Heterogeneous Multi-sensor Fusion with Random Finite Set Multi-object Densities

TL;DR

This paper introduces a novel heterogeneous multi-sensor fusion approach using random finite set multi-object densities, addressing limitations of scalar-weight based methods by factorizing local densities into smaller sub-Densities for improved accuracy and robustness.

Contribution

It proposes a general heterogeneous fusion method that factorizes local RFS densities into sub-Densities, enabling parallelizable and more accurate multi-object density fusion without specific model assumptions.

Findings

Enhanced fusion accuracy demonstrated in numerical experiments.

Robustness to space-varying information confidence levels.

Effective parallelization of the fusion process.

Abstract

This paper addresses the density based multi-sensor cooperative fusion using random finite set (RFS) type multi-object densities (MODs). Existing fusion methods use scalar weights to characterize the relative information confidence among the local MODs, and in this way the portion of contribution of each local MOD to the fused global MOD can be tuned via adjusting these weights. Our analysis shows that the fusion mechanism of using a scalar coefficient can be oversimplified for practical scenarios, as the information confidence of an MOD is complex and usually space-varying due to the imperfection of sensor ability and the various impacts from surveillance environment. Consequently, severe fusion performance degradation can be observed when these scalar weights fail to reflect the actual situation. We make two contributions towards addressing this problem. Firstly, we propose a novel heterogeneous fusion method to perform the information averaging among local RFS MODs. By factorizing each local MODs into a number of smaller size sub-MODs, it can transform the original complicated fusion problem into a much easier parallelizable multi-cluster fusion problem. Secondly, as the proposed fusion strategy is a general procedure without any particular model assumptions, we further derive the detailed heterogeneous fusion equations, with centralized network architecture, for both the probability hypothesis density (PHD) filter and the multi-Bernoulli (MB) filter. The Gaussian mixture implementations of the proposed fusion algorithms are also presented. Various numerical experiments are designed to demonstrate the efficacy of the proposed fusion methods.