Logarithm based adaptive Particle Filter for maneuvering target tracking in Wireless Sensor Networks with multiplicative noise

Abstract

Problem of maneuvering target tracking in a Wireless Sensor Network (WSN) with multiplicative noise is considered in this paper. To solve the problem of state dependent measurement noise of sensors, the multiplicative measurement model is adopted. Using natural logarithm, the observation model is turned into an equation with additive noise. The Probability Density Function (PDF) of this additive measurement noise is then obtained to construct the likelihood function and to weight the samples in Particle Filter (PF). To track the target with unknown maneuvers, Input Estimation (IE) technique is used. Moreover, the state transition prior PDF with adjusted covariance matrix is proposed as the importance density function to improve the estimation of target trajectory. Effectiveness of the proposed tracking approach is validated and compared with results of generic PF and Unscented Particle Filter (UPF) through Monte-Carlo simulations.

Adaptive Interacting Multiple Model Algorithm Based on Information-Weighted Consensus for Maneuvering Target Tracking

“…To solve the model uncertainty of the target by the input estimation technique, an adaptive particle filter for maneuvering target tracking [ 21 ] is proposed. The multiplicative measurement model is used to deal with the measurement noise (related to state) in the sensor network.…”