Title :
Video shot analysis using efficient multiple object tracking
Author :
Vinod, V.V. ; Murase, Hiroshi
Author_Institution :
NTT Basic Res. Labs., Kanagawa, Japan
Abstract :
We present a method for analyzing video shots by tracking interesting objects in the video. Tracking employs efficient object search using upper bound pruning and statistical prediction of search area. The trades are analyzed to identify representative frames in shot and to build a concise representation. Experimental results on different types of video data are promising
Keywords :
image representation; image sequences; motion estimation; object recognition; optical tracking; concise visual representation; efficient multiple object tracking; key frames; object search; representative frames; upper bound pruning; video data; video shot analysis; Animation; Focusing; Histograms; Image motion analysis; Indexing; Layout; Motion analysis; Object detection; Shape; Upper bound;
Conference_Titel :
Multimedia Computing and Systems '97. Proceedings., IEEE International Conference on
Conference_Location :
Ottawa, Ont.
Print_ISBN :
0-8186-5530-5
DOI :
10.1109/MMCS.1997.609762
