Paper Info
Title
Road Crack Detection Using Deep Convolutional Neural Network and Adaptive Thresholding
Abstract
Crack is one of the most common road distresses which may pose road safety hazards. Generally, crack detection is performed by either certified inspectors or structural engineers. This task is, however, time-consuming, subjective and labor-intensive. In this paper, a novel road crack detection algorithm which is based on deep learning and adaptive image segmentation is proposed. Firstly, a deep convolutional neural network is trained to determine whether an image contains cracks or not. The images containing cracks are then smoothed using bilateral filtering, which greatly minimizes the number of noisy pixels. Finally, cracks are extracted from the road surface using an adaptive thresholding method. The experimental results illustrate that our network can classify images with an accuracy of 99.92%, and the cracks can be successfully extracted from the images using our proposed thresholding algorithm.
Year
DOI
Venue
2019
10.1109/IVS.2019.8814000
2019 IEEE Intelligent Vehicles Symposium (IV)
Keywords
Field
DocType
road surface,adaptive thresholding method,deep convolutional neural network,road safety hazards,road crack detection algorithm,deep learning,adaptive image segmentation,road distresses,bilateral filtering
Pattern recognition,Computer science,Convolutional neural network,Thresholding algorithm,Image segmentation,Road surface,Pixel,Artificial intelligence,Thresholding,Deep learning,Bilateral filter
Journal
Volume
ISSN
ISBN
abs/1904.08582
1931-0587
978-1-7281-0561-1
Citations 
PageRank 
References 
1
0.35
17
Authors
8
Name
Order
Citations
PageRank
Rui Fan125828.91
Mohammud Junaid Bocus2215.48
Yilong Zhu366.16
Jianhao Jiao4196.68
Li Wang5151.08
Fulong Ma6202.32
Shanshan Cheng710.35
Ming Liu877594.83