DocumentCode :
2511560
Title :
Motion-sketch Based Video Retrieval Using a Trellis Levenshtein Distance
Author :
Hu, Rui ; Collomosse, John
Author_Institution :
Centre for Vision, Speech & Signal Process. (CVSSP), Univ. of Surrey, Guildford, UK
fYear :
2010
fDate :
23-26 Aug. 2010
Firstpage :
121
Lastpage :
124
Abstract :
We present a fast technique for retrieving video clips using free-hand sketched queries. Visual keypoints within each video are detected and tracked to form short trajectories, which are clustered to form a set of space-time tokens summarising video content. A Viterbi process matches a space-time graph of tokens to a description of colour and motion extracted from the query sketch. Inaccuracies in the sketched query are ameliorated by computing path cost using a Levenshtein (edit) distance. We evaluate over datasets of sports footage.
Keywords :
graph theory; image colour analysis; image motion analysis; image retrieval; object detection; video signal processing; Trellis Levenshtein distance; Viterbi process; motion extraction; motion-sketch based video retrieval; query sketch; space-time graph; space-time tokens; sports footage; video content; Color; Histograms; Horses; Image color analysis; Trajectory; Visualization; Viterbi algorithm; retrieval; sketch; video;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition (ICPR), 2010 20th International Conference on
Conference_Location :
Istanbul
ISSN :
1051-4651
Print_ISBN :
978-1-4244-7542-1
Type :
conf
DOI :
10.1109/ICPR.2010.38
Filename :
5597613
Link To Document :
بازگشت