Abstract
We propose a hybrid dynamical model of human motion and develop a classification algorithm for the purpose of analysis and recognition. We assume that some temporal statistics are extracted from the images, and use them to infer a dynamical model that explicitly represents ground contact events. Such events correspond to “switches” between symmetric sets of hidden parameters in an auto-regressive model. We propose novel algorithms to estimate switches and model parameters, and develop a distance between such models that explicitly factors out exogenous inputs that are not unique to an individual or his/her gait. We show that such a distance is more discriminative than the distance between simple linear systems for the task of gait recognition.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
Agarwal, A., & Triggs, B. (2004). Tracking articulated motion using a mixture of autoregressive models. In Proc. ECCV (Vol. III, pp. 54–65). Prague 2004.
Bissacco, A. (2005). Modeling and learning contact dynamics in human motion. In Proc. CVPR (pp. 421–428).
BenAbdelkader, C., Cutler, R., & Davis, L. (2004). Gait recognition using image self-similarity. EURASIP Journal on Applied Signal Processing, 4, 1–14.
Bickel, P. J., & Freedman, D. A. (1981). Some asymptotic theory for the bootstrap. Annals of Statistics, 9, 1196–1217.
Bissacco, A., Chiuso, A., Ma, Y., & Soatto, S. (2001). Recognition of human gaits. In Proc. IEEE int. conf. on comp. vis. and pattern recognit., December 2001.
Bobick, A. F., & Davis, J. W. (2001). The recognition of human movement using temporal templates. IEEE Transactions on PAMI, 23(3), 257–267.
Bregler, C. (1997). Learning and recognizing human dynamics in video sequences. In Proc of CVPR (pp. 568–574).
Bregler, C., & Malik, J. (1998). Tracking people with twists and exponential maps. In Proc. of CVPR.
De Coch, K., & De Moor, B. (2000). Subspace angles and distances between ARMA models. In Proc. of the int. symp. of math. theory of networks and systems.
Del Vecchio, D., Murray, R. M., & Perona, P. (2003). Decomposition of human motion into dynamics based primitives with application to drawing tasks. Automatica, 39(12), 2085–2098.
Dowson, D. C., & Landau, B. V. (1982). The Frechet distance between multivariate normal distributions. Journal Multivariate Analysis, 12(3), 450–455.
Efros, A. A., Berg, A. C., Mori, G., & Malik, J. (2003). Recognizing action at a distance. In Proc. of ICCV.
Garcia, M., Chatterjee, A., & Ruina, A. (1998). The simplest walking model: stability, complexity and scaling. Journal of Biomechanical Engineering, 120, 281–288.
Gavrila, D. M. (1999). The visual analysis of human movement: A survey. In CVIU (Vol. 73, pp. 82–98).
Ghahramani, Z., & Hinton, G. E. (1998). Switching state-space models (Technical Report). Toronto, Canada.
Greenspan, H., Dvir, G., & Rubner, Y. (2004). Context-dependent segmentation and matching in image databases. Computer Vision and Image Understanding, 93, 86–109.
Gustafsson, F. (2000). Adaptive filtering and change detection. New York: Wiley.
He, Q., & Debrunner, C. (2000). Individual recognition from periodic activity using hidden Markov models. In IEEE workshop on human motion, USA, December 2000.
Johansson, G. (1973). Visual perception of biological motion and a model for its analysis. Perception and Psychophysics, 14(2), 201–211.
Juang, B. H., & Rabiner, L. R. (1985). Mixture autoregressive hidden Markov models for speech signals. Transactions on Acoustic Speech Signal Processing, 33(6), 1404–1413.
Kale, A., Sundaresan, A., Rajagopalan, A. N., Cuntoor, N., RoyChowdhury, A., Krueger, V., & Chellappa, R. (2004). Identification of humans using gait. IEEE Transactions on Image Processing, 13(9), 1163–1173.
Krishnaprasad, P. S., & Brockett, R. W. (1979). A scaling theory for linear systems. IEEE Transactions on Automatic Control, AC-25(2), 197–207.
Lee, C. S., & Elgammal, A. (2004). Gait style and gait content: bilinear models for gait recognition using gait resampling. In Proc. automatic face and gesture recognition, Seoul, Korea, 17–19 May 2004.
