Abstract
Dynamic probabilistic networks have been widely used in activity recognition. However, few models are competent for long-term complex activities involving multi-person interactions. Based on the study of activity characteristics, this paper proposes a decomposed hidden Markov modelĀ (DHMM) to capture the structures of activity both in time and space. The model combines spatial decomposition and hierarchical abstraction to reduce the complexity of state space as well as the number of parameters greatly, with consequent computational benefits in efficiency and accuracy. Experiments on two-person interactions and individual activities demonstrate that DHMMs are more powerful than Coupled HMMs and Hierarchical HMMs.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Moeslund, T.B., Hilton, A., Krger, V.: A survey of advances in vision-based human motion capture and analysis. International Journal on Computer Vision and Image UnderstandingĀ 104(2-3), 90ā127 (2006)
Zacks, J.Z., Tversky, B.: Event structure in perception and conception. Psychological BulletinĀ 127, 3ā21 (2001)
Murphy, K.P.: Hidden Semi-Markov modelsĀ (HSMMs) (2002), http://www.ai.mit.edu/muphyk
Hongeng, S., Nevatia, R.: Large-scale event detection using Semi-hidden Markov models. In: Proc. ICCV, pp. 1455ā1462 (2003)
Ghahramani, Z.: An introduction to hidden Markov models and bayesian networks. Journal of Pattern Recognition and Artificial Intelligence 15(1), 9C42 (2001)
Brand, M., Oliver, N.M., Pentland, A.P.: Coupled hidden Markov models for complex action recognition. In: Proc. CVPR, pp. 994ā999 (1997)
Oliver, N.M., Rosario, B., Pentland, A.P.: A Bayesian computer vision system for modeling human interactions. IEEE Trans. PAMIĀ 22, 831ā843 (2000)
Gong, S., Xiang, T.: Recognition of group activities using dynamic probabilistic networks. In: Proc. ICCV, pp. 742ā749 (2003)
Galata, A., Johnson, N., Hogg, D.: Learing variable-length markov models of behavior. Comuter Vision and Image UnderstandingĀ 81, 398ā413 (2001)
Bui, H.H., Venkatesh, S., West, G.: Policy recognition in the abstract hidden Markov model. Journal of Artificial Intelligence ResearchĀ 17, 451ā499 (2002)
Oliver, N., Garg, A., Horvitz, E.: Layered representations for learning and inferring office activity from multiple sensory channels. Computer Vision and Image UnderstandingĀ 96(2), 163ā180 (2004)
Fine, S., Singer, Y., Tishby, N.: The hierarchical hidden Markov model: analysis and applications. Machine LearningĀ 32(1), 41ā62 (1998)
Murphy, K.P, Paskin, M.: Linear time inference in hierarchical HMMs. In: Proc. NIPS, pp. 833ā840 (2001)
Liu, X.H., Chua, C.S.: Multi-agent activity recognition using observation decomposed hidden Markov models. Image and Vision ComputingĀ 24, 166ā175 (2006)
Nguyen, N.T., Phung, D.Q., Venkatesh, S., Bui, H.: Learning and detecting activities from movement trajectories using the hierarchical hidden Markov model. In: Proc. CVPR, pp. 955ā960 (2005)
Zhang, W.D, Chen, F., Xu, W.L., Zhang, E.W.: Real-time video intelligent surveillance system. In: Proc. ICME, pp. 1021ā1024 (2006)
Du, Y.T., Chen, F., Xu, W.L., Li, Y.B.: Recognizing interaction activities using dynamic Bayesian network. In Proc. ICPR, pp. 618ā621 (2006)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
Ā© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Zhang, W., Chen, F., Xu, W., Cao, Z. (2007). Decomposition in Hidden Markov Models for Activity Recognition. In: Sebe, N., Liu, Y., Zhuang, Y., Huang, T.S. (eds) Multimedia Content Analysis and Mining. MCAM 2007. Lecture Notes in Computer Science, vol 4577. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-73417-8_30
Download citation
DOI: https://doi.org/10.1007/978-3-540-73417-8_30
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-73416-1
Online ISBN: 978-3-540-73417-8
eBook Packages: Computer ScienceComputer Science (R0)