DocumentCode :
3433953
Title :
An improved side information refinement using color-texture features for distributed video coding
Author :
Hou, Mengjie ; Men, Aidong ; Yang, Bo
Author_Institution :
Sch. of Inf. & Commun. Eng., Beijing Univ. of Posts & Telecommun., Beijing, China
fYear :
2010
fDate :
24-26 Sept. 2010
Firstpage :
230
Lastpage :
234
Abstract :
Side Information (SI) generation is a key function in the DVC decoder, and plays a critical impact on the compression efficiency. This paper proposes an improved side information generation scheme of transform domain distributed video coding considering a novel content-based side information refinement technique, which is performed with the color and texture features to segment the side information into different regions with different reliance. Then the low-reliance regions´ side information could be corrected by 3-D recursive search. In addition, an adaptive overlapped block motion compensation technique is implemented to improve performance on the base of results from the content-based approach. Experiments illustrated that a significant improvement of performance has been achieved by the proposed approach compared to the cases without it.
Keywords :
data compression; image colour analysis; image texture; motion compensation; video coding; 3D recursive search; DVC decoder; adaptive overlapped block motion compensation; color feature; color-texture feature; compression efficiency; content-based side information refinement; distributed video coding; side information generation scheme; Decoding; Feature extraction; Image color analysis; Image segmentation; Pixel; Silicon; Video coding; content-based technical; distributed video coding (DVC); side information refinement;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Network Infrastructure and Digital Content, 2010 2nd IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-6851-5
Type :
conf
DOI :
10.1109/ICNIDC.2010.5657778
Filename :
5657778
Link To Document :
بازگشت