Lee, L., & Grimson, W. E. L. (2002). Gait analysis for recognition and classification. In Proc. automatic face and gesture recognition (pp. 148–155). 20–21 May 2002.
Little, J. J., & Boyd, J. E. (1998). Recognizing people by their gait: the shape of motion. Videre, 1(2), 1–32.
Ljung, L. (1987). System identification: theory for the user. New York: Prentice Hall.
Ma, Y., & Vidal, R. (2005). A closed form solution to the identification of hybrid ARX models via identification of algebraic varieties. In Hybrid systems comput. and control.
Ma, Y., Soatto, S., Kosecka, J., & Sastry, S. (2003). An invitation to 3D vision: from images to geometric models. Berlin: Springer.
Martin, R. (2000). A metric for ARMA processes. IEEE Transactions on Signal Processing, 48(4), 1164–1170.
Mazzaro, C., Sznaier, M., Camps, O., Soatto, S., & Bissacco, A. (2002). A model (in)validation approach to gait recognition. In Proc. of the 3DPTV, June 2002.
North, B., Blake, A., Isard, M., & Rittscher, J. (2000). Learning and classification of complex dynamics. IEEE Transactions on PAMI, 22(9), 1016–34.
O’Brien, J. F., Bodenheimer, R. E., Brostow, G. J., & Hodgins, J. K. (2000). Automatic joint parameter estimation from magnetic motion capture data. In Proc. of graphics interface 2000 (pp. 53–60). Montreal, Canada, May 2000.
Oh, S. M., Rehg, J. M., Balch, T., & Dellaert, F. (2005). Learning and inference in parametric switching linear dynamic systems In International conference on computer vision (ICCV 05) (Vol. 2, pp. 1161–1168). Beijing, China, October 2005.
Oliver, N. M., Rosario, B., & Pentland, A. P. (2000). A Bayesian computer vision system for modeling human interactions. IEEE Transactions on PAMI, 22(8), 831–843.
Pavlovic, V., & Rehg, J. (2000). Impact of dynamic model learning on classification of human motion In Proc. of CVPR.
Rubner, Y., Tomasi, C., & Guibas, L. J. (1998). A metric for distributions with applications to image databases. In Proc. of ICCV (pp. 59–66). Bombay, January 1998.
Sarkar, S., Phillips, P. J., Liu, Z., Vega, I. R., Grother, P., & Bowyer, K. W. (2005). The HumanID gait challenge problem: data sets, performance, and analysis. IEEE Transactions on PAMI, 27(2), 162–177.
Shah, M., & Jain, R. (1999). Motion-based recognition. Dordrecht: Kluwer.
Tugnait, J. K. (1982). Detection and estimation for abruptly changing systems. Automatica, 18(5), 607–615.
Veres, G. V., Gordon, L., Carter, J. N., & Nixon, M. S. (2004). What image information is important in silhouette-based gait recognition? In Proc. CVPR 04, June 2004.
Wilson, A. D., & Bobick, A. F. (1999). Parametric hidden Markov models for gesture recognition. IEEE Transactions on PAMI, 21(9), 884–900.
Zames, G., & El-Sakkary, A. K. (1980). Unstable systems and feedback: the gap metric. In Proc. of the Allerton conference (pp. 380–385). October 1980.
Zelnik-Manor, L., & Irani, M. (2006). Statistical analysis of dynamic actions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(9), 1530–1535.
Author information
Authors and Affiliations
Corresponding author
Additional information
Research supported by ONR 67F-1080868 and AFOSR FA9550-06-1-0138.
Rights and permissions
Open Access This is an open access article distributed under the terms of the Creative Commons Attribution Noncommercial License (https://creativecommons.org/licenses/by-nc/2.0), which permits any noncommercial use, distribution, and reproduction in any medium, provided the original author(s) and source are credited.
About this article
Cite this article
Bissacco, A., Soatto, S. Hybrid Dynamical Models of Human Motion for the Recognition of Human Gaits. Int J Comput Vis 85, 101–114 (2009). https://doi.org/10.1007/s11263-009-0248-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11263-009-0248-7