Road Crack Detection Using Deep Convolutional Neural Network and Adaptive Thresholding
This addresses the labor-intensive and subjective nature of manual crack inspection for road safety, though it is incremental as it builds on existing deep learning and image processing techniques.
The paper tackles road crack detection by combining a deep convolutional neural network for classification with adaptive thresholding for segmentation, achieving 99.92% accuracy in image classification and successful crack extraction.
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, we propose a novel road crack detection algorithm based on deep learning and adaptive image segmentation. 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, we utilize an adaptive thresholding method to extract the cracks from road surface. 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.