We propose a statistical formulation for 2D human pose estimation from single images. The human body configuration is modeled by a Markov network and the estimation problem is to infer pose parameters from image cues such as appearance, shape, edge, and color. From a set of hand labeled images, we accumulate prior knowledge of 2D body shapes by learning their low-dimensional representations for inference of pose parameters. A data driven belief propagation Monte Carlo algorithm, utilizing importance sampling functions built from bottom-up visual cues, is proposed for efficient probabilistic inference. Contrasted to the few sequential statistical formulations in the literature, our algorithm integrates both top-down as well as bottom-up reasoning mechanisms, and can carry out the inference tasks in parallel. Experimental results demonstrate the potency and effectiveness of the proposed algorithm in estimating 2D human pose from single images.
Learning to estimate human pose with data driven belief propagation
2005-01-01
586506 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Loose-limbed People: Estimating 3D Human Pose and Motion Using Non-parametric Belief Propagation
British Library Online Contents | 2012
|Path Planning in Belief Space with Pose SLAM
Springer Verlag | 2017
|Nonparametric Belief Propagation
British Library Conference Proceedings | 2003
|Nonparametric belief propagation
IEEE | 2003
|