DocumentCode
3402435
Title
Motion detail preserving optical flow estimation
Author
Xu, Li ; Jia, Jiaya ; Matsushita, Yasuyuki
Author_Institution
Chinese Univ. of Hong Kong, Hong Kong, China
fYear
2010
fDate
13-18 June 2010
Firstpage
1293
Lastpage
1300
Abstract
We discuss the cause of a severe optical flow estimation problem that fine motion structures cannot always be correctly reconstructed in the commonly employed multi-scale variational framework. Our major finding is that significant and abrupt displacement transition wrecks small-scale motion structures in the coarse-to-fine refinement. A novel optical flow estimation method is proposed in this paper to address this issue, which reduces the reliance of the flow estimates on their initial values propagated from the coarser level and enables recovering many motion details in each scale. The contribution of this paper also includes adaption of the objective function and development of a new optimization procedure. The effectiveness of our method is borne out by experiments for both large- and small-displacement optical flow estimation.
Keywords
image motion analysis; image reconstruction; image sequences; coarse-to-fine refinement; displacement transition; motion detail preserving optical flow estimation; motion structures; multiscale variational framework; objective function; optimization procedure; Asia; Cameras; Councils; Image motion analysis; Motion estimation; Neck; Optical computing; Optical propagation; Robustness; Visualization;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on
Conference_Location
San Francisco, CA
ISSN
1063-6919
Print_ISBN
978-1-4244-6984-0
Type
conf
DOI
10.1109/CVPR.2010.5539820
Filename
5539820
Link To Document