基于改进YOLOv8的桥梁裂缝无人机检测方法  

Drone-based bridge crack detection based on improved YOLOv8

作　　者：唐菲菲 杨浩[1,2] 刘娜 姜敏 庞荣 张朋 周泽林 TANG Feifei;YANG Hao;LIU Na;JIANG Min;PANG Rong;ZHANG Peng;ZHOU Zelin(School of Smart City,Chongqing Jiaotong University,Chongqing 400074,China;Chongqing Geological and Mineral Surveying and Mapping Institute Co.,Ltd.,Chongqing 401121,China;China Merchants Chongqing Highway Engineering Testing Center Co.,Ltd.,Chongqing 400072,China;China 19th Metallurgical Group Corporation Limited,Chengdu 610031,China)

机构地区：[1]重庆交通大学智慧城市学院(重庆智慧城市学院),重庆400074 [2]重庆市地矿测绘院有限公司,重庆401121 [3]招商局重庆公路工程检测中心有限公司,重庆400072 [4]中国十九冶集团有限公司,成都610031

出　　处：《南京信息工程大学学报》2025年第2期172-180,共9页Journal of Nanjing University of Information Science & Technology

基　　金：重庆市技术创新与应用发展专项重点项目(CSTB2022TIAD-KPX0098)。

摘　　要：针对桥梁裂缝识别效率低、实时性差等问题,本文提出一种基于改进YOLOv8模型的桥梁裂缝无人机图像检测方法.首先,将动态蛇形卷积核融入YOLOv8骨干部分中的C2f模块,以增强裂缝特征提取能力;然后,引入CAM模块,提升小目标检测能力;最后,通过优化预测框损失函数,减少了低质量数据集对检测结果的影响.实验结果表明,改进后模型的GFLOPs达到14.4,mAP@50达到94%,较基础模型实现了较大的精度提升,检测速度达到147帧/s,能够满足无人机实时裂缝检测需求.To tackle the current challenges of low efficiency,poor performance,and inadequate real-time capabilities in bridge crack detection,this paper introduces a drone-based image detection method for bridge cracks using an improved YOLOv8 model.Firstly,the dynamic snake convolution kernel is integrated into the C2f module in the backbone of YOLOv8 to enhance the crack feature extraction.Then,the Context Augmentation Module(CAM)is introduced to improve the detection capability for small targets.Finally,the influence of low-quality datasets on detection results is reduced via optimizing the prediction box loss function.Experimental results show that the improved model achieves a GFLOPs of 14.4 and a mean Average Precision(mAP@50)of 94%,exhibiting a significant accuracy improvement compared to the baseline models.The detection speed reaches 147 frames per second,satisfying the requirements for real-time crack detection by UAVs.

关 键 词：无人机图像 桥梁裂缝检测 YOLOv8 动态蛇形卷积 深度学习 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] U446[自动化与计算机技术—计算机科学与技术]