taken metal, rock, rubber and clod as sensing targets that are common in agricultural. By deploying a tag matrices to create a sensing region, we observed the signal variations before and after the appearance of the targets in this sensing region, determined the targets’ positions and their types. Here, we buried the targets in the media of seedless cotton and wheat, and detected static targets with a non-contact method in the NLOS. Researches illustrated that by deploying appropriate tag matrices and adjusting the angle of a single RFID antenna, the matrices signals can be sensitive to the static targets’ positions and their properties,i.e. matrices signals vary with different targets and their positions. Specifically, we achieved a 100% success rate in locating metallic targets, while the success rate for clods was the lowest at 86%. We achieved a 100% recognition rate for the types of all the four objects.

A major challenge of augmented and mixed reality applications is identifying the context and semantics of the real environment. Studies on object and action recognition were developed based on the improvement of machine learning techniques, allowing them to be annotated and recognized. This study aims to characterize current knowledge on the use of machine learning for recognizing objects and actions in augmented and mixed reality environments, increasing context awareness. Therefore, a systematic literature review of works related to these topics was made, using the Scopus and Web of Science knowledge bases. We searched articles and conference reviews or papers published between 2018 and 2022 and selected fifteen studies to be reviewed. The results indicate that there is a great demand for using machine learning to immersive technologies in factories, engineering, entertainment, education, health, among other application domains. However, these real-time interactive systems still have challenges and limitations to be solved, involving network communication, prediction time and the creation of a model that recognize objects and actions in broad contexts. Furthermore, additional research is needed to investigate how object and action recognition can increase context awareness in augmented reality applications.

Recent advancements in Artificial Intelligence (AI), Deep Learning (DL), and computer vision have revolutionized various industrial processes through image classification and object detection. State-of-the-art Optical Character Recognition (OCR) and Object Detection (OD) technologies, such as YOLO and PaddleOCR, have emerged as powerful solutions for addressing challenges in recognizing textual and non-textual information on printed stickers. However, a well-established framework integrating these cutting-edge technologies for industrial applications still needs to be discovered. In this paper, we propose an innovative framework that combines advanced OCR and OD techniques to automate visual inspection processes in an industrial context. Our primary contribution is a comprehensive framework adept at detecting and recognizing textual and non-textual information on printed stickers within a company, harnessing the latest AI tools and technologies for sticker information recognition. Our experiments reveal an overall macro accuracy of 0.88 for the sticker OCR across three distinct patterns. Furthermore, the proposed system goes beyond traditional Printed Character Recognition (PCR) by extracting supplementary information, such as barcodes and QR codes present in the image, significantly streamlining industrial workflows and minimizing manual labor demands.

Detecting small objects in images poses significant challenges due to their limited pixel representation and the difficulty in extracting sufficient features, often leading to missed or false detections. To address these challenges and enhance detection accuracy, this paper presents an improved small object detection algorithm, CRL-YOLOv5. The proposed approach integrates the CBAM attention mechanism into the C3 module of the backbone network, which enhances the localization accuracy of small objects. Additionally, the Receptive Field Block (RFB) module is introduced to expand the model's receptive field, thereby fully leveraging contextual information. Furthermore, the network architecture is restructured to include an additional detection layer specifically for small objects, allowing for deeper feature extraction from shallow layers. When tested on the VisDrone2019 small object dataset, CRL-YOLOv5 achieved an mAP50 of 39.2%, representing a 5.4% improvement over the original YOLOv5, effectively boosting the detection precision for small objects in images.

Fine-grained image classification remains an ongoing challenge in the computer vision field, which is particularly intended to identify objects within sub-categories. It is a difficult task since there is a minimal and substantial intra-class variance. The current methods address the issue by first locating selective regions with Region Proposal Networks (RPN), object localization, or part localization, followed by implementing a CNN Network or SVM classifier to those selective regions. This approach, however, makes the process simple by implementing a single-stage end-to-end feature encoding with a localization method, which leads to improved feature representations of individual tokens/regions by integrating the transformer encoder blocks into the Yolov5 backbone structure. These Transformer Encoder Blocks, with their self-attention mechanism, effectively captured the global dependencies and enabled the model to learn relationships between distant regions. This improved the model ability to understand context and captured long-range spatial relationships in the image. We also replaced the Yolov5 detection heads with three transformer heads at the output for object recognition using the discriminative and informative features maps from transformer encoder blocks. We established the potential of the single stage detector for the fine-grained image recognition task, by achieving state of the art 93.4% accuracy, as well as outperforming the existing Yolov5 model. The effectiveness of our approach is assessed using the Stanford car dataset, which includes 16,185 images of 196 different classes of vehicles with significantly identical visual appearances.

All types of sports are potential application scenarios for automatic and real-time visual object and event detection. In rink hockey, the popular roller quad skate variant of hockey team sports, it is of great interest to automatically track player’s movements and positions, player’s sticks and, also, making other judgments, such as being able to locate the ball. In this work, we introduce a real-time pipeline composed by an object detection model, created specifically for rink hockey games, followed by a knowledge-based event detection module. Even in the presence of occlusions and quick motions, our deep learning object detection model effectively identifies and tracks, in real-time, important visual elements such as: ball; players; sticks; referees; crowd; goalkeeper; and goal. Using a curated dataset composed by a collection of videos of rink hockey, comprising 2525 annotated frames, we trained and evaluated the algorithm performance and compare it to state of the art object detection techniques. Our object detection model, based on YOLOv7, presents a global accuracy of 80%, and presents a good performance in terms of accuracy and speed, according to our results, making it a good choice for rink hockey applications. In our initial tests, the event detection module successfully detected one important event type in rink hockey games, the occurrence of penalties.

With the increasing demand for security surveillance, assisted driving, and remote sensing, target detection networks with rich environmental perception capabilities and high detection accuracy have become a research hotspot. However, detection techniques based on single-modality images face limitations in environmental adaptability, as they are easily affected by lighting conditions, as well as obstacles such as smoke, rain, and vegetation, leading to information loss and failing to meet the required accuracy. To address these issues, we propose a target detection network—IV-YOLO, which integrates features from both visible and infrared images. We built a dual-branch fusion network based on YOLOv8 (You Only Look Once v8) that combines infrared and visible images for target detection. On this foundation, we designed a Bidirectional Pyramid Feature Fusion structure (Bi-Fusion) to fully integrate complementary features from different modalities, reducing detection errors caused by feature redundancy and extracting fine-grained features of small targets through dual-modal fusion. Additionally, we developed the Shuffle-SPP structure, which combines channel and spatial attention mechanisms to enhance focus on deep features and further aggregate upsampling, extracting richer features. To improve the model’s expressive power, we designed a loss function tailored for multi-scale target detection boxes, accelerating the network’s convergence during training. Experimental results show that the proposed IV-YOLO network achieves an average precision (mAP) of 74.6% on the UAV remote sensing dataset, 75.4% on the KAIST pedestrian dataset, and 84.8% on the FLIR dataset. While ensuring detection accuracy, our model significantly reduces computational load, making it well-suited to meet real-time requirements. This architecture is expected to find broad application in fields such as autonomous driving, public safety, and others.

The use of autonomous Unmanned Aerial Vehicles (UAVs) has been increasing, and the autonomy of these systems and their capabilities in dealing with uncertainties is crucial. Autonomous landing is pivotal for the success of an autonomous mission of UAVs. This paper presents an autonomous landing system for quadrotor UAVs with the ability to perform smooth landing even in undesirable conditions like obstruction by obstacles in and around the designated landing area and inability to identify or the absence of a visual marker establishing the designated landing area. We have integrated algorithms like version 5 of You Only Look Once (YOLOv5), DeepSORT, Euclidean distance transform, and Proportional-Integral-Derivative (PID) controller to strengthen the robustness of the overall system. While the YOLOv5 model is trained to identify the visual marker of the landing area and some common obstacles like people, cars, and trees, the DeepSORT algorithm keeps track of the identified objects. Similarly, using the detection of the identified objects and Euclidean distance transform, an open space without any obstacles to land could be identified if necessary. Finally, the PID controller generates appropriate movement values for the UAV using the visual cues of the target landing area and the obstacles. To warrant the validity of the overall system without risking the safety of the involved people, initial tests are performed, and a software-based simulation is performed before executing the tests in real life. A full-blown hardware system with an autonomous landing system is then built and tested in real life. The designed system is tested in various scenarios to verify the effectiveness of the system.

Design process can be divided into stages of analysis and synthesis. This paper presents the application of the object-oriented technique to the synthesis as well as theoretical considerations concerning to design of gear size ranges. The synthesis consists in composition (aggregation) of single details into units – according to the rule: “from details up to general view”. The basics of the object-oriented synthesis were formulated. Furthermore, the consecutive stages of synthesis were formulated. The interactions between these stages were discussed. Some aspects were described in details e.g.: creation of interfaces for performance of the embodiment phase the designed artefact via CAD system drawing with specification (dimensions are still parametrically set). The final step of the procedure is creation of so called substantial (concrete) form of artifacts i.e. final assignment of dimensions which stored in the special data base. The final stage of the design process is issuing of technical documentation (technical drawings) created automatically via CAD system. The considerations are terminated by the list of advantages connected with the object-oriented approach to design (in comparison to the traditional way).

YOLOv8, as an efficient object detection method, can swiftly and precisely identify objects within images. However, traditional algorithms encounter difficulties when detecting small targets in remote sensing images, such as missing information, background noise, and interactions among multiple objects in complex scenes, which may affect performance. To tackle these challenges, we propose an enhanced algorithm optimized for detecting small objects in remote sensing images, named HP-YOLOv8. Firstly, we design the C2f-D-Mixer (C2f-DM) module as a replacement for the original C2f module. This module integrates both local and global information, significantly improving the ability to detect features of small objects. Secondly, we introduce a feature fusion technique based on attention mechanisms, named Bi-Level Routing Attention in Gated Feature Pyramid Network (BGFPN). This technique utilizes an efficient feature aggregation network and reparameterization technology to optimize information interaction between different scale feature maps, and through the Bi-level Routing Attention (BRA) mechanism, it effectively captures critical feature information of small target objects. Finally, we propose the Smooth Mean Perpendicular Distance Intersection over Union (SMPDIoU) loss function. The method comprehensively considers the shape and size of detection boxes, enhances the model's focus on the attributes of detection boxes and provides a more accurate bounding box regression loss calculation method. To demonstrate our approach's efficacy, we conduct comprehensive experiments across the RSOD, NWPU VHR-10, and VisDrone2019 datasets. The experimental results show that the HP-YOLOv8 achieves 95.11%, 93.05%, and 53.49% in the [email protected] metric, and 72.03%, 65.37%, and 38.91% in the more stringent [email protected]:0.95 metric, respectively.

Design process can be divided into stages of analysis and synthesis. This paper presents the application of the object-oriented technique to the analysis as well as theoretical considerations concerning to design of gear size ranges. This analysis consists in decomposition of the designed artefact (a gear) according to the rule “from general to details view”. The basics of the object-oriented analysis were formulated. Furthermore, design phases and the objects related to theses phases were discussed. The following models have been considered: hierarchical model, entity-relationship model, data-flow model and object model. Analysis is additionally connected with interactions between particular design phases.

The indications for TACE in the treatment of hepatocellular carcinoma have become more stringent with the development of systemic pharmacotherapy. Radical TACE is expected to be used only in situations such as for tumors with small volume which fulfill the “up-to-7”. Furthermore, a combination of molecular-targeted agents is expected to maximize the efficacy of TACE. In the intermediate stage, TACE and drug therapy play complementary roles, and it is important to select a treatment strategy that considers tumor status and hepatic reserve. However, no studies have investigated the various types of TACE in the treatment of such patients. Currently, TACE in Japan is broadly classified into conventional TACE, balloon occluded TACE (B-TACE), and drug-eluting beads TACE (DEB-TACE). This article outlines the evolution of B-TACE for hepatocellular carcinoma in the drug therapy era.

The key links of face recognition are digital image preprocessing, facial feature extraction and pattern recognition, this article aimed at the current problem of slow speed and low recognition accuracy of face recognition , from the above three key links, on the basic of analyzing the therories of Fractional Differential Masks Operator (FDMO), Principal Component Analysis (PCA) and Support Vector Machine (SVM), design a kind of FDMO+PVA+SVM coupling algorithm that applies to face recognition to improve the speed and accuracy of it. To realize FDMO+PCA+SVM coupling algorithm, first, we should apply FDMO to face image processing binary marginalization, the purpose is getting face contour; Then, we apply PCA to get the feature of face image which is disposed by binary marainalization. At last, we can apply One-Against All of the SVM classifier and LibSVM software package to realize face recognition. Beside, the article with nine different coupling algorithm design four groups of experimental reaults on the ORL face database verified by comparative analysic FDMO+PCA+SVM coupling algorithm in the superiority of face recognition accuracy and speed.

