基于Transformer模型的卫星单目位姿估计方法

doi:10.7527/S1000-6893.2021.25298

电子电气工程与控制

本期目录 | 过刊浏览 | 高级检索

前一篇 | 后一篇

基于Transformer模型的卫星单目位姿估计方法

王梓¹, 孙晓亮¹, 李璋¹, 程子龙², 于起峰¹

1. 国防科技大学空天科学学院, 长沙 410073;
2. 中国航天员科研训练中心, 北京 100094

收稿日期:2021-01-21 修回日期:2021-02-05 发布日期:2021-03-09
通讯作者: 孙晓亮 E-mail:alexander_sxl@nudt.edu.cn
基金资助:
国家自然科学基金（62003357）；湖南省研究生科研创新项目（CX20200024，CX20200025，CX20200088）

Transformer based monocular satellite pose estimation

WANG Zi¹, SUN Xiaoliang¹, LI Zhang¹, CHENG Zilong², YU Qifeng¹

1. College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, China;
2. China Astronaut Research and Training Center, Beijing 100094, China

Received:2021-01-21 Revised:2021-02-05 Published:2021-03-09
Supported by:
National Natural Science Foundation of China (62003357); Postgraduate Scientific Research Innovation Project of Hunan Province (CX20200024, CX20200025, CX20200088)

摘要/Abstract

摘要： 鉴于测量精度高、设备成本低等优点，基于单目图像的卫星位姿估计方法在交会对接、空间攻防等应用中具有广泛前景。得益于强大的特征提取与表达能力，卷积神经网络在目标单目位姿估计应用中取得了明显优于传统方法的性能表现，但已有基于卷积神经网络的方法存在诸如归纳偏置、绝对距离描述不直接、长距离建模能力不足等问题。聚焦卫星单目位姿估计应用需求，针对以上问题，创新地将Transformer模型应用于卫星目标位姿估计中，提出了一种新颖的端到端卫星单目位姿估计方法。首先，设计了一种基于关键点集合的卫星目标表示方法，并构建了基于该表示方法的损失函数，进一步，结合关键点回归任务特点，设计了端到端的关键点回归网络模型，并改进了用于特征提取的主干网络结构。在公开数据集上实验测试结果表明：本文方法实现了可靠、高效的卫星目标单目位姿估计，并取得了优于已有同类方法的性能。

关键词: 卫星位姿估计, Transformer模型, 非合作目标, 注意力机制, 关键点回归

Abstract: With the advantages of measurement accuracy and low equipment cost, the satellite pose estimation method based on monocular image has a broad prospect in rendezvous and docking, space attack-defense and other applications. Due to the strong power of feature extraction and representation, the convolutional neural network has achieved significantly better performance than traditional methods in monocular pose estimation. However, the existing methods based on convolutional neural network have some problems, such as inductive bias, indirect description of absolute distance, and lack of long-distance modeling ability. Considering the application requirements of satellite monocular pose estimation, this paper applies the transformer model for satellite pose estimation innovatively to overcome the problems above, and proposes a novel end-to-end satellite monocular pose estimation method. A satellite target representation method is proposed based on the set of key points, and the loss function based on the representation method is established. Then, an end-to-end key point regression network model is developed based on characteristics of the key point regression task, and the backbone network structure for feature extraction is improved. Experimental results on public datasets show that the proposed method can achieve reliable and efficient monocular pose estimation of satellite targets, demonstrating better performance than existing similar methods.

Key words: satellite pose estimation, transformer model, no-cooperative target, attention mechanism, key points regression

中图分类号:

V248.1

王梓, 孙晓亮, 李璋, 程子龙, 于起峰. 基于Transformer模型的卫星单目位姿估计方法[J]. 航空学报, 2022, 43(5): 325298-325298.

WANG Zi, SUN Xiaoliang, LI Zhang, CHENG Zilong, YU Qifeng. Transformer based monocular satellite pose estimation[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(5): 325298-325298.

