doi: 10.18178/ijfcc.2015.4.5.412
Accurate 3D Human Pose Recognition via Fusion of Depth and Motion Sensors
S. B. Nam
1
,
S. U. Park
1
,
J. H. Park
1
,
M. D. Zia Uddin
2
,
T. S. Kim
1
- 1 Department of Biomedical Engineering, Kyung Hee University, Seocheon-Dong, Giheung-Gu, Yongin-Si, Gyeonggi-Do, 446-701, Republic of Korea.
- 2 Department of Computer Education, Sungkyunkwan University, Jongno-Gu, Seoul, Republic of Korea.
Abstract
In this work, we present an accurate 3D humanpose recognition (HPR) work via multi-sensor fusion. Lately, 3DHPR is widely performed using a depth imaging sensor, but thisapproach has limitations: 1) orientations of body parts cannot beaccurately recognized and 2) it suffers from occlusion.<br>To achieve an accurate and stable recognition of human posesin real-time, in this study, we propose to use inertialmeasurement units (IMUs) which are used to estimate theorientation of body limbs and solve the occlusion problem. Viafusion of depth and IMU sensors, our results demonstratesignificantly improved 3D human pose reconstruction: ourresults show the accurate recognition of twist and location of thearms even under occlusion. Our presented approach could becritical if 3D HPR is to be used for medical applications such asmusculoskeletal analysis via in 3D as demonstrated in this study.
Keywords
- Human pose recognition
- depth sensors
- inertial measurement units
- sensor fusion
- musculoskeletalanalysis
How to Cite
S. B. Nam, S. U. Park, J. H. Park, M. D. Zia Uddin, and T. S. Kim, "Accurate 3D Human Pose Recognition via Fusion of Depth and Motion Sensors," International Journal of Future Computer and Communication, vol. 4, no. 5, pp. 336-340, 2015. https://doi.org/ 10.18178/ijfcc.2015.4.5.412
Copyright & License
Copyright © 2015 by the authors. 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).