Real-time Human Pose Estimation from Body-scanned Point Clouds

Jilliam María Díaz Barros, Frederic Garcia, Désiré Sidibé

Abstract

This paper presents a novel approach to estimate the human pose from a body-scanned point cloud. To do so, a predefined skeleton model is first initialized according to both the skeleton base point and its torso limb obtained by Principal Component Analysis (PCA). Then, the body parts are iteratively clustered and the skeleton limb fitting is performed, based on Expectation Maximization (EM). The human pose is given by the location of each skeletal node in the fitted skeleton model. Experimental results show the ability of the method to estimate the human pose from multiple point cloud video sequences representing the external surface of a scanned human body; being robust, precise and handling large portions of missing data due to occlusions, acquisition hindrances or registration inaccuracies.

References

  1. (2014). Human Proportion Calculator. anatomy4sculptors.com/.
  2. Au, O. K.-C., Tai, C.-L., Chu, H.-K., Cohen-Or, D., and Lee, T.-Y. (2008). Skeleton extraction by mesh contraction. In ACM SIGGRAPH 2008 Papers, pages 44:1-44:10. ACM.
  3. Bradski, G. and Kaehler, A. (2008). Learning OpenCV: Computer Vision with the OpenCV Library. O'Reilly Media, 1st edition.
  4. Cao, J., A., T., M., O., Zhang, H., and Su, Z. (2010). Point cloud skeletons via laplacian based contraction. In Shape Modeling International Conference (SMI), pages 187-197.
  5. Fischler, M. A. and Bolles, R. C. (1981). Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 24(6):381-395.
  6. Garcia, F. and Ottersten, B. (2014a). CPU-Based Real-Time Surface and Solid Voxelization for Incomplete Point Cloud. In IEEE International Conference on Pattern Recognition (ICPR).
  7. Garcia, F. and Ottersten, B. (2014b). Real-time CurveSkeleton Extraction from Incomplete Point Clouds: Application in Human Pose Estimation. In International Conference on Computer Vision Theory and Applications (VISAPP).
  8. Ke, S.-R., Hwang, J.-N., Lan, K.-M., and Wang, S.-Z. (2011). View-invariant 3d human body pose reconstruction using a monocular video camera. In Distributed Smart Cameras (ICDSC), 2011 Fifth ACM/IEEE International Conference on, pages 1-6. IEEE.
  9. Lehment, N. H., Arsic, D., Kaiser, M., and Rigoll, G. (2010). Automated pose estimation in 3d point clouds applying annealing particle filters and inverse kinematics on a gpu. In Computer Vision and Pattern Recognition Workshops (CVPRW), 2010 IEEE Computer Society Conference on, pages 87-92. IEEE.
  10. Li, M., Yang, T., Xi, R., and Lin, Z. (2009). Silhouettebased 2d human pose estimation. In International Conference on Image and Graphics (ICIG), pages 143-148.
  11. Sam, V., Kawata, H., and Kanai, T. (2012). A robust and centered curve skeleton extraction from 3d point cloud. Computer-Aided Design and Applications, 9(6):969-879.
  12. Shotton, J., Girshick, R., Fitzgibbon, A., Sharp, T., Cook, M., Finocchio, M., Moore, R., Kohli, P., Criminisi, A., Kipman, A., et al. (2013). Efficient human pose estimation from single depth images. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 35(12):2821-2840.
  13. Tagliasacchi, A., Zhang, H., and Cohen-Or, D. (2009). Curve skeleton extraction from incomplete point cloud. In ACM SIGGRAPH 2009 Papers, SIGGRAPH 7809, pages 71:1-71:9. ACM.
  14. Ye, M., Wang, X., Yang, R., Ren, L., and Pollefeys, M. (2011). Accurate 3d pose estimation from a single depth image. In Computer Vision (ICCV), 2011 IEEE International Conference on, pages 731-738. IEEE.
  15. Zhang, L., Sturm, J., Cremers, D., and Lee, D. (2012). Realtime human motion tracking using multiple depth cameras. In Intelligent Robots and Systems (IROS), 2012 IEEE/RSJ International Conference on, pages 2389-2395. IEEE.
Download


Paper Citation


in Harvard Style

Díaz Barros J., Garcia F. and Sidibé D. (2015). Real-time Human Pose Estimation from Body-scanned Point Clouds . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-089-5, pages 553-560. DOI: 10.5220/0005309005530560


in Bibtex Style

@conference{visapp15,
author={Jilliam María Díaz Barros and Frederic Garcia and Désiré Sidibé},
title={Real-time Human Pose Estimation from Body-scanned Point Clouds},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={553-560},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005309005530560},
isbn={978-989-758-089-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015)
TI - Real-time Human Pose Estimation from Body-scanned Point Clouds
SN - 978-989-758-089-5
AU - Díaz Barros J.
AU - Garcia F.
AU - Sidibé D.
PY - 2015
SP - 553
EP - 560
DO - 10.5220/0005309005530560