Sonar tracking of multiple targets using joint probabilistic data association

TLDR

Data association in cluttered multi‑target environments is challenging; the probabilistic data association (PDA) method assumes a single target and Poisson clutter, limiting its applicability to passive sonar tracking. The authors introduce the joint probabilistic data association (JPDA) algorithm to compute joint posterior association probabilities for multiple targets in cluttered passive sonar environments. JPDA is applied to a passive sonar tracking scenario with multiple sensors and targets, modeling each target with four geographic states, two or more acoustic states, and realistic low detection probabilities, enabling estimation when a target is not fully observable from a single sensor. Simulation of two heavily interfering targets demonstrates dramatic tracking improvements when using JPDA compared to traditional methods.

Abstract

The problem of associating data with targets in a cluttered multi-target environment is discussed and applied to passive sonar tracking. The probabilistic data association (PDA) method, which is based on computing the posterior probability of each candidate measurement found in a validation gate, assumes that only one real target is present and all other measurements are Poisson-distributed clutter. In this paper, a new theoretical result is presented: the joint probabilistic data association (JPDA) algorithm, in which joint posterior association probabilities are computed for multiple targets (or multiple discrete interfering sources) in Poisson clutter. The algorithm is applied to a passive sonar tracking problem with multiple sensors and targets, in which a target is not fully observable from a single sensor. Targets are modeled with four geographic states, two or more acoustic states, and realistic (i.e., low) probabilities of detection at each sample time. A simulation result is presented for two heavily interfering targets illustrating the dramatic tracking improvements obtained by estimating the targets' states using joint association probabilities.