tailieunhanh - Báo cáo hóa học: " Research Article Hierarchical Keyframe-based Video Summarization Using QR-Decomposition and Modified k-Means Clustering"

Tuyển tập báo cáo các nghiên cứu khoa học quốc tế ngành hóa học dành cho các bạn yêu hóa học tham khảo đề tài: IResearch Article Hierarchical Keyframe-based Video Summarization Using QR-Decomposition and Modified k-Means Clustering | Hindawi Publishing Corporation EURASIP Journal on Advances in Signal Processing Volume 2010 Article ID 892124 16 pages doi 2010 892124 Research Article Hierarchical Keyframe-based Video Summarization Using QR-Decomposition and Modified fc-Means Clustering Ali Amiri and Mahmood Fathy Computer Engineering Department Iran University of Science and Technology 1684613114 Narmak Tehran Iran Correspondence should be addressed to Ali Amiri a_amiri@ Received 20 May 2010 Revised 8 September 2010 Accepted 28 October 2010 Academic Editor Moon Kang Copyright 2010 A. Amiri and M. Fathy. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use distribution and reproduction in any medium provided the original work is properly cited. We propose a novel hierarchical keyframe-based video summarization system using QR-decomposition. Specially we attend to the challenges of defining some measures to detect the dynamicity of a shot and video and extracting appropriate keyframes that assure the purity of video summary. We derive some efficient measures to compute the dynamicity of video shots using QR-decomposition and we utilize it in detecting the number of keyframes that must be selected from each shot. Also we derive a theorem that illustrates an important property of QR-decomposition. We utilize it in order to summarize video shots with low redundancy. The proposed algorithm is implemented and evaluated on TRECVID 2006 benchmark platform. Compared with other algorithms our results are among the best. 1. Introduction The latest rapid growths in multimedia applications expansion of the digital multimedia in the Internet and large databases of video have initiated an increasing demand for efficient tools and methods for fast browsing and accessing the information pursued. Supplying information for pervasive access and use of multimedia is the most important objective in multimedia researches. To attain .