Video Retrieval System Based On Avs And Implementation

With the advance of technology of computer,telecommunication,wide-band network and compression of video and audio,it is not a difficult problem for the store and video data. Digital video is widely coming into the life of people. It is becoming the emergent and important issues for efficent organization, representation, store and management of video data as well as rapid retrieval and browsing of video data. The traditional data management and retrieval method cannot do better to search the requiring information from the huge amount of video data. As a result the content-based video retaieval system emerges(CBVR), as the times require.The AVS standard is the series of "information technology advanced Audio and Video Coding" standard abbreviation. The AVS standard includes four main technical standards: system, video, audio and digital copyright management, and support standard: consistency test. The fully Intellectual Property of second generation Source Coding-Decoding Standard– AVS is owned by China. Source coding technology mainly focuses on mass video and audio (original data and sources) compression technology, also known as digital video and audio coding technology. Obviously, as the premise of digital information transmission, storage and broadcast it is also the general foundation character standard of the digital video & audio industry. Since 2006 AVS standard video (AVS-P2)part officially passed the public show and became the national standard , the emergence of many outstanding technical proposals,and sucessfully developed for high-definition digital TV broadcasting, streaming media transmission, mobile multimedia communications applications such as video coding standard, in addition to norms in the system, audio coding, digital copyright protection and other areas has also been made in some of the fruits and has begun to take shape with our own proprietary intellectual property of the standard system.In this paper,AVS video as the research object, content-based video retrieval as a starting point, a content-based video retrieval model AVS. Because in the current video image database, basically a color picture-based, so at content-based video retrieval AVS technology, the use of color characteristics of video key frame extraction as a basis. And based on the model to study the key-frame extraction and video retrieval technology. The main thesis of the job are as follows:The use of key frames greatly reduces the amount of data indexed Videos meanwhile one for video retrieval and browsing provides an organizational framework. Videos consecutive frames based on the similarity between this characteristic, this paper proposes an approach based on image similarity of the key frame extraction algorithm, based on the algorithm selected keyframe more representative, and the number of key frame extraction can be effective control and reduce the key-frame redundancy.In this paper, a global feature and local feature a combination of video retrieval algorithms, based on this algorithm can improve the process of retrieval precision.