基于改进YOLOv4的公路路面病害检测算法  

Road Surface Disease Detection Algorithm Based on Improved YOLOv4

作　　者：罗晖[1] 贾晨 李健[1] Luo Hui;Jia Chen;Li Jian(School of Information Engineering,East China JiaoTong University,Nanchang,Jiangxi 330013,China)

机构地区：[1]华东交通大学信息工程学院,江西南昌330013

出　　处：《激光与光电子学进展》2021年第14期328-336,共9页Laser & Optoelectronics Progress

基　　金：江西省重点研发计划项目(20202BBEL53001)。

摘　　要：针对公路路面病害存在的类别多、尺度变化大及样本数据集小导致的病害检测困难等问题,提出了基于改进YOLOv4的公路路面多尺度病害检测算法。首先,在CSPDarknet-53骨干网络中采用深度可分离卷积替代普通卷积,降低了网络参数计算量;然后,基于Focal loss改进YOLOv4的损失函数,解决了网络训练过程中正、负样本不平衡而导致的检测精度较低的问题;最后,借助迁移学习思想对YOLOv4网络进行预训练,并运用翻转、裁剪、亮度变换、噪声扰动等方法进行数据集扩充,解决了公路路面病害样本不足导致的网络训练过拟合问题。实验结果表明,所提基于YOLOv4+DC+FL算法对公路路面病害检测的平均精度均值可达到93.64%,相较于原始的YOLOv4检测网络提高了3.25%,检测每张图片平均时间为35.8 ms,缩减了7.9 ms。In order to solve the problems of multiple types of road surface diseases,large scale changes in the scale,and small sample data sets in road surface disease detection,a road surface multi-scale disease detecting algorithm based on improved YOLOv4 is proposed.First,the depth separable convolution method is used to replace the ordinary convolution method in the CSPDarknet-53 backbone network,which reduces the amount of network parameter calculations.Then,the loss function of YOLOv4 is improved based on the focal loss,which solves the problem of low detection accuracy caused by the imbalance of positive and negative samples in the process of network training.Finally,the YOLOv4 network is pre-trained with the help of transfer learning ideas,and the data set is expanded using methods such as flipping,cropping,brightness conversion,noise disturbance and other methods,so as to solve the problem of over-fitting of network training caused by insufficient samples of road surface disease.Experimental results show that,compared with original YOLOv4 detection network,the mean average precision of road surface disease detection based on YOLOv4+DC+FL algorithm can reach 93.64%,which increases by 3.25%.The detection time is 35.8 ms per picture,which is reduced by 7.9 ms.

关 键 词：图像处理 公路路面病害 YOLOv4 深度可分离卷积 Focal loss 迁移学习 数据增广 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]