摘要
针对常规裂纹检测方法难适用于坝面裂纹检测的问题,提出一种基于全卷积神经网络的裂纹检测方法,主要解决混凝土坝面裂纹的定量化检测问题。该检测方法引入图像预处理与形态学后处理相结合的方式,分别对原始数据和预测结果进行优化,提升检测精度;并根据坝面数据特点对传统FCN(fully convolutional network)网络进行改进,得到针对性更强的裂纹检测网络C-FCN(crack fully convolutional network),提升对裂纹检测的准确率;结合成像原理提取定量化信息,避免繁杂的相机标定工作,更加高效客观。利用该检测方法对实际工程进行实测,像素准确率、召回率和交并比分别达到75.13%、86.84%和60.15%,相比传统FCN网络,三项指标分别提升5.61%、16.56%、13.22%,同时定量化误差小于5%,裂纹平均宽度均不超过5 mm。该检测方法能够实现对坝面裂纹的精准识别和定量,为坝面后期风险评估和维护提供有力的数据支撑,具有显著的工程意义。
Aimed at the drawback of conventional crack detection methods not applicable to the detection of dam surface cracks,this paper presents a new method for quantitative detection based on a full convolution network(FCN).This method combines image preprocessing with morphological post-processing to achieve an improvement on detection accuracy through optimizing raw data and predictions.Oriented at dam surface data,it further improves the accuracy by modifying the traditional FCN network into a more targeted crack detection network,namely a crack full convolution network(C-FCN).And its quantitative information is extracted based on the imaging principle,which avoids complicated camera calibration and is more efficient and objective.We have applied it to in-situ measurements at a dam face and achieved a pixel accuracy of 75.13%,a recall rate of 86.84%,and an intersection ratio of 60.15%.These three indexes are improved by 5.61%,16.56% and 13.22% respectively in comparison with the traditional FCN network.And the quantified error of detection is less than 5%,and the average opening of the cracks detected is less than 5 mm.Thus,our new detection method would provide a useful tool for dam surface risk assessment and maintenance of water dams.
作者
陈波
张华
汪双
王皓冉
刘昭伟
李永龙
谢辉
CHEN Bo;ZHANG Hua;WANG Shuang;WANG Haoran;LIU Zhaowei;LI Yonglong;XIE Hui(School of Information and Engineering,Southwest University of Science and Technology,Mianyang,Sichuan 621010;State Key Laboratory of Hydroscience and Engineering,Tsinghua University,Beijing 100084;Sichuan Energy Internet Research Institute,Tsinghua University,Chengdu 610042)
出处
《水力发电学报》
EI
CSCD
北大核心
2020年第7期52-60,共9页
Journal of Hydroelectric Engineering
基金
国家“十三五”核能开发科研项目资助(20161295)
四川省科技计划资助项目(2018GZDZX0043)
四川省科技计划资助项目(2019YFG0144)
关键词
深度学习
全卷积神经网络
坝面裂纹检测
双边滤波
定量化检测
deep learning
full convolution neural network
dam surface crack detection
bilateral filtering
quantitative detection