参考文献

[1] 于浛, 魏喜庆, 宋申民, 等. 基于自适应容积卡尔曼滤波的非合作航天器相对运动估计[J]. 航空学报, 2014, 35(8):2251-2260. YUH, WEI X Q, SONG S M, et al. Relative motion estimation of non-cooperative spacecraft based on adaptive CKF[J]. Acta Aeronautica et Astronautica Sinica, 2014, 35(8):2251-2260(in Chinese).
[2] 宗群, 王丹丹, 邵士凯, 等. 多无人机协同编队飞行控制研究现状及发展[J]. 哈尔滨工业大学学报, 2017, 49(3):1-14. ZONG Q, WANG D D, SHAO S K, et al. Research status and development of multi UAV coordinated formation flight control[J]. Journal of Harbin Institute of Technology, 2017, 49(3):1-14(in Chinese).
[3] FORSHAW J L, AGLIETTI G S,NAVARATHINAM N, et al. Remove DEBRIS:An in-orbit active debris removal demonstration mission[J]. Acta Astronautica, 2016, 127:448-463.
[4] KISANTAL M, SHARMA S, PARK T H, et al. Satellite pose estimation challenge:Dataset, competition design, and results[J]. IEEE Transactions on Aerospace and Electronic Systems, 2020, 56(5):4083-4098.
[5] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[6] BAY H, TUYTELAARS T, GOOL L V. SURF:Speeded up robust features[C]//Proceedings of the 9th European conference on Computer Vision-Volume Part I. Springer-Verlag, 2006.
[7] ANSAR A, DANIILIDIS K.Linear pose estimation from points or lines[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(5):578-589.
[8] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6):84-90.
[9] PROENÇA P F, GAO Y. Deep learning for spacecraft pose estimation from photorealistic rendering[C]//2020 IEEE International Conference on Robotics and Automation. Piscataway:IEEE Press, 2020:6007-6013.
[10] SHARMA S, D'AMICO S. Neural network-based pose estimation for noncooperative spacecraft rendezvous[J]. IEEE Transactions on Aerospace and Electronic Systems, 2020, 56(6):4638-4658.
[11] CHEN B, CAO J W, PARRA A, et al. Satellite pose estimation with deep landmark regression and nonlinear pose refinement[C]//2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). Piscataway:IEEE Press, 2019:2816-2824.
[12] PARK T H, SHARMA S, D'AMICO S. Towards robust learning-based pose estimation of noncooperativespacecraft[DB/OL]. arXiv preprint:1909.00392, 2019.
[13] LEPETIT V, MORENO-NOGUER F, FUA P.EPnP:An accurate O(n) solution to the PnP problem[J]. International Journal of Computer Vision, 2008, 81(2):155-166.
[14] HUAN W X, LIU M M, HU Q L. Pose estimation for non-cooperative spacecraft based on deep learning[C]//202039th Chinese Control Conference (CCC). Piscataway:IEEE Press, 2020:3339-3343.
[15] GEIRHOS R, RUBISCH P, MICHAELIS C, et al. ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy androbustness[DB/OL]. arXiv preprint:1811.12231, 2018.
[16] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Advances in Neural Information Processing Systems, 2017;30.
[17] CARION N, MASSA F, SYNNAEVE G, et al. End-to-end object detection with transformers[C]//Computer Vision-ECCV 2020, 2020:213-229.
[18] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN:Towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6):1137-1149.
[19] HE J, ZHAO L N, YANG H W, et al. HSI-BERT:Hyperspectral image classification using the bidirectional encoder representation from transformers[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(1):165-178.
[20] LIU R J, YUAN Z J, LIU T, et al. End-to-end lane shape prediction with transformers[C]//2021 IEEE Winter Conference on Applications of Computer Vision. Piscataway:IEEE Press, 2021:3693-3701.
[21] 于起峰, 尚洋. 摄像测量学原理与应用研究[M]. 北京:科学出版社, 2009:23-32. YU Q F, SHANG Y. Videometrics:Principles and researches[M]. Beijing:Science Press, 2009:23-32(in Chinese).
[22] WOLFE W J, MATHIS D, SKLAIR C W, et al. The perspective view of three points[J]. IEEE Transactions on Pattern Analysisand Machine Intelligence, 1991, 13(1):66-73.
[23] FISCHLER M A, BOLLES R C. A paradigm for model fitting with applications to image analysis and automated cartography[J]. Commun. ACM, 1981, 24(6):381-395.
[24] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2016:770-778.
[25] CHEN K, WANG J Q, PANG J M, et al. MMDetection:Open MMLab detection toolbox and benchmark[DB/OL]. ArXiv preprint:1906.07155, 2019.
[26] WANG J D, SUN K, CHENG T H, et al. Deep high-resolution representation learning for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(10):3349-3364.

