A Semi-Supervised Object Detection Method for Close Range Detection of Spacecraft and Space Debris

With the continuous development of space missions, a large number of artificial objects have been produced and deployed in Earth orbit, and there is an urgent need to equip satellites with the ability to autonomously detect nearby space targets to cope with the harm caused by non-cooperative targets to the safety of in orbit satellites. To meet the needs of intelligent detection of spacecraft and space debris, we propose a semi supervised target detection method with domain generalization capability. This method aims to improve the detection methods for spacecraft and debris, utilizing limited labeled data and a large amount of unlabeled data to train end-to-end networks and reduce dependence on data labeled information. In the Semi-Supervised Learning framework, we optimized and improved the dense detection network model, enhanced the Receptive field of the model, and optimized the feature fusion and representation capabilities of the model. The improved semi supervised object detection algorithm trained with only 10