Advertisement

Occlusion detection and gait silhouette reconstruction from degraded scenes

  • Aditi Roy
  • Shamik Sural
  • Jayanta Mukherjee
  • Gerhard Rigoll
Original Paper

Abstract

Gait, which is defined as the style of walking of a person, has been recognized as a potential biometric feature for identifying human beings. The fundamental nature of gait biometric of being unconstrained and captured often without a subject’s knowledge or co-operation has motivated many researchers over the last one decade. However, all of the approaches found in the literature assume that there is little or no occlusion present at the time of capturing gait images, both during training and during testing and deployment. We look into this challenging problem of gait recognition in the presence of occlusion. A novel approach is proposed, which first detects the presence of occlusion and accordingly extracts clean and unclean gait cycles from the whole input sequence. In the second step, occluded silhouette frames are reconstructed using Balanced Gaussian Process Dynamical Model (BGPDM). We evaluated our approach on a new data set TUM-IITKGP featuring inter-object occlusion. Algorithms have also been tested on CMU’s Mobo data set by introducing synthetic occlusion of different degrees. The proposed approach shows promising result on both the data sets.

Keywords

Gait Occlusion Pose detection Dynamic programming BGPDM Silhouette reconstruction 

References

  1. 1.
    Larsen P.K., Simonsen E.B., Lynnerup N.: Gait analysis in forensic medicine. J. Forensic Sci. 53(5), 1149–1153 (2008)CrossRefGoogle Scholar
  2. 2.
    Cunado D., Nixon M.S., Carter J.N.: Automatic extraction and description of human gait models for recognition purposes. Proc. CVIU 90(1), 1–41 (2003)Google Scholar
  3. 3.
    Bobick, A., Johnson, A.: Gait recognition using static, activity-specific parameters In: Proceedings of the IEEE Conference on CVPR, vol. 1, pp. 423–430 (2001)Google Scholar
  4. 4.
    Yam C., Nixon M.S., Carter J.N.: Automated person recognition by walking and running via model-based approaches. Pattern Recognit. 37(5), 1057–1072 (2004)CrossRefGoogle Scholar
  5. 5.
    Jain, A., Dube, T., Ghosh, D.: A fuzzy approach to person identification using gait. In: Proceedings of the IET International Conference on Visual Information Engineering (VIE), pp. 174–179 (2006)Google Scholar
  6. 6.
    Zhang R., Vogler C., Metaxas D.: Human gait recognition at sagittal plane. Image Vis. Comput. 25(3), 321–330 (2007)CrossRefGoogle Scholar
  7. 7.
    Lu, H., Plataniotis, K.N., Venetsanopoulos, A.N.: A full-body layered deformable model for automatic model-based gait recognition. EURASIP J. Adv. Signal Process. 2008(Article ID 261317) (2008). doi: 10.1155/2008/261317
  8. 8.
    Huang, X., Boulgouris, N.V. Model-based human gait recognition using fusion of features. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 0, pp. 1469–1472 (2009)Google Scholar
  9. 9.
    Kale A., Sundaresan A., Rajagopalan A.N., Cuntoor N.P., Roy-Chowdhury A.K., Kruger V., Chellappa R.: Identification of humans using gait. IEEE Trans. Image Process. 13, 1163–1173 (2004)CrossRefGoogle Scholar
  10. 10.
    Kale, A., Rajagopalan, A., Cuntoor, N., Krueger, V.: Gait-based recognition of humans using continuous HMMs. In: Proceedings of the International Conference on Automatic Face and Gesture Recognition, pp. 321–326 (2002)Google Scholar
  11. 11.
    Chen C.H., Liang J., Zhao H., Hu H., Tian J.: Factorial HMM and parallel HMM for gait recognition. IEEE Trans. Syst. Man Cybern. C Appl. Rev. 39(1), 114–123 (2009)CrossRefGoogle Scholar
  12. 12.
    Sundaresan, A., Roy-Chowdhury, A.K., Chellappa, R.: A hidden markov model based framework for recognition of humans frem gait sequences. In: Proceedings of the IEEE Conference Image Processing, vol. 2, pp. 93–99 (2003)Google Scholar
  13. 13.
    Niyogi, S.A., Adelson, E.H.:Analyzing and recognizing walking figures in XYT. In: Proceedings of the CVPR, pp. 469–474 (1994)Google Scholar
  14. 14.
    Little J., Boyd J.: Recognizing people by their gait: the shape of motion. Videre J. Comput. Vis. Res. 1(2), 1–32 (1998)Google Scholar
  15. 15.
    BenAbdelkader, C., Cutler, R., Davis, L.: Motion-based recognition of people in eigengait space. In: Proceedings of International Conference on Automatic Face and Gesture Recognition, pp. 267–274 (2002)Google Scholar
  16. 16.
    Vega, I., Sarkar, S.: Experiments on gait analysis by exploiting nonstationarity in the distribution of feature relationships. In: Proceedings of the International Conference on Pattern Recognition, vol. 1, pp. 1–4 (2002)Google Scholar
