Title :
Fast extraction method for video motion region of interest combining visual characteristics
Author :
Pengyu, Liu ; Kebin, Jia
Author_Institution :
Sch. of Electron. Inf. & Control Eng., Beijing Univ. of Technol., Beijing, China
Abstract :
When the new generation video encoding standard H.264/AVC achieved higher compression ratio and transmission robustness, computational complexity was increased acutely, and was unfavorable in real-time environmental application. Combined the visual perception characteristics and video encoding information, a new extraction method for motion region of interest and optimized coding scheme were proposed in this paper. The simulation results show that the proposed method can obtain video motion region of interest accurately, and the optimized coding scheme can achieve reduction of 53.11% encoding time on average with almost the same quality and bit-rate compared with H.264/AVC, and can be unified with other H.264/AVC fast coding technology to enhance the encoding speed further, in order to satisfy the heterogeneous networks and diversity terminal environment.
Keywords :
computational complexity; feature extraction; image motion analysis; video coding; compression ratio; computational complexity; diversity terminal environment; fast extraction method; heterogeneous networks; real-time environmental application; transmission robustness; video encoding standard H.264-AVC; video motion region of interest; visual perception characteristics; Containers; Data mining; Encoding; ISO standards; Rate-distortion; Streaming media; Visual perception; H.264/AVC; encoding information; region of interest; visual perception;
Conference_Titel :
Computer Science and Service System (CSSS), 2011 International Conference on
Conference_Location :
Nanjing
Print_ISBN :
978-1-4244-9762-1
DOI :
10.1109/CSSS.2011.5972227