一种超轻量化卫星目标形心定位算法

doi:10.19665/j.issn1001-2400.20230307

西安电子科技大学学报 ›› 2023, Vol. 50 ›› Issue (6): 120-132.doi: 10.19665/j.issn1001-2400.20230307

• 信息与通信工程 & 计算机科学与技术 • 上一篇下一篇

一种超轻量化卫星目标形心定位算法

刘路远¹(),韩璐瑶¹(),李娇娇¹(),夏晖²(),饶鹏²(),宋锐¹()

1.西安电子科技大学空天地一体化综合业务网全国重点实验室,陕西西安 710071
2.中国科学院上海技术物理研究所,中国科学院红外探测与成像技术重点实验室,上海 200083

收稿日期:2022-11-03 出版日期:2023-12-20 发布日期:2024-01-22
通讯作者: 宋锐(1982—),男,教授,E-mail:rsong@xidian.edu.cn
作者简介:刘路远(2000—),男,西安电子科技大学硕士研究生,E-mail:1953882136@qq.com;|韩璐瑶(1996—),女,西安电子科技大学硕士研究生,E-mail:han_xidian@sina.com;|李娇娇(1987—),女,副教授,E-mail:jjli@xidian.edu.cn;|夏晖(1979—),女,副研究员,E-mail:tracey_xia@hotmail.com;|饶鹏(1977—),男,研究员,E-mail:peng_rao@mail.sitp.ac.cn。
基金资助:
芜湖-西电产学研合作专项资金(XWYCXY-012021002);国家自然科学基金(61901343);111计划(B08038);地理信息工程国家重点实验室开放基金(SKLGIE2020-M-3-1);中国博士后科学基金(2018T111019);陕西高校青年创新团队

Lightweight centroid locating method for the satellite target

LIU Luyuan¹(),HAN Luyao¹(),LI Jiaojiao¹(),XIA Hui²(),RAO Peng²(),SONG Rui¹()

1. State Key Laboratory of Integrated Services Networks,Xidian University,Xi’an 710071,China
2. CAS Key Laboratory of Infrared System Detection and Imaging Technology,Shanghai Institute of Technical Physics of the Chinese Academy of Sciences,Shanghai 200083,China

Received:2022-11-03 Online:2023-12-20 Published:2024-01-22

摘要/Abstract

摘要：

天基光电探测单元具有视场角大、载重小和机动灵活的特性,在空间作业的监视任务中有重要应用,其中卫星目标的识别和形心定位是其重要功能之一。由于目前在轨载荷处理器的算力较弱,在近距离测角任务中无法使用深度神经网络算法进行复杂定位。针对这一问题,深入分析了目标的特点,依据卫星几何特性设计了一种超轻量化实时处理方法。该算法设计了直线特征和帆板边缘特征提取器,提出了一种利用特殊几何关键点计算目标最小外接矩形的策略,提升外接矩形与目标边缘的贴合度。算法在仿真数据集上进行了测试,并在物理模拟试验场采集的影像数据上进行了验证。测试结果表明,算法的检测精度优于主流深度学习目标检测网络Yolov5n,计算量仅为对比算法的10%。在嵌入式实时处理平台上移植后,实时定位速度可达到5 120×5 120@5 fps。在验证环境下,基于所提算法形心定位的结果进行测角,测角精度优于0.05°,满足应用场景的精度要求。

关键词: 空间站, 卫星, 目标定位, 目标检测, 实时处理

Abstract:

The space-based photoelectric detection unit is vital in satellite identification and positioning.It has a large field of view,a small load,and flexible maneuvering properties.However,the computational capability of the CPU mounted on an on-orbit satellite could be much higher,which can hardly afford the necessity of deep learning networks.In this paper,we analyze the character of space targets deeply and designed a lightweight real-time processing algorithm.We specifically design feature extractors for the line and satellite contour patterns in the algorithm and propose a minimum bounding box calculation strategy.The algorithm is tested on the simulation dataset and verified on the images captured by the physical emulation platform.Testing results demonstrate the effectiveness of our algorithm.The detecting accuracy of our algorithm is better than YOLOv5n,and the computational load is only 10% that of the competitive methods.We transplant the algorithm to an on-orbit real-time processing platform.The positioning speed reaches 5 120×5 120@5fps.The accuracy for angle measurement based on the centroid positioning results is more significant than 0.05°,which meets the requirement for real application systems.

