Rapid Object Tracking on Compressed Video

Rapid object tracking algorithm is proposed in this paper. The algorithm operates on the DC sequence and motion vectors. Full-frame decompression is not necessary to extract the DC sequence and motion vectors from compressed video sequence, which speeds up the tracking process remarkably. More than one moving objects can be tracked in a video sequence simultaneously. Global motion compensation based on compressed streams is applied to track moving objects whenever there is global motion. Experimental results show that the proposed algorithm is effective in real-time object tracking on MPEG-2 video sequence.

[1]  Jakub Segen,et al.  A camera-based system for tracking people in real time , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[2]  A. Murat Tekalp,et al.  Digital Video Processing , 1995 .

[3]  Soon Ki Jung,et al.  A model-based 3-D tracking of rigid objects from a sequence of multiple perspective views , 1998, Pattern Recognit. Lett..

[4]  Murat Kunt,et al.  Object tracking based on temporal and spatial information , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[5]  Lorenzo Favalli,et al.  Object tracking for retrieval applications in MPEG-2 , 2000, IEEE Trans. Circuits Syst. Video Technol..

[6]  Z. M. Hefed.  Object tracking , 1999 .

[7]  André Gagalowicz,et al.  Three dimensional model-based tracking using texture learning and matching , 2000, Pattern Recognit. Lett..

[8]  Boon-Lock Yeo,et al.  Rapid scene analysis on compressed video , 1995, IEEE Trans. Circuits Syst. Video Technol..

[9]  Jonathan D. Courtney.  Automatic video indexing via object motion analysis , 1997, Pattern Recognit..

[10]  Henri Nicolas,et al.  Global motion identification for image sequence analysis and coding , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.