  17. 17.
    Sarkar S., Phillips P.J., Liu Z., Robledo-Vega I., Grother P., Bowyer K.W.: The human ID gait challenge problem: data sets, performance, and analysis. IEEE Trans. Pattern Anal. Mach. Intel. 27(2), 162–177 (2005)CrossRefGoogle Scholar
  18. 18.
    Hayfron-Acquah, J., Nixon, M., Carter, J.: Human identification by spatio-temporal symmetry. In: Proceedings of the International Conference on Pattern Recognition, vol. 1, pp. 632–635 (2002)Google Scholar
  19. 19.
    Lee L., Grimson, W.: Gait analysis for recognition and classification. In: Proceedings of the International Conference on Automatic Face and Gesture Recognition, pp. 155–162 (2002)Google Scholar
  20. 20.
    Boulgouris N.V., Hatzinakos D., Plataniotis K.N.: Gait recognition: a challenging signal processing technology for biometrics identification. IEEE Signal Process. Mag. 22(6), 78–90 (2005)CrossRefGoogle Scholar
  21. 21.
    Lu J., Zhang E.: Gait recognition for human identification based on ICA and fuzzy SVM through multiple views fusion. Pattern Recognit. Lett. 28, 2401–2411 (2007)MathSciNetCrossRefGoogle Scholar
  22. 22.
    Nixon, M.S., Carter, J.N.: Advances in automatic gait recognition. In: Proceedings of the IEEE International Conference on Automatic Face and Gesture Recognition, pp. 139–144 (2004)Google Scholar
  23. 23.
    Han J., Bhanu B.: Individual recognition using gait energy image. IEEE Trans. Pattern Anal. Mach. Intel. 28(2), 316–322 (2006)CrossRefGoogle Scholar
  24. 24.
    Yanga X., Zhoua Y., Zhanga T., Shua G., Yanga J.: Gait recognition based on dynamic region analysis. Signal Process. 88(9), 2350–2356 (2008)CrossRefGoogle Scholar
  25. 25.
    Chen C., Liang J., Hu H., Tian J.: Frame difference energy image for gait recognition with incomplete silhouettes. Pattern Recognit. Lett. 30(11), 977–984 (2009)CrossRefGoogle Scholar
  26. 26.
    Zhanga E., Zhao Y., Xionga W.: Energy image plus 2DLPP for gait recognition. Signal Process. 90(7), 2295–2302 (2010)CrossRefGoogle Scholar
  27. 27.
    Pullen, K., Bregler, C.: Motion capture assisted animation: texturing and synthesis. In: Proceedings of theof SIGGRAPH, pp. 501–508 (2002)Google Scholar
  28. 28.
    Wang J.M., Fleet D.J., Hertzmann A.: Gaussian process dynamical models for human motion. IEEE Trans. PAMI 30(2), 283–298 (2008)CrossRefGoogle Scholar
  29. 29.
    Lawrence, N.D.(2004) Gaussian process latent variable models for visualisation of high dimensional data. In: Thrun, S., Saul, L., Schlkopf, B. (eds.). Advances in Neural Information Processing Systems, pp. 329–336 MIT Press, Cambridge, MAGoogle Scholar
  30. 30.
    Rabiner L.R.: A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE 77(2), 257–286 (1989)CrossRefGoogle Scholar
  31. 31.
    Wang, J.M., Fleet, D.J., Hertzmann, A.: Gaussian process dynamical models. In: Proceedings of the NIPS, pp. 1441–1448 (2005)Google Scholar
  32. 32.
    Urtasun, R., Fleet, D.J., Fua, P.: 3D people tracking with Gaussian process dynamical models. In: Proceedings of the CVPR, pp. 238–245 (2006)Google Scholar
  33. 33.
    Gross, R., Shi, J.: The CMU Motion of Body (MoBo) Database. Technical report CMU-RI-TR-01-18, Robotics Institute, Carnegie Mellon University (2001)Google Scholar
  34. 34.
    Center for biometrics and security research, CASIA. http://www.cbsr.ia.ac.cn
  35. 35.
    Turk M., Pentland A.: Eigenfaces for recognition. J. Cogn. Neurosci. 3(1), 71–86 (1991)CrossRefGoogle Scholar
  36. 36.
    Hofmann, M., Sural, S., Rigoll, G.: Gait recognition in the presence of occlusion: a new dataset and baseline algorithms. In: Proceedings of the International Conference on Computer Graphics, Visualization and Computer Vision (WSCG). Plzen, Czech Republic (2011)Google Scholar
  37. 37.
  38. 38.
    Staufferand, C., Grimson, W.E.L.: Adaptive background mixture modelsfor real-time tracking. In: Proceedings of the CVPR, pp. 246–252 (1999)Google Scholar
  39. 39.
    Tanimoto, T.T.: IBM Internal Report, 17 Nov (1957)Google Scholar

Copyright information

© Springer-Verlag London Limited 2011

Authors and Affiliations

  • Aditi Roy
    • 1
  • Shamik Sural
    • 1
  • Jayanta Mukherjee
    • 2
  • Gerhard Rigoll
    • 3
  1. 1.School of Information TechnologyIndian Institute of Technology KharagpurKharagpurIndia
  2. 2.Department of CSEIndian Institute of Technology KharagpurKharagpurIndia
  3. 3.Institute for Human Machine CommunicationTechnical University of MunichMunichGermany

Personalised recommendations