PROJECT TITLE :

Cost-Aware Coalitions for Collaborative Tracking in Resource-Constrained Camera Networks

ABSTRACT:

We propose an approach to form camera coalitions in resource-constrained camera networks and demonstrate it for collaborative target tracking. We have a tendency to forged coalition formation as a decentralized resource allocation method where the most effective cameras among those viewing a target are assigned to a coalition based mostly on marginal utility theory. A manager is dynamically selected to barter with cameras whether they will be part of the coalition and to coordinate the tracking task. This negotiation is based not solely on the utility brought by every camera to the coalition, but additionally on the associated value (i.e. extra processing and communication). Experimental results and comparisons using simulations and real knowledge show that the proposed approach outperforms connected state-of-the-art strategies by improving tracking accuracy in value-free settings. Moreover, under resource limitations, the proposed approach controls the tradeoff between accuracy and value, and achieves energy savings with only a minor reduction in accuracy.