An Improved Multi-target Tracking Trajectory Association Algorithm in Dense Clutter Environment
Xiangsong Huang, Wenyan Wang, Dapeng Pan, Yuan Jia · 2021 7th International Conference on Computer and Communications (ICCC) · 2021
In order to solve the trajectory association of multi-target tracking in dense clutter environment, we propose a joint probabilistic data association algorithm based on Sequential Probability Ratio Test with the simplified association probability(S-SPRT-JPDA). First, we use the sequential probability ratio test to introduce a target tracking management system, to solve the problem of the trajectory initiation and termination in dense clutter environment; and we redefine the confirmation matrix in the joint probability data association algorithm to simplify the calculation of the association probability when the target and the measurement are interconnected. The theoretical analysis and simulation experimental results show that the algorithm runs faster by 55% under the condition of ensuring the accuracy of association, which greatly reduces the calculation amount of trajectory association algorithm in the process of multi-target tracking and effectively improves the real-time performance of multi-target tracking data association algorithm in dense clutter environment.