Unsupervised Learning of Complex Articulated Kinematic Structures combining Motion and Skeleton Information

File Description SizeFormat 
CVPR2015_Chang.pdfAccepted version10 MBAdobe PDFDownload
Title: Unsupervised Learning of Complex Articulated Kinematic Structures combining Motion and Skeleton Information
Author(s): Chang, HJ
Demiris, Y
Item Type: Conference Paper
Abstract: 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.
Publication Date: 7-Jun-2015
Date of Acceptance: 1-Mar-2015
URI: http://hdl.handle.net/10044/1/26460
DOI: https://dx.doi.org/10.1109/CVPR.2015.7298933
Publisher: IEEE
Start Page: 3138
End Page: 3146
Journal / Book Title: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Copyright Statement: © 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The embargo on this paper will end once published.
Conference Name: IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publication Status: Published
Start Date: 2015-06-07
Finish Date: 2015-06-12
Conference Place: Boston, MA
Appears in Collections:Faculty of Engineering
Electrical and Electronic Engineering



Items in Spiral are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commons