MULS-Net: A multilevel supervised network for ship tracking from low-resolution remote-sensing image sequences

Ship detection and tracking from remote-sensing image sequences has become an increasingly important research point. However, there are still many challenges for ship tracking from low-resolution remote-sensing image sequences: 1) the dim and small objects contain only a few shape and texture features, making it difficult to detect and track ships; 2) broken clouds often resemble ships, resulting in false tracking; and 3) the ship may be occluded by clouds leading to missed tracking. To address these challenges, we proposed a novel multilevel supervision network for ship tracking from low-resolution remote-sensing image sequences. First, we designed a gradient difference-guided object clarification network component to significantly improve the object saliency, which is also implemented based on the multiframe correlation enhancement images to improve the feature strength of small targets in the input data. Second, to reduce the difficulty of completing complex tasks, a multilevel supervised network (MULS-Net) framework with multiple components was presented to improve the target clarity, detecting targets, and tracking targets step by step. Finally, to improve the trajectory integrity and tracking accuracy, a joint tracking method based on a low-frame-rate tracking criterion was proposed to control the state of the target tracking module. The method was validated on a self-assembled dataset from the GaoFen-4 satellite. The experiment results show the stronger competition and accuracy of the proposed method than other state-of-the-art object trackers.