Target tracking with size estimation in wireless sensor networks

Abstract

The information of target size is useful for a lot of target tracking applications of wireless sensor networks, however, it has been neglected in most existing work. This paper considers the problem of target tracking with size estimation by ultrasonic sensors, which are able to measure the relative distance with satisfactory accuracy. We first propose a recursive algorithm for single target tracking and size estimation by adopting the Extended Kalman Filter (EKF) method. For the multiple-target case, a novel target identification algorithm, which aims to minimize the consecutive square estimate error, is given to track multiple targets and estimate the corresponding size simultaneously at each time step. Extensive simulations demonstrate the effectiveness of the proposed algorithms.