ERCUnet：一种基于U-Net改进的道路裂缝检测模型

计算机与现代化 ›› 2022, Vol. 0 ›› Issue (07): 33-39.

ERCUnet：一种基于U-Net改进的道路裂缝检测模型

（1.郑州大学软件学院，河南郑州450001；2.中国科学院空天信息创新研究院，北京100101）

出版日期:2022-07-25 发布日期:2022-07-25
作者简介:刘宇翔（2000—）,男,河南焦作人,本科生,研究方向:人工智能,大数据分析,图像识别，E-mail: lyx2019@stu.zzu.edu.cn；佘维（1977—）,男,湖南常德人,教授,博士,研究方向:人工智能,信息安全,能源区块链,E-mail: wshe@zzu.edu.cn; 通信作者：沈占峰（1977—）,男,黑龙江大庆人,研究员,博士,研究方向:高分辨率遥感影像信息提取,深度学习,E-mail: Shenzf@radi.ac.cn; 谭帅（2003—）,男,河南信阳人,本科生,研究方向:物联网,人工智能,E-mail: 2826598617@qq.com。
基金资助:
郑州大学大学生创新创业训练计划资助项目(202110459167)；国家自然科学基金资助项目(41971375); 国家重点研发计划项目(2018YFB0505000)

ERCUnet: An Improved Road Crack Detection Model Based on U-Net

(1. School of Software Technology, Zhengzhou University, Zhengzhou 450001, China；
2. Aerospace Information Research Institute, Chinese Academy of Sciences， Beijing 100101, China)

Online:2022-07-25 Published:2022-07-25

摘要/Abstract

摘要： 针对传统的道路裂缝检测方法存在灵活度不高、普适性不强等问题，本文参考ResNet中的残差设计和U-Net模型的U形编码解码结构，设计一种基于U-Net改进的道路裂缝检测模型——ERCUnet。该模型以残差块为主体，针对裂缝检测优化不同深度卷积层的卷积核数量，模型中所有的残差块结构相同，模型整体结构更加整齐和简单，具有可塑性好、结构性强，残差结构不仅使特征融合更加充分，也避免了深层卷积神经网络梯度消失的问题。实验在CrackForest数据集上进行，将CrackForest的118张含标注图片按照5〖DK〗∶1的比例划分训练集和测试集，通过一系列数据增广方法，有效缓解了训练数据过少的问题。损失函数融合了交叉熵和F1分数，缓解了正负样本不均衡的问题，最终的实验结果显示ERCUnet模型参数量仅为U-Net(BN)模型的13.30%，在测试集上的查全率、查准率、F1值均达70%以上，噪声率、准确率分别为29.05%、99.01%。为证实ERCUnet的可塑性，通过修改模型参数得到ERCUnet-tiny模型，其参数量仅为U-Net(BN)模型的2.39%，在测试集上取得了与U-Net(BN)相近的效果。

关键词: 道路裂缝检测, U-Net, 残差结构, 数据增广

Abstract: Aiming at the problems of traditional road crack detection methods, such as low flexibility and poor universality, refering to the residual design in ResNet and the U-shaped encoding and decoding structure of U-Net model, an improved road crack detection model based on U-Net, named ERCUnet, is designed. The model takes residual blocks as the main body, and optimizes the number of convolution cores of convolution layers at different depths for crack detection. All residual blocks in the model have the same structure, the overall structure of the model is more neat and simple, with good elasticity and strong structure. The residual structure not only makes the feature fusion more sufficient but also avoids the problem of gradient disappearance of deep convolution neural network. The experiment is conducted on the CrackForest dataset. The 118 labeled pictures of CrackForest are divided into training set and testing set according to the ratio of 5〖DK(〗∶〖DK)〗1. Through a series of data expansion methods, the problem of too little training data is effectively alleviated. The loss function combines cross entropy and F1 score to alleviate the imbalance between positive and negative samples. The final experimental results show that the number of parameters of ERCUnet model is only 13.30% of that of U-Net model, the recall, precision, and F1 are all greater than 70%, and noise rate and accuracy are 29.05% and 99.01% on testing set. ERCUnet-tiny model is obtained by modifying model parameters to confirm the plasticity of ERCUnet, and the number of its parameters is only 2.39% of that of U-Net model, similar effect to U-Net is achieved on testing set.

Key words: road crack detection, U-Net, residual structure, data expansion

刘宇翔, 佘维, 沈占峰, 谭帅. ERCUnet：一种基于U-Net改进的道路裂缝检测模型[J]. 计算机与现代化, 2022, 0(07): 33-39.

LIU Yu-xiang, SHE Wei, SHEN Zhan-feng, TAN Shuai. ERCUnet: An Improved Road Crack Detection Model Based on U-Net[J]. Computer and Modernization, 2022, 0(07): 33-39.

