DocumentCode
2646882
Title
Robust Superresolution Reconstruction from Compressed Video Sequences with Occlusion
Author
Chen, Hsi-Kuan ; Chen, Chin-Hsing ; Wang, Shih-Jen
Author_Institution
Inst. of Comput. & Commun. Eng., Nat. Cheng Kung Univ., Tainan
fYear
2008
fDate
15-17 Aug. 2008
Firstpage
639
Lastpage
642
Abstract
In this paper, a simple block-wise motion vector selection (BWMVS) strategy was incorporated into the motion estimation algorithm. The occlusion that severely damages the quality of the reconstructed video sequence in superresolution (SR) problem is effectively removed. The stability due to the BWMVS could be seen from the reconstruction results in comparison with the standard interpolation.
Keywords
computer graphics; data compression; image motion analysis; image reconstruction; image resolution; image sequences; interpolation; video coding; block-wise motion vector selection; compressed video sequences; interpolation; motion estimation algorithm; occlusion; superresolution problem; video reconstruction; Bayesian methods; Image coding; Image reconstruction; Motion estimation; Robustness; Signal resolution; Spatial resolution; Strontium; Video compression; Video sequences; block-wise motion vector selection (BWMVS); superresolution (SR);
fLanguage
English
Publisher
ieee
Conference_Titel
Intelligent Information Hiding and Multimedia Signal Processing, 2008. IIHMSP '08 International Conference on
Conference_Location
Harbin
Print_ISBN
978-0-7695-3278-3
Type
conf
DOI
10.1109/IIH-MSP.2008.281
Filename
4604137
Link To Document