Advertisement

Human Skeleton Extraction of Depth Images Using the Polygon Evolution

  • Huan Du
  • Jian Wang
  • Xue-xia Zhong
  • Ying He
  • Lin Mei
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8529)

Abstract

This paper proposes a novel skeleton extraction approach in the depth image based on the polygon evolution. The external contour of person is firstly extracted from the depth image and evolved to a external polygon using a polygon evolution method. Subsequently, the depth histogram is used to extract internal self-occlusion body parts, and contours of these parts are evolved to internal polygons. In external and internal polygons, skeleton points are extracted under different criterias respectively. Finally, all skeleton points are linked to a complete skeleton. Experimental results on a variety of postures demonstrate the robustness and reasonability of our skeleton extraction approach.

Keywords

skeleton extraction depth image polygon evolution external polygon internal polygon 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Urtasun, R., Darrell, T.: Sparse probabilistic regression for activity-independent human pose inference. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (2008)Google Scholar
  2. 2.
    Jaeggli, T., Koller-Meier, E., Gool, L.V.: Learning generative models for multi-activity body pose estimation. International Journal of Computer Vision 83(2), 121–134 (2009)CrossRefGoogle Scholar
  3. 3.
    Kehl, R., Gool, L.: Markerless tracking of complex human motions from multiple views. Computer Vision and Image Understanding 104(2), 190–209 (2006)CrossRefGoogle Scholar
  4. 4.
    Bandouch, J., Engstler, F., Beetz, M.: Accurate human motion capture using an ergonomics-based anthropometric human model. In: Proceedings of V Conference on Articulated Motion and Deformable Objects Andratx, Mallorca, Spain (2008)Google Scholar
  5. 5.
    Zhang, Z.: Microsoft Kinect sensor and its effect. IEEE Multimedia 19(2), 4–10 (2012)CrossRefGoogle Scholar
  6. 6.
    Kohli, P., Shotton, J.: Key developments in human pose estimation for Kinect. In: Consumer Depth Cameras for Computer Vision, pp. 63–70. Springer, London (2013)CrossRefGoogle Scholar
  7. 7.
    Kondori, F.A., Yousefi, S., Li, H., et al.: 3D head pose estimation using the Kinect. In: Proceedings of International Conference on Wireless Communications and Signal Processing, Nanjing, China, pp. 1–4 (2011)Google Scholar
  8. 8.
    Baak, A., Müller, M., Bharaj, G., et al.: A data-driven approach for real-time full body pose reconstruction from a depth camera. In: Proceedings of IEEE International Conference on Computer Vision, Barcelona, Spain, pp. 1092–1099. IEEE (2011)Google Scholar
  9. 9.
    Choi, W.-P., Lam, K.-M., Siu, W.-C.: Extraction of the Euclidean skeleton based on a connectivity criterion. Pattern Recognition 36, 721–729 (2003)zbMATHCrossRefGoogle Scholar
  10. 10.
    Schwarz, L.A., Mkhitaryan, A., Mateus, D., et al.: Human skeleton tracking from depth data using geodesic distances and optical flow. Image and Vision Computing 30, 217–226 (2012)CrossRefGoogle Scholar
  11. 11.
    Jiang, W., Xu, K., Cheng, Z.-Q., et al.: Curve skeleton extraction by coupled graph contraction and surface clustering. Graphical Models 75(3), 137–148 (2013)CrossRefGoogle Scholar
  12. 12.
    Shen, W., Xiao, S., Jiang, N., et al.: Unsupervised human skeleton extraction from Kinect depth images. In: Proceedings of the 4th International Conference on Internet Multimedia Computing and Service, Wuhan, China, pp. 66–69 (2012)Google Scholar
  13. 13.
    Shen, W., Bai, X., Yang, X., et al.: Skeleton pruning as trade-off between skeleton simplicity and reconstruction error. Science China Information Sciences 56(4), 1–14 (2013)CrossRefGoogle Scholar
  14. 14.
    Bai, X., Latecki, L.J., Liu, W.Y.: Skeleton Pruning by Contour Partitioning with Discrete Curve Evolution. IEEE Transactions on Pattern Analysis and Machine Intelligence 29(3), 449–462 (2007)CrossRefGoogle Scholar
  15. 15.
    Benhabiles, H., Lavoue, G., Vandeborre, J., et al.: Kinematic skeleton extraction based on motion boundaries for 3D dynamic meshes. In: Proceedings of Eurographics Workshop on 3D Object Retrieval, Cagliari, Italy, pp. 71–76 (2012)Google Scholar
  16. 16.
    Leyvand, T., Meekhof, C., Wei, Y.-C., et al.: Kinect Identity: Technology and Experience. Computer 44(4), 94–96 (2011)CrossRefGoogle Scholar
  17. 17.
    Douglas, D.H., Peucker, T.K.: Algorithms for the reduction of the number of points required to represent a line or its caricature. The Canadian Cartographer 10(2), 112–122 (1973)CrossRefGoogle Scholar
  18. 18.
    Canny, J.: A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 8(6), 679–698 (1986)CrossRefGoogle Scholar
  19. 19.
    Antonisses, H.J.: Image segmentation in pyramids. Computer Graphics and Image Processing 19, 367–383 (1982)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Huan Du
    • 1
  • Jian Wang
    • 1
    • 2
  • Xue-xia Zhong
    • 3
    • 1
  • Ying He
    • 1
  • Lin Mei
    • 1
  1. 1.The Third Research Institute of Ministry of Public SecurityCyber Physical System R&D CenterP. R. China
  2. 2.School of Electronic Information and Electrical EngineeringShanghai Jiao Tong UniversityP. R. China
  3. 3.School of Communication and Information EngineeringShanghai UniversityChina

Personalised recommendations