基于YOLOv5s的卫星光通信初始捕获方法(特邀)  

Rough Tracking Method for Satellite Laser Communication Based on YOLOv5s(Invited)

作　　者：尹鹏 倪小龙[2,4,5] 陈纯毅 于信[4] Yin Peng;Ni Xiaolong;Chen Chunyi;Yu Xin(School of Electronics and Information Engineering,Changchun University of Science and Technology,Changchun 130022,Jilin,China;Institute of Space Ophotoelectronics Technology,Changchun University of Science and Technology,Changchun 130022,Jilin,China;School of Computer Science and Technology,Changchun University of Science and Technology,Changchun 130022,Jilin,China;School of Optoelectronic Engineering,Changchun University of Science and Technology,Changchun 130022,Jilin,China;Changchun Lighteek Photonics Inc.,Changchun 130022,Jilin,China)

机构地区：[1]长春理工大学电子信息工程学院,吉林长春130022 [2]长春理工大学空间光电技术研究所,吉林长春130022 [3]长春理工大学计算机科学技术学院,吉林长春130022 [4]长春理工大学光电工程学院,吉林长春130022 [5]长春光客科技有限公司,吉林长春130022

出　　处：《激光与光电子学进展》2024年第7期125-132,共8页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(62275033,61775022);重庆市自然科学基金(cstc2021jcyj-msxmX0457);国家自然科学基金青年基金(62205032);吉林省科技发展计划项目(20210201139GX);长春理工大学青年基金(XQNJJ-2019-01)。

摘　　要：为解决在卫星激光通信初始捕获阶段传统信标激光光斑检测算法容易受到复杂背景干扰的问题,基于YOLOv5s神经网络针对卫星平台初始指向场景进行优化、改进。选用平滑交并比(SIoU)损失函数替代原损失函数,将原本的上采样结构替换为轻量化的内容感知特征重组(CARAFE)上采样结构,为C3层增加卷积块注意力模块(CBAM)机制,使用SimSPPF替代原本结构,增加了利于感知位置信息的Coordconv结构。经过改进后的神经网络在精度上优于传统的信标光斑检测算法,能够在复杂背景下准确检测出光斑的位置,适合用于初始捕获阶段以及粗跟踪阶段进行信标光斑检测。优化后的YOLOv5s神经网络精确率达到99.7%,召回率达到99.3%,在平均精度(mAP)@0.5指标上超过99.7%,在mAP@0.5∶0.95指标上超过了74%。To solve the problem of traditional beacon laser spot detection algorithms being susceptible to complex background interference during the initial capture stage of satellite laser communication.YOLOv5s neural network is used to optimize and improve the initial pointing scene of satellite platforms.Selecting the original loss function with the smoothed intersection over union(SIoU)loss function and replacing the original upsampling structure with a lightweight content aware feature recombination(CARAFE)upsampling structure,adding convolutional block attention module(CBAM)attention mechanism to C3 layer,using SimSPPF to replace the original structure,and adding Coordconv structure that is conducive to perceiving position information.The improved neural network has better accuracy than traditional coarse tracking beacon spot detection algorithms,and can accurately detect the position of the spot in complex backgrounds.It is suitable for beacon spot detection in the initial capture stage and coarse tracking stage.The optimized YOLOv5s neural network achieves a precision rate of 99.7%,a recall rate of 99.3%,and exceeds the average accuracy(mAP)@0.5 by 99.7%and mAP@0.5∶0.95 by 74%.

关 键 词：激光通信 初始捕获 信标激光 复杂背景 

分 类 号：TN929.13[电子电信—通信与信息系统]