Real-time object detection remains a pivotal topic in the realm of computer vision. Balancing the accuracy and speed of object detectors poses a formidable challenge for both academic researchers and industry practitioners. While recent transformer-based models have showncase the prowess of the attention mechanism, delivering remarkable performance improvements over CNNs, their computational demands can hinder their effectiveness in real-time detection tasks. In this paper, we elect to use YOLOX as our robust starting point and introduce a series of effective enhancements, culminating in a new high-performance detector named YOLOAX. To further exploit the power of the attention mechanism, we devise multi-dimensional attention-based modules that activate CNNs, emphasizing the most pertinent regions and bolstering the capacity to learn the most informative image representations from feature maps. Moreover, we introduce a novel leading label assignment strategy called STA, along with a groundbreaking loss function named GEIOU Loss, to further refine our detector's performance. We provide extensive ablation studies on the COCO and PASCAL VOC 2012 detection datasets to validate our proposed methods. Remarkably, our YOLOAX is trained solely on the MS-COCO dataset from scratch, without leveraging any prior knowledge, which achieves an impressive 54.2% AP on the COCO 2017 test set while maintaining a real-time speed of 72.3 fps, surpassing YOLOX by a significant margin of 3.0% AP. Our source code and pre-trained models are openly accessible at https://github.com/KejianXu/yoloax.

The electroencephalogram (EEG) is a record of brain activity. Brain Computer Interface (BCI) technology formed by the EEG signal has become one of the hotspots at present. How to extract the feature signal of EEG is the most basic research of BCI technology. In this paper, A new method of recognizing fatigue, conscious, concentrated state of human brain is proposed by the combination of discrete wavelet transform and the neural network based on EEG signal. First of all, the law signal is preprocessed by the wavelet denoising method because the law EEG signal contains a large number of high frequency noise, which is decomposed into multi-layer high frequency signal and low frequency signal. thus, δ wave, θ wave, α wave, β wave are obtained by the wavelet transform. And then, frequency band energy of the different wave is regards as the feature signal of EEG. In the experiment, the feature signal is classified by radial basic function (RBF) and annealed chaotic competitive learning network (ACCLN). RBF and ACCLN networks are trained with 500 sets of sample data and are tested by 100 sets of samples in different mental states. The experimental results show that the average accuracy of RBF network under three conditions are 88.75%, 88.25%, 88.5%, respectively, and the correct rate of ACCLN network is 97%, 98%, 98%, respectively.

Few-shot object detection (FSOD) aims to address the challenge of requiring a substantial amount of annotations for training in conventional object detection, which is very labor-intensive. However, existing few-shot methods achieve high precision with the sacrifice of time-consuming for exhaustive fine-tuning, or take poor performance in novel-class adaptation. We presume the major reason is that the valuable correlation feature among different categories is insufficiently exploited, hindering the generalization of knowledge from base to novel categories for object detection. In this paper, we propose Few-Shot object detection via Correlation-RPN and Transformer Encoder-Decoder (CRTED), a novel training network to learn object-relevant features of inter-class correlation and intra-class compactness while suppressing object-agnostic features in the background with limited annotated samples. And we also introduce a 4-way tuple-contrast training strategy to positively activate the training progress of our object detector. Experiments over two few-shot benchmarks (Pascal VOC, MS-COCO) demonstrate that, our proposed CRTED without further fine-tuning can achieve comparable performance with current state-of-the-art fine-tuned works. The codes and pre-trained models will be released.

With the rapid development of space programs in various countries, the number of satellites in space is increasing, resulting in an increasingly complex space environment. Therefore, improving space object identification technology has become highly important. We proposes a method of applying deep learning to intelligent detection of space object. We utilize 49 authentic 3D satellite models including 16 scenarios to generate a dataset comprising 17,942 images, which contains over 500 actual satellite photos. Additionally, we acquired a substantial amount of annotated data using a semi-automatic labeling method, which resulted in significant labor cost savings, and obtained a total of 39,000 labels. We validate the feasibility of the dataset using YOLOv3 and YOLOv7 models. What's more, we optimize the YOLOv7 model by integrating deformable convolution RepPoint into the YOLOv7 backbone to obtain the YOLOv7-R model. Through training with these two models, experimental results show that YOLOv3 achieves an accuracy of 0.927, YOLOv7 reaches an accuracy of 0.964, and YOLOv7-R achieves the highest accuracy at 0.983. This provides an effective solution for intelligent space object detection.

Effectively mapping and monitoring rubber plantation is still changing. Previous studies have explored the potential of phenology features for rubber plantation mapping through a pixel-based approach (pixel-based phenology approach). However, in fragmented mountainous Xishuangbanna, it could lead to noises and low accuracy of resultant maps. In this study, we investigated the capability of an integrated approach by combining phenology information with an object-based approach (object-based phenology approach) to map rubber plantations in Xishuangbanna. Moderate Resolution Imaging Spectroradiometer (MODIS) data were firstly used to acquire the temporal profile and phenological features of rubber plantations and natural forests, which delineates the time windows of defoliation and foliation phases. Landsat images were then used to extract a phenology algorithm comparing three different approaches: pixel-based phenology, object-based phenology, and extended object-based phenology to separate rubber plantations and natural forests. The results showed that the two object-based approaches achieved higher accuracy than the pixel-based approach, having overall accuracies of 96.4%, 97.4%, and 95.5%, respectively. This study proved the reliability of a phenology-based rubber mapping in fragmented landscapes with a distinct dry/cool season using Landsat images. This study indicated that the object-based phenology approaches can effectively improve the accuracy of the resultant maps in fragmented landscapes.

Optical coherence tomography (OCT) is a non-invasive imaging technique widely used in ophthalmology for visualizing retinal layers, aiding in early detection and monitoring of retinal diseases. OCT is useful for detecting diseases such as age-related macular degeneration (AMD) and diabetic macular edema (DME), which affect millions of people globally. Over the past decade, the area of application of Artificial Intelligence (AI), particularly Deep Learning (DL), has significantly increased. The number of medical applications is also rising, with solutions from other domains being increasingly applied to OCT. The segmentation of biomarkers is an essential problem that can enhance the quality of retinal disease diagnostics. For 3D OCT scans, AI is beneficial since manual segmentation is very labor-intensive. In this paper, we employ the new SAM 2 and MedSAM 2 for the segmentation of OCT volumes for two open-source datasets, comparing their performance with the traditional U-Net. The model achieved an overall Dice score of 0.913 and 0.902 for macular holes (MH) and intraretinal cysts (IRC) on OIMHS and 0.888 and 0.909 for intraretinal fluid (IRF) and pigment epithelial detachment (PED) on the AROI dataset, respectively.

Motion related human activity recognition using wearable sensors can potentially enable various useful daily applications. So far, most studies view it as a stand-alone mathematical classification problem without considering the physical nature of human motions. Consequently, they suffer from data dependencies and encounter the dimension disaster problem and the over-fitting issue, and their models are never human-readable. In this study, we start from a deep analysis on natural physical properties of human motions, and then propose a useful feature selection method to quantify each feature's classification contribution capability. On one hand, the "dimension disaster" problem can be avoid to some extent, due to the affined dimension of key features; On the other hand, over-fitting issue can be depressed since the knowledge implied in human motions are nearly invariant, which compensates the possible data inadequacy. The experiment results indicate that the proposed method performs superior to those adopted in related works, such as decision tree, k-NN, SVM, neural networks.

Determining the general-name-derived semantic relationships between geographic names often requires consulting many geographic name documents for verification. In geographic name translation and geographic name knowledge graphs, this method cannot meet the needs of large-scale extraction of general-name-derived semantic relationships between geographic entities. To solve this problem, this paper proposes a general-name derivation relation recognition method based on Prompt learning and Semantic Spatiotemporal Distribution Attention Feature Fusion (SSD-AFF). This method adopts a pipe-based relationship recognition strategy. First, the Prompt learning method is adopted to form a general-name derivation pattern with the general-name-derived geographical name category and the original geographical name category as the prompt word, and then the derivation pattern is combined with the geographical name as the input of the model so that the recognition problem of the general-name derivation of the geographical name can be transformed into a classification problem using the bidirectional language model. Then, by analyzing the characteristics of the semantic association and geographical spatio-temporal distribution between the general-name-derived geographical name and the original geographical name, the semantic spatio-temporal distribution characteristics of the general-name-derived geographical name are constructed. Finally, the network model based on the semantic spatio-temporal distribution Attention Feature Fusion (SSD-AFF) is used to distinguish the general-name-derived semantic relationships. The experimental results show that the proposed method has good performance. It can effectively mine the general-name-derived semantic relations between the vector data of geographical entities and has important application value in geographical name translation and geographical name knowledge maps.

In this comprehensive review, we delve into the realm of intention recognition within the context of digital forensics and cybercrime. The rise of cybercrime has become a major concern for individuals, organizations, and governments worldwide. Digital forensics is a field that deals with the investigation and analysis of digital evidence in order to identify, preserve, and analyze information that can be used as evidence in a court of law. Whereas, Intention recognition is a subfield of artificial intelligence that deals with the identification of agents’ intentions based on their actions and change of states. In the context of cybercrime, intention recognition can be used to identify the intentions of cybercriminals and even to predict their future actions. Employing a meticulous six-step systematic review approach, we curated research articles from reputable journals and categorized them into three distinct modeling approaches: logic-based, classical machine learning-based, and deep learning-based. Notably, intention recognition has transcended its historical confinement to network security, now addressing critical challenges across various subdomains, including social engineering attacks, AI black box vulnerabilities, and physical security. While deep learning emerges as the dominant paradigm, its inherent lack of transparency poses unique challenges in the digital forensics landscape. We advocate for hybrid solutions that blend deep learning’s power with interpretability. Furthermore, we propose the creation of a comprehensive taxonomy to precisely define intention recognition, paving the way for future advancements in this pivotal field.

Background: In recent years, computational aesthetics and neuroaesthetics have provided novel insights into understanding beauty. Building upon the findings of traditional aesthetics, this study aims to combine these two research methods to explore an interdisciplinary approach to studying aesthetics; Method: Abstract artworks were used as experimental materials. Based on traditional aesthetics and in combination, features of composition, tone, and texture were selected. Computational aesthetic methods were then employed to correspond these features to physical quantities: blank space, gray histogram, GLCM, LBP, and Gabor filters. An EEG experiment was carried out, in which participants conducted aesthetic evaluations of the experimental materials in different contexts (genuine, fake), and their EEG data was recorded to analyze the impact of various feature classes in the aesthetic evaluation process. Finally, a SVM was utilized to model the feature data, EEG data, context data, and subjective aesthetic evaluation data; Result: Behavioral data revealed that higher aesthetic ratings in the genuine context. EEG data indicated that genuine contexts elicited more negative deflections in the prefrontal lobes between 200-1000ms. Class II compositions demonstrated more positive deflections in the parietal lobes at 50-120ms, while Class I tones evoked more positive amplitudes in the occipital lobes at 200-300ms. Gabor features showed significant variations in the parieto-occipital area at an early stage. Class II LBP elicited a prefrontal negative wave with a larger amplitude. The results of the SVM models indicated that the model incorporating aesthetic subject and context data (ACC=0.76866) outperforms the model using only parameters of the aesthetic object (ACC=0.68657); Conclusion: A positive context tends to provide participants with a more positive aesthetic experience, but abstract artworks may not respond to this positivity. During aesthetic evaluation, the ERP data activated by different features show a trend from global to local. The SVM model based on multimodal data fusion effectively predicts aesthetics, further demonstrating the feasibility of the combined research approach of computational aesthetics and neuroaesthetics.

