Video shot analysis using efficient multiple object tracking

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.

[1]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[2]  R. Chellappa,et al.  Recursive 3-D motion estimation from a monocular image sequence , 1990 .

[3]  Rachid Deriche,et al.  Tracking line segments , 1990, Image Vis. Comput..

[4]  Takeo Kanade,et al.  Visual tracking of a moving target by a camera mounted on a robot: a combination of control and vision , 1993, IEEE Trans. Robotics Autom..

[5]  Forouzan Golshani,et al.  Motion recovery for video content classification , 1995, TOIS.

[6]  Dragutin Petkovic,et al.  Query by Image and Video Content: The QBIC System , 1995, Computer.

[7]  Hiroshi Murase,et al.  Object location using complementary color features: histogram and DCT , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[8]  Boon-Lock Yeo,et al.  Extracting story units from long programs for video browsing and navigation , 1996, Proceedings of the Third IEEE International Conference on Multimedia Computing and Systems.

[9]  Hiroshi Murase,et al.  Focused color intersection with efficient searching for object detection and image retrieval , 1996, Proceedings of the Third IEEE International Conference on Multimedia Computing and Systems.

[10]  A. Del Bimbo,et al.  Structured digital video indexing , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[11]  Hiroshi Murase,et al.  Focused color intersection with efficient searching for object extraction , 1997, Pattern Recognit..