Marine Navigation Radar Multi-Target Tracking Using Adaptive Innovation Sequence-Based Joint Probability Data Association
Qiang Wang, Xiao Huang, Hao Tao, Zhiwei Xia, Chun Liu, Xiaoqiang Ren · 2024
To address the challenges associated with marine navigation radar tracking in scenarios characterized by dense clutter and high-speed targets, this paper presents a multi-target tracking approach featuring an adaptive innovation sequence-based non-linear joint probability data association (AIS-JPDA) algorithm. The introduction of a straightforward calculation method for association probability aims to mitigate the issue of incorrect associations in target tracking within dense clutter environments. This method incorporates common measurements and their membership degrees to rectify the association probability, thereby enhancing the accuracy and real-time efficiency of multi-target track associations. The adaptive innovation policy is integrated to allow for the dynamic adjustment of the covariance matrix, accommodating process and measurement noise in non-linear maneuvering models. Furthermore, a lifecycle-based target track maintenance method is introduced to tackle the challenge of track disconnection resulting from high target relative velocity. Finally, simulation results demonstrate the effectiveness of the proposed algorithm.