Video Indexing

— Video has involved in almost every industry. Today video is shared 1200 times more than texts and images on social media. Unfortunately, users are still facing some difficult to get relevant data. Indexing and retrieval of video is a very challenging problem among computer vision researchers because of the huge amount of data available in internet. In this survey paper describes about video indexing, video retrieval, content based video indexing, visual content based video indexing and multimodal video indexing, key frame extraction and various indexing techniques. Instead of text and image this study is focuses on indexing and retrieval techniques for video.

Retrieval of multimedia has become a requirement for many contemporary information systems. These systems need to provide browsing, querying, navigation, and, sometimes, composition capabilities involving various forms of media. In this survey, we review techniques for text, image, audio and video retrieval. We first look at indexing and retrieval techniques for text, audio, image and video. We also discuss features visual features for video retrieval such as colour, texture, shape. The indexing techniques are discussed for these features. We also compare most popular techniques used for indexing and retrieval.

This paper concerns shot boundary detection in digital video. Automatic video segmen- tation is a first step towards video indexing. An efficient yet robust algorithm is needed to separate video sequences into smaller segments called shots. Although many researchers have tackled the problem of finding shot boundaries, few have been able to accurately detect gradual transition boundaries such as fades

The paper focuses on an approach to a near-duplicate videos search. The search is based on the comparison of scene relative lengths in the space L2. The comparison is made with Gale-Church hypothesis. The concept "shot descriptor" was introduced. To speed up the performance of this method, semantic hashing was suggested, i.e. a generalization of locally sensitive hashing. 

В работе рассмотрен подход для поиска нечетких дубликатов видео. Поиск основан на сравнении относительных длин сцен в пространстве L2. Сравнение проводится с учетом гипотезы Гейла-Черча. Вводится понятие «дескриптора сцены». Для ускорения работы метода предложено использовать семантическое хеширование, обобщение локально чувствительного хеширования.

Nowadays visual information is gaining much more importance than textual information as pictures convey more than words. As image has richer content than text, Video database is increasing exponentially over the Internet. Content-based Video retrieval (CBVR) from large video storage has become a challenging and important issue for researchers over worldwide. There is lack of tools so it is difficult to distinguish between low and high level feature. There has been lot of CBVR systems developed but still there is a lack of efficient retrieval system, as many retrieval techniques are not suitable for extensive search and so it deteriorates the overall performance of system. In this paper we have given an outline of the sequential steps of existing CBVR systems.

— In this paper, we propose a video summarization algorithm by multiple extractions of key frames in each shot. This algorithm is based on the k partition algorithms. We choose the ones based on k-medoid clustering methods so as to find the best representative object for each partitions. In order to find the number of partition (i.e. the number of representative frames of each shot), we introduce a quantity based on the distance between frames and on the size of the video shot. This algorithm, which is applicable to all types of descriptors, consists of extracting key frames by similarity clustering according to the given index (histogram features, motion features, texture features, or a combination of these features). In our proposal, the distance between frames is calculated using a fast full search block matching algorithm based on the frequency domain. The proposed approach is computationally tractable and robust with respect to sudden changes in mean intensity within a shot. Ad...

The actual generation of video search engines offers low-level abstractions of the data while users seek for high-level semantics. The main challenge in video retrieval remains bridging the semantic gap. Thus, the effectiveness of video retrieval is based on the result of the interaction between query selection and a goal-oriented human user. The system exploits the human capability for rapidly scanning imagery augmenting it with an active learning loop, which tries to always present the most relevant material based on the current information. We describe in this paper, a machine learning system for interactive video retrieval. The core of this system is a kernel-based SVM classifier. The video retrieval uses the core as an active learning classifier. We perform an experiment against the 2005 NIST TRECVID benchmark in the high-level task.

Soccer event detection deals with identifying interesting segments in soccer video via audio/visual content analysis. This task enables automatic high-level index creation, which circumvents large-scale manual annotation and facilitates semantic-based retrieval. This thesis proposes two frameworks for event detection through collaborative analysis of textual, aural and visual features. The frameworks share a common initial component where both utilize an external textual resource, which is the minute-by-minute (MBM) reports from sports broadcasters, to accurately localize sections of video containing the desired events. The first framework identifies
an initial estimate of an eventful segment via audio energy analysis. Visual semantic features are then observed to further refine the detected eventful segment. The second framework
implements a ranking procedure where semantic visual features are firstly analyzed to generate a shortlist of candidates. This is followed by aural or visual analysis to rank the actual eventful candidate top-most within the respective shortlist. Both frameworks rely on uncomplicated audio/visual feature sets, which is the main advantage compared to previously proposed works. Furthermore, manually labeled data are not needed since audio/visual considerations are based on automatically classified semantic visual features and low-level aural calculations. Evaluation made over a large video dataset shows promising results for goal, penalty, yellow card, red card and substitution events detection.

In this paper we describe a system we have developed for automatic broadcast-quality video indexing that successfully combines results from the fields of speaker verification, acoustic analysis, very large vocabulary speech recognition, content based sampling of video, information retrieval, natural language processing, dialogue systems, and MPEG2 delivery over IP. Our audio classification and anchorperson detection (in the case of news material) classifies video into news versus commercials using acoustic features and can reach 97% accuracy on our test data set. The processing includes very large vocabulary speech recognition (over 230K-word vocabulary) for synchronizing the closed caption stream with the audio stream. Broadcast news corpora are used to generate language models and acoustic models for speaker identification. Compared with conventional discourse segmentation algorithms based on only text information, our integrated method operates more efficiently with more accurate...

