Distributed Multi-Sensor Control for Multi-Target Tracking Using Adaptive Complementary Fusion for LMB Densities

TL;DR

This paper introduces a distributed multi-sensor control method with adaptive fusion for multi-target tracking, enhancing accuracy and efficiency in large-scale sensor networks.

Contribution

It presents a novel adaptive complementary fusion approach combined with multi-agent coordinate descent for fully distributed, scalable multi-target tracking.

Findings

Significant improvement in tracking accuracy over existing methods.

Enhanced computational efficiency enabling real-time processing.

Scalability demonstrated in large-scale sensor network scenarios.

Abstract

Tracking multiple targets in dynamic environments using distributed sensor networks is a fundamental problem in statistical signal processing. In such scenarios, the network of mobile sensors must coordinate their actions to accurately estimate the locations and trajectories of multiple targets, balancing limited computation and communication resources with multi-target tracking accuracy. Multi-sensor control methods can improve the performance of these networks by enabling efficient utilization of resources and enhancing the accuracy of the estimated target states. This paper proposes a novel multi-sensor control method that utilizes multi-agent coordinate descent to address this problem, ensuring distributed consensus of optimal sensor actions throughout the sensor network. To achieve this, a novel adaptive complementary fusion approach that prioritizes information from the most informative sensors is developed. Our method improves computational tractability and enables fully distributed control, ensuring the scalability and flexibility necessary for large-scale real-time sensing systems. Experimental results on several challenging multi-target tracking scenarios demonstrate that our approach significantly improves both multi-target tracking accuracy and computation efficiency over competing methods.