In this section
@inproceedings{Chang:2015:10.1109/CVPR.2015.7298933,
author = {Chang, HJ and Demiris, Y},
doi = {10.1109/CVPR.2015.7298933},
pages = {3138--3146},
publisher = {IEEE},
title = {Unsupervised Learning of Complex Articulated Kinematic Structures combining Motion and Skeleton Information},
url = {http://dx.doi.org/10.1109/CVPR.2015.7298933},
year = {2015}
}
TY - CPAPER
AB - In this paper we present a novel framework for unsupervised kinematic structure learning of complex articulated objects from a single-view image sequence. In contrast to prior motion information based methods, which estimate relatively simple articulations, our method can generate arbitrarily complex kinematic structures with skeletal topology by a successive iterative merge process. The iterative merge process is guided by a skeleton distance function which is generated from a novel object boundary generation method from sparse points. Our main contributions can be summarised as follows: (i) Unsupervised complex articulated kinematic structure learning by combining motion and skeleton information. (ii) Iterative fine-to-coarse merging strategy for adaptive motion segmentation and structure smoothing. (iii) Skeleton estimation from sparse feature points. (iv) A new highly articulated object dataset containing multi-stage complexity with ground truth. Our experiments show that the proposed method out-performs state-of-the-art methods both quantitatively and qualitatively.
AU - Chang,HJ
AU - Demiris,Y
DO - 10.1109/CVPR.2015.7298933
EP - 3146
PB - IEEE
PY - 2015///
SP - 3138
TI - Unsupervised Learning of Complex Articulated Kinematic Structures combining Motion and Skeleton Information
UR - http://dx.doi.org/10.1109/CVPR.2015.7298933
UR - http://hdl.handle.net/10044/1/26460
ER -
