Agent orientated annotation in model based visual surveillance

The paper presents an agent based surveillance system for use in monitoring scenes involving both pedestrians and vehicles. The system supplies textual descriptions for the dynamic activity occurring in the 3D world. These are derived by means of dynamic and probabilistic inference based on geometric information provided by a vision system that tracks vehicles and pedestrians. The symbolic scene annotation is given at two major levels of description: the object level and the inter-object level. At object level, each tracked pedestrian or vehicle is assigned a behaviour agent which uses a Bayesian network to infer the fundamental features of the objects' trajectory, and continuously updates its textual description. The inter-object interaction level is interpreted by a situation agent which is created dynamically when two objects are in close proximity. In the work included here the situation agent can describe a two-object interaction in terms of basic textual annotations, to summarise the dynamics of the local action.

[1]  Tieniu Tan,et al.  Recognising Objects on the Ground-plane , 1993, BMVC.

[2]  Margaret M. Fleck.  Boundaries and Topological Algorithms , 1988 .

[3]  Yoav Shoham.  Agent-Oriented Programming , 1993, Artif. Intell..

[4]  Tieniu Tan,et al.  Recognizing objects on the ground-plane , 1994, Image Vis. Comput..

[5]  Henrik I. Christensen,et al.  Bayesian methods for interpretation and control in multiagent vision systems , 1992, Defense, Security, and Sensing.

[6]  Jitendra Malik,et al.  Automatic Symbolic Traffic Scene Analysis Using Belief Networks , 1994, AAAI.

[7]  Shaogang Gong,et al.  Visual Surveillance in a Dynamic and Uncertain World , 1995, Artif. Intell..

[8]  Hilary Buxton,et al.  Analogical representation of space and time , 1992, Image Vis. Comput..

[9]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[10]  Bernd Neumann,et al.  On the Use of Motion Concepts for Top-Down Control in Traffic Scenes , 1990, ECCV.

[11]  Aaron F. Bobick,et al.  Computers Seeing Action , 1996, BMVC.

[12]  Hans-Hellmut Nagel,et al.  From image sequences towards conceptual descriptions , 1988, Image Vis. Comput..

[13]  Glenn Shafer,et al.  Probabilistic expert systems , 1996, CBMS-NSF regional conference series in applied mathematics.

[14]  Ann Elizabeth Nicholson,et al.  Monitoring discrete environments using dynamic belief networks (robotics) , 1992 .

[15]  Tieniu Tan,et al.  An Integrated Traffic and Pedestrian Model-Based Vision System , 1997, BMVC.

[16]  Geoffrey D. Sullivan,et al.  Model-based vehicle detection and classification using orthographic approximations , 1997, Image Vis. Comput..

[17]  A F Bobick,et al.  Movement, activity and action: the role of knowledge in the perception of motion. , 1997, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[18]  Monique Thonnat,et al.  The PASSWORDS Project [intelligent video image analysis system] , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[19]  David C. Hogg,et al.  An efficient method for contour tracking using active shape models , 1994, Proceedings of 1994 IEEE Workshop on Motion of Non-rigid and Articulated Objects.

[20]  Christopher M. Brown,et al.  Where to Look Next Using a Bayes Net: Incorporating Geometric Relations , 1992, ECCV.

[21]  Hans-Hellmut Nagel,et al.  Algorithmic characterization of vehicle trajectories from image sequences by motion verbs , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.