Title :
A compressed domain video object segmentation system
Author :
Jamrozik, Michele L. ; Hayes, Monson H.
Author_Institution :
Dept. of Electr. & Comput. Eng., Georgia Tech Lorraine, Metz, France
Abstract :
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.
Keywords :
discrete cosine transforms; image segmentation; image sequences; transform coding; video coding; DCT coefficient values; I-frames; background objects; compressed video stream; foreground objects; low-level features; motion vectors; object segmentation; spatial segmentation system; video database searching; video sequence; Discrete cosine transforms; Image coding; Image resolution; Image segmentation; Jamming; MPEG 4 Standard; Object segmentation; Streaming media; Video compression; Video sequences;
Conference_Titel :
Image Processing. 2002. Proceedings. 2002 International Conference on
Print_ISBN :
0-7803-7622-6
DOI :
10.1109/ICIP.2002.1037972
