DocumentCode :
59556
Title :
Nonrigid Structure From Motion via Sparse Representation
Author :
Kun Li ; Jingyu Yang ; Jianmin Jiang
Author_Institution :
Sch. of Comput. Sci. & Technol., Tianjin Univ., Tianjin, China
Volume :
45
Issue :
8
fYear :
2015
fDate :
Aug. 2015
Firstpage :
1401
Lastpage :
1413
Abstract :
This paper proposes a new approach for nonrigid structure from motion with occlusion, based on sparse representation. We address the occlusion problem based on the latest developments on sparse representation: matrix completion, which can recover the observation matrix that has high percentages of missing data and can also reduce the noises and outliers in the known elements. We introduce sparse transform to the joint estimation of 3-D shapes and motions. 3-D shape trajectory space is fit by wavelet basis to achieve better modeling of complex motion. Experimental results on datasets without and with occlusion show that our method can better estimate the 3-D shapes and motions, compared with state-of-the-art algorithms.
Keywords :
image motion analysis; image representation; matrix algebra; wavelet transforms; 3D shape trajectory space; complex motion modeling; matrix completion; nonrigid structure-from-motion; observation matrix; occlusion; sparse representation; sparse transform; wavelet basis; Discrete cosine transforms; Matrix decomposition; Shape; Sparse matrices; Trajectory; Wavelet transforms; Matrix completion; nonrigid structure from motion (NR-SFM); occlusion; sparse representation; wavelet basis;
fLanguage :
English
Journal_Title :
Cybernetics, IEEE Transactions on
Publisher :
ieee
ISSN :
2168-2267
Type :
jour
DOI :
10.1109/TCYB.2014.2351831
Filename :
6894159
Link To Document :
بازگشت