Search by item HOME > Access full text > Search by item

JBE, vol. 25, no. 7, pp.1095-1106, December, 2020


High Accuracy Skeleton Estimation using 3D Volumetric Model based on RGB-D

Kyung-Jin Kim, Byung-Seo Park, Ji-Won Kang, Jin-Kyum Kim, Woo-Suk Kim, Dong-Wook Kim, and Young-Ho Seo

C.A E-mail:


In this paper, we propose an algorithm that extracts a high-precision 3D skeleton using a model generated using a distributed RGB-D camera. When information about a 3D model is extracted through a distributed RGB-D camera, if the information of the 3D model is used, a skeleton with higher precision can be obtained. In this paper, in order to improve the precision of the 2D skeleton, we find the conditions to obtain the 2D skeleton well using the PCA. Through this, high-quality 2D skeletons are obtained, and high-precision 3D skeletons are extracted by combining the information of the 2D skeletons. Even though this process goes through, the generated skeleton may have errors, so we propose an algorithm that removes these errors by using the information of the 3D model. We were able to extract very high accuracy skeletons using the proposed method.


Keyword: skeleton, RGB-D, depth image, 3D model, calibration, pose estimation, joint, registration

[1] Y. Guo, M. Bennamoun, F. Sohel, M. Lu and J. Wan, "An Integrated Framework for 3-D Modeling, Object Detection, and Pose Estimation From Point-Clouds," in IEEE Transactions on Instrumentation and Measurement, vol. 64, no. 3, pp. 683-693, March 2015
[2] O. Schreer et al., "Advanced Volumetric Capture and Processing," in SMPTE Motion Imaging Journal, vol. 128, no. 5, pp. 18-24, June 2019
[3] T. L. Munea, Y. Z. Jembre, H. T. Weldegebriel, L. Chen, C. Huang and C. Yang, "The Progress of Human Pose Estimation: A Survey and Taxonomy of Models Applied in 2D Human Pose Estimation," in IEEE Access, vol. 8, pp. 133330-133348, 2020, doi: 10.1109/ACCESS. 2020.3010248.
[4] Rim, Beanbonyka, et al. "Real-time Human Pose Estimation using RGB-D images and Deep Learning." Journal of Internet Computing and Services 21.3 (2020): 113-121.
[5] Cao, Zhe, et al. "OpenPose: realtime multi-person 2D pose estimation using Part Affinity Fields." arXiv preprint arXiv:1812.08008 (2018).
[6] He, Haoyang, et al. "Interacting Multiple Model-Based Human Pose Estimation Using a Distributed 3D Camera Network." IEEE Sensors Journal 19.22 (2019): 10584-10590.
[7] An, Gwon Hwan, et al. "Charuco board-based omnidirectional camera calibration method." Electronics 7.12 (2018): 421.
[8] Z. Zhang, “A flexible new technique for camera calibration,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.22, No.11, pp.1330-1334, 2000.
[9] Ruder, Sebastian. "An overview of gradient descent optimization algorithms." arXiv preprint arXiv:1609.04747 (2016).
[10] S. Lee, “Convergence Rate of Optimization Algorithms for a Non-strictly Convex Function”, Institute of Control Robotics and Systems, pp. 349-350, May 2019.
[11] Jackins, C.L.
Tanimoto, S.L.: Oct-trees and their use in representingthree-dimensional objects. Comput. Graphics Image Process., 14 (3)(1980), 249–270.
[12] K. Kim, B. Park, J. Kim, D. Kim, and Young-Ho Seo, "Holographic augmented reality based on three-dimensional volumetric imaging for a photorealistic scene," Optics Express 28, 35972-35985 (2020).
[13] Svante Wold, Kim Esbensen, Paul Geladi, “Principal component analysis,” Chemometrics and Intelligent Laboratory Systems, Vol. 2, Issues 1–3, pp. 37-52, 1987.
[14] Barequet, Gill, and Sariel Har-Peled. "Efficiently approximating the minimum-volume bounding box of a point set in three dimensions." Journal of Algorithms 38.1 (2001): 91-109.
[16] Luvizon, Diogo. Machine Learning for Human Action Recognition and Pose Estimation based on 3D Information. Diss. Cergy Paris Université, 2019.


Editorial Office
1108, New building, 22, Teheran-ro 7-gil, Gangnam-gu, Seoul, Korea
Homepage: TEL: +82-2-568-3556 FAX: +82-2-568-3557
Copyrightⓒ 2012 The Korean Institute of Broadcast and Media Engineers
All Rights Reserved