Title :
A unified approach to temporal segmentation of motion JPEG and MPEG compressed video
Author :
Boon-Lock Yeo ; Liu, Bede
Author_Institution :
Dept. of Electr. Eng., Princeton Univ., NJ, USA
Abstract :
A common framework for rapid scene analysis for detecting scene changes in compressed motion JPEG and MPEG videos is proposed. We develop algorithms to detect both abrupt and gradual scene changes. The algorithms operate directly on the DC sequence which can be easily extracted from motion JPEG and MPEG compressed video without decompression. The DC images capture most of the essential “global” information, but is of a small fraction of the original data size. Operating on these images offers significant computation savings. Experimental results show that the proposed algorithms are fast and effective in detecting abrupt scene changes and gradual transitions
Keywords :
data compression; image segmentation; image sequences; motion estimation; multimedia systems; video coding; DC images; DC sequence; abrupt scene change; algorithms; computation savings; global information; gradual scene change; motion JPEG compressed video; motion MPEG compressed video; rapid scene analysis; scene change detection; temporal segmentation; Histograms; Image analysis; Image coding; Image segmentation; Layout; Motion analysis; Motion detection; Multimedia systems; Transform coding; Video compression;
Conference_Titel :
Multimedia Computing and Systems, 1995., Proceedings of the International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-8186-7105-X
DOI :
10.1109/MMCS.1995.484911