SSWS: An edge detection algorithm with strong semantics and high detectability for spacecraft

Abstract

Space tasks such as docking, capture and maintenance of spacecraft in orbit are increasingly dependent on visual system. High-order features extraction, target recognition and spacecraft pose measurement are essential image processing technologies to accomplish above tasks, for which image edge detection is one of the most critical and basic techniques. Traditional edge detection algorithms such as Canny have good extraction effect, but cannot extract and obtain semantic information. Besides, most of the edge detection algorithms based on deep-learning rely on a large number of annotation labels and require huge workload. Therefore, they cannot be applied to non-cooperative space targets. In this paper, we propose an edge detection algorithm with strong semantics and weak supervision (SSWS) to combine edge detection with image semantic segmentation. By learning geometric boundaries of ellipse and quadrilateral for docking ring and solar panel of spacecraft, and using the training method of weak supervision, our algorithm achieves effective boundary detection of important parts of spacecraft from images regardless of the background interference and light intensity. Real image experiments show that SSWS can effectively extract the boundary of important parts of spacecraft and filter out the background information and noise. In the performance verification experiment of BSDS500 dataset, with weakly supervised annotation tags, SSWS obtains the best OIS (0.831), in comparison with traditional edge detection algorithms and excellent recent deep-learning edge detection algorithms in recent years; in the contrast experiment of image segmentation in PASCAL VOC 2012 test set, SSWS gets the best mIoU value (66.9%).