A Multi Target Tracking Algorithm Based on Acoustic Feature Correlation

This paper proposes a joint probability data association based on acoustic feature correlation (JPDA-AF) to address the issue of poor target tracking stability caused by low acoustic positioning accuracy. This algorithm utilizes the correlation information between the measured values and the acoustic characteristics of the tracked target, sets up dual gate detection, and weights the joint probability density of JPDA. The simulation analysis and experimental data processing results show that this method can effectively improve the stability of target tracking, enhance the integrity of tracking trajectory, reduce the number of false targets, and estimate the number of targets more accurately.