Font Size: a A A

Study And Application About Key Frame Extraaction Algorithm Of Video Based On Compressed Domain

Posted on:2013-01-26Degree:MasterType:Thesis
Country:ChinaCandidate:Z D XiongFull Text:PDF
GTID:2218330371956055Subject:Computer application technology
Abstract/Summary:PDF Full Text Request
In recent years, with the rapid development of digital technology, multimedia resources are used more and more, in which contains video data with a large amount of information, intuitive and strong communication skills, etc. which has become the most important information carrier in daily life. People love gradually videos. However, the video data is chaotic, unstructured; so, how to organize, manage, index and query effectively the unstructured data is a key issue. The technology of key-frame extraction provides a feasible way to solve this problem, has become a research hotspot in recent years. The traditional methods about key-frame extraction are carried out in the pixel domain, which can not meet the practical needs; but the algorithms of key-frame extraction in compressed domain are processing speed faster, less resource consumption, high efficiency, and have become the preferred technology for video structured processing.This paper is mainly to analyze and research the algorithm about video key frame extraction in the compressed domain, and contact closely with practical application to do a lot of detailed work. Details are as follows.(1) According to the research background, I find and read a lot of English literatures, and have a certain understanding about the forefront of the dynamic field of study on this subject. The framework of international video coding standards and its related technologies are to do in-depth analysis and discussion. The extraction and quantification to video feature have been understood more comprehensively.(2) After analysis and comparison of existing algorithms, with the DCT coefficients information carried by the I-frame in video streams, a new key frame extraction method is proposed in compressed domain; and a large number of experimental data has been obtained to show that the method is efficient and robust.(3) The paper in VC++ platform with open source FFMPEG codec library and SDL multimedia library implements the application of the algorithm, and completes a video key frame extraction system about basketball in compressed domain. At the same time, the paper looks to the future development trend of the subject.
Keywords/Search Tags:Compressed Domain, DCT, Shot Segmentation, Key frames Extraction, FFMPEG, SDL
PDF Full Text Request
Related items