SU-Net：用于非合作航天器在轨的位姿估计网络
SU-Net: Pose estimation network for non-cooperative spacecraft on-orbit
AI总结：
针对在轨非合作航天器雷达图像模糊、轮廓识别难导致位姿估计困难的问题，提出基于DR-U-Net的SU-Net端到端位姿估计网络，通过引入残差与密集连接降低特征损失并避免网络退化，实验表明该方法不依赖人工特征且精度优于现有方法。
摘要：
航天器位姿估计在许多在轨空间任务中发挥着至关重要的作用，例如交会对接、碎片清除和在轨维护。目前，空间图像包含变化广泛的照明条件、高对比度和低分辨率，使得空间物体的位姿估计比地球上物体的位姿估计更具挑战性。在本文中，我们分析了在轨航天器的雷达图像特征，随后提出了一种名为 Dense Residual U-shaped Network（DR-U-Net）的深度学习神经网络结构来提取图像特征。我们进一步引入了一种基于 DR-U-Net 的新型神经网络，即 Spacecraft U-shaped Network（SU-Net），以实现对非合作航天器的端到端位姿估计。具体而言，SU-Net 首先对非合作航天器的图像进行预处理，然后使用迁移学习进行预训练。随后，为了解决雷达图像模糊以及航天器轮廓识别能力低的问题，我们在主干网络 U-Net 中添加了残差连接和密集连接，并将其命名为 DR-U-Net。通过这种方式，减少了特征损失和模型的复杂性，并避免了训练期间深度神经网络的退化。最后，使用一层前馈神经网络进行非合作航天器在轨的位姿估计。实验证明，所提出的方法不依赖人工制作的物体特定特征，模型具有强大的鲁棒性，且计算精度优于最先进的位姿估计方法。绝对误差为 0.1557 到 0.4491，平均误差约为 0.302，标准差约为 0.065。
英文摘要：
Spacecraft pose estimation plays a vital role in many on-orbit space missions, such as rendezvous and docking, debris removal, and on-orbit maintenance. At present, space images contain widely varying lighting conditions, high contrast and low resolution, pose estimation of space objects is more challenging than that of objects on earth. In this paper, we analyzing the radar image characteristics of spacecraft on-orbit, then propose a new deep learning neural Network structure named Dense Residual U-shaped Network (DR-U-Net) to extract image features. We further introduce a novel neural network based on DR-U-Net, namely Spacecraft U-shaped Network (SU-Net) to achieve end-to-end pose estimation for non-cooperative spacecraft. Specifically, the SU-Net first preprocess the image of non-cooperative spacecraft, then transfer learning was used for pre-training. Subsequently, in order to solve the problem of radar image blur and low ability of spacecraft contour recognition, we add residual connection and dense connection to the backbone network U-Net, and we named it DR-U-Net. In this way, the feature loss and the complexity of the model is reduced, and the degradation of deep neural network during training is avoided. Finally, a layer of feedforward neural network is used for pose estimation of non-cooperative spacecraft on-orbit. Experiments prove that the proposed method does not rely on the hand-made object specific features, and the model has robust robustness, and the calculation accuracy outperforms the state-of-the-art pose estimation methods. The absolute error is 0.1557 to 0.4491 , the mean error is about 0.302 , and the standard deviation is about 0.065 .
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
