Marine Radar Multiobject Tracking Based on Improved Space-Time Memory Network

A novel marine radar multiobject tracking (MOT) algorithm is proposed based on the space-time memory network (STMN), which is specifically designed to markedly enhance the accuracy and stability of vessel tracking in complex marine environments. Especially, compared to traditional point- or shape-based radar object tracking methods, the proposed algorithm can significantly enhance robustness with respect to the occluded and rapid target deformation. First, we define the macro- and micro-velocities for each object, integrating them into the proposed algorithm for newborn targets recognition, thereby improving the accuracy of target identification in occluded or cluttered environments. Second, we propose a feature extraction module that enables STMN to handle multiple targets simultaneously, which can efficiently differentiate the newborn, survival, and suspicious targets in complex scenarios. Finally, to enhance the shape estimation accuracy of survival targets, we propose a width-height difference intersection over union (WH-IOU) algorithm, which can improve the consistency between detection boxes and object contours, thereby boosting overall tracking performance. Experimental results demonstrate that the proposed algorithm outperforms existing methods in X-band radar MOT tasks, achieving substantial improvements in both tracking accuracy and robustness.