Deep Learning Based Pavement Road Crack Detection

• Published in: Journal of the Eastern Asia Society for Transportation Studies Vol. 15; pp. 2315 - 2321
• Main Authors: NGUYEN, Le Minh, BUI, Ngoc Dung, DAVID, Asirvatham
• Format: Journal Article
• Language: English
• Published: Eastern Asia Society for Transportation Studies 2024
• Subjects: convolutional neural network; crack detection; deep learning
• ISSN: 1881-1124
• DOI: 10.11175/easts.15.2315

In pavement management system, evaluating the pavement condition is an essential step in determining the appropriate rehabilitation strategy to use for a pavement. However, it remains a challenging task due to the intensity inhomogeneity of cracks and complexity of the background. These conditions are a limiting factor when working with computer vision systems based on conventional digital image processing methods. In this study, the developed crack detection model relies on a deep learning convolutional neural network (CNN) image classification algorithm. For this work, a dataset with 40.000 images of concrete surfaces balanced between images with and without cracks was used. In each experiment, the model’s accuracy was recorded to identify the best result. For the dataset used in this work, the best experiment yielded a model with accuracy of 95.99%, showcasing the potential of using deep learning for concrete crack detection.