E-mail：hkxb@buaa.edu.cn

关于我们

期刊社服务

专业学科

封面文章

友情链接

主管单位：中国科学技术协会主办单位：中国航空学会北京航空航天大学

基于Transformer模型的卫星单目位姿估计方法

Transformer based monocular satellite pose estimation

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	陈斌, 郗厚印, 张晓东, 罗敏, 郭治栋. 基于测地线距离的空间非合作目标点云配准[J]. 航空学报, 2023, 44(1): 326336-326336.
[2]	刘芳, 韩笑. 基于多尺度深度学习的自适应航拍目标检测[J]. 航空学报, 2022, 43(5): 325270-325270.
[3]	夏鹏程, 罗建军, 王明明, 谭龙玉. 空间双臂机器人抓捕非合作目标后的协调稳定控制[J]. 航空学报, 2022, 43(2): 325398-325398.
[4]	孙博文, 王大轶, 王炯琦, 周海银, 葛东明, 董天舒. 基于序列图像的航天器自主导航降维滤波方法[J]. 航空学报, 2021, 42(4): 524971-524971.
[5]	董凯凯, 罗建军, 马卫华, 高登巍, 谭龙玉. 非合作目标交会的双层MPC全局轨迹规划控制[J]. 航空学报, 2021, 42(11): 524903-524903.
[6]	牟金震, 刘宗明, 韩飞, 周彦, 李爽. 失效卫星远距离相对位姿估计与优化方法[J]. 航空学报, 2021, 42(11): 524959-524959.
[7]	万文娅, 孙冲, 袁建平. 空间非合作目标多指包络抓捕路径设计[J]. 航空学报, 2020, 41(12): 324041-324041.
[8]	刘冰雁, 叶雄兵, 高勇, 王新波, 倪蕾. 基于分支深度强化学习的非合作目标追逃博弈策略求解[J]. 航空学报, 2020, 41(10): 324040-324040.
[9]	朱云峰, 孙永荣, 赵伟, 黄斌, 吴玲. 包含乘性噪声自适应修正的非合作目标相对导航算法[J]. 航空学报, 2019, 40(7): 322884-322884.
[10]	路勇, 刘晓光, 周宇, 刘崇超. 空间翻滚非合作目标消旋技术发展综述[J]. 航空学报, 2018, 39(1): 21302-021302.
[11]	于大腾, 王华, 孙福煜. 考虑潜在威胁区的航天器最优规避机动策略[J]. 航空学报, 2017, 38(1): 320202-320202.
[12]	孙俊, 张世杰, 马也, 楚中毅. 空间非合作目标惯性参数的Adaline网络辨识方法[J]. 航空学报, 2016, 37(9): 2799-2808.
[13]	陈路, 黄攀峰, 蔡佳. 基于改进HOG特征的空间非合作目标检测[J]. 航空学报, 2016, 37(2): 717-726.
[14]	戴崇, 徐振海, 肖顺平. 非合作目标动态RCS仿真方法[J]. 航空学报, 2014, 35(5): 1374-1384.
[15]	韦文书, 荆武兴, 高长生. 捕获非合作目标后航天器的自主稳定技术研究[J]. 航空学报, 2013, 34(7): 1520-1530.