Hybrid-driven Gaussian process online learning for highly maneuvering multi-target tracking

2023, Volume 24, Issue 11

Abstract

Keywords

Related Research

Frontiers of Information Technology & Electronic Engineering >> 2023, Volume 24, Issue 11 doi: 10.1631/FITEE.2300348

Hybrid-driven Gaussian process online learning for highly maneuvering multi-target tracking

College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China; China National Aeronautical Radio Electronics Research Institute, Shanghai 200233, China; College of Automation, Hangzhou Dianzi University, Hangzhou 310018, China;

Received: 2023-05-18 Accepted: 2023-12-04 Available online: 2023-12-04

HTML4 PDF 39 Collect 0

Next Previous

Abstract

The performance of existing maneuvering methods for highly maneuvering targets in cluttered environments is unsatisfactory. This paper proposes a hybrid-driven approach for tracking multiple highly maneuvering targets, leveraging the advantages of both and model-based algorithms. The time-varying constant velocity model is integrated into the (GP) of to improve the performance of GP prediction. This integration is further combined with a generalized algorithm to realize multi-. Through the simulations, it has been demonstrated that the hybrid-driven approach exhibits significant performance improvements in comparison with widely used algorithms such as the interactive multi-model method and the GP motion tracker.

Keywords

Target tracking ; Gaussian process ; Data-driven ; Online learning ; Model-driven ; Probabilistic data association

Related Research