Localized policy-based target tracking using wireless sensor networks

Abstract

Wireless Sensor Networks (WSN)-based surveillance applications necessitate tracking a target's trajectory with a high degree of precision. Further, target tracking schemes should consider energy consumption in these resource-constrained networks. In this work, we propose an energy-efficient target tracking algorithm, which minimizes the number of nodes in the network that should be activated for tracking the movement of the target. We model the movement of a target based on the Gauss Markov Mobility Model [Camp et al. 2002]. On detecting a target, the cluster head which detects it activates an optimal number of nodes within its cluster, so that these nodes start sensing the target. A Markov Decision Process (MDP)-based framework is designed to adaptively determine the optimal policy for selecting the nodes localized with each cluster. As the distance between the node and the target decreases, the Received Signal Strength (RSS) increases, thereby increasing the precision of the readings of sensing the target at each node. Simulations show that our proposed algorithm is energy-efficient. Also, the accuracy of the tracked trajectory varies between 50% to 1% over time.