Next Article in Journal
Characterizations of Anti-Alpha-Fetoprotein-Conjugated Magnetic Nanoparticles Associated with Alpha-Fetoprotein for Biomedical Applications
Previous Article in Journal
Analysis of Multi-Level Simultaneous Driving Technique for Capacitive Touch Sensors
Article Menu
Issue 9 (September) cover image

Export Article

Open AccessArticle
Sensors 2017, 17(9), 2019; https://doi.org/10.3390/s17092019

Capturing Complex 3D Human Motions with Kernelized Low-Rank Representation from Monocular RGB Camera

1,2,3,4
,
1,2,3,4,* and 1,2,3,4
1
The Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, No.28 Xianning West Road, Xi’an 710048, China
2
The School of Software Engineering, Xi’an Jiaotong University, No.28 Xianning West Road, Xi’an 710048, China
3
National Engineering Laboratory for Visual Information Processing and Application, Xi’an Jiaotong University, No.28 Xianning West Road, Xi’an 710048, China
4
Shaanxi Digital Technology and Intelligent System Key Laboratory, Xi’an Jiaotong University, No.28 Xianning West Road, Xi’an 710048, China
*
Author to whom correspondence should be addressed.
Received: 5 July 2017 / Revised: 23 August 2017 / Accepted: 24 August 2017 / Published: 3 September 2017
(This article belongs to the Section Physical Sensors)
View Full-Text   |   Download PDF [3771 KB, uploaded 4 September 2017]   |  

Abstract

Recovering 3D structures from the monocular image sequence is an inherently ambiguous problem that has attracted considerable attention from several research communities. To resolve the ambiguities, a variety of additional priors, such as low-rank shape basis, have been proposed. In this paper, we make two contributions. First, we introduce an assumption that 3D structures lie on the union of nonlinear subspaces. Based on this assumption, we propose a Non-Rigid Structure from Motion (NRSfM) method with kernelized low-rank representation. To be specific, we utilize the soft-inextensibility constraint to accurately recover 3D human motions. Second, we extend this NRSfM method to the marker-less 3D human pose estimation problem by combining with Convolutional Neural Network (CNN) based 2D human joint detectors. To evaluate the performance of our methods, we apply our marker-based method on several sequences from Utrecht Multi-Person Motion (UMPM) benchmark and CMU MoCap datasets, and then apply the marker-less method on the Human3.6M datasets. The experiments demonstrate that the kernelized low-rank representation is more suitable for modeling the complex deformation and the method consequently yields more accurate reconstructions. Benefiting from the CNN-based detector, the marker-less approach can be applied to more real-life applications. View Full-Text
Keywords: 3D human pose estimation; monocular reconstruction; non-rigid structure from motion; kernel low-rank representation 3D human pose estimation; monocular reconstruction; non-rigid structure from motion; kernel low-rank representation
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (CC BY 4.0).

Share & Cite This Article

MDPI and ACS Style

Wang, X.; Wang, F.; Chen, Y. Capturing Complex 3D Human Motions with Kernelized Low-Rank Representation from Monocular RGB Camera. Sensors 2017, 17, 2019.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Sensors EISSN 1424-8220 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top