Abstract
This paper presents a novel multi-objective optimization based sensor selection method for multi-target tracking in sensor networks. The multi-target states are modelled as multi-Bernoulli random finite sets and the multi-Bernoulli filter is used to propagate the multi-target posterior density. The proposed method is designed to select the sensor that provides the most reliable cardinality estimate, since more accurate cardinality estimate indicates more accurate target states. In the multi-Bernoulli filter, the updated multi-target density is a multi-Bernoulli random finite set formed by a union of legacy tracks and measurement-updated tracks. The legacy track and the measurement-updated track have different theoretical and physical meanings, and hence these two kinds of tracks are considered separately in the sensor management problem. Specifically, two objectives are considered: (1) maximizing the mean cardinality of the measurement-updated tracks, (2) minimizing the cardinality variance of the legacy tracks. Considering the conflicting objectives simultaneously is a multi-objective optimization problem. Tradeoff solutions between two conflicting objectives will be derived. Theoretical analysis and examples show that the proposed approach is effective and direct. The performance of the proposed method is demonstrated using two scenarios with different levels of observability of targets in the passive sensor network.
Highlights
Tracking of multi-target in sensor networks is an important but challenging task for radar, sonar and other surveillance systems [1]
When it is difficult to know the true underlying model, joint Bayesian parameter estimation and model selection have been extensively studied within the Monte Carlo (MC) methodology [2,3]
Multi-target tracking under these circumstances is nontrivial and the difficulty is further compounded in the sensor selection problem [6]
Summary
Tracking of multi-target in sensor networks is an important but challenging task for radar, sonar and other surveillance systems [1]. The probability hypothesis density (PHD) [8] and cardinalized PHD (CPHD) [9] filters are two popular approaches within FISST They propagate moment approximations of the RFS of states in time and avoid the combinatorial problem arising from data association. This paper formulates the sensor management problem as a multi-objective optimization problem with two different objective functions, to improve the tracking performance while maintaining low computation cost. The objective functions are developed as the mean cardinality of the measurement-updated tracks and the cardinality variance of the legacy tracks, both of which can be computed analytically. Maximizing the mean cardinality of the measurement-updated tracks while minimizing the cardinality variance of the legacy tracks is conflicting and is modelled as a multi-objective optimization problem.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
