基于改进YOLOv5的无人机障碍物检测算法  

UAV Obstacle Detection Algorithm Based on Improved YOLOv5

作　　者：陈明强[1] 冯树娟 张勇 李奇峰 CHEN Ming-qiang;FENG Shu-juan;ZHANG Yong;LI Qi-feng(School of Flight Technology,Civil Aviation Flight University of China,Guanghan 618307,China;The Second Research Institute of the Civil Aviation Administration of China,Chengdu 610041,China)

机构地区：[1]中国民用航空飞行学院飞行技术学院,广汉618307 [2]中国民航总局第二研究所,成都610041

出　　处：《科学技术与工程》2024年第31期13627-13634,共8页Science Technology and Engineering

基　　金：民航飞行技术与飞行安全重点实验室自主研究项目(FZ2021ZZ06)。

摘　　要：无人机被广泛应用于救援、物流、巡检等场景,在飞行过程中及时检测障碍物是安全完成任务的前提保障。为了满足无人机飞行中对障碍物检测的要求,以YOLOv5算法为基础提出一种改进算法。使用卷积模块代替Focus模块并在原有网络结构中增加一个检测头,以提高检测性能;在特征提取网络中融合CA(coordinate attention)注意力机制以加强模型特征提取能力,降低背景干扰。实验结果表明,改进的算法相比原YOLOv5模型精确率提升了13.8%,召回率提升了12%,mAP@0.5提升了15.4%,mAP@0.5:0.95提升了10.2%,证明了改进算法的优越性。UAV are widely used in rescue,logistics,inspection and other scenarios,and timely detection of obstacles during flight is a prerequisite for safe completion of tasks.In order to meet the requirements of obstacle detection in UAV flight,an improved algorithm was proposed based on YOLOv5 algorithm.The convolution module was used instead of the Focus module and a detection probe was added to the original network structure to improve the detection performance.The CA(coordinate attention)attention mechanism was integrated in the feature extraction network to strengthen the feature extraction ability of the model and reduce background interference.Experimental results show that compared with the original YOLOv5 model,the improved algorithm improves the accuracy by 13.8%,the recall rate by 12%,the mAP@0.5 by 15.4%,and the mAP@0.5:0.95 by 10.2%,which proves the superiority of the improved algorithm.

关 键 词：YOLOv5 障碍物检测 卷积模块 CA注意力机制 

分 类 号：V279[航空宇航科学与技术—飞行器设计] TP391.4[自动化与计算机技术—计算机应用技术]