Mepco Schlenk Engineering College. Department of Computer Science and Engineering. IV CSE 2010-2011 Project Proposal.

Name : K.Naveenkumar (07cs051) M.Munish Kumar (07cs049) Project Title Synopsis : Video Subsequence Identification. :

The rapid advances in multimedia and network technologies popularize many applications of video databases, and sophisticated techniques for representing, matching, and indexing videos are in high demand. A video sequence is an ordered set of a large number of frames, and from the database research perspective, each frame is usually represented by a high-dimensional vector, which has been extracted from some low-level content features, such as colour distribution, texture pattern, or shape structure within the original media domain. Video subsequence identification involves locating the position of the most similar part with respect to a user-specified query clip from a long prestored video sequence. Subsequence identification task aims at finding if there exists any subsequence of a long database video that shares similar content to a query clip. The procedures to find the same sequence are to use the novel batch query algorithm which retrieves similar frames, the mapping relationship between the query and database video is first represented by a bipartite graph. The densely matched parts along the long sequence are then extracted, followed by a filter-and-refine search strategy to prune some irrelevant sub sequences. Using the filtering method, maximum size matching is deployed for each sub graph constructed by the query and candidate subsequence to obtain a smaller set of candidates. During the refinement stage, sub-maximum similarity matching is devised to identify the subsequence with the highest aggregate score from all candidates, according to a robust video similarity model that incorporates visual content, temporal order, and frame alignment information. From these analysis and algorithms the short query video clip can be identified in the long video sequence. Base Paper : Effective and Efficient Query Processing for Video Subsequence Identification IEEE Transactions on Knowledge and Data Engineering, vol. 21, no. 3, march 2009. Page no.-321-334 Language : Java. Signature Date : :