Real-Time Simultaneous Pose and Shape Estimation for Articulated Objects Using a Single Depth Camera

• Published in: 2014 IEEE Conference on Computer Vision and Pattern Recognition pp. 2353 - 2360
• Main Authors: Ye, Mao, Yang, Ruigang
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.06.2014
• Subjects: Algorithms; Articulated; Articulated Pose Estimation; Bones; Cameras; Computer vision; Deformable models; Depth Cameras; Estimation; Joints; Parametrization; Pattern recognition; Probabilistic logic; Probabilistic methods; Probability theory; Real time; Shape; Shape Estimation; State of the art
• ISSN: 1063-6919; 1063-6919; 2575-7075
• DOI: 10.1109/CVPR.2014.301

In this paper we present a novel real-time algorithm for simultaneous pose and shape estimation for articulated objects, such as human beings and animals. The key of our pose estimation component is to embed the articulated deformation model with exponential-maps-based parametrization into a Gaussian Mixture Model. Benefiting from the probabilistic measurement model, our algorithm requires no explicit point correspondences as opposed to most existing methods. Consequently, our approach is less sensitive to local minimum and well handles fast and complex motions. Extensive evaluations on publicly available datasets demonstrate that our method outperforms most state-of-art pose estimation algorithms with large margin, especially in the case of challenging motions. Moreover, our novel shape adaptation algorithm based on the same probabilistic model automatically captures the shape of the subjects during the dynamic pose estimation process. Experiments show that our shape estimation method achieves comparable accuracy with state of the arts, yet requires neither parametric model nor extra calibration procedure.