In pattern recognition domain, deep architectures are widely used nowadays and they have achieved fine grades. However, these deep architectures need special demands, especially big datasets and GPU. Aiming to gain better grades without deep networks, we propose a simplified algorithm framework using fusion features extracted from the salient areas of faces. Furthermore, the proposed algorithm has achieved a better result than some deep architectures. For extracting more effective features, this paper firstly defines the salient areas on the faces. This paper normalizes the salient areas of the same location in the faces to the same size, therefore it can gain more similar features from different subjects. LBP and HOG features are extracted from the salient areas, fusion features’ dimensions are reduced by Principal Component Analysis( PCA) and we apply softmax to classify the six basic expressions at once. This paper proposes a salient areas definitude method which uses peak expressions frames to compare with their neutral faces. This paper also proposes and applies the idea of normalizing the salient areas to align the specific areas which express the different expressions. This makes the salient areas found from different subjects have the same size. Besides, gamma correction method is firstly applied on LBP features in our algorithm framework which improves our recognition rates significantly. By applying this algorithm framework, our research has gained state-of-the-art performances on CK+ database and JAFFE database.

Crowd abnormal behavior recognition is one of the research hotspots in computer vision. Its goal is to use computer vision technology and abnormal behavior detection models to accurately perceive, predict, and intervene in potential abnormal behaviors of the crowd, and monitor the status of the crowd system in public places in real-time, to effectively prevent and deal with public security risks and ensure public life safety and social order. To this end, focusing on the crowd abnormal behavior recognition technology in the computer vision system, a systematic review study of its theory and cutting-edge technology is conducted. First, the crowd level and abnormal behaviors in public places are defined, and the challenges faced by crowd abnormal behavior recognition are expounded. Then, from the dimensions based on traditional methods and based on deep learning, the mainstream technologies of abnormal behavior recognition are discussed, and the design ideas, advantages, and limitations of various methods are analyzed. Next, the mainstream software tools are introduced to provide a comprehensive reference for the technical framework; Secondly, typical abnormal behavior datasets at home and abroad are sorted out, and the characteristics of these datasets are compared in detail from multiple perspectives such as scale, characteristics and uses, and the performance indicators of different algorithms on the datasets are compared and analyzed; Finally, the full text is summarized and the future development direction of crowd abnormal behavior recognition technology is prospected.

Prompt removal of misfolded membrane proteins and misassembled membrane protein complexes is essential for membrane homeostasis. However, the elimination of these toxic proteins from the hydrophobic membrane environment has high energetic barriers. Transmembrane FtsH is the only known ATP-dependent protease responsible for this task, unlike other well-studied soluble ATP-dependent proteases. The mechanisms by which FtsH recognizes, unfolds, translocates, and proteolyzes its substrates remain unclear. Here, we report the crystal structures of the Thermotoga maritima FtsH periplasmic domain (PD) in an associative trimeric state at a 1.5-1.95 Å resolution. We also describe the pH-dependent oligomerization states of the isolated PD using dynamic light scattering. These observations help us understand how FtsH recognizes membrane-anchored misfolded proteins.

In this paper, we proposed the fusion of two projection based face recognition algorithms: local binary Patterns in DCT domain and singular value decomposition (SVD) characterized by its simplicity and efficiently. Standard databases ORL are used to test the experimental results which prove that proposed system achieves more accurate face recognition as compared to individual method.

This paper describes the first results of an Image Recognition Based Location (IRBL) for mobile application focusing on the procedure to generate a Database of range images (RGB-D). In an indoor environment, to estimate the camera position and orientation, a prior spatial knowledge of the surrounding is needed. In order to achieve this objective a complete 3D survey of two different environment (Bangbae metro station of Seoul and E.T.R.I. building in Daejeon – Republic of Korea) was performed using LiDAR (Light Detection And Ranging) instrument and the obtained scans were processed in order to obtain a spatial model of the environments. From this, two databases of reference images were generated using a specific software realized by the Geomatics group of Politecnico di Torino (ScanToRGBDImage). This tool allow to generate synthetically different RGB-D images) centered in the each scan position in the environment. Later, the external parameters (X, Y, Z, ω, φ, κ) and the range information extracted from the DB images retrieved, are used as reference information for pose estimation of a set of acquired mobile pictures in the IRBL procedure. In this paper the survey operations, the approach for generating the RGB-D images and the IRB strategy are reported. Finally the analysis of the results and the validation test are described.

This research introduces a hybrid feature extraction approach that combines Linear Discriminant Analysis (LDA) and Multilayer Perceptron (MLP) methods to address the challenges of reducing feature vector dimensionality and accurately classifying smartphone-based human activities. Moreover, to refine activity classification accuracy, Support Vector Machine (SVM) optimization with Stochastic Gradient Descent (SGD) is employed. LDA, a statistical tool, is leveraged to derive a new feature space for data projection, enhancing class separation and test feature label prediction. The proposed approach, named LMSS, was evaluated using the UCI-HAR dataset and compared with state-of-the-art models. The results demonstrate that the proposed approach outperformed the best-performing method over this dataset. It achieved an accuracy rate of 99.52%, precision of 99.55%, recall of 99.53%, and an F1-score of 99.54%, highlighting the effectiveness of the proposed method in accurately classifying the data.

Musical instrument recognition is a relatively unexplored area of machine learning due to the need to analyze complex spatial-temporal audio features. Traditional methods using individual spectrograms, like STFT, Log-Mel, and MFCC, often miss the full range of features. We propose a hierarchical residual attention network using a scaled combination of multiple spectrograms, including STFT, Log-Mel, MFCC, and CST features (chroma, spectral contrast, and Tonnetz), to create a comprehensive sound representation. This model enhances focus on relevant spectrogram parts through attention mechanisms. Experimental results with the OpenMIC-2018 dataset show significant improvement in classification accuracy, especially with the "Magnified 1/4 Size" configuration. Future work will optimize CST feature scaling, explore advanced attention mechanisms, and apply the model to other audio tasks to assess its generalizability.

The detection performance of small objects in remote sensing images has not been satisfactory compared to large objects, especially in low-resolution and noisy images. A generative adversarial network (GAN)-based model called enhanced super-resolution GAN (ESRGAN) showed remarkable image enhancement performance, but reconstructed images usually miss high-frequency edge information. Therefore, object detection performance showed degradation for small objects on recovered noisy and low-resolution remote sensing images. Inspired by the success of edge enhanced GAN (EEGAN) and ESRGAN, we applied a new edge-enhanced super-resolution GAN (EESRGAN) to improve the quality of remote sensing images and used different detector networks in an end-to-end manner where detector loss was backpropagated into the EESRGAN to improve the detection performance. We proposed an architecture with three components: ESRGAN, EEN, and Detection network. We used residual-in-residual dense blocks (RRDB) for both the ESRGAN and EEN, and for the detector network, we used a faster region-based convolutional network (FRCNN) (two-stage detector) and a single-shot multibox detector (SSD) (one stage detector). Extensive experiments on a public (car overhead with context) dataset and another self-assembled (oil and gas storage tank) satellite dataset showed superior performance of our method compared to the standalone state-of-the-art object detectors.

In recent years, electroencephalogram (EEG) emotion recognition has emerged as a research hotspot in the field of artificial intelligence (AI). Despite advancements in EEG-based emotion recognition, room for enhancing performance persists due to EEG signal redundancy and limitations in feature extraction, leading to inefficient models and emotional information loss. To fully utilize EEG's emotional information and improve recognition accuracy while reducing computational costs, this paper proposes a Convolutional-Recurrent Hybrid Network with a dual-stream adaptive approach and an attention mechanism (CSA-SA-CRTNN). Firstly, the model utilizes a CSAM module to assign corresponding weights to EEG channels. Then, an adaptive dual-stream convolutional-recurrent network (SA-CRNN and MHSA-CRNN) is applied to extract local spatial-temporal features. After that, the extracted local features are concatenated and fed into a temporal convolutional network with a multi-head self-attention mechanism (MHSA-TCN) to capture global information. Finally, the extracted EEG information is used for emotion classification. We conducted binary and ternary classification experiments on the DEAP dataset, achieving 99.26% and 99.15% accuracy for arousal and valence in binary classification, and 97.69% and 98.05% in ternary classification, surpassing relevant algorithms. Additionally, the model's efficiency is significantly higher than other models, achieving better accuracy with lower resource consumption.

With the development of educational technology, machine learning and deep learning provide technical support for traditional classroom observation assessment. However, in real classroom scenarios, the technique faces challenges such as lack of clarity of raw images, complexity of datasets, multi-target detection errors and complexity of character interactions.Based on the above problems, a student classroom behavior recognition network incorporating super-resolution and target detection is proposed. To cope with the problem of unclear original images in the classroom scenario, SRGAN (Super Resolution Generative Adversarial Network for Images) is used to improve the image resolution and thus the recognition accuracy.To address the dataset complexity and multi-targeting problems, feature extraction is optimized and multi-scale feature recognition is enhanced by introducing AKConv and LASK attention mechanisms into the Backbone module of YOLOv8s algorithm. To improve the character interaction complexity problem, the CBAM attention mechanism is integrated to enhance the recognition of important feature channels and spatial regions. Experiments show that it can detect six behaviors of students raising their hands, reading, writing, playing cell phones, looking down, and lying on the table in high-definition images. And the accuracy and robustness of this network are verified.Compared with small target detection algorithms such as Faster R-CNN, YOLOv5, and YOLOv8s, this network has better detection performance and can efficiently deal with the behavior recognition of multiple students.

Graph query languages such as Cypher are widely adopted to match and retrieve data in a graph representation, due to their ability of retrieving and transforming information. Despite the most natural way to match and transform information is through rewriting rules, those are scarcely or partially adopted in graph query languages. Their inability of doing so has a major impact on the subsequent way the information is structured, as it might then appear more natural to provide major constraint over the data representation so to consequently constraint the way the information should be represented. On the other hand, recent works are starting to move towards an opposite direction, as the provision of a truly general semistructured model (GSM) allows to both represent all the available data formats (Network-Based, Relational, and Semistructured) as well as support an holistic query language expressing all major queries in such languages. In this paper, we show that the usage of GSM enables the definition of a general rewriting mechanism which can be expressed in current graph query languages only at the cost of adhering the query to the specificity of the underlying data representation. We formalise the proposed query language in terms graph rewriting mechanisms described as a set of production rules $L\to R$ while providing restriction to the characterization of L, while extending it to support structural graph nesting operations, useful to aggregate similar information around an entry-point of interest. We discuss how GSM, by fully supporting index-based data representation, allows for a better physical model implementation leveraging the benefits of columnar database storages. Preliminary benchmarks shows the scalability of this proposed implementation in comparison with state-of-the-art implementations.

Train fault detection primarily relies on the comparative analysis of collected images with standard reference images, making the accurate identification of the collected image types crucial for effective fault detection. Most current systems achieve indirect classification of carriage images by using Automatic Equipment Identification (AEI) devices to recognize carriage identification number information while capturing the carriage images. However, damaged RF tags or blurred characters can hinder these devices, obstructing further train fault analyses. The unique features of carriage linear array images, such as high resolution, extreme aspect ratios, and local non-linear distortions, pose significant challenges to recognition algorithms. This paper proposes a method specifically designed to recognize these types of images. First, we implement an object detection algorithm to locate the positions of key components in carriage linear array images. By leveraging the spatial layout mapping between these key components and the carriage type classification, we simplify the complex image recognition problem into a sparse point set alignment task. To ensure effective registration despite local distortions in the linear array images, we propose a weighted radial basis function. To address the issues of unknown matching relationships and quantity mismatches during point set alignment, the proposed objective function is designed to maximize the similarity between Gaussian mixtures of point sets, thereby determining the RBF weights. Extensive experiments have demonstrated that our algorithm achieves 100% recognition accuracy under local nonlinear scale distortions of less than 15%. The algorithm remains effective even in the presence of some false positives or missed detections in key component object detection results. It can accurately identify the target category from 79 image categories within 24 milliseconds on an i7 CPU without GPU support. It is of great significance to reduce system cost and promote automatic exterior fault detection for train rolling stock.

Aerial image classification has become popular and has attracted extensive research efforts in recent decades. The main challenge lies in its very high spatial resolution but relatively insufficient spectral information. To this end, spatial-spectral feature extraction is a popular strategy for classification. However, parameter determination for that feature extraction is usually time-consuming and depends excessively on experience. In this paper, an automatic spatial feature extraction approach based on image raster and segmental vector data cross-analysis is proposed for the classification of very high spatial resolution (VHSR) aerial imagery. First, multi-resolution segmentation is used to generate strongly homogeneous image objects and extract corresponding vectors. Then, to automatically explore the region of a ground target, two rules, which are derived from Tobler’s First Law of Geography (TFL) and a topological relationship of vector data, are integrated to constrain the extension of a region around a central object. Third, the shape and size of the extended region are described. A final classification map is achieved through a supervised classifier using shape, size, and spectral features. Experiments on three real aerial images of VHSR (0.1 to 0.32 m) are done to evaluate effectiveness and robustness of the proposed approach. Comparisons to state-of-the-art methods demonstrate the superiority of the proposed method in VHSR image classification.

