Enhancing Multi-Object Tracking Through Distributed Information Fusion in Connected Vehicle Networks

This paper introduces an approach to distributed multi-object tracking for connected vehicles, aiming to overcome the inherent challenges of label inconsistency and double counting prevalent in distributed information fusion methods, particularly in the context of situational awareness for connected vehicles. Our proposed method expands the label space by incorporating sensor identity into the object's label. Furthermore, we present an intuitive merging algorithm designed to effectively eliminate instances of double counting. The approach is formulated, and an algorithm is developed for implementation within a labeled multi-Bernoulli filter, executed locally on each node of a distributed network responsible for information fusion. To assess the efficacy of our solution, we evaluate its performance in a highly demanding scenario specifically designed for intelligent transport systems and compare its performance against alternative approaches.