Machine Vision and Applications

, Volume 26, Issue 7–8, pp 919–932 | Cite as

Human body motion parameters capturing using kinect

  • Shih-Chung Hsu
  • Jun-Yang Huang
  • Wei-Chia Kao
  • Chung-Lin HuangEmail author
Original Paper


This paper introduces a new real-time human motion parameters capturing method using Kinect. It consists of five modules. First, the hybrid action type classifier categories human body motion into four different action types. Second, for each action type, there is a body part (BP) classifier which segments the human silhouette into 16 BP regions of which the centroids become the BP joints. These BP joints are linked to represent the human body skeleton. Third, an action type validation process verifies the identified action type. Fourth, the partial occlusion recovery method relocates the occluded BP joints. Fifth, the offset compensation process fine tunes the positions of BP joints and then validates the compensation results. The major contributions of this paper are hybrid action type classification and correction, offset compensation, and partial occlusion recovery. The experimental results show that this method can estimate human upper limb motion parameters in real time accurately and effectively.


Motion parameter estimation Random forest (RF) classifier Action type classifier Body part (BP) classifier Offset compensation 


  1. 1.
    Shotton, J., Fitzgibbon, A., Cook, M., Sharp, T., Finocchio, M., Moore, R., Kipman, A., Blake, A.: Real-time human pose recognition in parts from single depth images. In: IEEE CVPR (2011)Google Scholar
  2. 2.
    Ganapathi, V., Plagemann, C., Koller, D., Thrun, S.: Real time motion capture using a single time-of-flight camera. In: IEEE CVPR (2010)Google Scholar
  3. 3.
    Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. IEEE Trans. PAMI 24(3), 509–522 (2002)CrossRefGoogle Scholar
  4. 4.
    Baak, A., Müller, M., Bharaj, G., Seidel, H.-P., Theobalt, H.: A data-driven approach for real-time full body pose reconstruction from a depth camera. In: ICCV (2011)Google Scholar
  5. 5.
    Hara, K.: Real-time inference of 3D human poses by assembling local patches. In: WACV (2009)Google Scholar
  6. 6.
    Moeslund, T., Hilton, A., Krüger, V.: A survey of advances in vision-based human motion capture and analysis. In: CVIU (2006)Google Scholar
  7. 7.
    Poppe, R.: Vision-based human motion analysis: an overview. In: CVIU, p 108 (2007)Google Scholar
  8. 8.
    Microsoft Xbox 360 Kinect Launches November 4, Microsoft Corp. Redmond WA (2010)Google Scholar
  9. 9.
    Grest, D., Woetzel, J., Koch, R.: Nonlinear body pose estimation from depth images. In: Proceedings of DAGM (2005)Google Scholar
  10. 10.
    Knoop, S., Vacek, S., Dillmann, R.: Sensor fusion for 3D human body tracking with an articulated 3D body model. in: Proceedings of ICRA (2006)Google Scholar
  11. 11.
    Zhu, Y., Fujimura, K.: Constrained optimization for human pose estimation from depth sequences. In: Proceedings of ACCV (2007)Google Scholar
  12. 12.
    Siddiqui, M., Medioni, G.: Human pose estimation from a single view point, real-time range sensor. In: CVCG at CVPR (2010)Google Scholar
  13. 13.
    Plagemann, C., Ganapathi, V., Koller, D., Thrun, S.: Real-time identification and localization of BPs from depth images. In: Proceedings of ICRA (2010)Google Scholar
  14. 14.
    Mori, G., Malik, J.: Estimating human body configurations using shape context matching. In: IEEE ICCV (2003)Google Scholar
  15. 15.
    Bourdev, L., Malik, J.: Poselets: BP detectors trained using 3D human pose annotations. In: ICCV (2009)Google Scholar
