Share Email Print

Journal of Electronic Imaging

Coupled multiview autoencoders with locality sensitivity for three-dimensional human pose estimation
Author(s): Jialin Yu; Jifeng Sun; Shasha Luo; Bichao Duan
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper 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.

Paper Details

Date Published: 27 October 2017
PDF: 13 pages
J. Electron. Imag. 26(5) 053026 doi: 10.1117/1.JEI.26.5.053026
Published in: Journal of Electronic Imaging Volume 26, Issue 5
Show Author Affiliations
Jialin Yu, South China Univ. of Technology (China)
Jifeng Sun, South China Univ. of Technology (China)
Shasha Luo, South China Univ. of Technology (China)
Bichao Duan, South China Univ. of Technology (China)

© SPIE. Terms of Use
Back to Top