Abstract
The scene interpretation system proposed below integrates computer vision and artificial intelligence techniques to combine the information generated by multiple cameras on typical secure sites. A multi-agent architecture is proposed as the backbone of the system within which the agents control the different components of the system and incrementally build a model of the scene by merging the information gathered over time and between cameras. The choice of a distributed artificial intelligence architecture is justified by the need for scalable designs capable of co-operating to infer an optimal interpretation of the scene. Decentralizing intelligence means creating more robust and reliable sources of interpretation, but also allows easy maintenance and updating of the system. The scene model is learned using Hidden Markov models which capture the range of possible scene behaviours. The employment of such probabilistic interpretation techniques is justified by the very nature of surveillance data, which is typically incomplete, uncertain and asynchronous.
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
A. Dempster, M. Laird, and D. Rubin. Maximum likelihood from incomplete data via the em algorithm. J.R.Stat. Soc., B, 39:1–38, 1977.
A. Bakowski and G.A. Jones. Video surveillance tracking using colour adjacency graphs. In IEE Conference on Image Processing and its Applications, pages 794–798, 1999.
V. Cadez, S. Gaffney, and P. Smyth. A general probabilistic framework for clustering individuals and objects. In Proceedings of the ACM KDD, 2000.
H. Buxton and S. Gong. Visual surveillance in a dynamic and uncertain world. Artificial Intelligence, 78:431–459, 1995.
L. Marchesotti, P. Remagnino, and G.A. Jones. Evaluating centralised and distributed multiagent architectures for visual surveillance. In Proceedings of European Signal Processing Conference, 2000.
L. Rabiner and B-H. Juang. Fundamentals of Speech Recognition. Prentice-Hall, 1993.
J. Orwell, P. Remagnino, and G.A. Jones. From connected components to object sequences. In First IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, pages 72–79, 2000.
H. Pasula and S. Russell. Approximate inference for first-order probabilistic languages. In Proceedings of the International Joint Conference of Artificial Intelligence, 2001.
P. Remagnino. Situated and ubiquitous behaviours: Layers of abstract for scene understanding. In Proceedings of Artificial Intelligence and Soft Computing (IASTED), pages 234–240, 2000.
P. Remagnino, J. Orwell, D. Greenhill, G.A. Jones, and L. Marchesotti. An agent society for scene interpretation. In G. Foresti, P. Mahonen, and C.S. Regazzoni, editors, Multimedia Video-based Surveillance Systems, Requirements, Issues and Solutions, pages 108–117. Kluwer, 2000.
P. Remagnino, T. Tan, and K. Baker. Agent orientated annotation in model based visual surveillance. In Proceedings of IEEE International Conference on Computer Vision, pages 857–862, 1998.
B. Rosario, N. Oliver, and A. Pentland. A synthetic agent system for bayesian modeling of human interactions. In Proceedings of Conference on Autonomous Agents, pages 342–343, 1999.
S.S. Intille and A.F. Bobick. A framework for recognizing multi-agent action from visual evidence. In Proceedings of the Sixteenth National Conference on Artificial Intelligence, pages 518–525, 1999.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Remagnino, P., Jones, G.A., Monekosso, N. (2001). Reasoning about Dynamic Scenes Using Autonomous Agents. In: Esposito, F. (eds) AI*IA 2001: Advances in Artificial Intelligence. AI*IA 2001. Lecture Notes in Computer Science(), vol 2175. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45411-X_21
Download citation
DOI: https://doi.org/10.1007/3-540-45411-X_21
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42601-1
Online ISBN: 978-3-540-45411-3
eBook Packages: Springer Book Archive