Premier guide (conçu et rédigé en 2005) pour une analyse systématique du contenu de données audiovisuelles enregistrées, traitées et diffusées sur les portails du programme de recherche "Archives Audiovisuelles de la Recherche" (AAR).
Principaux types de description/d'analyse:
1) Description paratextuelle.
2) Description textuelle.
3) Description pragmatique.
4) Description péritextuelle.
5) Description par mots clés.
6) Description référentielle.
7) Description rhétorique.
8) Description narrative.
9) Description-traduction.
10 Parcours de description.

The paper focuses on the algorithms of the event detection in content-based video retrieval. Video has a complex structure and can express the same idea in different ways. This makes the task of searching for video more complicated. Video titles and text descriptions cannot give the whole information about objects and events in the video. This creates a need for content-based video retrieval. There is a semantic gap between low-level video features, that can be extracted, and the users’ perception. The task of event detection is reduced to the task of video segmentation. Complex content-based video retrieval can be regarded as the bridge between traditional retrieval and semantic-based video retrieval. The properties of video as a time series are described. Introduced the concept of anomalies in the video. A method for event detection based on comparing moving averages with windows of different sizes is proposed. According to the classification given at the beginning of this article, our method refers to statistical methods. It differs from other methods with low computational complexity and simplicity. The video stream processing language is proposed for function-based description of video handling algorithms. So, our method is formulated in the form of a declarative description on an interpreted programming language. Unfortunately, most of the existing video processing methods use exclusively imperative approach, which often makes understanding more difficult. Examples of the use of this language are given. Its grammar is described too. As shown by experiments, the implementation of the proposed video events retrieval method, unlike their counterparts, can work for video streams too with a real-time and potentially infinite frame sequences. Such advantages within low computational requirements make implementation of the method helpful in aviation and space technology. The algorithm has some disadvantages due to necessity parameter selection for particular task classes. The theorem on near-duplicates of video is formulated at the end of the article. It asserts the near-duplicate videos express the same sequence of phenomena.

The paper focuses on an overview of the different existing methods in content-based video retrieval. During the last decade there was a~rapid growth of video posted on the Internet. This imposes urgent demands on video retrieval. Video has a complex structure and can express the same idea in different ways. This makes the task of searching for video more complicated. Video titles and text descriptions cannot give the hole information about objects and events in the video. This creates a need for content-based video retrieval. There is a semantic gap between low-level video features, that can be extracted, and the users' perception. Complex content-based video retrieval can be regarded as the bridge between traditional retrieval and semantic-based video retrieval.

Keywords: frames; near-duplicates video; scenes; shots; video annotation; video classification; video mining; video reranking; video retrieval.

В статье предлагается обзор различных существующих методов ассоциативного поиска по видео. В течение прошлого десятилетия наблюдался стремительный рост количества видео размещаемых в Интернете, что создало острую необходимость в появлении поиска по видео. Видео имеет сложную структуру. Одна и та же информация может быть выражена различными способами. Это серьёзно усложняет задачу видео-поиска. Заголовки и описания видео не могут дать полного представления о самом видео, что влечет за собой необходимость использования ассоциативного поиска по видео. Существует семантический разрыв между низкоуровневыми характеристиками видео и восприятием пользователей. Комплексный ассоциативный видео-поиск может рассматриваться как связующее звено между обычным поиском и смысловым поиском по видео.

Ключевые слова: анализ видео; аннотирование видео; видео-поиск; кадры; классификация видео; нечеткие дубликаты видео; ранжирование видео; сцены; съёмки.

In this paper, a novel algorithm meant for content based video indexing and retrieval based on key frames Discrete Wavelet Center Symmetric Local Binary Patterns (DWCSLBP) is introduced. The algorithm is applied on a dataset of three hundred and thirty five videos, in which one hundred and forty eight videos are of airplane type, seventy two videos are of boat type, eighty videos are of car type, and thirty five videos are of war tank type (Which are collected from Google, BBC, and TRECVID 2005). The performance of the algorithm is compared with existing volume local binary patterns (VLBP) extraction method. The proposed method has shown good results compare to existing method.

The systems currently available for contentbased image and video retrieval work without semantic knowledge, i. e. they use image processing methods to extract low level features of the data. The similarity obtained by these approaches does not always correspond to the similarity a human user would expect. A way to include more semantic knowledge into the indexing process is to

In the context of video indexing, we present the Clavis system in which typical video sequences of television programs are represented by templates. Templates are terminological constraint networks in which video segments coming from automatic analysis tools are represented in a description logic formalism. Templates allow to express complex classes of video sequences with temporal constraints associated to a regular

This paper presents the use of video parsing and video analysis techniques to attain a radical change in Content Analysis processes. Content Analysis provides frameworks for a better understanding of information, mass media information in particular. The goals of the work presented in this paper are to assess the feasibility of designing Content Analysis processes under much faster and much

This paper presents two motion descriptors which were recommended by MPEG to become part of the first visual reference model (XM 1.0) of the evolving MPEG-7 standard in development. These motion descriptors are: (i) the camera motion descriptor which describes the global motion of the camera or of the observer in a natural 3-D scene, and (ii) the object motion

Даны два видео файла или потока. Нужно выяснить являются ли они дубликатами друг друга. Здесь, под словом дубликат понимается не формализуемое условие: «На этих файлах изображено одно и то же?».  Возможна, и другая постановка этой задачи. Дан набор видео, для нового добавляемого в этот набор видео нужно определить,  есть ли дубликат этого нового видео в наборе или нет. Понятие «нечеткий дубликат» является устоявшимся термином в задачах информационного поиска и обычно употребляется применительно к документам и изображениям. Нечеткость в данном случае интерпретируется как неполное или частичное совпадение документов или изображений.