UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Latent variable pictorial structure for human pose estimation on depth images

He, L; Wang, G; Liao, Q; Xue, J-H; (2016) Latent variable pictorial structure for human pose estimation on depth images. Neurocomputing , 203 pp. 52-61. 10.1016/j.neucom.2016.04.009. Green open access

[thumbnail of He et al Latent variable pictorial structure for human pose estimation on depth images.pdf]
Preview
Text
He et al Latent variable pictorial structure for human pose estimation on depth images.pdf

Download (3MB) | Preview

Abstract

Prior models of human pose play a key role in state-of-the-art techniques for monocular pose estimation. However, a simple Gaussian model cannot represent well the prior knowledge of the pose diversity on depth images. In this paper, we develop a latent variable-based prior model by introducing a latent variable into the general pictorial structure. Two key characteristics of our model (we call Latent Variable Pictorial Structure) are as follows: (1) it adaptively adopts prior pose models based on the estimated value of the latent variable; and (2) it enables the learning of a more accurate part classifier. Experimental results demonstrate that the proposed method outperforms other state-of-the-art methods in recognition rate on the public datasets.

Type: Article
Title: Latent variable pictorial structure for human pose estimation on depth images
Open access status: An open access version is available from UCL Discovery
DOI: 10.1016/j.neucom.2016.04.009
Publisher version: http://dx.doi.org/10.1016/j.neucom.2016.04.009
Language: English
Additional information: Copyright © 2016. This manuscript version is published under a Creative Commons Attribution Non-commercial Non-derivative 4.0 International licence (CC BY-NC-ND 4.0). This licence allows you to share, copy, distribute and transmit the work for personal and non-commercial use providing author and publisher attribution is clearly stated. Further details about CC BY licences are available at http://creativecommons.org/licenses/by/4.0. Access may be initially restricted by the publisher.
Keywords: Pose estimation; Pictorial structure; Latent variable; Body silhouette; Regression forest; Depth images
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science
URI: https://discovery.ucl.ac.uk/id/eprint/1492859
Downloads since deposit
145Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item