A compressed domain video object segmentation system

A fast means of object segmentation in a video sequence using low-level features existing in the compressed video stream is presented. These features include the DCT coefficient values of I-frames and motion vectors. The work described here is the foundation of a spatial segmentation system that approaches real time. Potential applications for the system include the separation of foreground and background objects and video database searching.

[1]  Shih-Fu Chang,et al.  A highly efficient system for automatic face region detection in MPEG video , 1997, IEEE Trans. Circuits Syst. Video Technol..

[2]  Shih-Fu Chang,et al.  Long-term moving object segmentation and tracking using spatio-temporal consistency , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[3]  Boon-Lock Yeo.  Efficient processing of compressed images and video , 1996 .

[4]  Yao Wang,et al.  An unsupervised multi-resolution object extraction algorithm using video-cube , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).