基于深度学习的路面缺陷自动检测系统北大核心CSCD

路面缺陷自动检测对公路养护和路况等级评估具有重要意义。为此,使用YOLOv5x结合透视变换和图像分割设计了路面缺陷检测系统。首先,为证明系统可行性采集并制作了多类型路面缺陷数据集(pavement defect dataset,PDD)。然后,使用SSD(single shot multibox detector)、Faster R-CNN、YOLOv5x(you only look once v5x)和YOLOX 4种模型对PDD进行训练检测。经过训练,4种模型的mAP(mean average precision)均超过了77%,其中YOLOv5x的结果最优,mAP达到了91%,同时证明创建的数据集PDD有效。最后,使用YOLOv5x作为系统主要检测方法结合透视变换、图像分割和骨架提取获取缺陷的长度、宽度和面积等信息,进而计算路面状况指数(pavement condition index,PCI)得到路面破损等级,以及相应的维修建议,提高了路面缺陷检测的实用性。

Automatic detection of pavement defects based on deep learning

Automatic detection of pavement defect s is of great importance for road maintenance and road condition rating assessment.To this end,a pavement defect detection system was designed using YOLOv5x combined with perspective transformation and image segmentation.First,a m ulti-type pavement defect dataset (PDD) was collected and produced to demonstrate the feas ibility of the system.Then,four models single shot multibox detector (SSD),Faster R-CNN,you only look once v5x (YOLOv5x) and YOLOX,were used to train the PDDs for detection.After training,the mean average precision (mAP) of all four models exceeded 77%,with YOLOv5x showing the best results with 91% mAP,while proving the validity of the created dataset PDD s.Finally,YOLOv5x was used as the main detection method of the system combined with perspective tran sformation, image segmentation and skeleton extraction to obtain information such as length, width and area of defects,and then calculating the pavement condition index (PCI) to obtain the pavemen t damage level and the corresponding repair suggestions,improving the practicality of pavement defe ct detection.