Recent Trends and Research Issues in Video Association Mining
📝 Abstract
With the ever-growing digital libraries and video databases, it is increasingly important to understand and mine the knowledge from video database automatically. Discovering association rules between items in a large video database plays a considerable role in the video data mining research areas. Based on the research and development in the past years, application of association rule mining is growing in different domains such as surveillance, meetings, broadcast news, sports, archives, movies, medical data, as well as personal and online media collections. The purpose of this paper is to provide general framework of mining the association rules from video database. This article is also represents the research issues in video association mining followed by the recent trends.
💡 Analysis
With the ever-growing digital libraries and video databases, it is increasingly important to understand and mine the knowledge from video database automatically. Discovering association rules between items in a large video database plays a considerable role in the video data mining research areas. Based on the research and development in the past years, application of association rule mining is growing in different domains such as surveillance, meetings, broadcast news, sports, archives, movies, medical data, as well as personal and online media collections. The purpose of this paper is to provide general framework of mining the association rules from video database. This article is also represents the research issues in video association mining followed by the recent trends.
📄 Content
The International Journal of Multimedia & Its Applications (IJMA) Vol.3, No.4, November 2011 DOI : 10.5121/ijma.2011.3405 49
RECENT TRENDS AND RESEARCH ISSUES IN VIDEO ASSOCIATION MINING
Vijayakumar.V 1 and Nedunchezhian.R 2 1 Research Scholar, Bharathiar University, Coimbatore, & Department of Computer Applications, Sri Ramakrishna Engineering College, Coimbatore, Tamil Nadu, India - 641 022 veluvijay20@gmail.com 2 Professor and Head, Department of Information Technology, Sri Ramakrishna Engineering College, Coimbatore, Tamil Nadu, India-641 022 rajuchezhian@gmail.com
ABSTRACT
With the ever-growing digital libraries and video databases, it is increasingly important to understand and
mine the knowledge from video database automatically. Discovering association rules between items in a
large video database plays a considerable role in the video data mining research areas. Based on the
research and development in the past years, application of association rule mining is growing in different
domains such as surveillance, meetings, broadcast news, sports, archives, movies, medical data, as well as
personal and online media collections. The purpose of this paper is to provide general framework of
mining the association rules from video database. This article is also represents the research issues in
video association mining followed by the recent trends.
KEYWORDS
Temporal Frequent Pattern; Video classification; Event Detection
- INTRODUCTION Multimedia data is being acquired at an increasing rate due to technological advances in sensors, computing power, and storage. Multimedia Data Mining is the process of extracting previously unknown knowledge and detecting interesting patterns from a massive set of multimedia data [3]. Video is rapidly becoming one of the most popular multimedia due to its high information and entertainment capability. It also consists of audio, video and text together.
Video mining is a process which can not only automatically extract content and structure of video, features of moving objects, spatial or temporal correlations of those features, but also discover patterns of video structure, objects activities, video events, etc. from vast amounts of video data without little assumption about their contents [1][28]. Many video mining approaches have been proposed for extracting useful knowledge from video database. Finding desired information in a video clip or in a video database is still a difficult and laborious task due to its semantic gap between the low-level feature and high-level video semantic concepts. Video data mining can be classified in following categories, such as pattern detection, video clustering and classification and video association mining [2][8]. The International Journal of Multimedia & Its Applications (IJMA) Vol.3, No.4, November 2011 50 One of the important problems in video data mining is video association rule mining. Mining association rule from video data is usually a straightforward extension of association rule mining in transaction databases. Video Association Mining is a relatively new and emerging research trend. It is the process of discovering associations in a given video. It aims to extract interesting correlations, frequent patterns, associations or casual structures among sets of items in the video databases. This technique is an extension of data mining to image domain. It is an inter disciplinary field that combines techniques like computer vision, image processing, data mining, machine learning, data base and artificial intelligence. A lot of work was developed to find the association in the traditional transactional database. Video association mining is still in its infancy, and an under-explored field. Only limited work was developed in this area.
A video database contains lot of semantic information. The semantic information describes what is happening in the video and also what is perceived by human users. The semantic information of a video has two important aspects [4][8][10]. They are (a). A spatial aspect which means a semantic content presented by a video frame, such as the location, characters and objects displayed in the video frame. (b). A temporal aspect which means a semantic content presented by a sequence of video frames in time, such as character’s action and object’s movement presented in the sequence. To represent temporal aspects, the higher-level semantic information of video is extracted by examining the features audio, video, and superimposed text of the video. The semantic information includes the detecting trigger events, determining typical and anomalous patterns of activity, generating person-centric or object-centric views of an activity, classifying activities into named categories, and clustering and determining the inter
This content is AI-processed based on ArXiv data.