Abstract
A new approach of modeling/recognizing multi-agent activities from image sequences is presented. In recent years, Hidden Markov Models (HMMs) have been widely used to recognize activity units ranging from individual gestures to multi-people interactions. However, traditional HMMs meet many problems when the number of agents increases in the scene. One significant reason for this inability is the fact that HMMs require their ‘observations’ to be of fixed length and order. Unlike conventional HMMs, a new algorithm to model multi-agent activities is proposed. This has two sub-processes: one for modelling the activity based on decomposed observations and the other for recording the ‘role’ information of each agent in the activity. This new algorithm allows changing of the observations’ length, and does not require initial agent assignment. The experimental results show that this algorithm is also robust when the agents’ information is only partially represented.
This is a preview of subscription content, log in via an institution to check access.
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
Aggarwal, J.K., Cai, Q.: Human Motion Analysis: A Review. Computer vision and image understanding, Vol. 73, No. 2, March, (1999) 428–440
Gavrila, D.M.: The Visual Analysis of Human Movement: A survey. Computer and image understanding, Vol. 73, No. 1, January, (1999) 82–98
Campbell, L.W., Becker, D.A., Azarbayejani, A., Bobick, A.F., Pentland, A.: Invariant feature for 3-D gesture recognition. Proceedings of the Second International Conference on Automatic Face and Gesture Recognition, (1996) 157–162
Starner, T., Weaver, J., Pentland, A.: Real-time American Sign Language Recognition Using Desk and Wearable Computer Based Video. IEEE Trans. PAMI, Vol. 20, No, 12, December, (1998) 1371–1375
Wilson, A.D., Bobick, A.F.: Parametric Hidden Markov Models for Gesture Recognition. IEEE Trans. PAMI, Vol.21, No. 9, Sep, (1999) 884–899
Lee, H.K., Kim, J.H.: An HMM-Based Threshold Model approach for Gesture Recognition. IEEE Trans. PAMI, Vol. 21, No. 10, (1999) 961–973
Yang, M.H., Ahujia, M., Tabb M.: Extraction of 2D Motion Trajectories and Its Application to Hand Gesture Recogntion. IEEE Trans. PAMI, Vol.24, No. 8, Aug, (2002) 1061–1074
Yamato, J., Ohya, J., Ishii, K.: Recognizing human action in time-sequential images using hidden Markov model. IEEE CVPR, (1992) 379–385
Krahnstöver, N., Yeasin, M., Sharma, R.: Towards a Unified Framework for Tracking and Analysis of Human Motion. IEEE Workshop on Detection and Recognition of Events in Video, (2001) 47–54
Galata, A., Johnson, N., Hogg D.: Learing Variable-length Markov Models of Behavior. Comuter Vision and Image Understanding, Vol. 81, No. 3, (2001) 398–413
Bobick, A.F., Davis, J.W.: The recognition of Human Movement Using Temporal Template. IEEE Trans. PAMI, Vol.23, No. 23, (2001) 257–267
Toshikazu, W., Takashi, M.: Multiobject Behavior Recognition by Event Driven Selective Attention Method. IEEE Trans. PAMI, Vol. 22, No. 8, Aug. (2000) 873–887
Oliver, N.M., Rosario, B., Pentland, A.: A Bayesian Computer Vision System for Modeling Human Interactions. IEEE Trans. PAMI, Vol. 22, No. 8, August, (2002) 831–843
Hongeng, S., Nevatia, R.: Multi-agent event recognition. Eighth ICCV, Vol. 2, (2001) 84–91
Rabiner L. R.: A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. IEEE, Vol. 77, No. 2, (1989) 257–286
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Liu, X., Chua, CS. (2003). Multi-agent Activity Recognition Using Observation Decomposed Hidden Markov Model. In: Crowley, J.L., Piater, J.H., Vincze, M., Paletta, L. (eds) Computer Vision Systems. ICVS 2003. Lecture Notes in Computer Science, vol 2626. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-36592-3_24
Download citation
DOI: https://doi.org/10.1007/3-540-36592-3_24
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-00921-4
Online ISBN: 978-3-540-36592-1
eBook Packages: Springer Book Archive