基于YOLOv5网络架构的着陆跑道检测算法研究  

Landing Runway Detection Algorithm Based on YOLOv5Network Architecture

作　　者：马宁 曹云峰 王指辉 翁祥瑞 吴林滨 Ma Ning;Cao Yunfeng;Wang Zhihui;Weng Xiangrui;Wu Linbin(College of Astronautics,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,Jiangsu,China)

机构地区：[1]南京航空航天大学航天学院,江苏南京211106

出　　处：《激光与光电子学进展》2022年第14期189-195,共7页Laser & Optoelectronics Progress

基　　金：空间光电探测与感知工业和信息化部重点实验室开放课题资助(NJ2020021-01);江苏省研究生科研与实践创新计划(SJCX21_0103);江苏省JMRH创新平台资助。

摘　　要：为突破无人机自主着陆技术工程应用中跑道目标快速鲁棒检测这一技术瓶颈,提出了一种基于YOLOv5网络架构的快速跑道检测方法。在YOLOv5网络架构的基础上进行改进,首先,对获取的机载前视图像进行数据增强,以提升网络模型的鲁棒性;其次,对不同尺度、不同维度特征进行融合,以提升网络检测精度;然后,在预测层损失函数的设计中融入跑道的几何特征,以优化预测模型。为验证方法的有效性,采用AirSim开发了复杂着陆场景下的可见光图像数据集,在此基础上对方法进行了测试。仿真结果表明,所提跑道检测方法的平均检测速度可达125 frame/s,平均检测精度为99%,优于传统目标检测方法,满足对跑道区域快速、精确检测的要求。This study proposes a method of landing runway detection based on YOLOv5 network architecture to solve the critical problem of fast and robust runway detection for engineering applications of UAV autonomous landing technology.First,the captured airborne front-view images were enhanced to improve the robustness of the network model based on the YOLOv5 network architecture.Then,features with different scales and different dimensions were fused to improve the precision of the detection network model.Furthermore,the geometric features of the runway were incorporated into the loss function design in the prediction layer to optimize the prediction model.In this study,AirSim was used to simulate visual image landing datasets under complex conditions to validate the effectiveness of the proposed method.The simulation results on these datasets show that the average detection speed of the runway detection algorithm proposed in this study can reach 125 frame/s,and the average detection accuracy is 99%,which outperforms other traditional methods and can meet the fast and accurate requirements of runway detection.

关 键 词：YOLOv5 卷积神经网络 跑道检测 自主着陆 单目视觉 

分 类 号：V249[航空宇航科学与技术—飞行器设计]