Font Size: a A A

Study On Method Of Video Key Frame Extraction

Posted on:2009-05-08Degree:MasterType:Thesis
Country:ChinaCandidate:J G CaoFull Text:PDF
GTID:2178360272475663Subject:Signal and Information Processing
Abstract/Summary:PDF Full Text Request
With the arrival of information and network times, a great deal of visual information is collected, transferred and applied all over the world. However, the problem that the information increases rapidly has been very serious. In many fields a lot of visual resource collected is set aside since it is not processed, which brings about large waste of resource. The appearance of this problem boosts the development of multimedia technology, especially, the development of video analysis technology. Among these techniques, video summary and video information retrieval have been the hotspots in recent years. In the field of video summary and video information retrieval, the problem of key frame extraction is of great importance. The methods of key frame extraction will be discussed in this thesis.In this dissertation, firstly, the development and applications of the key frame extraction technology are introduced and the characteristics and structure of the digital video have been studied on in detail. Then the technology of shot boundary detection has been researched, because key frame is extracted from the shot after shots are segmented. The study of method of key frame extraction is focused on in this thesis. Based on lots of references, the several typical methods and related technologies of key frame extraction are analyzed and summarized. At last, in order to overcome the shortcomings of the existing approaches, a new algorithm for key frame extraction based on unsupervised clustering is introduced. The proposed algorithm can capture the important salient content as the key frames, and the number of key frame are adaptive. The experiments prove that it is robust and adaptive.
Keywords/Search Tags:Shot, Key frame, Characteristics extraction, Similarity, Unsupervised clustering
PDF Full Text Request
Related items