Coupled multiview autoencoders with locality sensitivity for three-dimensional human pose estimation

Jialin Yu; Jifeng Sun; Shasha Luo; Bichao Duan

doi:10.1117/1.JEI.26.5.053026

27 October 2017 Coupled multiview autoencoders with locality sensitivity for three-dimensional human pose estimation

Jialin Yu, Jifeng Sun, Shasha Luo, Bichao Duan

Author Affiliations +

Journal of Electronic Imaging, Vol. 26, Issue 5, 053026 (October 2017). https://doi.org/10.1117/1.JEI.26.5.053026

Abstract

Estimating three-dimensional (3D) human poses from a single camera is usually implemented by searching pose candidates with image descriptors. Existing methods usually suppose that the mapping from feature space to pose space is linear, but in fact, their mapping relationship is highly nonlinear, which heavily degrades the performance of 3D pose estimation. We propose a method to recover 3D pose from a silhouette image. It is based on the multiview feature embedding (MFE) and the locality-sensitive autoencoders (LSAEs). On the one hand, we first depict the manifold regularized sparse low-rank approximation for MFE and then the input image is characterized by a fused feature descriptor. On the other hand, both the fused feature and its corresponding 3D pose are separately encoded by LSAEs. A two-layer back-propagation neural network is trained by parameter fine-tuning and then used to map the encoded 2D features to encoded 3D poses. Our LSAE ensures a good preservation of the local topology of data points. Experimental results demonstrate the effectiveness of our proposed method.

Citation Download Citation

Jialin Yu, Jifeng Sun, Shasha Luo, and Bichao Duan "Coupled multiview autoencoders with locality sensitivity for three-dimensional human pose estimation," Journal of Electronic Imaging 26(5), 053026 (27 October 2017). https://doi.org/10.1117/1.JEI.26.5.053026

Received: 17 June 2017; Accepted: 3 October 2017; Published: 27 October 2017

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available