Simultaneous Segmentation and Pose Estimation of Humans Using Dynamic Graph Cuts

• Published in: International journal of computer vision Vol. 79; no. 3; pp. 285 - 298
• Main Authors: Kohli, Pushmeet, Rihan, Jonathan, Bray, Matthieu, Torr, Philip H. S.
• Format: Journal Article
• Language: English
• Published: Boston Springer US 01.09.2008; Springer; Springer Nature B.V
• Subjects: Applied sciences; Artificial Intelligence; Computer Imaging; Computer Science; Computer science; control theory; systems; Exact sciences and technology; Image Processing and Computer Vision; Pattern Recognition; Pattern Recognition and Graphics; Pattern recognition. Digital image processing. Computational geometry; Studies; Vision; Segmentation; Pose estimation; Energy minimization; Bayes estimation; Prior information; Probabilistic approach; Image processing; Inference; Minimization; N body system; Conditional probability; Deformable body; Optimization; Posture; Multiple view; Graph cut; Linkage mechanism; Tridimensional image
• ISSN: 0920-5691; 1573-1405
• DOI: 10.1007/s11263-007-0120-6

This paper presents a novel algorithm for performing integrated segmentation and 3D pose estimation of a human body from multiple views. Unlike other state of the art methods which focus on either segmentation or pose estimation individually, our approach tackles these two tasks together. Our method works by optimizing a cost function based on a Conditional Random Field ( CRF ). This has the advantage that all information in the image (edges, background and foreground appearances), as well as the prior information on the shape and pose of the subject can be combined and used in a Bayesian framework. Optimizing such a cost function would have been computationally infeasible. However, our recent research in dynamic graph cuts allows this to be done much more efficiently than before. We demonstrate the efficacy of our approach on challenging motion sequences. Although we target the human pose inference problem in the paper, our method is completely generic and can be used to segment and infer the pose of any rigid, deformable or articulated object.