航空学报 > 2021, Vol. 42 Issue (4): 524984-524984   doi: 10.7527/S1000-6893.2021.24984

低照度小样本限制下的失效卫星相对位姿估计与优化

刘付成1, 牟金震2,3,4, 刘宗明2,3, 韩飞2,3, 李爽4   

  1. 1. 上海航天技术研究院, 上海 201109;
    2. 上海航天控制技术研究所, 上海 201109;
    3. 上海市空间智能控制技术重点实验室, 上海 201109;
    4. 南京航空航天大学 航天学院, 南京 210016
  • 收稿日期:2020-11-18 修回日期:2020-12-22 发布日期:2021-02-08
  • 通讯作者: 牟金震 E-mail:jinzhen_mu@163.com
  • 基金资助:
    国家重点研发计划(2016YFB0501003);国家自然科学基金(61690214,11972182);上海市科研专项(19511120900,19YF1420200)

Relative pose estimation and optimization of a failure satellite with low-light few-shot images

LIU Fucheng1, MU Jinzhen2,3,4, LIU Zongming2,3, HAN Fei2,3, LI Shuang4   

  1. 1. Shanghai Academy of Spaceflight Technology, Shanghai 201109, China;
    2. Shanghai Institute of Spaceflight Control Technology, Shanghai 201109, China;
    3. Shanghai Key Laboratory of Space Intelligent Control Technology, Shanghai 201109, China;
    4. College of Astronautics, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
  • Received:2020-11-18 Revised:2020-12-22 Published:2021-02-08
  • Supported by:
    National Key Research and Development Program (2016YFB0501003); National Natural Science Foundation of China (61690214, 11972182); Shanghai Scientific Research Program (19511120900, 19YF1420200)

摘要: 低照度图像信息受损严重,会导致失效卫星的位姿估计精度和鲁棒性降低。基于此,提出了无监督生成式对抗网络低照度图像增强模型。生成器以U-Net网络为基础,并设计密集残差连接结构。判别器设计为全局-局部的双辨别器结构,由传统的单一标量扩展为多标量判别。在小样本的条件下,基于进化训练与并行训练方式改进基于SinGAN的数据增广方法。最后,在基于ORB-SLAM位姿初始化的基础上,建立特征信息的局部地图,克服位姿估计对参考帧的依赖;通过关键帧ROI的稠密匹配,建立关于平面法向量和单目相机安装高度的非线性优化模型求解尺度因子;通过闭环检测后的相似性变换,构建关键帧集合的联合位姿图优化方程,实现对位姿矩阵的全局校正。实验结果表明:测量稳定后,低照度图像的姿态角误差最大值为4°,而图像增强后的姿态角误差最大为0.5°;对于以角速度20°/s运动的失效卫星旋转5周,相对静止下的跟踪测量为5周,1 m水平方向机动下的跟踪测量为4.5周。可以满足失效卫星相对姿态测量的任务需求。

关键词: 失效卫星, 旋转目标, 生成式对抗网络, 低照度图像增强, 小样本, 相对位姿估计

Abstract: The serious damage of information in images under a low-light imaging condition may reduce the accuracy and robustness of the pose estimation of a failure satellite. Thus, this paper proposes an unsupervised Generative Adversarial Network (GAN)-based low-light image enhancement model. The generator is based on the U-Net with dense residual connection. The discriminator is designed as a global-local structure, and the traditional single scalar output of the discriminator is extended to the multiple scalar output. The single natural image Generative Adversarial Network (SinGAN) is improved based on evolutionary and parallel training methods to augment the few-shot training samples. Finally, a local map of feature information is established based on initialization of ORB-SLAM to alleviate dependence of pose estimation on reference frame. Through dense matching of Region of Interest (ROI) in key-frames, a nonlinear optimization model of the normal vector of plane and the mounting height of monocular camera is established to solve the scale factor. Through the similarity transformation after closed-loop detection, an equation for combined pose optimization in key-frames is established to achieve global correction of the pose transformation matrix. The experimental results show that the maximum error of the attitude angle is 4° in low-light images, while the maximum error of the attitude angle is 0.5°in enhanced images. When the target is rotating 5 cycles at 20°/s, our method can track 5 cycles in relatively static state, and 4.5 cycles in the range of 1 m horizontal maneuver. Hence, the proposed method can satisfy the need for relative pose measurement of failure satellites.

Key words: failure satellite, rotating target, generative adversarial network, low-light image enhancement, few-shot, relative pose estimation

中图分类号: