Multi-Target Tracking Considering the Uncertainty of Deep Learning-based Object Detection of Marine Radar Images

In this paper, a multi-target tracking approach that integrates the extended Kalman filter and deep learning-based object detection in marine radar images is presented. The Gaussian YOLOv3 method is utilized for object detection, providing both position measurements and their uncertainties. The extended Kalman filter is employed to estimate the position, heading, and speed of each detected target considering the uncertainty values obtained from the object-detection process. The global nearest neighbor-based data association and a dual filter structure composed of a confirmed track and a reserved track are applied to enhance the robustness of the tracking process. The feasibility of the proposed algorithm is validated through a real-world marine radar dataset collected in a coastal environment.