MAVI: a multi-agent system for visual integration

This paper presents a control architecture for building integrated vision systems. This system is based on a multi-agent approach which allows the definition of an open and flexible architecture for the integration of visual modules. It is shown how this architecture permits the dynamic definition of the control with some visual goals to satisfy in the context of an active vision system.<<ETX>>

[1]  Jean-Luc Koning,et al.  Using interaction protocols to control vision systems , 1994, Proceedings of IEEE International Conference on Systems, Man and Cybernetics.

[2]  Yves Demazeau,et al.  Using the active object model to implement multi-agent systems , 1993, Proceedings of 1993 IEEE Conference on Tools with Al (TAI-93).

[3]  Amy L. Lansky,et al.  Reactive Reasoning and Planning , 1987, AAAI.

[4]  R. Bajcsy Active perception , 1988 .

[5]  James J. Clark,et al.  Control of visual attention in mobile robots , 1989, Proceedings, 1989 International Conference on Robotics and Automation.

[6]  Andrea Califano,et al.  Data and model driven foveation , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[7]  Monique Thonnat,et al.  A knowledge-based approach to integration of image processing procedures , 1993 .

[8]  Olivier Boissier,et al.  ASIC: An Architecture for Social and Individual Control and its Application to Computer Vision , 1994, MAAMAW.

[9]  James L. Crowley,et al.  Perceptual Grouping for Scene Interpretation in an Active Vision System , 1991, Geometric Reasoning for Perception and Action.