Deep Learning-Based Crack Detection: A Survey

• Published in: International journal of pavement research & technology Vol. 16; no. 4; pp. 943 - 967
• Main Authors: Nguyen, Son Dong, Tran, Thai Son, Tran, Van Phuc, Lee, Hyun Jong, Piran, Md. Jalil, Le, Van Phuc
• Format: Journal Article
• Language: English
• Published: Singapore Springer Nature Singapore 01.07.2023; Springer Nature B.V
• Subjects: Algorithms; Asphalt pavements; Building Construction and Design; Civil Engineering; Classification; Cracks; Deep learning; Engineering; Flaw detection; Generative adversarial networks; Image processing; Image segmentation; Machine learning; Object recognition; Original Research Paper; Structural Materials; Supervised learning; Unsupervised learning; Deep learning; Crack detection; GANs with crack segmentation; Unsupervised learning
• ISSN: 1996-6814; 1997-1400
• DOI: 10.1007/s42947-022-00172-z

Cracks are an acute distress in an asphalt pavement, which must be detected and quantified to diagnose the pavement’s health. Hence, many researchers have developed methods to detect cracks based on three main techniques: image processing, machine learning (ML), and deep learning (DL). Among these three techniques, DL has been recognised as an excellent method for crack detection because it assures high accuracy with an adequate analysis time. However, choosing an appropriate DL algorithm to identify cracks in an asphalt pavement is challenging for both transportation agencies and researchers. This study has identified the bigger picture of DL methods for crack identification in asphalt pavement. The authors evaluated several DL-based crack identification algorithms from the literature, such as crack classification, crack object detection, pixel-level crack segmentation, generative adversarial networks (GANs) for crack segmentation, and crack identification using unsupervised learning. Moreover, 26 DL-based crack detection models (25 supervised learning models and one unsupervised learning model) were analysed on the same dataset to test the performance of each model using consistent assessment metrics. The testing results suggest that ResNet and DenseNet are the best options for crack classification, while Faster R-CNN should be used for crack object detection and pix2pix is suggested for crack segmentation. It is also recommended that semi-supervised and unsupervised learning be further studied to efficiently detect cracks in an asphalt pavement.