Key words: spacecraft, satellites, target positioning, object detection, real-time processing

中图分类号:

TP391.4

刘路远, 韩璐瑶, 李娇娇, 夏晖, 饶鹏, 宋锐. 一种超轻量化卫星目标形心定位算法[J]. 西安电子科技大学学报, 2023, 50(6): 120-132.

LIU Luyuan, HAN Luyao, LI Jiaojiao, XIA Hui, RAO Peng, SONG Rui. Lightweight centroid locating method for the satellite target[J]. Journal of Xidian University, 2023, 50(6): 120-132.

图/表 13

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

表1

图12

参考文献 31

[1]	王翔, 张峤, 王为. 中国空间站建设系统方案特点与展望[J]. 航天器工程, 2022, 31(6):26-39.
	WANG Xiang, ZHANG Qiao, WANG Wei. System Characteristics and Prospect of China Space Station[J]. Spacecraft Engineering, 2022, 31(6):26-39.
[2]	张伟, 张晓, 王伟, 等. 基于联邦UPF的火星环绕器测角测距组合导航算法研究[J]. 中国科学:技术科学, 2020, 50(9):1175-1184.
	ZHANG Wei, ZHANG Xiao, WANG Wei, et al. Mars Orbiter Integrated Navigation Algorithm for Angle and Range Measurement Based on Federal UPF[J]. Scientia Sinica(Technologica), 2020, 50(9):1175-1184.
[3]	姜秀鹏, 常新亚, 姚芳, 等. 合成孔径雷达小型卫星进展[J]. 空间电子技术, 2016, 13(1):77-82.
	JIANG Xiupeng, CHANG Xinya, YAO Fang, et al. Progress of Small Satellite of Synthetic Aperture Radar[J]. Space Electronic Technology, 2016, 13(1):77-82.
[4]	韩世静, 苗书锋, 郝向阳, 等. 监控视频动态目标的空间定位方法[J]. 测绘通报, 2022, 8:87-92.
	HAN Shijing, MIAO Shufeng, HAO Xiangyang, et al. Spatial Location Method of Dynamic Targets in Surveillance Videos[J]. Bulletin of Surveying and Mapping, 2022, 8:87-92.
[5]	王平, 江雨泽, 赵光辉. 目标检测的多尺度定位提升算法[J]. 西安电子科技大学学报, 2021, 48(3):85-90.
	WANG Ping, JIANG Yuze, ZHAO Guanghui. Object Detection Based on the Multiscale Location Enhancement Network[J]. Journal of Xidian University, 2021, 48(3):85-90.
[6]	田蕾, 梁书立, 陈恒. 基于速度估计的目标能量累积算法在空间探测中的应用[J]. 航天电子, 2022, 38(4):50-53.
	TIAN Lei, LIANG Shuli, CHEN Heng. Application of Target Energy Accumulation Algorithm Based on Speed Estimation for Space Detection[J]. Aerospace Electronic Warfare, 2022, 38(4):50-53.
[7]	王敏, 赵金宇, 陈涛. 基于各向异性高斯曲面拟合的星点质心提取算法[J]. 光学学报, 2017, 37(5):226-235.
	WANG Min, ZHAO Jinyu, CHEN Tao. Center Extraction Method for Star-Map Targets Based on Anisotropic Gaussian Surface Fitting[J]. Acta Optica Sinica, 2017, 37(5):226-235.
[8]	WANG Z, WANG T, HAO K. Spacecraft Target Recognition and Tracking Based on Ellipse Detection[C]// 2021 33rd Chinese Control and Decision Conference(CCDC).Piscataway:IEEE, 2021:1618-1623.
[9]	LAWIYUNIARTI M P, RAHMADIANTRI E, ALAMSYAH I M, et al. Application of Least-Squares Fitting of Ellipse and Hyperbola for Two Dimensional Data[J]. Journal of Physics Conference Series, 2018, 948:012069. doi: 10.1088/1742-6596/948/1/012069
[10]	WEI Z. Composite Insulator Defect Identification and Quantitative Method Based on Random Hough Transform Ellipse Detection[J]. Journal of Physics:Conference Series, 2022, 2170(1):012021. doi: 10.1088/1742-6596/2170/1/012021
[11]	WANG Y S, QI Y, MAN Y. An Improved Hough Transform Method for Detecting Forward Vehicle and Lane in Road[J]. Journal of Physics Conference Series, 2021, 1757(1):012082. doi: 10.1088/1742-6596/1757/1/012082
[12]	JIA Q, FAN X, LUO Z, et al. A Fast Ellipse Detector Using Projective Invariant Pruning[J]. IEEE Transactions on Image Processing, 2017, 26(8):3665-3679. doi: 10.1109/TIP.2017.2704660 pmid: 28534774
[13]	崔平远, 贾贺, 朱圣英. 小天体不规则度与光学导航质心提取及应用[J]. 宇航学报, 2021, 42(1):83-91.
	CUI Pingyuan, JIA He, ZHU Shengying. T Asteroid Irregularity Degree and Application in Centroid Extraction of Optical Navigation[J]. Journal of Astronautics, 2021, 42(1):83-91.
[14]	SHI J F, ULRICH S, RUEL S. Cubesat Simulation and Detection Using Monocular Camera Images and Convolutional Neural Networks[C]// 2018 AIAA Guidance,Navigation,and Control Conference.Reston:AIAA, 2018:1-23.