Human Activity Recognition (HAR) technology enables continuous behavior monitoring, particularly valuable in healthcare. This study investigates the viability of using an ear-worn motion sensor for classifying daily activities, including lying, sitting/standing, walking, ascending stairs, descending stairs, and running. Fifty healthy participants (between 20 and 47 years old) engaged in these activities while under monitoring. Various machine learning algorithms, ranging from interpretable shallow models to state-of-the-art deep learning approaches designed for HAR, were employed for classification. Results demonstrate the ear sensor's efficacy, with deep learning models achieving 98% accuracy rate of classification. The obtained classification models are agnostic regarding which ear the sensor is worn and robust against moderate variations in sensor orientation (e.g., due to differences in auricle anatomy), meaning no initial calibration of the sensor orientation is required. The study underscores the ear's efficacy as a suitable site for monitoring human daily activity and suggests its potential for combining HAR with in-ear vital signs monitoring. This approach offers a practical method for comprehensive health monitoring by integrating sensors in a single anatomical location. This integration facilitates individualized health assessments, with potential applications in tele-monitoring, personalized health insights, and optimizing athletic training regimes.

Over the past decades, overweight and obesity has become a global epidemic and the leading threat for death. To prevent the serious risk, an overweight or obese individual must apply a long-term weight-management strategy to control food intake and physical activities, which is however, not easy. Recently, with the advances of information technology, more and more people can use wearable devices and smartphones to obtain physical activity information, while they can also access various health-related information from Internet online social networks (OSNs). Nevertheless, there is a lack of an integrated approach that can combine these two methods in an efficient way. In this paper, we address this issue and propose a novel mobile-social framework for health recognition and recommendation, namely, H-Rec². The main ideas of H-Rec² include (1) to recognize the individual's health status using smartphone as a general platform, and (2) to recommend physical activity and food intake based on personal health information, life science principles, and health-related information obtained from OSNs. To demonstrate the potentials of the H-Rec² framework, we develop a prototype that consists of four important components: (1) an activity recognition module that senses physical activity using accelerometer, (2) a health status modeling module that applies a novel algorithm to generate personalized health status index, (3) a restaurant information collection module that collects relevant information from OSN, and (4) a restaurant recommendation module that provides personalized and context-aware recommendation. To evaluate the prototype, we conduct both objective and subjective experiments, which confirm the performance and effectiveness of the proposed system.

Background: Microscopic examination of acid-fast stained sputum smears for detecting mycobacterial acid-fast bacilli (AFB) remains the most economical and readily available method for laboratory diagnosis of tuberculosis (TB). However, this conventional approach has limitations, including low sensitivity and labor-intensive procedures. Methods: An automated microscopy system incorporating artificial intelligence (AI) and machine learning for AFB identification was evaluated. The study was conducted at an Infectious Disease Hospital in Jiangsu Province, China, utilizing an intelligent microscope system (TB-Scan, Wellgen Medical, Kaohsiung). A total of 1,000 sputum smears were included in the analysis, with the system capturing digital microscopic images and employing an image recognition model to automatically identify and classify AFB. Referee technicians provided the gold standard for discrepant results. Results: The automated system demonstrated an overall accuracy of 95.00% (950/1,000), sensitivity of 91.24% (177/194), and specificity of 95.91% (773/806). Notably, the system identified 21 smears as positive that were previously reported as negative, with referee technicians confirming 17 of these as true positive and retracting the test results accordingly. Recalculating the performance, the accuracy increased to 96.70% (967/1,000), sensitivity to 91.94% (194/211), and specificity to 97.97% (773/789), with a false negative rate of 8.06% (17/211) and a false positive rate of 2.03% (16/789). Conclusions: The incorporation of AI and machine learning into an automated microscopy system demonstrated the potential to enhance the sensitivity and efficiency of AFB detection in sputum smears compared to conventional manual microscopy. This approach holds promise for widespread application in TB diagnostics and potentially other fields requiring labor-intensive microscopic examination.

Modification of electrode surface with a selective layer gives the possibility to detect target ana-lytes of forensic interest. 3-(4-trifluoromethyl)-phenyl)-thiophene (ThPhCF3) was deposited on a graphite (G) electrode by electrochemical oxidation and characterized as a receptor for the recognition of synthetic stimulants (2-aminoindane, buphedrone, naphyrone). First, the structural characterization of the polymeric layer were obtained from Raman spectroscopy. Second, the electrochemical profiles of selected synthetic stimulants and their affinity to ThPhCF3/G-modified electrodes were studied using square wave voltammetry and electrochemical impedance spec-troscopy. The values of the adsorption constant show the importance of – PhCF3 groups in the interaction with synthetic stimulants, namely recognition by the formation of hydrogen bonds (Kads (buphedrone) < Kads (2-AI)) and interaction with aromatic H atoms (Kads (buphedrone) < Kads (naphyrone)). It was demonstrated that the polymeric layer derived from thiophene with – PhCF3 group is capable to increase the intensity of the electrochemical signal.

This paper proposes a novel facial expression recognition network called the Lightweight Facial Network with Spatial Bias (LFNSB). The LFNSB model balances model complexity and recognition accuracy. It has two key components: a lightweight feature extraction network (LFN) and a Spatial Bias (SB) module for aggregating global information. The LFN introduces combined channel operations and depthwise convolution techniques, effectively reducing the number of parameters while enhancing feature representation capability. The Spatial Bias module enables the model to focus on local facial features while also capturing the dependencies between different facial regions. Additionally, a novel loss function called Cosine-Harmony Loss is designed. This function optimizes the relative positions of feature vectors in high-dimensional space, resulting in better feature separation and clustering. Experimental results on the AffectNet and RAF-DB datasets show that the proposed LFNSB model performs excellently in facial expression recognition tasks. It achieves high recognition accuracy while significantly reducing the number of parameters, thus substantially lowering model complexity.

Real time camouflaged object detection so far using CAMO or COD10K datset has been able to achieve mAP50 less than 64%. We present a fourier transfom and Milkyway filament extraction based method extracting shape and edges of camouflaged object, achieving 88%+ mAP50 while continuing to deliver real time detection using YOLOv8s based models. This allows for search and rescue of wilelife and humans in smoke, fog, natural disasters possible by combining low compute Yolov8s model on headup display for rescue workers such as firefighters, first reponders etc.

Digital photogrammetry has attracted widespread attention in the field of geotechnical and geological survey due to its low-cost, ease of use and contactless mode. In this work, with the purpose of studying the progressive block surficial detachments of a landslide we developed a monitoring system based on fixed multi-view time-lapse cameras. Thanks to a new-developed photogrammetric algorithm based on the comparison of photo sequences through a structural similarity metric and the computation of the disparity map of two convergent views we can quickly detect the occurrence of collapse events, determine their location and calculate the collapse volume. With the field data obtained at the Perarolo landslide site (Belluno Province, Italy), we have preliminary tested the effectiveness of the algorithm and its accuracy in the volume calculation. The method of quickly and automatically obtaining collapse information proposed in this paper can extend the potentials of landslide monitoring system based on videos or photo sequence and it will be of great significance for further research on the link between the frequency of collapse events and the driving factors.

Recent advancements in brain stimulation and nanomedicine have ushered in a new era of therapeutic interventions for psychiatric and neurodegenerative disorders. This review explores the cutting-edge innovations in brain stimulation techniques, including their applications in alleviating symptoms of main neurodegenerative disorders and addiction. Emphasis is placed on the underlying main neurotransmitter modifications and their specific brain area location, particularly focusing on the dopaminergic system, which plays a critical role in these conditions. Furthermore, the review delves into the groundbreaking developments in nanomedicine, highlighting how nanotechnology can be utilized to target aberrant signaling in neurodegenerative diseases, with a specific focus on the dopaminergic system. The discussion extends to emerging technologies such as magnetoelectric nanoparticles (MENPs), which represent a novel intersection between nanoformulation and brain stimulation approaches. These innovative technologies offer promising avenues for enhancing the precision and effectiveness of treatments by enabling non-invasive, targeted delivery of therapeutic agents as well as on site, on-demand stimulation. By integrating insights from recent research and technological advances, this review aims to provide a comprehensive understanding of how brain stimulation and nanomedicine can be synergistically applied to address complex neuropsychiatric and neurodegenerative disorders, paving the way for future therapeutic strategies.

Recently, attention mechanisms have developed into an important tool for performance improvement of deep neural networks. In computer vision, attention mechanisms are generally divided into two main branches: spatial and channel attention. Both attention categories have their own advantages. The fusion of both attentions achieves higher performance, on the cost of the computational load. This paper introduces an innovative and lighter n-shifted sigmoid channel and spatial attention (CSA) module to reduce the computational cost and to improve the 3D scene relevant features selection. To validate the proposed attention module, 3D scene object detection in the deep Hough voting point sets is considered as the testing application. The proposed attention module with its piecewise n-shifted sigmoid activation function improves the network’s learning and generalization capacity which effectively predict bounding box parameters directly from 3D scenes and detect objects more accurately. This advantage is achieved by selectively attending to more relevant features of the input data. When used in the deep Hough voting point sets, the proposed attention module outperforms state-of-the-art 3D detection methods on the sizable SUNRGBD dataset. Experiments conducted showed an increase of 12.02 mean accuracy precision (mAP) when compared to the celebrated VoteNet (without attention). It also got 9.92 mAP higher compared to the MLVCNet, and 10.32 mAP higher than the Point Transformer. The proposed model not only decreases the sigmoid vanishing gradient problem but also brings out valuable features by fusing channel-wise and spatial information while improving accuracy results in 3D object detection.

Imaging systems mounted to ground vehicles are used to image fruit tree canopies for estimation of fruit load, but frequently need correction for fruit occluded by branches, foliage or other fruits. This can be achieved using an orchard ‘occlusion factor’, estimated from a manual count of fruit load on a sample of trees (referred to as the reference method). It was hypothesised that canopy images could hold information related to the number of occluded fruit. Five approaches to correct for occluded fruit based on canopy images were compared using data of three mango orchards in two seasons. However, no attribute correlates to the number of hidden fruit were identified. Several image features obtained through segmentation of fruit and canopy areas, such as the proportion of fruit that were partly occluded, were used in training Random forest and multi-layered perceptron (MLP) models for estimation of a correction factor per tree. In another approach, deep learning convolutional neural networks (CNNs) were directly trained against harvest fruit count on trees. The supervised machine learning methods for direct estimation of fruit load per tree delivered an improved prediction outcome over the reference method for data of the season/orchard from which training data was acquired. For a set of 2017 season tree images (n=98 trees), a R2 of 0.98 was achieved for the correlation of the number of fruits predicted by a Random forest model and the ground truth fruit count on the trees, compared to a R2 of 0.68 for the reference method. The best prediction of whole orchard (n = 880 trees) fruit load, in the season of the training data, was achieved by the MLP model, with an error to packhouse count of 1.6% compared to the reference method error of 13.6%. However, the performance of these models on new season data (test set images) was at best equivalent and generally poorer than the reference method. This result indicates that training on one season of data was insufficient for the development of a robust model. This outcome was attributed to variability in tree architecture and foliage density between seasons and between orchards, such that the characters of the canopy visible from the interrow that relate to the proportion of hidden fruit are not consistent. Training of these models across several seasons and orchards is recommended.

Timely and accurate acquisition of information on distribution of the crop planting structure in Loess Plateau of eastern Gansu Province, one of the most important agricultural areas in western China, is crucial for promoting fine management of agriculture and ensuring food security. In this study, the Object-Based Image Classification (OBIC), the Random Forest (RF) and Convolutional Neural Network (CNN) models were employed to classify the crop planting structure of four representative test areas in Qingyang City in a precise manner. Firstly, different optimal segmentation scales for various crops were selected using the Estimation of Scale Parameter 2 (ESP2) tool and the Ratio of Mean Difference to Neighbors(ABS) to Standard Deviation (RMAS)model. The images were then segmented through multiresolution segmentation combined with the Canny Edge Detection algorithm. Secondly, the L1 regularized logistic regression model was utilized to select and optimize 39 spatial feature factors including spectral, textural, geometric, and index features, in conjunction with phenological factors. Lastly, under the multi-level classification framework, the Random Forest (RF) classifier and Convolutional Neural Network (CNN) model, combined with object-based multiresolution segmentation, was used to classify the crop planting structure. The findings show that: Thanks to the Canny Edge Detection algorithm, we can obtain a more complete boundary of the segmented objects and improve the separability. The optimal segmentation scales for corn, vegetables, and buckwheat were found to be 55, 70, and 35, respectively, while wheat and apple had optimal segmentation scales of 65. In addition to phenological characteristics, the number of selected spatial features for corn, vegetables, buckwheat, wheat, and apple were 9, 7, 16, 12, and 10, respectively. The CNN model demonstrated high consistency with the RF model in the classification results, but the accuracy of RF model is higher than that of CNN model on the whole. The overall accuracy of classification using RF model in four test areas registered 91.93%, 94.92%, 89.37% and 90.68%, respectively. This paper introduced crop phenological factors, effectively improving the extraction precision of shattered agricultural planting structure in the Loess Plateau of eastern Gansu Province. Its findings have important application value in crop monitoring, management, food security and other related fields.

