The Community for Technology Leaders
Green Image
Issue No. 09 - Sept. (2012 vol. 34)
ISSN: 0162-8828
pp: 1744-1757
Y. Matsushita , Microsoft Res. Asia, Beijing, China
Jiaya Jia , Dept. of Comput. Sci. & Eng., Chinese Univ. of Hong Kong, Shatin, China
Li Xu , Dept. of Comput. Sci. & Eng., Chinese Univ. of Hong Kong, Shatin, China
A common problem of optical flow estimation in the multiscale variational framework is that fine motion structures cannot always be correctly estimated, especially for regions with significant and abrupt displacement variation. A novel extended coarse-to-fine (EC2F) refinement framework is introduced in this paper to address this issue, which reduces the reliance of flow estimates on their initial values propagated from the coarse level and enables recovering many motion details in each scale. The contribution of this paper also includes adaptation of the objective function to handle outliers and development of a new optimization procedure. The effectiveness of our algorithm is demonstrated by Middlebury optical flow benchmarkmarking and by experiments on challenging examples that involve large-displacement motion.
optimisation, image motion analysis, image sequences, image motion, optical flow estimation, multiscale variational framework, motion structure, displacement variation, extended coarse-to-fine refinement framework, EC2F refinement framework, motion detail, objective function, outlier, optimization procedure, Middlebury optical flow benchmarkmarking, large-displacement motion, Estimation, Optimization, Optical imaging, Vectors, Adaptive optics, Image color analysis, Robustness, features., Optical flow, image motion, video motion, variational methods, optimization
Y. Matsushita, Jiaya Jia, Li Xu, "Motion Detail Preserving Optical Flow Estimation", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 34, no. , pp. 1744-1757, Sept. 2012, doi:10.1109/TPAMI.2011.236
238 ms
(Ver 3.1 (10032016))