[15]	GARCIA A, MUSALLAM M A, GAUDILLIERE V, et al. Lspnet:A 2D Localization-Oriented Spacecraft Pose Estimation Neural Network[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE, 2021:2048-2056.
[16]	ZENG L, LV W J, ZHANG X Y, et al. ParametricNet:6DoF Pose Estimation Network for Parametric Shapes in Stacked Scenarios[C]// 2021 IEEE International Conference on Robotics and Automation(ICRA).Piscataway:IEEE, 2021:772-778.
[17]	BLACK K, SHANKAR S, FONSEKA D, et al. Real-Time,Flight-Ready,Non-Cooperative Spacecraft Pose Estimation Using Monocular Imagery(2021)[J/OL].[2021-01-23]. https://arxiv.org/abs/2101.09553.
[18]	SHARMA S, D’AMICO S. Pose Estimation for Non-Cooperative Rendezvous Using Neural Networks(2019)[J/OL].[2019-06-24]. https://arxiv.org/abs/1906.09868.
[19]	任笑圆, 蒋李兵, 钟卫军, 等. 视觉的非合作空间目标三维姿态估计方法[J]. 电子与信息学报, 2021, 43(12):3476-3485.
	REN Xiaoyuan, JIANG Libing, ZHONG Weijun, et al. A Vision-Based Method for 3D Pose Estimation of Non-Cooperative Space Target[J]. Journal of Electronics & Information Technology, 2021, 43(12):3476-3485.
[20]	SHARMA S, VENTURA J, D’AMICO S. Robust Model-Based Monocular Pose Initialization for Noncooperative Spacecraft Rendezvous[J]. Journal of Spacecraft and Rockets, 2018, 55(6):1414-1429. doi: 10.2514/1.A34124
[21]	COMELLINI A, ZENOU E, ESPINOSA C, et al. Vision-Based Navigation for Autonomous Space Rendezvous with Non-Cooperative Targets[C]// 2020 11th International Conference on Information,Intelligence,Systems and Applications(IISA).Piscataway:IEEE, 2020:1-8.
[22]	OZUYSAL M, CALONDER M, LEPETIT V, et al. Fast Keypoint Recognition Using Random Ferns[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 32(3):448-461. doi: 10.1109/TPAMI.2009.23
[23]	PENG S, LIU Y, HUANG Q, et al. Pvnet:Pixel-Wise Voting Network for 6dof Pose Estimation[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE, 2019:4561-4570.
[24]	PAVLAKOS G, ZHOU X, CHAN A, et al. 6-Dof Object Pose from Semantic Keypoints[C]// 2017 IEEE International Conference on Robotics and Automation(ICRA).Piscataway:IEEE, 2017:2011-2018.
[25]	TEKIN B, SINHA S N, FUA P. Real-Time Seamless Single Shot 6D Object Pose Prediction[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE, 2018:292-301.
[26]	BARROSO-LAGUNA A, RIBA E, PONSA D, et al. Net:Keypoint Detection by Handcrafted and Learned CNN Filters[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision.Piscataway:IEEE, 2019:5836-5844.
[27]	HU Y, HUGONOT J, FUA P, et al. Segmentation-Driven 6D Object Pose Estimation[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE, 2019:3385-3394.
[28]	SHI J F, ULRICH S, RUEL S. Spacecraft Pose Estimation Using Principal Component Analysis and a Monocular Camera[C]// AIAA Guidance,Navigation,and Control Conference.Reston:AIAA, 2017:1-24.
[29]	黄超, 茅健, 徐斌, 等. 基于最小外接矩形和Hough变换的定位算法[J]. 组合机床与自动化加工技术, 2021, 8:66-71.
	HUANG Chao, MAO Jian, XU Bin, et al. Location Algorithm Based on Minimum Enclosing Rectangle and Hough Transform[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2021, 8:66-71.
[30]	REDMON J, DIVVALA S, GIRSHICK R, et al. You Only Look Once:Unified,Real-Time Object Detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE, 2016:779-788.
[31]	侯占伟, 贾玉兰, 王志衡. 基于最小外接矩形的珠宝定位技术研究[J]. 计算机工程, 2016, 42(2):254-260. doi: 10.3969/j.issn.1000-3428.2016.02.045
	HOU Zhanwei, JIA Yulan, WANG Zhiheng. Research on Jewelry Positioning Technology Based on Minimum Bounding Rectangle[J]. Computer Engineering, 2016, 42(2):254-260. doi: 10.3969/j.issn.1000-3428.2016.02.045

