Curvature-based Human Body Parts Segmentation in Physiotherapy

Francis Deboeverie, Roeland De Geest, Tinne Tuytelaars, Peter Veelaert, Wilfried Philips

2015

Abstract

Analysing human sports activity in computer vision requires reliable segmentation of the human body into meaningful parts, such as arms, torso and legs. Therefore, we present a novel strategy for human body segmentation. Firstly, greyscale images of human bodies are divided into smooth intensity patches with an adaptive region growing algorithm based on low-degree polynomial fitting. Then, the key idea in this paper is that human body parts are approximated by nearly cylindrical surfaces, of which the axes of minimum curvature accurately reconstruct the human body skeleton. Next, human body segmentation is qualitatively evaluated with a line segment distance between reconstructed human body skeletons and ground truth skeletons. When compared with human body parts segmentations based on mean shift, normalized cuts and watersheds, the proposed method achieves more accurate segmentations and better reconstructions of human body skeletons.

References

  1. Aggarwal, J. K. and Ryoo, M. (2011). Human activity analysis: A review. ACM Computing Surveys, 43(3).
  2. Barnard, M. and Heikkila, J. (2008). Body part segmentation of noisy human silhouette images. In Proc. of IEEE Int. Conf. on Mult. and Expo, pages 1189-1192.
  3. Bartlett, R. (2007). Analysing Human Movements Patterns. Routledge.
  4. Comaniciu, D. and Meer, P. (2002). Mean shift: A robust approach toward feature space analysis. IEEE Trans. on Pattern Analysis and Machine Intelligence, 24(5):603-619.
  5. Deboeverie, F., Veelaert, P., and Philips, W. (2013). Image segmentation with adaptive region growing based on a polynomial surface model. Journal of Electronic Imaging, 22(4).
  6. Gao, Y. and Leung, M. K. (2002). Face recognition using line edge map. IEEE Trans. on Pattern Analysis and Machine Intelligence, 24(6):764-779.
  7. Guo, G. and Lai, A. (2014). A survey on still image based human action recognition. Pattern Recognition, 47(10):3343 - 3361.
  8. Hou, Y.-L. and Pang, G. K. H. (2011). People counting and human detection in a challenging situation. IEEE Trans. on Systems, Man, and Cybernetics - Part A: Systems and Humans, 41(1):24-33.
  9. Hsieh, J.-W., Chuang, C.-H., Chen, S.-Y., Chen, C.-C., and Fan, K.-C. (2010). Segmentation of human body parts using deformable triangulation. IEEE Trans. on Systems, Man, and Cybernetics - Part A: Systems and Humans, 40(3):596-610.
  10. Hu, Z., Lin, X., and Yan, H. (2006). Torso detection in static images. In Proc. of Int. Conf. on Signal Processing.
  11. Hu, Z., Wang, G., Lin, X., and Yan, H. (2009). Recovery of upper body poses in static images based on joints detection. Pattern Recognition Letters, 30:503-512.
  12. Juang, C.-F., Chang, C.-M., Wu, J.-R., and Lee, D. (2009). Computer vision-based human body segmentation and posture estimation. IEEE Trans. on Systems, Man, and Cybernetics - Part A: Systems and Humans, 39(1):119-133.
  13. Lambert, J. (1760). Photometria Sive de Mensura de Gratibus Luminis. Colorum et Umbrae. Augsberg, Germany: Eberhard Klett.
  14. Lee, M. W. and Cohen, I. (2006). A model-based approach for estimating human 3d poses in static images. IEEE Trans. on Pattern Analysis and Machine Intelligence, 28(6):905-916.
  15. Li, S., Lu, H.-C., Ruan, X., and Chen, Y.-W. (2011). Human body segmentation based on deformable models and two-scale superpixel. Pattern Analysis and Applications, pages 1-15.
  16. Li, S., Shao, X., et al. (2014). Human body segmentation via data-driven graph cut. IEEE Trans. on Cybernetics. DOI:10.1109/TCYB.2014.2301193.
  17. Liang, Y.-M., Shih, S.-W., Shih, C.-C., Liao, H.-Y. M., and Lin, C.-C. (2009). Learning atomic human actions using variable-length markov models. IEEE Trans. on Systems, Man, and Cybernetics - Part B: Cybernetics, 39(1):268-280.
