Segmentation-based orbiting satellite tracking

To obtained the trajectory of an orbiting satellite is a fundamental and vital step for space rendezvous and manipulation by space robots. Due to the freely and rapidly motion of on-orbiting satellites, the sudden change in appearance, orbiting satellite tracking is difficult for traditional tracker, which usually relies on a single bounding box of the target object. However, more information should be provided by visual tracking such as binary mask. In this paper, we proposed a SOST (Segmentation-based Orbiting Satellite Tracking) algorithm that improves the performance of tracking. Our method, SOST, improves the tracking performance by generating a mask map obtained from segmentation within the initial bounding box. The final bounding box will be refined using the segmentation result. Experiment using real on-orbit rendezvous and docking video from NASA (Nation Aeronautics and Space Administration), simulated satellite animation sequence from ESA (European Space Agency) and image sequences of 3D printed satellite model took in our laboratory demonstrate the robustness, versatility and fast speed of our method compared to state-of-the-art tracking methods. Our dataset will be released for academic use in future.