Underwater Multitarget Tracking With Sonar Images Using Thresholded Sequential Monte Carlo Probability Hypothesis Density Algorithm
Tian Zhou, Yuqian Wang, Baowei Chen, Jianjun Zhu, Xiaoyang Yu · IEEE Geoscience and Remote Sensing Letters · 2022
This letter presents a multi-target tracking algorithm—thresholded Sequential Monte Carlo probability hypothesis density (TH-SMC-PHD) algorithm. The TH-SMC-PHD aims to overcome the problem that underwater multi-target tracking is prone to missing tracking on sonar images, resulting in the breakage of trajectories. First, CA-CFAR and K-means are employed to detect potential underwater targets from sonar images, respectively. Then TH-SMC-PHD is applied to the detection results for tracking, using a continuously lost frame threshold to reduce the missing tracking rate and the Minimum-Sampling-Variance (MSV) resampling to improve tracking accuracy. An actual underwater multi-target tracking experiment using a forward-looking sonar was contracted in a water tank to evaluate the tracking performance. Compared with the other two PHD tracking algorithms, the results demonstrate that the proposed algorithm achieves high-precision, non-fracture, non-missing tracking of three targets. In addition, the TH-SMC-PHD is more stable and less affected by different detection algorithms, which has the potential for practical applications.