  18. Liu, Q., Li, H., and Ngan, K. N. (2011). Automatic body segmentation with graph cut and self-adaptive initialization level set (sails). J. Vis. Commun. Image R., 22:367-377.
  19. Mori, G. and Malik, J. (2006). Recovering 3d human body configurations using shape contexts. IEEE Trans. Pattern Analysis Machine Intelligence, 28(7):1052-1062.
  20. Mori, G., Ren, X., Efros, A. A., and Malik, J. (2004). Recovering human body configuration: Combining segmentation and recognition. In Proc. of Computer Vision and Pattern Recognition, pages 326-333.
  21. Park, J.-S., Oh, H.-S., Chang, D.-H., and Lee, E.-T. (1999). Human posture recognition using curve segments for image retrieval. In Proc. of SPIE.
  22. Park, S. and Aggarwal, J. K. (2004). Semantic-level understanding of human actions and interactions using event hierarchy. In Proc. of Computer Vision and Pattern Recognition Workshop, page 12.
  23. Poppe, R. (2007). Vision-based human motion analysis: An overview. Computer vision and image understanding, 108(1):4-18.
  24. Porikli, F. and Tuzel, O. (2003). Human bodytracking byadaptive background models and mean-shift analysis. In IEEE Int. Workshop on Performance Evaluation of Tracking and Surveillance.
  25. Shao, L., Ji, L., Liu, Y., and Zhang, J. (2012). Human action segmentation and recognition via motion and shape analysis. Pattern Recognition Letters, 33:438-445.
  26. Shi, J. and Malik, J. (2000). Normalized cuts and image segmentation. IEEE Trans. on Pattern Analysis and Machine Intelligence, 22(8):888-905.
  27. Srinivasan, P. and Shi, J. (2007). Bottom-up recognition and parsing of the human body. In Proc. of Computer Vision and Pattern Recognition, pages 1-8.
  28. Veelaert, P. (1997). Constructive fitting and extraction of geometric primitives. CVGIP: Graphical Models and Image Processing, 59(4):233-251.
  29. Veelaert, P. (2012). Separability and tight enclosure of point sets, digital geometry algorithms. Theoretical Foundations and Appl. to Computational Imaging, 2.
  30. Veelaert, P. and Teelen, K. (2006). Fast polynomial segmentation of digitized curves. In Proc. of Discrete Geometry for Computer Imagery, pages 482-493.
  31. Vincent, L. and Soille, P. (1991). Watersheds in digital spaces: An efficient algorithm based on immersion simulations. IEEE Trans. on Pattern Analysis and Machine Intelligence, 13(6):583-598.
  32. Wagemans, J., Doorn, A. J. V., and Koenderink, J. (2010). The shading cue in context. i-Perception, 1(3):159- 178.
  33. Wu, C. and Aghajan, H. (2007). Model-based image segmentation for multi-view human gesture analysis. In Proc. of Advanced Concepts for Intelligent Vision Systems, pages 310-321.
  34. Xiao, Y., Lu, H., and Sun, C. (2014). Pose estimation based on pose cluster and candidates recombination. IEEE Trans. on Circuits and Systems for Video Technology. DOI:10.1109/TCSVT.2014.2347511.
Download


Paper Citation


in Harvard Style

Deboeverie F., De Geest R., Tuytelaars T., Veelaert P. and Philips W. (2015). Curvature-based Human Body Parts Segmentation in Physiotherapy . 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 630-637. DOI: 10.5220/0005338906300637


in Bibtex Style

@conference{visapp15,
author={Francis Deboeverie and Roeland De Geest and Tinne Tuytelaars and Peter Veelaert and Wilfried Philips},
title={Curvature-based Human Body Parts Segmentation in Physiotherapy},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={630-637},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005338906300637},
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 - Curvature-based Human Body Parts Segmentation in Physiotherapy
SN - 978-989-758-089-5
AU - Deboeverie F.
AU - De Geest R.
AU - Tuytelaars T.
AU - Veelaert P.
AU - Philips W.
PY - 2015
SP - 630
EP - 637
DO - 10.5220/0005338906300637