航天器识别与跟踪是航天领域的核心技术,对确保天体中航天器运行的安全性和有效性至关重要.然而在太空环境中,密集星点常常干扰目标的识别过程,同时复杂多变的光照条件也可能导致成像结果不完整,进而影响目标的清晰呈现.因此,提出一种基于星点识别与多帧聚合的航天器识别与定位算法,实现在相机抵近状态下对航天器目标的精准识别.首先,通过星图识别将星点信息映射到航天器成像平面中,剔除天体背景下的密集干扰星点;在此基础上,引入目标聚合算法与连续帧局部区域定位方法解决光照影响下航天器成像不完整及单帧航天器信息受限问题.实验结果表明,所提出算法可有效剔除97%以上的干扰星点,并满足0.2$^{\circ}$偏差范围内的航天器定位精度,具有较高的准确度和鲁棒性.
Spacecraft identification and tracking, which are core technologies in the aero-space field, are crucial for ensuring the safety and effectiveness of spacecraft operation in celestial bodies. However, in the space environment, dense stars interfere with the recognition of targets, and complex and variable lighting conditions may result in incomplete imaging, thereby affecting the clear presentation of targets. Therefore, a spacecraft recognition and positioning algorithm based on star-point recognition and multiframe aggregation is proposed in this study to accurately identify spacecraft targets within the proximity of a camera. This algorithm first maps star-point information to the spacecraft imaging plane via star-map recognition, thus eliminating dense interfering star points in the background of celestial bodies. Subsequently, a target-aggregation algorithm and a continuous-frame local-area localization method are introduced to address the incomplete spacecraft imaging and limited information of single-frame spacecraft due to lighting. Experimental results show that the proposed algorithm effectively eliminates more than 97% of interfering star points and satisfies the spacecraft positioning accuracy within a deviation range of $0.2^{\circ}$, thus demonstrating its high accuracy and robustness.
[1] 初广丽. 航天器合作靶标自动识别关键技术研究[D]. 北京: 中国科学院大学, 2015.
[2] 李磊. 基于点云的非合作航天器自主识别与位姿估计研究[D]. 南京: 南京航空航天大学, 2019.
[3] Gernot B, Raul S, Gerd L. Multi-modal image analysis for tracking and identiflcation of space debris [J]. Acta Astronautica, 2014, 103(6): 176-184.
[4] Chen C, Liao M, Wu H. Multi-modal sensor fusion for space object detection [C]// International Conference on Control Decision and Information Technologies (CoDIT). 2019: 144-149.
[5] Yosinski J, Clune J, Bengio Y, et al. How transferable are features in deep neural networks? [C]// Advances in Neural Information Processing Systems. 2014: 3320-3328.
[6] 田伟杰, 郭大波, 孙佳. 基于YOLOv3-satellite的航天器模型目标检测方法[J]. 电子设计工程, 2021, 29(20): 43-47.
[7] 张晓鹏, 何纯, 杨萍, 等. 在轨航天器遥测系统信号的实时检测仿真研究[J]. 计算机仿真, 2019, 36(10): 83-87.
[8] 严南, 姚捃, 黄宇. 基于改进区域分割遥感图像的航天器目标自动识别方法[J]. 计算机测量与控制, 2020, 28(10): 151-154;164.
[9] 白子扬. 基于星敏感器的航天器姿态确定算法[D]. 哈尔滨: 哈尔滨工业大学, 2020.
[10] Padgett C, Kreutz-Delgado K, Udomkesmalee S. Evaluation of star identiflcation techniques [J]. Journal of Guidance Control and Dynamics, 1997, 20(2): 259-267．
[11] Padgett C, Kreutz-Delgado K. A grid algorithm for autonomous star identiflcation [J]. IEEE Transactions on Aerospace and Electronic Systems, 1997, 33(1): 202-213.
[12] Cole C L. Fast star pattern recognition using spherical triangles [D]. Bufialo: State University of New York at Bufialo, 2004.
[13] Wu F. Study on the key technologies for autonomous star sensors [D]. Suzhou: Soochow University, 2012.
[14] Kosi K J. Star pattern identiflcation aboard an inertially stabilized aircraft [J]. Journal of Guidance, Control and Dynamics, 2013, 14(1): 230-235.
[15] Zhang G J. Star identiflcation [M]. Beijing: National Defense Industry Press, 2011.
[16] Qian H M, Sun L, Cai J N, et al. An extended grid algorithm in star identiflcation fleld [J]. Journal of Harbin Institute of Technology, 2015, 47(2): 110-116．
[17] Li Y S, Zhang Y J, Yu J G, et al. A novel spatio-temporal saliency approach for robust dim moving target detection from airborne infrared image sequences [J]. Information Sciences, 2016, 369: 548-563.
[18] Sarfraz S, Sharma V, Stiefelhagen R. E-cient parameter-free clustering using flrst neighbor relations [C]// IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2019: 8926-8935.
