Title :
Fast coarse-to-fine video retrieval using shot-level spatio-temporal statistics
Author :
Ho, Yu-Hsuan ; Lin, Chia-Wen ; Chen, Jing-Fung ; Liao, Hong-Yuan Mark
Author_Institution :
Realtek Semicond. Corp., Hsinchu, Taiwan
fDate :
5/1/2006 12:00:00 AM
Abstract :
In this paper, we propose a fast coarse-to-fine video retrieval scheme using shot-level spatio-temporal statistics. The scheme consists of a two-step coarse search followed by a fine search. In the coarse search stage, the shot-level motion and color distribution is computed as spatio-temporal features for shot matching. The first-step coarse search uses the shot-level global statistics to reduce the size of the search space drastically. By adding an adjacent shot of the first query shot, the second-step coarse search introduces a "causality" relation between two consecutive shots to improve the search accuracy. Finally, the fine-search step refines the search result by using the local color features extracted from the key frames of the query shots. Our experimental results show that the proposed method achieves good retrieval performance with a much reduced complexity compared to single-pass methods.
Keywords :
feature extraction; image colour analysis; image matching; statistics; video retrieval; coarse-to-fine video retrieval; color distribution; color feature extraction; query shots; shot matching; shot-level spatio-temporal statistics; Content based retrieval; Distributed computing; Feature extraction; Gunshot detection systems; Indexing; Information retrieval; Multimedia databases; Statistical distributions; Statistics; Video compression; Coarse-to-fine search; query by clip; video database; video matching; video retrieval;
Journal_Title :
Circuits and Systems for Video Technology, IEEE Transactions on
DOI :
10.1109/TCSVT.2006.873156