The sleeping and grazing behaviors of horses play a crucial role in their health and welfare. In the horse industry, with the prevalent trend of individual single-stall farming in stable, accurately identifying various behaviors of horses within stables is imperative. This study has established a spatio-temporal dataset for horse postures and behaviors, proposed an algorithm utilizing a SE-SlowFast network with an enhanced loss function. This algorithm achieves automatic recognition of multiple postures and behaviors of horse simultaneously. The model developed in this study demonstrates high accuracy in identifying three postures within the stable: Standing, Crouching, and Lying, achieving respective accuracies of 92.73%, 91.87%, and 92.58%. Additionally, it accurately recognizes two behaviors: Sleeping and Grazing, achieving best accuracies of 93.56% and 98.77%. The overall best accuracy of the model is 93.9%. Experiments on video recognition confirm that the suggested model recognizes horse video data accurately. This study marks the first time computer vision technology has been used in the horse farming industry, achieving non-intrusive recognition of multiple horse postures and behaviors. This study provides valuable data support for livestock managers to evaluate the health conditions of horses, enhances the welfare of horses in stables, and contributes to the advancement of modern horse husbandry practices.

Event-based vision is an emerging field of computer vision that offers unique properties such as asynchronous visual output, high temporal resolutions, and dependence on brightness changes to generate data. These properties can enable robust high-temporal-resolution object detection and tracking when combined with frame-based vision. In this paper, we present a hybrid, high-temporal-resolution, object detection and tracking approach, that combines learned and classical methods using synchronized images and event data. Off-the-shelf frame-based object detectors are used for initial object detection and classification. Then, event masks, generated per each detection, are used to enable inter-frame tracking at varying temporal resolutions using the event data. Detections are associated across time using a simple low-cost association metric. Moreover, we collect and label a traffic dataset using the hybrid sensor DAVIS 240c. This dataset is utilized for quantitative evaluation using state-of-the-art detection and tracking metrics. We provide ground truth bounding boxes and object IDs for each vehicle annotation. Further, we generate high-temporal-resolution ground truth data to analyze the tracking performance at different temporal rates. Our approach shows promising results with minimal performance deterioration at higher temporal resolutions (48 – 384 Hz) when compared with the baseline frame-based performance at 24 Hz.

Recent progress in deep learning has led to accurate and efficient generic object detection networks. Training of highly reliable models depends on large datasets with highly textured and rich images. However, in real-world scenarios, the performance of the generic object detection system decreases when (i) occlusions hide the objects, (ii) objects are present in low-light images, or (iii) they are merged with background information. In this paper, we refer to all these situations as challenging environments. With the recent rapid development in generic object detection algorithms, notable progress has been observed in the field of object detection in challenging environments. However, there is no consolidated reference to cover state-of-the-art in this domain. To the best of our knowledge, this paper presents the first comprehensive overview, covering recent approaches that have tackled the problem of object detection in challenging environments. Furthermore, we present the quantitative and qualitative performance analysis of these approaches and discuss the currently available challenging datasets. Moreover, this paper investigates the performance of current state-of-the-art generic object detection algorithms by benchmarking results on the three well-known challenging datasets. Finally, we highlight several current shortcomings and outline future directions.

Identifying punch types as part of punch kinematic analysis is a key component for both coaches and players, providing critical insights into the variety and effectiveness of punches, which are essential for refining overall performance. Existing research indicates that punch type classification typically relies on data from either wearables or video data. Both approaches have their merits and demerits but require a significant amount of labeled data for modeling the classification algorithm. In this work, we propose a novel approach that significantly reduces the labeling effort by one-sixth by leveraging video data to enhance the training information of sensor data. This enriched training phase enables more accurate punch classification with reduced labeled data. Subsequently, the real-time punch identification and classification use only the wearable data. On a real dataset, with 15% of the labeling efforts, our approach achieved an accuracy rate of 91.41% for rear hand punch recognition and 91.91% for lead hand punch recognition, along with 92.33% and 94.56% for punch classification, respectively. Through the development of our Smart Boxer system, we aim to revolutionize punch analytics in boxing, providing comprehensive insights while enhancing the overall training and competitive experience for athletes and enriching fan engagement with the sport.

This paper presents an analysis of the sensitivity of controlling an autonomous surface object among a group of encountered objects to the inaccuracy of state control process data. For this purpose, a safe and optimal model of the control process was defined. An algorithm for determining the optimal and safe trajectory of an object, based on the multi-object game model, was developed; for comparative analysis, an algorithm for calculating only the optimal trajectory, not taking into account the maneuverability of other objects, was additionally developed. First, simulation-based studies of the algorithms enabled a comparative analysis of a number of different acceptable strategies for optimally shifting the trajectory of maneuvering objects from a single initial direction. Thereafter, the main goal of this paper was implemented: an analysis of the sensitivity characteristics of safe control, assessed with the risk of collision, both on the inaccuracy of navigation data and on the number of possible control strategies. Finally, final conclusions and a plan for further research on the subject of the paper were formulated.

Pipelines extend thousands of kilometers to transport and distribute oil and gas. Given the challenges often faced with corrosion, fatigue, and other issues on steel pipes, the demand for glass fiber reinforced plastics (GFRP) pipes is increasing in the oil and gas gathering and transmission systems. However, the medium transported through these pipelines contains multiple acid gases such as CO2 and H2S, as well as ions including Cl-、Ca2+、Mg2+、SO42-、CO32- and HCO3-. These substances can cause a series of problems, such as aging, debonding, delamination, and fracture. In this study, a series of aging damage experiments were conducted on V-shaped GFRP pipes with depths of 2mm and 5mm. The aging and failure of GFRP were studied under the combined effects of external force and acidic solution using acoustic emission (AE) techniques. It was found that the acidic aging solution promoted matrix damage, fiber/matrix desorption, and delamination damage in GFRP pipes over a short period. However, the overall aging effect was relatively weak. Based on the experimental data, the SSA-LSSVM algorithm was proposed and applied to the damage pattern recognition of GFRP. An average recognition rate of up to 90% was achieved, indicating that this method is highly suitable for analyzing AE signals related to GFRP damage.

Moving object detection plays a crucial role in various applications, particularly in traffic surveillance and collision warning systems. However, the high cost of training and slow detection pose significant challenges to the practicality and real-time performance of existing methods. These challenges hinder the practicality and real-time performance of existing methods. The need for a reliable and efficient moving object detection system prompts the search for cost-effective strategies. Enhancing detection speed without sacrificing accuracy is crucial for real-time applications. Overcoming these challenges is essential to advance the field of moving object detection and improve its applicability in various domains. This paper presents a comprehensive review of the literature on moving object detection, proposes novel strategies to overcome the challenges of high training costs and slow detection. The study emphasizes the importance of reliable speed monitoring systems and advancements in control systems to enhance driver assistance on urban highways. Each frame in the dataset undergoes YOLOv6 processing to detect and classify objects, generating bounding box predictions and class probabilities. Optical flow, specifically the Lucas-Kanade method, is then utilized to compute motion vectors between consecutive frames. These motion vectors facilitate object tracking across frames, enabling refined bounding box positions and improving overall object tracking accuracy. The results demonstrate the effectiveness of the proposed technique in reducing training costs, improving detection speed, and maintaining a high level of accuracy when compared to existing methods. The paper concludes by summarizing the findings and highlighting the potential of the proposed strategy for precise and reliable moving object recognition in real-world traffic scenarios

We propose a novel method for salient object detection in different images. Our method integrates spatial features for efficient and robust representation to capture meaningful information about the salient objects. We then train a conditional random field (CRF) using the integrated features. The trained CRF model is then used to detect salient objects during the online testing stage. We perform experiments on two standard datasets and compare the performance of our method with different reference methods. Our experiments show that our method outperforms the compared methods in terms of precision, recall, and F-Measure.

Rett syndrome (RTT) is an X-linked neurodevelopment disorder associated with the single monogenic mutation in methyl-CpG binding protein 2 (MeCP2) in up to 95% of cases. The growing number of genome-wide association studies and incomplete concordance for autoimmune diseases in monozygotic twins concur to support the involvement of environmental factors, like infectious agents or chemicals, in the breakdown of tolerance leading to autoimmunity. In fact, the coexistence of a perturbation of the immune system in RTT patients has been previously hypothesized. We herein explored the hypothesis that an autoimmune component derived from environmental bacterial infection of non typeable Haemophilus influenzae may coexist in RTT. At this purpose we screened sera from RTT syndrome patients, non-RTT pervasive developmental disorders patients and healthy controls with the hyperglucosylated adhesin protein HMW1ct(Glc) used as a precise antigen in ELISA in order to identify specific antibodies to N-glucosylation sites. Results showed that HMW1ct(Glc) is able to significantly discriminate antibodies among RTT sera and controls. Competitive ELISA confirmed the specific interaction between antibodies characteristic of RTT syndrome and the N-glucosylation motifs of the bacterial adhesin protein HMW1ct(Glc).

Understanding the distribution of rock glaciers provides key information for investigating and recognizing the status and changes of the periglacial environment. Deep learning algorithms and red-green-blue (RGB) bands from high-resolution satellite images have been extensively employed to map rock glaciers. However, the near-infrared (NIR) band offers rich spectral information and sharp edge features that could significantly contribute to semantic segmentation tasks, but it is rarely utilized in constructing rock glacier identification models due to the limitation of three input bands for classical semantic segmentation networks, like DeeplabV3+. In this study, a dual-encoder DeeplabV3+ network (DEDNet) was designed to overcome the flaws of classical DeeplabV3+ network (CDNet) when identifying rock glaciers using multispectral remote sensing images by extracting spatial and spectral features from RGB and NIR bands, respectively. This network, trained with manually labeled rock glacier samples from QiLian Mountains, established a model with accuracy, precision, recall, specificity, and mIoU (Mean Intersection over Union) of 0.9131, 0.9130, 0.9270, 0.9195, and 0.8601, respectively. The well-trained model was applied to identify new rock glaciers in a test region, achieving a producer's accuracy of 93.68% and a user's accuracy of 94.18%. Furthermore, the model was employed to two study areas in northern Tien Shan (Kazakhstan) and Daxue Shan (Hengduan Shan, China) with high accuracy, which proved that the DEDNet offers an innovative solution to more accurately map rock glaciers on a larger scale due to its robustness across diverse geographic regions.

Parkinson’s Disease (PD) is a neurodegenerative and progressive disease that impacts the nerve cells in the brain and varies from person to person. The exact cause of PD is still unknown, and the diagnosis of PD does not include a specific objective test with certainty. Although deep learning has made great progress in medical neuroimaging analysis, these methods are very susceptible to biases present in neuroimaging datasets. An innovative decorrelated deep learning technique is introduced to mitigate class bias and scanner bias while simultaneously focusing on finding distinguishing characteristics in resting-state functional MRI (rs-fMRI) data, which assist in recognizing the PD with good accuracy. The decorrelation function reduces the non-linear correlation between features and bias in order to learn bias-invariant features. The Parkinson’s Progression Markers Initiative (PPMI) dataset, referred to as a single scanner imbalanced dataset in this study used to validate our method. The imbalanced dataset problem affects the performance of the deep learning framework by overfitting to the majority class. To resolve this problem, we propose a new Decorrelated Convolutional Neural Networks (DcCNN) framework by applying decorrelation-based optimization to Convolutional Neural Networks(CNN). An analysis of evaluation metrics comparisons shows that integrating the decorrelation function boosts the performance of PD recognition by removing class bias. Specifically, our DcCNN model performs significantly better than existing traditional approaches to tackle the imbalance problem. Finally, the same framework can be extended to create scanner invariant features without significantly impacting the performance of a model. The obtained dataset is a multi-scanner dataset which leads to scanner bias due to the differences in acquisition protocols and scanners. The multi-scanner dataset is a combination of two datasets, namely PPMI and FTLDNI - frontotemporal lobar degeneration neuroimaging initiative (NIFD) dataset. The results of t-distributed stochastic neighbor embedding (t-SNE) and scanner classification accuracy of our proposed Feature Extraction-DcCNN (FE-DcCNN) model validated the effective removal of scanner bias. Our method achieves an average accuracy of 77.80% on a multi-scanner dataset for differentiating PD from healthy control, which is superior to the DcCNN model trained on a single scanner imbalanced dataset.

