Jiang, H.; Luo, T.; Peng, H.; Zhang, G. MFCANet: Multiscale Feature Context Aggregation Network for Oriented Object Detection in Remote-Sensing Images. IEEE Access 2024, 1–1, doi:10.1109/access.2024.3381539.
Jiang, H.; Luo, T.; Peng, H.; Zhang, G. MFCANet: Multiscale Feature Context Aggregation Network for Oriented Object Detection in Remote-Sensing Images. IEEE Access 2024, 1–1, doi:10.1109/access.2024.3381539.
Jiang, H.; Luo, T.; Peng, H.; Zhang, G. MFCANet: Multiscale Feature Context Aggregation Network for Oriented Object Detection in Remote-Sensing Images. IEEE Access 2024, 1–1, doi:10.1109/access.2024.3381539.
Jiang, H.; Luo, T.; Peng, H.; Zhang, G. MFCANet: Multiscale Feature Context Aggregation Network for Oriented Object Detection in Remote-Sensing Images. IEEE Access 2024, 1–1, doi:10.1109/access.2024.3381539.
Abstract
Detecting rotated objects in remote sensing images poses a substantial challenge. These images usually cover a wide field of view, containing diverse and complex backgrounds with variously sized ground objects densely distributed. Therefore, identifying objects of interest in remote-sensing images is challenging. While integrating Convolutional Neural Networks (CNNs) and Transformer networks has exhibited progress in detecting rotated objects, there is still scope for enhancing feature extraction and fusion. To address this issue, we propose a feature extraction module, a feature context aggregation module, and a multi-scale feature fusion module. Initially, we substitute the Spatial Pyramid Pooling Bottleneck (SPPFBottleneck) with a new module aimed at extracting multi-scale features, thereby enhancing the detection of small objects in complex backgrounds. Next, we develop a novel module for the multi-scale fusion of contextual information within feature maps, extracting valuable information. Finally, we combine the original features with the fused ones to prevent the loss of specific features in the fusion process. We refer to our newly proposed model as the "Multi-scale Feature Context Aggregation Network" (MFCANet). We assess our approach on three challenging remote sensing datasets: MAR20, SRSDD, and HRSC. Comprehensive experimental results show that our method surpasses baseline models by 2.13%, 10.28%, and 1.46% mAP on the MAR20, SRSDD, and HRSC datasets, respectively.
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.