Techno Press
Techno Press

You have a Free online access/download for a limited time.
Advances in Robotics Research   Volume 2, Number 2, June 2018, pages 129-140
DOI: http://dx.doi.org/10.12989/arr.2018.2.2.129
 
Robust 2D human upper-body pose estimation with fully convolutional network
Seunghee Lee, Jungmo Koo, Jinki Kim and Hyun Myung

 
Abstract     [Full Text]
    With the increasing demand for the development of human pose estimation, such as human-computer interaction and human activity recognition, there have been numerous approaches to detect the 2D poses of people in images more efficiently. Despite many years of human pose estimation research, the estimation of human poses with images remains difficult to produce satisfactory results. In this study, we propose a robust 2D human body pose estimation method using an RGB camera sensor. Our pose estimation method is efficient and cost-effective since the use of RGB camera sensor is economically beneficial compared to more commonly used high-priced sensors. For the estimation of upper-body joint positions, semantic segmentation with a fully convolutional network was exploited. From acquired RGB images, joint heatmaps accurately estimate the coordinates of the location of each joint. The network architecture was designed to learn and detect the locations of joints via the sequential prediction processing method. Our proposed method was tested and validated for efficient estimation of the human upper-body pose. The obtained results reveal the potential of a simple RGB camera sensor for human pose estimation applications.
 
Key Words
    human pose estimation; skeleton extraction; fully convolutional network; semantic segmentation; upper-body joint segmentation
 
Address
Seunghee Lee, Jungmo Koo and Jinki Kim: Department of Civil and Environmental Engineering, Korean Advanced Institute for Science and Technology, 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Republic of Korea

Hyun Myung: 1.) Department of Civil and Environmental Engineering, Korean Advanced Institute for Science and Technology, 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Republic of Korea
2.) Robotics Program, Korean Advanced Institute for Science and Technology, 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Republic of Korea
 

Techno-Press: Publishers of international journals and conference proceedings.       Copyright © 2019 Techno Press
P.O. Box 33, Yuseong, Daejeon 305-600 Korea, Tel: +82-42-828-7996, Fax : +82-42-828-7997, Email: technop@chol.com