Active-Vision for the Autonomous Surveillance of Dynamic, Multi-Object Environments

  • Authors:

  • Ardevan Bakhtari;Matthew Mackay;Beno Benhabib

  • Affiliations:

  • Computer Integrated Manufacturing Laboratory, Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, Canada M5S 3G8;Computer Integrated Manufacturing Laboratory, Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, Canada M5S 3G8;Computer Integrated Manufacturing Laboratory, Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, Canada M5S 3G8

  • Venue:
  • Journal of Intelligent and Robotic Systems
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents a novel method for active-vision-based sensing-system reconfiguration for the autonomous surveillance of an object-of-interest as it travels through a multi-object dynamic workspace with an a priori unknown trajectory. Several approaches have been previously proposed to address the problem of sensor selection and control. However, these have primarily relied on off-line planning methods and rarely utilized on-line planning to compensate for unexpected variations in a target's trajectory. The method proposed in this paper, on the other hand, uses a multi-agent system for on-line sensing-system reconfiguration, eliminating the need for any a priori knowledge of the target's trajectory. Thus, it is robust to unexpected variations in the environment. Simulations and experiments have shown that the use of dynamic sensors with the proposed on-line reconfiguration algorithm can tangibly improve the performance of an active-surveillance system.