A Novel Model for Human Activity Representation and Classification Based on Trajectory

Abstract:

In this paper, a novel model, HDP-HMM-SCFG is proposed for representing and classifying activities based on motion trajectories. In the model, activities are represented by stochastic grammar using trajectory, where trajectory segments are considered as observations emitted by the grammar terminals attached with HMMs. Then, by replacing the Euclidian distance in the kernel function of Gaussian radial radix with EMD-DTW, which is proposed to measure the distance between two trajectories by integrating the pros. of both EMD and DTW, multi-class SVM classifier is constructed. Experiments on ASL dataset are carried on to validate our approach.

• Periodical: Advanced Materials Research (Volumes 1044-1045)
• Pages: 1007-1010
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.1044-1045.1007
• Online since: October 2014
• Authors: Wei Xing Zhu*, Wei Guang Xu, Guo Lin Hou, Jun You
• Keywords: Classification, HDP-HMM-SCFG, Human Activity, Representation, Trajectory

References

[1] R. Basri, T. Hassner, et al., Approximate nearest subspace search, IEEE Transactions on Pattern Analysis and Machine Intelligence 2 (33) (2011) 266-278.

DOI: 10.1109/tpami.2010.110

[2] M. S. Dao, N. Babaguchi, A new spatio-temporal method for event detection and personalized retrieval of sports video, Multimedia Tools and Applications 50 (1) 2010 227-248.

DOI: 10.1007/s11042-009-0379-4

[3] P. S. Dhillon, S. Nowozin, C. H. Lampert, Combining appearance and motion for human action classification in videos, in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2009, pp.22-29.

DOI: 10.1109/cvprw.2009.5204237

[4] V. K. Singh, F. M. Khan, R. Nevatia, Multiple pose context trees for estimating human pose in object context, in: Proceedings of the International Conference on Computer Vision Workshop, 2010, pp.17-24.

DOI: 10.1109/cvprw.2010.5543186

[5] M. C. Yuksek, B. Barshan, et al., Human activity classification with miniature inertial and magnetic sensors, in: Proceedings of the IEEE 19th Conference on Signal Processing and Communications Applications, 2011, pp.1052-1055.

DOI: 10.1109/siu.2011.5929835

[6] S. Singh, H. Y. Tu, et al., Anomaly Detection via Feature-Aided Tracking and Hidden Markov Models, IEEE Transactions on Systems, Man and Cybernetics, Part A: Systems and Humans 39 (1) 2009 144-159.

DOI: 10.1109/tsmca.2008.2007944

[7] F. I. Bashir, A. A. Khokhar, D. Schonfeld, Object trajectory-based activity classification and recognition using hidden markov models. IEEE Transactions on Image Processing 16 (7) (2007) 1912-(1919).

DOI: 10.1109/tip.2007.898960

[8] M. Albanese, R. Chellappa, et al. A constrained probabilistic Petri Net framework for human activity detection in video, IEEE Transaction on Multimedia 10 (6) 2008 982-996.

DOI: 10.1109/tmm.2008.2001369

[9] D. Riboni, L. Pareschi, et al., Is ontology-based activity recognition really effective? in: Proceedings of IEEE International Conference onf Pervasive Computing and Communications Workshops, 2011, pp.427-431.

DOI: 10.1109/percomw.2011.5766927

[10] Y. A. Ivanov and A. F. Bobick, Recognition of visual activities and interactions by stochastic parsing, IEEE Transactions on Pattern Analysis and Machine Intelligence 22 (8) (2000) 852–872.

DOI: 10.1109/34.868686

[11] G. Lavee , E. Rivlin , M. Rudzsky, Understanding video events: a survey of methods for automatic interpretation of semantic occurrences in video, IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews 39 (5) 2009 489-504.

DOI: 10.1109/tsmcc.2009.2023380

[12] P. Liang, M. I. Jordan, D. Klein, Probabilistic grammar and hierarchical dirichlet processes. The Handbook of Applied Bayesian Analysis, In pressed.

[13] S. Hettich and S. D. Bay, The UCI KDD archive. Irvine, CA: Dept. Inform. Comput. Sci., Univ. California.

[14] X. Weiguang, Z. Yafei, L. Jianjiang, W. Jiabao, HDP-HMM-SCFG: A Novel Model for Trajectory Representation and Classification, Procedia Engineering, (2011).

DOI: 10.1016/j.proeng.2011.08.117