Coopetitive multi-camera surveillance using model predictive control

Abstract

We present a generic framework for enhanced active multi-sensing. We propose a coopetitive interaction approach, which combines the salient features of cooperation and competition with an aim to optimize the cooperation among sensors to achieve best results at the system level rather than redundantly implementing cooperation at each stage. We also employ model predictive control based forward state estimation method for counter-acting various delays faced in multi-sensor environments. The results obtained for two different visual surveillance adaptations with different number of cameras and different surveillance goals provide clear evidence for the improvements created by adoption of the proposed enhancements.