Distributed Expectation Propagation for Multi-Object Tracking over Sensor Networks

TL;DR

This paper introduces a distributed expectation propagation algorithm that allows sensor networks to collaboratively track multiple objects efficiently without central data aggregation, improving communication and inference in cluttered environments.

Contribution

It proposes a novel distributed expectation propagation framework with a Rao-Blackwellised Gibbs sampling scheme for improved multi-object tracking in sensor networks.

Findings

Enhanced tracking accuracy in cluttered environments.

Reduced communication overhead among sensors.

Improved inference efficiency with dynamic connectivity.

Abstract

In this paper, we present a novel distributed expectation propagation algorithm for multiple sensors, multiple objects tracking in cluttered environments. The proposed framework enables each sensor to operate locally while collaboratively exchanging moment estimates with other sensors, thus eliminating the need to transmit all data to a central processing node. Specifically, we introduce a fast and parallelisable Rao-Blackwellised Gibbs sampling scheme to approximate the tilted distributions, which enhances the accuracy and efficiency of expectation propagation updates. Results demonstrate that the proposed algorithm improves both communication and inference efficiency for multi-object tracking tasks with dynamic sensor connectivity and varying clutter levels.