Open Access

ARTICLE

Intelligent Detection Model Based on a Fully Convolutional Neural Network for Pavement Cracks

by Duo Ma, Hongyuan Fang, Binghan Xue, Fuming Wang, Mohammed A. Msekh, Chiu Ling Chan

1 School of Water Conservancy Engineering, Zhengzhou University, Zhengzhou, 450001, China.
2 National Local Joint Engineering Laboratory of Major Infrastructure Testing and Rehabilitation Technology, Zhengzhou, 450001, China.
3 Collaborative Innovation Center of Water Conservancy and Transportation Infrastructure Safety, Zhengzhou, 450001, China.
4 Civil Engineering Department, College of Engineering, University of Babylon, Babylon, Iraq.
5 Institute of Structural Mechanics, Bauhaus Universität Weimar, Weimar, Germany

* Corresponding Author: Hongyuan Fang. Email: .

(This article belongs to the Special Issue: Machine Learning based Methods for Mechanics)

Computer Modeling in Engineering & Sciences 2020, 123(3), 1267-1291. https://doi.org/10.32604/cmes.2020.09122

Received 13 November 2019; Accepted 09 January 2020; Issue published 28 May 2020

Abstract

The crack is a common pavement failure problem. A lack of periodic maintenance will result in extending the cracks and damage the pavement, which will affect the normal use of the road. Therefore, it is significant to establish an efficient intelligent identification model for pavement cracks. The neural network is a method of simulating animal nervous systems using gradient descent to predict results by learning a weight matrix. It has been widely used in geotechnical engineering, computer vision, medicine, and other fields. However, there are three major problems in the application of neural networks to crack identification. There are too few layers, extracted crack features are not complete, and the method lacks the efficiency to calculate the whole picture. In this study, a fully convolutional neural network based on ResNet-101 is used to establish an intelligent identification model of pavement crack regions. This method, using a convolutional layer instead of a fully connected layer, realizes full convolution and accelerates calculation. The region proposals come from the feature map at the end of the base network, which avoids multiple computations of the same picture. Online hard example mining and data-augmentation techniques are adopted to improve the model’s recognition accuracy. We trained and tested Concrete Crack Images for Classification (CCIC), which is a public dataset collected using smartphones, and the Crack Image Database (CIDB), which was automatically collected using vehicle-mounted charge-coupled device cameras, with identification accuracy reaching 91.4% and 86.4%, respectively. The proposed model has a higher recognition accuracy and recall rate than Faster RCNN and different depth models, and can extract more complete and accurate crack features in CIDB. We also analyzed translation processing, fuzzy, scaling, and distorted images. The proposed model shows a strong robustness and stability, and can automatically identify image cracks of different forms. It has broad application prospects in practical engineering problems.

---

Keywords

---

Citations