Cross-lingual sentiment analysis is crucial for understanding and interpreting emotions expressed in text across diverse linguistic contexts. However, cross-lingual sentiment analysis faces challenges such as differences in emotional lexicons, data imbalance, and the need for multi-language sentiment normalization. In this study, we propose a novel approach to address these challenges by leveraging low-resource language training techniques to enhance cross-lingual sentiment analysis. Our method aims to bridge the gap in emotional lexicons by adapting sentiment analysis models to diverse linguistic contexts. Additionally, we tackle issues of data imbalance through innovative data augmentation strategies tailored to each language, and we introduce a multi-language sentiment normalization technique to ensure consistent sentiment interpretation across different languages. Our method achieved state-of-the-art results in twelve languages across four domains, demonstrating superior performance in both text-level and sentence-level sentiment analysis tasks. By conducting comprehensive evaluations across diverse linguistic contexts and domains, we showcase the versatility and effectiveness of our approach in achieving top-tier results in cross-lingual sentiment analysis.

This paper focuses on enhancing the object detection and decision-making capabilities of Autonomous Emergency Medical Response Systems (AEMRS). Using advanced sensors, Convolutional Neural Networks (CNN), and reinforcement learning, we propose a model that processes environmental data to identify obstacles and make optimal navigation decisions. The integration of these technologies aims to minimize response time and improve the efficiency of emergency medical services. The perception system utilizes radar, LiDAR, and camera inputs to create a comprehensive understanding of the environment. These data are processed through a series of CNN layers to detect and classify objects such as vehicles, pedestrians, and road signs. On the decision-making front, a Q-learning algorithm is employed to enable the ambulance to learn from its interactions with the environment, continuously improving its route planning and collision avoidance strategies. By combining these advanced AI techniques, the proposed AEMRS can significantly enhance the speed and reliability of emergency responses, ultimately saving more lives. This paper presents the design, implementation, and simulation results of the proposed system, demonstrating its potential to revolutionize emergency medical services.

3D object reconstruction from depth image streams using Kinect-style depth cameras has been extensively studied. In this paper, we propose an approach for accurate camera tracking and volumetric dense surface reconstruction assuming a known cuboid reference object is present in the scene. Our contribu¬tion is three-fold. (a) We maintain drift-free camera pose tracking by incorporating the 3D geometric constraints of the cuboid reference object into the image registration process. (b) We reformulate the problem of depth stream fusion as a binary classification problem, enabling high-fidelity surface reconstruction, especially in the con¬cave zones of objects. (c) We further present a surface denoising strategy to mitigate the topological inconsistency (e.g., holes and dangling triangles), which facilitates the generation of a noise-free triangle mesh. We extend our public dataset CU3D with several new image sequences, test our algorithm on these sequences and quantitatively compare them with other state-of-the-art algorithms. Both our dataset and our algorithm are available as open-source content at https://github.com/zhangxaochen/CuFusion for oth-er researchers to reproduce and verify our results.

Named Entity Recognition (NER) serves as a fundamental and pivotal stage in the development of various knowledge-based support systems, including knowledge retrieval and question answering systems. In the domain of pig diseases, Chinese NER models encounter several challenges such as the scarcity of annotated data, domain-specific vocabulary, diverse entity categories, and ambiguous entity boundaries.To address these challenges, a corpus, labeled datasets and a lexicon specific to pig diseases for Chinese named entity recognition were constructed. Subsequently, a Pig Disease Chinese Named Entity Recognition (PDCNER) model was proposed. The model integrates external lexicon knowledge of pig disease by employing Lexicon-enhanced BERT and enhance feature representation by incorporating contrastive learning. Experimental results show that the model achieved the best recognition results, with a precision of 86.92%, a recall of 85.08%, and an F1-score of 85.99% respectively. Furthermore, the model exhibits robustness and generalizability across few-shot and publicly available datasets. Experimental results illustrate the proposed model could effectively identify Chinese named entities of pig diseases, outperforming several existing baseline methods. Moreover, the proposed model can be extended to other animal disease domains, such as chicken and cattle, thereby facilitating seamless adaptation for named entity identification across diverse contexts.

Exact sequential state estimation of orbiting objects in space can be found by predicting the state using Fokker Planck Kolmogorov Equation (FPKE) and measurement correction using Bayes’ conditional/posterior Probability Density Function (PDF). Posterior PDF can be expressed as Gaussian density expanded in terms of Hermite polynomials named as Gram Charlier Series (GCS). This research is an extension of an earlier work on second order linearized solution to nonlinear Bayesian filtering using Taylor series and third order GCS expansion of posterior PDF. In this new extension, Bayes’ posterior PDF is approximated by a mixture of GCS functions for which the parameters are propagated using linear propagation theory. The update of weights of different components of GCS mixture model uses the FPKE error as feedback to adapt for the amplitude of different GCS components while solving a quadratic programming problem earlier used for Gaussian Mixture Model (GMM) PDF. Proposed filtering method is applied on tracking of space debris. The simulation results for the filter shows performance is moderately better than single GCS filter, Extended Kalman Filter (EKF) and Gaussian Sum Filter (GSF) under space debris’ highly uncertain initial conditions and sparse measurement availability.

Object segmentation is still considered a challenging problem in autonomous driving, particularly in consideration of real world conditions. Following this line of research, this paper approaches the problem of object segmentation using LiDAR-camera fusion and semi-supervised learning implemented in a fully-convolutional neural network. Our method is tested on real-world data acquired using our custom vehicle iseAuto shuttle. The data include all-weather scenarios, featuring night and rainy weather. In this work, it is shown that LiDAR-camera fusion with only a few annotated scenarios and semi-supervised learning, it is possible to achieve robust performance on real-world data in a multi-class object segmentation problem. The performance of our algorithm is measured in terms of intersection over union, precision, recall and area-under-the-curve average precision. Our network achieves 82% IoU in vehicle detection in day fair scenarios and 64% IoU in vehicle segmentation in night rain scenarios.

With the advancement of technology, signal modulation types are becoming increasingly diverse and complex. The phenomenon of signal time-frequency overlap during transmission poses significant challenges for the classification and recognition of mixed signals, including poor recognition capabilities and low generality. This paper presents a recognition model for fine-grained analysis of mixed signal characteristics, proposing a Geometry Coordinate attention mechanism and introducing a low-rank bilinear pooling module to more effectively extract signal features for classification. The model employs a residual neural network as its backbone architecture and utilizes the Geometry Coordinate attention mechanism for time-frequency weighted analysis based on information geometry theory. This analysis targets multiple-scale features within the architecture, producing time-frequency weighted features of the signal. These weighted features are further analyzed through a low-rank bilinear pooling module, combined with the backbone features, to achieve fine-grained feature fusion. This results in a fused feature vector for mixed signal classification. Experiments were conducted on a simulated dataset comprising 39,600 mixed signal time-frequency plots. The model was benchmarked against a baseline using a residual neural network. The experimental outcomes demonstrated an improvement of 9% in the exact match ratio and 5% in the Hamming score. These results indicate that the proposed model significantly enhances the recognition capability and generalizability of mixed signal classification.

Autonomous driving systems are increasingly becoming a necessary trend towards building smart cities of the future. Numerous proposals have been presented in recent years to tackle particular aspects of the working pipeline towards creating a functional end-to-end system, such as object detection, tracking, path planning, sentiment or intent detection. Nevertheless, few efforts have been made to systematically compile all of these systems into a single proposal that effectively considers the real challenges these systems will have on the road, such as real-time computation, hardware capabilities, etc. This paper has reviewed various techniques towards proposing our own end-to-end autonomous vehicle system, considering the latest state on the art on computer vision, DSs, path planning, and parallelization.

The article’s goal is to overview challenges and problems on the way from the state of the art CUDA accelerated neural networks code to multi-GPU code. For this purpose, the authors describe the journey of porting the existing in the GitHub, fully-featured CUDA accelerated Darknet engine to OpenCL. The article presents lessons learned and the techniques that were put in place to make this port happen. There are few other implementations on the GitHub that leverage the OpenCL standard, and a few have tried to port Darknet as well. Darknet is a well known convolutional neural network (CNN) framework. The authors of this article investigated all aspects of the porting and achieved the fully-featured Darknet engine on OpenCL. The effort was focused not only on the classification with the use of YOLO1, YOLO2, and YOLO3 CNN models. They also covered other aspects, such as training neural networks, and benchmarks to look for the weak points in the implementation. The GPU computing code substantially improves Darknet computing time compared to the standard CPU version by using underused hardware in existing systems. If the system is OpenCL-based, then it is practically hardware independent. In this article, the authors report comparisons of the computation and training performance compared to the existing CUDA-based Darknet engine in the various computers, including single board computers, and, different CNN use-cases. The authors found that the OpenCL version could perform as fast as the CUDA version in the compute aspect, but it is slower in memory transfer between RAM (CPU memory) and VRAM (GPU memory). It depends on the quality of OpenCL implementation only. Moreover, loosening hardware requirements by the OpenCL Darknet can boost applications of DNN, especially in the energy-sensitive applications of Artificial Intelligence (AI) and Machine Learning (ML).

As climate changes, our daily life has been much influenced by abnormal meteorological phenomena such as heavy rainfall, heat wave, heavy snowfall, and fine dust. Atmospheric air quality is worsening day by day and indoor air quality is also affected by interconnected daily activities throughout the inside and outside of buildings and houses. Nowadays, pollutants from various sources are emitted, transformed by sunlight, vapor, and ozone and transported into the city from country to country. Due to these reasons, there have been high demands to monitor the transportation of particulate matters and improve air quality. Monitoring of pollutants and identification of type and its concentration enables us to track and control its generation and consequently find out the solution. However, monitoring of pollutants, especially, particulate matter generation and its transportation is still not fully operated in atmospheric air due to its open nature and meteorological factors. Even though indoor air is relatively easy to monitor and control than outdoor in the aspect of specific volume and contaminant source, but it still needs to consider the meteorological parameters because indoor air is not fully separated from the outdoor air flow and contaminants transportation. In this study, optical approach using spectral sensor was attempted to reveal the feasibility of wavelength and chromaticity values of reflected light from specific particles. From the analysis of reflected light of various particulate matters according to different liquid additives, parameter studies were performed to investigate which experimental conditions can contribute to the enhanced selective sensing of particulate matters. Five different particulate matters such as household dust, soil, talc powder, gypsum powder and yellow pine tree pollen were utilized and observed to elucidate the relationship between property of particulate matter and detected light spectrum. Applicable approaches to assist current particle matter sensors and improve the selective sensing were suggested.

Extracting entities from large volumes of chicken epidemic texts is crucial for knowledge sharing, integration, and application. However, Named Entity Recognition (NER) encounters significant challenges in this domain, particularly due to the prevalence of nested entities and domain-specific named entities, coupled with a scarcity of labeled data. To address these challenges, we compiled a corpus from 50 books on chicken diseases, covering 28 different disease types. Utilizing this corpus, we developed a nested NER model, MFGFF-BiLSTM-EGP. This model integrates the Multiple Fine-Grained Feature Fusion (MFGFF) module with a BiLSTM neural network and employs an Efficient Global Pointer (EGP) for predicts the entity location encoding. In MFGFF module we designed three encoders, character encoder, word encoder and sentence encoder, this design effectively captures fine-grained features and improves the recognition accuracy of nested entities. Experimental results show that the model performs robustly, with F1 scores of 91.98%, 73.32%, and 82.54% on the CDNER, CMeEE V2, and CLUENER datasets, respectively, outperforming other commonly used NER models. Specifically, on the CDNER dataset, the model achieved an F1 score of 79.68% for nested entity recognition. This research not only advances the development of knowledge graph and intelligent question-answering system for chicken diseases but also provides a viable solution for extracting disease information that can be applied to other livestock species.

