Track Optimization and Matching With Learnable Modules for LMB-Based Distributed Resolvable Group Target Tracking

This article integrates two data-driven learnable modules into the conventional distributed multisensor resolvable group target tracking (RGTT) framework based on the labeled multi-Bernoulli (LMB) filter to improve tracking performance. First, in RGTT scenarios with densely distributed targets, the LMB filter is prone to track fragmentation and label switching, which reduces accuracy and complicates multisensor data association. While some studies have attempted to address this, their methods typically overlook the group structure and are often offline and computationally intensive. To overcome this, we propose a track optimization module based on an attention mechanism that alleviates these issues efficiently in an online setting. Second, we replace traditional data association algorithms, which rely on fixed similarity metrics, with a track matching module based on a message passing network (MPN). This module leverages historical track data and learns to infer latent similarities across sensors, significantly improving matching accuracy. Simulation results demonstrate the effectiveness of the proposed modules.