Email this article An Algorithm of Unsupervised Posture Clustering and Modeling Based on GMM and EM Estimation
Abstract
this paper focuses on human posture clustering and modeling for human action recognition in the field of computer vision. Specifically we mainly talk about posture description with spatial temporal interesting point features rather than traditional posture segmentations; also we give the comparisons of four kinds of unsupervised clustering methods and continue to carry out unsupervised posture classifications based on Weizmann database. In the following we use GMMs based on EM algorithm to model each clustered posture type. Finally we test our method with Weizmann and KTH Action database. These experiments show its effectiveness and robustness.
Keywords
References
[1] Robertson, N., Reid, I.D, “A general method for human activity recognition in video,” Computer Vision and Image Understanding, vol.104, pp.232-248, 2006.
http://dx.doi.org/10.1016/j.cviu.2006.07.006
[2] Ahmad M., Seong-Whan Lee. “Human action recognition using multi-view image sequences features,” in Proc. AF GR, pp.523-528, 2006.
[3] Christoph Bregler. “Learning and Recognizing Human Dynamics in Video Sequences,” IEEE CVPR, pp.568-574, 1997.
[4] Junxia Gu, Xiaoqing Ding, Shengjin Wang. “Survey on action analysis,” Journal of china image and graphics, Vol.13, pp.377-387, 2010.
[5] Yilmaz Alper, Shah Mubarak, “Actions sketch: A novel action representation,” In Proc. CVPR, San Diego, California, USA, pp.984-989, 2005.
[6] Wang Liang, Suter David, “Informative shape representations for human action recognition,” In Proc. of Conf. on PR, Hong Kong, pp.1266-1269, 2006.
[7] Grimson W E L, Stauffer C, Romano R, et al, “Using adaptive tacking to classify and monitor activities in a site,” In Proc. CVPR, Santa Barbara, California, USA, pp.22-29,1998.
[8] Robertson N, Reid I, “Behavior understanding in videos: a combined method,” In: Proc. ICCV, Beijing, 2005, pp. 808-815.
[9] Ben-Arie Jezekiel, Wang Zhi-qian, Pandit Puvin, et a l, “ Human activity recognition using multidimensional indexing,” IEEE Trans. PAMI, vol.24, no.8, pp.1091-1104, 2002.
http://dx.doi.org/10.1109/TPAMI.2002.1023805
[10] Rourke J O, BadlerN, “Model-based image analysis of human motion using constraint propagation,” IEEE Trans. PAMI, vol.2, no.6, pp.522-536, 1980.
[11] Gavrila Dariu M, Vision-Based 3-D Tracking of Human in Action”. Maryland, USA: University of Maryland, 1996.
[12] Kehl R, BrayM, VanGool L. “Full body tracking from multip le views using stochastic sampling,” In Proc. CVPR, San Diego, California, USA, 2005, pp.129-136.
[13] M.Oren, C.Papageorigiou, P.Sinha,E.Osuna, T.Poggio, “Pedestrian detection using wavelet templates,” In Proc. CVPR,1997,pp.193-199.
[14] O.Chomat, J.L.Crowley, “Recognizing motion using local appearance,” In proc. on IRS, University of Edinburgh, 1998.
[15] S.X.Ju, M.J.Black, Y.Yacoob. “Cardboard people: A Parameterized model of articulated image motion,” in Proc. On AFGR, 1996, pp.38-44.
[16] Y.Yacoob, M.J.Black, “Parameterized modeling and recognition of activities,” In: Proc. ICCV, 1998, pp.120-127. [17] A. Bobick and J. Davis, “The recognition of human movement using temporal templates,” IEEE Trans. PAMI, vol. 23, pp. 257–267, 2001.
[18] M. Hu, “Visual pattern recognition by moment invariants,” IRE Trans. Information Theory, vol. 8, no. 2, pp. 179-187, 1962.
http://dx.doi.org/10.1109/TIT.1962.1057692
[19] H. Meng, N. Pears, and C. Bailey, “A human action recognition system for embedded computer vision application,” in Proc. CVPR, 2007.
[20] Lawrence R. Rabiner, “A Tutorial on Hidden Markov Model and Selected Applications in Speech Recognition,” in Proc. of IEEE,1989,vol.77, no.2, pp.257-286.
[21] Michael M, Yin, Jason T.L. Wang, “Application of Hidden Markov Models to Gene Prediction in DNA,” In Proc. on I IS,1999, pp.40-48.
[22] Shun-Zheng Yu, Hisashi Koayashi, “An efficient Forward-Backward Algorithm for an Explicit Duration Hidden Markov Model,” IEEE Signal Processing Letters, 2003, vol.10, no.1, pp.11-14.
http://dx.doi.org/10.1109/LSP.2002.806705
[23] Venkatesh Babu R., Anantharaman B., Ramakrishnan K.R., Srinivasan S.H., “Compressed domain action classification using HMM,” in IEEE workshop on Content-Based Access of Image and Video Libraries.2001,pp.44-49. [24] P. Kakumanu, S. Makrogiannis, N. Bourbakis, “A survey of skin-color modeling and detection methods”. Pattern Recognition vol.40, pp.1106-1122, 2007.
http://dx.doi.org/10.1016/j.patcog.2006.06.010
[25] Cheng duansheng, Liukaisheng, “Summarization of skin detection techniques,” Journal of computer, vol.29 no.2 Feb,2006, pp.194-207.
[26] Ivan Laptev and Tony Lindeberg, “Space-Time Interest Points,” In Proc. ICCV, 2003, Nice, France, pp.I:432-439. [27] P. Dollár, V. Rabaud, G. Cottrell, S. Belongie, "Behavior recognition via sparse spatial-temporal features," in Proc. IEEE International Workshop on VEPRTS, pp.65-72, 2005.
[28] Bezdek JC, Hathaway RJ, Sabin MJ, Tucker WT, “Convergence theory for fuzzy C-means: counterexamples and repairs,” IEEE Trans. on Systems, Man, and Cybernetics. Vol. SMC-17, no. 5, pp. 873-877. 1987.
[29] Mingzhou (Joe) Song and Lin Zhang, “Comparison of Cluster Representations from Partial Second- to Full Fourth-Order Cross Moments for Data Stream Clustering,” in Proc. 8th Conference on Data Mining, pp.560-570. 2008.
[30] Setnes M, Babuska R, “Fuzzy relational classifier trained by fuzzy clustering,” IEEE Trans Syst Man Cybern vol.29, no.5, pp.619-625, 1999.
http://dx.doi.org/10.1109/3477.790444
PMid:18252339
[31] Richard J. Hathaway and James C. Bezdek, “NERF c-means: Non-Euclidean relational fuzzy clustering,” Pattern Recognition, Vol. 27, No. 3, pp. 429-437, 1994.
http://dx.doi.org/10.1016/0031-3203(94)90119-8
Full Text: PDF