Superantigens are unconventional antigens which recognise immune receptors outside the usual binding sites e.g. complementary determining regions (CDRs), to elicit a response within the target cell. T-cell superantigens crosslink T-cell receptors and MHC Class II molecules on antigen-presenting cells, leading to lymphocyte recruitment, induction of cytokine storms and T-cell anergy or apoptosis among many other effects. B-cell superantigens, on the other hand, bind immunoglobulin receptors on B-cells affecting opsonisation, IgG-mediated phagocytosis, and drive B-cells into apoptosis. Here, through a review of the structural basis for recognition of immune receptors by superantigens, we show that their binding interfaces share specific physicochemical characteristics when compared with other protein-protein interaction complexes. Given that antibody-binding superantigens have been exploited extensively in industrial antibody purification, these observations could facilitate further protein engineering to optimize the use of superantigens in this and other areas of biotechnology.

It is a challenging problem that air-written Arabic letters has received a lot of attention in the past decades when compared to commonly spoken languages like English languages. To fill this gap, we propose a strong model that brings together machine learning (ML) and optical character recognition (OCR) methods. The model applied several ML methods, (i.e., Neural Networks (NN), Random Forest (RF), K-Nearest Neighbors (KNN), and Support Vector Machine (SVM), with deep convolutional neural networks (CNNs) such as VGG16, VGG19, and SqueezeNet for effective feature extraction. Our study utilizes the AHAWP dataset, which consists of varied writing styles and variations in hand signs, to train and evaluate the model. Preprocessing systems are applied to improve data quality by reduction bias. Besides, OCR methods are combined into our model to sequestrate individual letters from continuous air-written gestures and refine recognition results. Results of this study show that the proposed model has achieved the extreme accuracy of 88.8% using NN with VGG16. This study presents an inclusive approach that combines ML, deep CNNs, and OCR methods to address the issue of Arabic in air writing recognition research.

A large part of our understanding of the biological substrates of sex-recognition and mate-recognition is derived by studying animal models. In performing those tasks, rodents rely mostly of pheromones and other olfactory cues, whereas humans rely mostly on visual cues. That may hinder the translation of rodents’ biology to humans’ biology, especially at the neural-networks level, where those cues traverse different networks in humans and rodents brains. That may be called the “pheromonal-visual gap”. A theoretical model presented here addresses those issues. The model merges observations from humans and model-animals, as reported in specific scientific reports, and general biological principles that are accepted by the scientific community. The model suggests that the voices of men and women are the innate cues based on which humans learn to use visual cues in sex-recognition and mate-recognition. Children learn the two tasks in associative learning mechanisms, by being immersed in their community, and observing adult role-models in innocuous, non-sexual scenarios. The model proposes that the human medial-geniculate-nucleus (MGN) is the analog of the rodents’ accessory-olfactory-bulb (AOB) and the main-olfactory-bulb (MOB), and that the human MASH pathway (MGN, amygdala, bnST, hypothalamus) is the analog of the rodents’ VNOP (Vomeronasal-organ-pathway). Considering the differences in the pathways should facilitate the translation from rodents’ brain nuclei and tracks to humans’. Also, the model hypothesizes that innate direct and indirect connections between auditory centers, e.g., MGN, and sex-control centers, e.g., hypothalamus, vary across three groups of children, and those variations determine the individual’s mate-recognition that emerges at puberty.

Named Entity Recognition (NER) is a fundamental and pivotal stage in the development of various knowledge-based support systems, including knowledge retrieval and question-answering systems. In the domain of pig diseases, Chinese NER models encounter several challenges such as the scarcity of annotated data, domain-specific vocabulary, diverse entity categories, and ambiguous entity boundaries. To address these challenges, we propose PDCNER, a Pig Disease Chinese Named Entity Recognition method leveraging lexicon-enhanced BERT and contrastive learning. Firstly, we construct a domain-specific lexicon and pre-train word embeddings in the pig disease domain. Secondly, we integrate lexicon information of pig diseases into the lower layers of BERT using a Lexicon Adapter layer, which employs char-word pair sequences. Thirdly, to enhance feature representation, we propose a lexicon-enhanced contrastive loss layer on top of BERT. Finally, a Conditional Random Field (CRF) layer is employed as the model's decoder. Experimental results show that our proposed model demonstrates superior performance over several mainstream models, achieving a precision of 87.76%, a recall of 86.97%, and an F1-score of 87.36%. The proposed model outperforms BERT-BiLSTM-CRF and LEBERT by 14.05% and 6.8%, respectively, with only 10% of the samples available, showcasing its robustness in data scarcity scenarios. Furthermore, the model exhibits generalizability across publicly available datasets. Our work provides reliable technical support for the information extraction of pig diseases in Chinese and can be easily extended to other domains, thereby facilitating seamless adaptation for named entity identification across diverse contexts. The codes have been open-sourced at https://github.com/tufeifei923/pdcner.

How infants engage with objects changes dramatically over the first year of life. While some infants exhibit a consistent hand preference for acquiring objects during this period, others have no identifiable preference. The goal of this study was to test whether lateralization confers an advantage in the development of early object skills. We examined whether lateralized infants show different rates of growth in how they interact with multiple objects as compared to infants without a hand preference. In a longitudinal design consisting of seven monthly visits from 6-12 months, 303 infants were assessed for hand preference and object management skill (i.e., holding up to three objects). Group-Based Trajectory Modeling (GBTM) identified three hand preference trajectory groups: Left, Right, and No Preference (NP). A Hierarchical Generalized Linear Model (HGLM) found that Left and Right infants differed in their linear and quadratic slopes and transitioned from holding one to two objects more quickly than NP infants. While all infants showed similar trends in object management skill across time, lateralized infants had an advantage. Further work is needed to determine if this early object skill advantage cascades to later more complex object handling.

Recent advancements in computer vision, especially deep learning models, have shown considerable promise in tasks related to plant image object detection. However, the efficiency of these deep learning models heavily relies on input image quality, with low-resolution images significantly hindering model performance. Therefore, reconstructing high-quality images through specific techniques will help extract features from plant images, thus improve model performance. In this study, we explored the value of super-resolution technology for improving object detection model performance on plant images. Firstly, we built a comprehensive dataset comprising 1030 high-resolution plant images, named the PlantSR dataset. Subsequently, we developed a super-resolution model using the PlantSR dataset and benchmarked it against several state-or-the-art models designed for general image super-resolution tasks. Our proposed model demonstrated superior performance on the PlantSR dataset, indicating its efficacy in enhancing the super-resolution of plant images. Furthermore, we explored the effect of super-resolution on two specific object detection tasks: apple counting and soybean seed counting. By incorporating super-resolution as a pre-processing step, we observed a significant reduction in mean absolute error. Specifically, on the YOLOv7 model employed for apple counting, the mean absolute error decreased from 13.085 to 5.71. Similarly, on the P2PNet-Soy model utilized for soybean seed counting, the mean absolute error decreased from 19.159 to 15.085. These findings underscore the substantial potential of super-resolution technology in improving the performance of object detection models for accurately detecting and counting specific plants from images. The source codes and associated datasets are available at https://github.com/SkyCol/PlantSR.

Object detection is important in many applications, such as autonomous driving. While 2D images are lack of depth information and are sensitive to environmental conditions, 3D point cloud can provide accurate depth information and a more descriptive environment. However, sparsity is always a challenge in single-frame point cloud object detection. This paper introduces a two-stage proposal-based feature fusion method for object detection using multiple frames. The proposed method, called proposal features fusion (PFF), utilizes a cosine-similarity approach to associate proposals from multiple frames and employs an attention weighted fusion module to merge features from these proposals. It allows for feature fusion specific to individual objects and offers lower computational complexity while achieving higher precision. The experimental results on the nuScenes dataset demonstrate the effectiveness of our approach, achieving a mAP of 46.7%, which is 1.3% higher than the state-of-the-art 3D object detection method.

Object-level Simultaneous Localization and Mapping (SLAM) has gained popularity in recent years since it can provide a means for intelligent robot-to-environment interactions. However, most of these methods assume that the distribution of the errors is gaussian. This assumption is not valid under many circumstances. Further, these methods use a delayed initialization of the objects in the map. During this delayed period, the solution relies on the motion model provided by an Inertial Measurement Unit (IMU). Unfortunately, the errors tend to accumulate quickly due to the dead-reckoning nature of these motion models. Finally, the current solutions depend on a set of salient features on the object’s surface and not the object’s shape. This research proposes an accurate object-level solution to the SLAM problem with a 4.1 to 13.1 cm error in the position (0.005 to 0.021 of the total path). The developed solution is based on Rao-blackwellized Particle Filtering (RBPF) that does not assume any predefined error distribution for the parameters. Further, the solution relies on the shape and thus can be used for objects that lack texture on their surface. Finally, the developed tightly coupled IMU/camera solution is based on an undelayed initialization of the objects in the map.

This paper aims at trying to answer the question of whether a low cost drone equipped with a regular camera can serve as a simple device to estimate the size of objects. Ad-ditionally, it assesses if the accuracy of measurement is good enough for using a drone for measurements, relying solely on GPS position and camera. A review of the literature pertaining to ground object measurements was conducted. The availability of such in-struments was evaluated in terms of purchase and rental costs, the number of instru-ments on the market, and the time to obtain them. The most common measurement methods were considered and their unit costs were reviewed. The cost of professional surveying and measuring equipment was compared to the possibility of using low-cost, non-commercial drones to measure objects and surfaces. The quality of the images ob-tained was compared with high-resolution satellite systems. Is an ordinary drone with a standard camera suitable for length measurement without professional measuring equipment? Should the results be considered only in the category of size estimation?

Research has been growing on object detection using semi-supervised methods in past few years. We examine the intersection of these two areas for floor-plan objects to promote the research objective of detecting more accurate objects with less labelled data. The floor-plan objects include different furniture items with multiple types of the same class, and this high inter-class similarity impacts the performance of prior methods. In this paper, we present Mask R-CNN based semi-supervised approach that provides pixel-to-pixel alignment to generate individual annotation masks for each class to mine the inter-class similarity. The semi-supervised approach has a student-teacher network that pulls information from the teacher network and feeds it to the student network. The teacher network uses unlabeled data to form pseudo-boxes, and the student network uses both unlabeled data with the pseudo boxes and labelled data as ground truth for training. It learns representations of furniture items by combining labelled and unlabeled data. On the Mask R-CNN detector with ResNet-101 backbone network, the proposed approach achieves mAP of 98.8%, 99.7%, and 99.8% with only 1%, 5% and 10% labelled data, respectively. Our experiment affirms the efficiency of the proposed approach as it outperforms the fully supervised counterpart using only 10% of the labels.

Abstract: Hand gestures are an essential kind of nonverbal communication that let people engage and be expressive with one another. As technology has progressed, hand gesture recognition systems have become an important field of study, providing a link between human activities and artificial intelligence. An overview of the field of hand gesture recognition systems is given in this abstract, along with an explanation of its importance, difficulties, and possible uses. This abstract begins by examining the role that hand gestures have in communication. It then goes on to show the cultural significance and wide range of variations in gestural expressions that occur in many contexts and societies. Artificial intelligence systems face a unique problem in comprehending and interpreting these motions, which calls for the combination of computer vision, machine learning, and pattern recognition approaches. The abstract goes on to address why people develop hand motions. The purpose behind creating systems to recognize hand gestures is also covered in the abstract, with a focus on how these systems could improve human-computer interaction in several fields, including robotics, virtual reality, healthcare, and assistive technologies. These systems have the potential to enhance accessibility, efficiency, and user experience by allowing people to engage with devices and interfaces naturally and intuitively. The abstract also discusses environmental elements including backdrop clutter and lighting, as well as the technological difficulties in identifying and understanding hand gestures, which include variations in hand forms, orientations, and movements. To tackle these obstacles, strong algorithms that can record and interpret complex hand movements in real-time must be developed.

The idea of developing a robot controlled by iris movement to assist physically disabled individuals is indeed innovative and has the potential to significantly improve their quality of life. This technology can empower individuals with limited mobility and enhance their ability to interact with their environment. Disability of movement has huge impact on the life of physically disabled people. Therefore, there is need to develop a robot which can be controlled using iris movement. The main idea of this work revolves around iris recognition from an eye image, specifically identifying the centroid of the iris. The centroid's position is then utilized to issue commands to control the robot. This innovative approach leverages iris movement as a means of communication and control, offering a potential breakthrough in assisting individuals with physical disabilities. The proposed method aims to improve the precision and effectiveness of iris recognition by incorporating advanced segmentation techniques and fuzzy clustering methods. The fast gradient filters using a fuzzy inference system (FIS) is employed to separate the iris from its surroundings. Then, the bald eagle search (BES) algorithm is employed to locate and isolate the iris region. Subsequently, the Fuzzy KNN algorithm is applied for the matching process. This combined methodology aims to improve the overall performance of iris recognition systems by leveraging advanced segmentation, search, and classification techniques. The results of the proposed model are validated using True Success Rate (TSR) and compared to other existing models. The results highlight the effectiveness of the proposed method for the 400 tested images representing 40 people.