  16. 16.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)zbMATHCrossRefGoogle Scholar
  17. 17.
    Lepetit, V., Lagger, P., Fua, P.: Randomized trees for real-time keypoint recognition. In: CVPR (2005)Google Scholar
  18. 18.
    Shotton, J., Johnson, M., Cipolla, R.: Semantic texton forests for image categorization and segmentation. In: IEEE CVPR (2008)Google Scholar
  19. 19.
    Wang, R., Popovi’c, J.: Real-time hand-tracking with a color glove. In: Proceedings of ACM SIGGRAPH (2009)Google Scholar
  20. 20.
    Bregler, C., Malik, J.: Tracking people with twists and exponential maps. In: Proceedings of CVPR (1998)Google Scholar
  21. 21.
    Sigal, L., Bhatia, S., Roth, S., Black, M., Isard, M.: Tracking looselimbed people. In: IEEE CVPR (2004)Google Scholar
  22. 22.
    Grest, D., Woetzel, J., Koch, R.: Nonlinear body pose estimation from depth images. In: Proceedings of DAGM (2005)Google Scholar
  23. 23.
    Sharp, T.: Implementing decision trees and forests on a GPU. In: Procedings of ECCV (2008)Google Scholar
  24. 24.
    Ho, T.K.: Random decision forest. In: Proceedings of the 3rd ICDAR, Montreal, QC, 14–16 August 1995. pp. 278–282 (1995)Google Scholar
  25. 25.
    Morio, G., Malik, J.: Estimating human body configuration using shape context matching. In: ECCV (2002)Google Scholar
  26. 26.
    Athitsos, V., Sclaroff, S.: Estimating 3D hand pose from cluttered image. In: IEEE CVPR (2003)Google Scholar
  27. 27.
    Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. IEEE Trans. PAMI. 24(4) (2002)Google Scholar
  28. 28.
    Babich, G., Camps, O.: Weighted Parzen windows for pattern classification. IEEE Trans. PAMI 18(5) (1996)Google Scholar
  29. 29.
    Gionis, A., Indyk, P., Motwani, R.: Similarity search in high dimensions via hashing. In: 25th International Conference on Very Large Data Base (1999)Google Scholar
  30. 30.
    Shakhnarovich, G., Viola, P., Darrell, T.: Fast pose estimation with parameter sensitive hashing. In: Proceedings of ICCV (2003)Google Scholar
  31. 31.
    Comaniciu, D., Meer, P.: Mean shift: a robust approach toward feature space analysis. IEEE Trans. PAMI 24(4), 603–619 (2002)CrossRefGoogle Scholar
  32. 32.
    Adams, R., Bischof, L.: Seeded region growing. IEEE Trans. PAMI 16(5) (1994)Google Scholar
  33. 33.
    Shen, W., Deng, K., Bai, X.: Exemplar-based human action pose correction and tagging. In: IEEE CVPR (2012)Google Scholar
  34. 34.
    Hsu, S.-C., Huang, J.-Y., Huang, C.-L.: Human upper body posture recognition and upper limbs motion parameters estimation. In: APSIPA ASC, Kaohsiung, Taiwan (2013)Google Scholar
  35. 35.
    Wang, R., Paris, S., Popovic, J.: Practical color-based motion capture. In: Proceedings of 21th ACM SIGGRAPH/ Eurographics Symposium on Computer Animation (2011)Google Scholar
  36. 36.
    Freund, Y., Schapire, R.E.: a decision-theoretic generalization of on-line learning and an application to boosting. JCSS 55, 119–139 (1997)zbMATHMathSciNetGoogle Scholar
  37. 37.
    Oreifej, O., Liu, Z.: HON4D: Histogram of oriented 4D normal for activity recognition from depth sequences. In: IEEE CVPR (2013)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2015

Authors and Affiliations

  • Shih-Chung Hsu
    • 1
  • Jun-Yang Huang
    • 1
  • Wei-Chia Kao
    • 1
  • Chung-Lin Huang
    • 2
    Email author
  1. 1.Department of Electrical EngineeringNational Tsing-Hua UniversityHsin-ChuTaiwan
  2. 2.Department of Applied Informatics and MultimediaAsia UniversityTai-ChungTaiwan

Personalised recommendations