参考文献［28］

［1］	CANNY J. A computational approach to edge detection［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986,8(6):679-698.
［2］	OTSU N. Threshold selection method from gray-level histograms［J］. IEEE Transactions on Systems Man and Cybernetics, 1979,9(1):62-66.〖HJ1.33mm〗
［3］	李清泉,邹勤,毛庆洲. 基于最小代价路径搜索的路面裂缝检测［J］. 中国公路学报, 2010,23(6):28-33.
［4］	PRASANNA P, DANA K J, GUCUNSKI N, et al. Automated crack detection on concrete bridges［J］. IEEE Transactions on Automation Science and Engineering, 2016,13(2):591-599.
［5］	ZOU Q, CAO Y, LI Q Q, et al. Crack tree: Automatic crack detection from pavement images［J］. Pattern Recognition Letters, 2012,33(3):227-238.
［6］	LIAO T Y. On-line vehicle routing problems for carbon emissions reduction［J］. Computer-aided Civil and Infrastructure Engineering， 2017,32(1):1047-1063.
［7］	YANG X C， LI H， YU Y T， et al. Automatic pixel-aided crack detection and measurement using fully convolutional network［J］. Computer-aided Civil and Infrastructure Engineering， 2018,33(12):1090-1109.
［8］	LAI S L, LEE D H, WU J H， et al. Detecting the cracks and seepage line associated with an earthquake in an earth dam using the nondestructive testing technologies［J］. Journal of the Chinese Institute of Engineers， 2014,37（4）:428-437.
［9］	LIU W J， HUANG Y C， LI Y， et al. FPCNet： Fast pavement crack detection network based on encoder-decoder architecture［J］. arXiv preprint arXiv， 1907.02248, 2019.
［10］	LI S Y， ZHAO X F， ZHOU G Y. Automatic pixel-level multiple damage detection of concrete structure using fully convolutional network［J］. Computer-aided Civil and Infrastructure Engineering, 2019,34(7):616-634.
［11］	王健,胥燕军,汪力,等. 机器视觉在钢轨磨耗检测中的应用研究［J］. 铁道标准设计， 2014（9）：36-39.
［12］	KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neural networks［C］//2012 Advances in Neural Information Processing Systems. 2012:1097-1105.
［13］	SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition［J］. arXiv preprint arXiv:1409.1556, 2014.
［14］	CHA Y J, CHOI W, BYKZTRK O. Deep learning-based crack damage detection using convolutional neural networks［J］. Computer-aided Civil and Infrastructure Engineering, 2017,32（5）:361-378.
［15］	GIBB S， LA H M， LOUIS S. A genetic algorithm for convolutional network structure optimization for concrete crack detection［C］// 2018 IEEE Congress on Evolutionary Computation(CEC). 2018:1-8.
［16］	李岩,杨豪杰,刘辉,等. 基于深度学习的混凝土裂缝检测研究［J］. 信息技术与信息化, 2021(12):233-236.
［17］	李良福,王楠,武彪,等. 基于改进PSPNet的桥梁裂缝图像分割算法［J］. 激光与光电子学进展, 2021,58(22):93-101.
［18］	LONG J， SHELHAMER E， DARRELL T. Fully convolutional networks for semantic segmentation［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017,39:640-651.
［19］	RONNEBERGER O, FISCHER P, BROX T. U-Net: Convolutional networks for biomedical image segmentation［C］// 2015 International Conference on Medical Image Computing and Computer-Assisted Intervention. 2015:234-241.
［20］	张果荣. 基于深度学习的道路裂缝检测研究［D］. 南京:南京信息工程大学， 2021.
［21］	朱苏雅,杜建超,李云松,等. 采用U-Net卷积网络的桥梁裂缝检测方法［J］. 西安电子科技大学学报， 2019,49(4):35-42.
［22］	SHI Y, CUI L M, QI Z Q, et al. Automatic road crack detection using random structured forests［J］. IEEE Transactions on Intelligent Transportation Systems, 2016,17(12):3434-3445.
［23］	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition［C］// 2016 IEEE Conference on Computer Vision and Pattern Recognition. 2016:770-778.
［24］	IOFFE S, SZEGEDY C. Batch normalization: Accelerating deep network training by reducing internal covariate shift［C］// Proceedings of the 32nd International Conference on International Conference on Machine. 2015:448-456.
［25］	XU B, WANG N Y, CHEN T Q, et al. Empirical Evaluation of rectified activations in convolutional network［J］. arXiv preprint arXiv:1505.00853, 2015.
［26］	PASZKE A, GROSS S, MASSA F, et al. PyTorch: An imperative style, high-performance deep learning library［J］. Advances in Neural Information Processing Systems, 2019,32:8026-8037.
［27］	ZHAO H S, SHI J P, QI X J, et al. Pyramid scene parsing network［C］// 2017 IEEE Conference on Computer Vision and Pattern Recognition. 2017:6230-6239.
［28］	BADRINARAYANAN V, KENDALL A, CIPOLLA R. SegNet: A deep convolutional encoder-decoder architecture for image segmentation［J］. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017,39:2481-2495.