Title :
Semiautomatic segmentation using spatio-temporal gradual region merging for MPEG-4
Author :
Kim, Young-Ro ; Kim, Jae-Hwan ; Kim, Jin-Cheol ; Kim, Tae-Hyun ; Ko, Sung-Jea
Author_Institution :
Dept. of Electron. Eng., Korea Univ., Seoul, South Korea
Abstract :
We propose a new semiautomatic segmentation method using spatio-temporal similarity. In the proposed scheme, segmentation is performed using gradual region merging and bi-directional spatio-temporal refinement. Simulation results show the efficiency of the proposed method in semantic object extraction
Keywords :
code standards; data compression; feature extraction; image segmentation; image sequences; telecommunication standards; video coding; MPEG-4; bi-directional spatio-temporal refinement; semantic object extraction; semiautomatic segmentation; simulation results; spatio-temporal gradual region merging; spatio-temporal similarity; video sequences; Bidirectional control; Bismuth; Colored noise; Design for disassembly; Encoding; Humans; MPEG 4 Standard; Merging; Motion estimation; Video sequences;
Conference_Titel :
Consumer Electronics, 2001. ICCE. International Conference on
Conference_Location :
Los Angeles, CA
Print_ISBN :
0-7803-6622-0
DOI :
10.1109/ICCE.2001.935246