To date, the development of unmanned technologies using autonomous underwater vehicles (AUV) has become an urgent demand for solving the problem of inspection of industrial sub-sea structures. A key issue here is precise localization of AUVs relative to underwater objects. However, the well-known challenges of recognizing and coordinating underwater objects (impossibility to use GPS, undercurrents, etc.) do not allow high-precision navigation if based solely on a standard suite of AUV navigation tools (sonars, etc.). An alternative is a technology of processing of optical images that, at short distances, can provide higher accuracy of AUV navigation compared to a technology of acoustic measurement processing. In this study, in the context of the problem of subsea production system inspection, we propose a method to recognize underwater objects and provide coordinate reference of AUV to them, based on stereo-image processing. Its distinctive features are the use of a non-standard technique for generating a geometric model of an object from its views (foreshortening) taken from positions of a pre-made overview trajectory, the use of various characteristic geometric elements when recognizing objects, and the original algorithms for comparing visual data of the inspection trajectory with an a priori model of the object.

Using the senses is essential to interact with objects in real-world environments. However, not all the senses are available when interacting with virtual objects in virtual environments. This paper presents a diamond methodology to fuse two technologies to represent the senses of sight and touch when interacting with a virtual object. The sense of sight is represented through augmented reality, and the sense of touch is represented through kinesthetic haptics. The diamond methodology is centered on the user experience and comprises five general stages: Experience design, Sensory representation, Development, Display, and Fusion. The first stage comes from the expected, proposed, or needed user experience. Then, each technology takes its homologous activities from the second to the fourth stage, diverging from each other along their development. Finally, the technologies converge to the fifth and final stage for fusion in the user experience. The diamond methodology was tested by generating a user's dual sensation when interacting with the elasticity of a tension virtual spring. The user can simultaneously perceive the visual and tactile change of the virtual spring during the interaction, representing the object's deformation. The experimental results demonstrated that an interactive experience can be felt and seen in augmented reality following the diamond methodology.

Skin image analysis using artificial intelligence (AI) has recently attracted significant research interest, particularly for analyzing skin images captured by mobile devices. Acne is one of the most common skin conditions with profound effects in severe cases. In this study, we developed an AI system called AcneDet for automatic acne object detection and acne severity grading using facial images captured by smartphones. AcneDet includes two models for conducting two tasks: (1) a Faster R-CNN-based deep learning model for the detection of acne lesion objects of four types including blackheads/whiteheads, papules/pustules, nodules/cysts, and acne scars; and (2) a LightGBM machine learning model for grading acne severity using the Investigator’s Global Assessment (IGA) scale. The output of the Faster R-CNN model, i.e., the counts of each acne type, were used as input for the LightGBM model for acne severity grading. A dataset consisting of 1,572 labeled facial images captured by both iOS and Android smartphones was used for training. The results show that the Faster R-CNN model achieves a mAP of 0.54 for acne object detection. The mean accuracy of acne severity grading by the LightGBM model is 0.85. With this study, we hope to contribute to the development of artificial intelligent systems that are able to help acne patients understand more about their conditions and support doctors in acne diagnosis.

For autonomous driving, perception is a primary and essential element that fundamentally deals with the insight into the ego vehicle’s environment through sensors. Perception is a challenging task suffering from dynamic objects and continuous environmental changes. The issue gets worse due to interrupting the quality of perception by adverse weather like snow, rain, fog, night light, sand storm, strong daylight, etc. In this work, we have tried to improve camera-based perception accuracy, such as autonomous driving-related object detection in adverse weather. We proposed the improvement of YOLOv8-based object detection in adverse weather through transfer learning using merged data from various harsh weather datasets. Two prosperous open-source datasets (ACDC and DAWN) and their merged dataset were used to detect primary objects on the road in harsh weather. A set of training weights were collected from training on the individual datasets, their merged version, and several subsets of those datasets according to their characteristics. A comparison between the training weights also occurred by evaluating the detection performance on the above-mentioned datasets and their subsets. The evaluation revealed that using custom datasets for training significantly improves the detection performance compared to the YOLOv8 base weights. And using more images through the feature-related data merging technique steadily increases the object detection performance.

Plant phenotype plays an important role in crop breeding and planting. Leaf phenotype is an important part of plant phenotype. In order to analyze the leaf phenotype, the target leaf is required to be segmented from the complex background image. In this paper, an automatic soybean leaf segmentation method based on object detection and interactive segmentation models is proposed. Firstly, the Libra R-CNN object detection algorithm is used to detect all soybean leaves in the image. Then, based on the idea that the target soybean leaf is located in the center of the image and the area is large, the detection bounding box of the target leaf is selected. In order not to destroy the segmentation result, the bounding box is optimized to completely enclose the whole leaf. Finally, according to the optimized bounding box, the prior channels of foreground and background are constructed using Gaussian model. The two channels together with the original image are as the input of the interactive object segmentation with inside-outside guidance model to segment the target soybean leaf. A large number of qualitative and quantitative experimental results show that the method has high segmentation accuracy and strong generalization capacity.

The task of determining the distance from one object to another is one of the important tasks solved in robotics systems. Conventional algorithms rely on an iterative process of predicting distance estimates, which results in an increased computational burden. Algorithms used in robotic systems should require minimal time costs, as well as be resistant to the presence of noise. To solve these problems, the paper proposes an algorithm for Kalman combination filtering with a Goldschmidt divisor and a median filter. Software simulation showed an increase in the accuracy of predicting the estimate of the developed algorithm in comparison with the traditional filtering algorithm, as well as an increase in the speed of the algorithm. The results obtained can be effectively applied in various computer vision systems.

The article proposes to use a radio holography for the detection and identification of unmanned aerial vehicles (UAVs).

In response to the problem of poor detection ability of object detection models for small-scale targets in intelligent transportation scenarios, a fusion method is proposed to enhance the features of small-scale targets, starting from feature utilization and fusion methods. The algorithm is based on the YOLOv4 tiny framework and enhances the utilization of shallow and mid level features on the basis of FPN, improving the detection accuracy of small and medium-sized targets; In view of the problem that the background of the intelligent traffic scene image is cluttered and there is more redundant information, the CBAM attention module is used to improve the attention of the model to the traffic target; To address the problem of data imbalance and prior bounding box adaptation in custom traffic datasets that expand traffic images in COCO and VOC, we propose a Copy Paste method with improved generation method and a K-means algorithm with improved distance measurement to enhance the model's detection ability for corresponding categories. Comparative experiments were conducted on a customized 260 thousand traffic dataset containing public traffic images, and the results showed that compared to YOLOv4 tiny, the proposed algorithm improved mAP by 4.9% while still ensuring the real-time performance of the model.

In recent years, research on adversarial attack techniques for remote sensing object detection (RSOD) has made great progress. Still, most of the research nowadays is on end-to-end attacks, which mainly design adversarial perturbations based on the prediction information of the object detectors (ODs) to achieve the attack. These methods do not discover the common vulnerabilities of the ODs and thus the transferability is weak. Based on this, this paper proposes a foreground feature approximation (FFA) method to generate adversarial examples (AEs) that discover the common vulnerabilities of the ODs by changing the feature information carried by the image itself to implement the attack. Specifically, firstly, the high-quality predictions are filtered as attacked objects using the detector, after which a hybrid image without any target is made, and the hybrid foreground is created based on the attacked targets. The images' shallow features are extracted using the backbone network, and the features of the input foreground are approximated towards the hybrid foreground to implement the attack. In contrast, the model predictions are used to assist in realizing the attack. In addition, we have found the effectiveness of FFA for targeted attacks, and replacing the hybrid foreground with the targeted foreground can realize targeted attacks. Extensive experiments with seven rotating ODs on the RSOD datasets DOTA and UCAS-AOD show that FFA achieves both targetless and targeted attacks with a high success rate and transferability.

Polyhymnia (33 Polyhymnia) is a main belt asteroid in our solar system with a diameter of around 54km. The density of asteroid 33 Polyhymnia, located in the main asteroid belt, is calculated to be 75g/cc. Researchers have speculated the possibility that Polyhymnia could be composed of high-density superheavy elements near atomic number 164. Here we propose that Polyhymnia could be an asteroid composed of degenerate Dark Matter (DM) and there could be many such asteroids in our solar system (this is following our earlier work suggesting Planet Nine could be such an object).

In the realm of autonomous vehicle environment perception, the primary objective of point cloud target detection is to swiftly and accurately identify three-dimensional objects from point cloud data. To meet this requirement, the prevalent network architecture employed in the industry is the voxel-based PointPillars model. Nonetheless, this model faces challenges in maintaining detection accuracy when objects are obscured or diminutive in size. In response to this issue, we introduce AGPNet, a novel model that seamlessly integrates four key modules: Data Augmentation, Dynamic Graph CNN, Pillar Feature Net, and Detection Head (SSD). The Data Augmentation module enhances the adaptability of point cloud data to complex and ever-changing real-world environments. The Dynamic Graph CNN module endows the network structure with geometric features, which encapsulate not only the point itself but also its adjacent points. The Pillar Feature Net module translates three-dimensional point cloud data into pseudo-image data through the utilization of voxels. Subsequently, the Detection Head (SSD) module leverages this pseudo-image data to conduct target detection of three-dimensional objects. Our experiments, conducted on the KITTI dataset, demonstrate that our proposed method boosts object detection accuracy by 6-7 percentage points compared to the PointPillars model, while maintaining similar detection times.

Stemming from the object overlap and undertraining from the few samples, the road dense object detection is confronted with the poor object identification performance and the inability to recognize edge objects. Based on this, one transfer learning-based YOLOv3 approach for identifying dense objects in the road has been proposed. Firstly, Darknet-53 network structure is adopted to obtain pre-trained YOLOv3 model, then the transfer training is introduced as the output layer for the special dataset of 2000 images containing vehicles; in the proposed model, one random function is adapted to intialize and optimize the weights of the transfer training model, which is seperately designed from the pre-trained YOLOv3; and the object detection classifier replaces the fully connected layer, which further improves the detection effect, the reduced size of the network model can further reduce the training and detection time, and can be better applied to actual scenarios. The experimental results demonstrate that the object detection accuracy of the presented approach is 87.75% for the Pascal VOC 2007 dataset, which is superior to the traditional YOLOv3 and the traditional YOLOv2 by 3.05% and 11.15%, respectively. Besides, the test was carried out using UA-DETRAC, a public road vehicle detection dataset, the object detection accuracy of the presented approach reaches 79.23% in detecting images, which is 4.13% better than the traditional YOLOv3, and compared with the existing relatively new object detection algorithm YOLOv5, the detection accuracy is 1.36% better. Moreover, the detection speed of the proposed YOLOv3 method reaches 31.2 Fps/s in detecting images, which is 7.6 Fps/s faster than the traditional YOLOv3, and compared with the existing relatively new object detection algorithm YOLOv5, the speed is 4.3 Fps/s faster; the proposed YOLOv3 performs 79.38Bn of floating point operations per second in detecting video, which obviously surpasses the traditional YOLOv3 and the newer object detection algorithm YOLOv5.

Since the conventional split-merge algorithm is sensitive to the object scale variance and splitting starting point, a piecewise split-merge polygon approximation method is proposed to extract the object contour features. Specifically, the contour corner is used as the starting point for the contour piecewise approximation to reduce the sensitivity of the contour segment on the starting point; then, the split-merge algorithm is used to implement the polygon approximation for each contour segments. Both the distance ratio and the arc length ratio instead of the distance error are used as the iterative stop condition to improve the robustness to the object scale variance. Both the angle and length as two features describe the shape of the contour polygon, and affect each other along the contour order relationship. Since they have a strong coupling relationship. To improve the description correction of the contour, these two features are combined to construct a Coupled Hidden Markov Model to detect the object by calculating the probability of the contour feature. The proposed algorithm is validated on ETHZ Shape Classes and INRIA Horses standard datasets. Compared with other contour-based object detection algorithms, the proposed algorithm reduces the complexity of contour description, improves the robustness of contour features to scale variance, and has a higher object detection rate.