Distributed Fusion Architectures and Algorithms for Target Tracking

TLDR

Target tracking in modern surveillance relies on multiple distributed sensors whose data must be fused, and while centralized fusion is theoretically optimal, distributing fusion across processing nodes offers practical advantages. The study proposes distributed fusion architectures in which each node processes its own sensor data and exchanges information with others, and introduces an information graph to model flow and guide algorithm design. The authors present information‑graph‑based distributed estimation algorithms for arbitrary fusion architectures, address track‑to‑track association likelihoods, and provide distributed implementations of joint probabilistic data association and multiple hypothesis tracking with application examples.

Abstract

Modern surveillance systems often utilize multiple physically distributed sensors of different types to provide complementary and overlapping coverage on targets. In order to generate target tracks and estimates, the sensor data need to be fused. While a centralized processing approach is theoretically optimal, there are significant advantages in distributing the fusion operations over multiple processing nodes. This paper discusses architectures for distributed fusion, whereby each node processes the data from its own set of sensors and communicates with other nodes to improve on the estimates, The information graph is introduced as a way of modeling information flow in distributed fusion systems and for developing algorithms. Fusion for target tracking involves two main operations: estimation and association. Distributed estimation algorithms based on the information graph are presented for arbitrary fusion architectures and related to linear and nonlinear distributed estimation results. The distributed data association problem is discussed in terms of track-to-track association likelihoods. Distributed versions of two popular tracking approaches (joint probabilistic data association and multiple hypothesis tracking) are then presented, and examples of applications are given.