Title: Research on multi-target tracking of moving observation stations based on IL-PSO algorithm

Authors: Xinbiao Lu; Fang Li; Chenyang Hang

Addresses: College of Artificial Intelligence and Automation, Hohai University, Nanjing, 210000, China ' College of Artificial Intelligence and Automation, Hohai University, Nanjing, 210000, China ' School of Electrical and Power Engineering, Hohai University, Nanjing, 210000, China

Abstract: Regarding how the positional arrangement of mobile sensors affects multi-target tracking accuracy, the interactive learning particle swarm optimisation (IL-PSO) algorithm is introduced. It uses observation stations' motion models to predict multi-target states. First, targets are allocated for effective tracking. Then, joint probabilistic data association (JPDA), strong tracking filter (STF), and genetic algorithm particle filter (GAPF) algorithms are integrated to improve tracking accuracy. A comparative analysis based on IL-PSO shows its superior performance in metrics like relative point position error. This is due to its optimisation of station positions and the integration of algorithms enhancing precision and robustness.

Keywords: GAPF; genetic algorithm particle filter; JPDA; joint probabilistic data association; multi-target tracking; PSO; particle swarm optimisation; STF; strong tracking filter.

DOI: 10.1504/IJAAC.2026.150569

International Journal of Automation and Control, 2026 Vol.20 No.1, pp.68 - 87

Received: 21 Feb 2023
Accepted: 12 May 2024
Published online: 17 Dec 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article