算法	运行时间/s	标准测试集		扩展测试集
算法	运行时间/s	方位角误差/(°)	仰角误差/(°)	方位角误差/(°)	仰角误差/(°)
YOLOv5n^[30]	6.449	0.067 0	0.067 4	0.217 5	0.275 8
文献[31]	1.664	0.061 1	0.071 7	0.203 0	0.281 8
文中算法	0.690	0.039 7	0.036 6	0.096 6	0.126 4

一种超轻量化卫星目标形心定位算法

Lightweight centroid locating method for the satellite target

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献 31

相关文章 15

Metrics

本文评价

推荐阅读 10

[1]	车吉斌, 王常龙, 贾岩, 任紫正, 刘春恒, 周峰. 外辐射源雷达互模糊函数智能快速计算方法[J]. 西安电子科技大学学报, 2023, 50(6): 21-33.
[2]	李雅宁,李宏生,蔚保国. 一种室内伪卫星混合指纹定位方法[J]. 西安电子科技大学学报, 2023, 50(5): 21-31.
[3]	王娟,刘子杉,武明虎,陈关海,郭力权. 融合超分辨率重建技术的多尺度目标检测算法[J]. 西安电子科技大学学报, 2023, 50(3): 122-131.
[4]	国强,陈佳甜,戚连刚,CHORNOGOR Leonid. 改进奇异值分解的海杂波抑制算法[J]. 西安电子科技大学学报, 2023, 50(2): 188-196.
[5]	遆晶晶, 索志勇, 王婷婷, 赵秉吉, 张乐茹. 导航卫星星地双基SAR时频同步误差估计方法[J]. 西安电子科技大学学报, 2023, 50(2): 42-53.
[6]	张强, 杨欣朋, 赵世祥, 卫栋栋, 韩臻. 注意力机制的SAR图像车辆目标检测网络[J]. 西安电子科技大学学报, 2023, 50(1): 36-47.
[7]	李阳阳, 毛鹤亭, 张小龙, 陈彦桥, 柴兴华. 利用非局部上下文信息的遥感图像小目标检测[J]. 西安电子科技大学学报, 2022, 49(5): 117-124.
[8]	李悦言, 程培涛, 杜淑幸. 一种改进CenterNet的轻量化目标检测算法[J]. 西安电子科技大学学报, 2022, 49(5): 137-144.
[9]	刘迪,郭继昌,汪昱东,张怡. 融合注意力机制的多尺度显著性目标检测网络[J]. 西安电子科技大学学报, 2022, 49(4): 118-126.
[10]	陈金涛,梁俊,郭子桢,肖楠,刘波. 软件定义卫星网络多控制器部署策略[J]. 西安电子科技大学学报, 2022, 49(3): 59-67.
[11]	汪西莉,梁敏,刘涛. 特征增强的单阶段遥感图像目标检测模型[J]. 西安电子科技大学学报, 2022, 49(3): 160-170.
[12]	韩永赛,马时平,何林远,李承昊,朱明明,张飞. 改进YOLOv3的快速遥感机场区域目标检测[J]. 西安电子科技大学学报, 2021, 48(5): 156-166.
[13]	董如婵,焦李成,赵进,沈维燕. 一种深度融合机制的遥感图像目标检测技术[J]. 西安电子科技大学学报, 2021, 48(5): 128-138.
[14]	毛昭勇,王亦晨,王鑫,沈钧戈. 面向高速公路的车辆视频监控分析系统[J]. 西安电子科技大学学报, 2021, 48(5): 178-189.
[15]	张佳琦,陶海红,张修社,韩春雷. 一种利用量测空间聚类的多帧检测前跟踪算法[J]. 西安电子科技大学学报, 2021, 48(5): 231-238.