Automatic pixel-level detection method for concrete crack with channel-spatial attention convolution neural network. (March 2023)

• Record Type: Journal Article
• Authors: Li, Yuanyuan; Yu, Meng; Wu, Decheng; Li, Rui; Xu, Kefei; Cheng, Longqi
• Is Part Of: Structural health monitoring. Volume 22:Number 2(2023)
• Page Start: 1460
• Page End: 1477
• Publication Date: 2023-03
• Subjects: crack detection -- deep learning -- convolutional neural networks -- attention mechanism; Structural health monitoring -- Periodicals; Structural stability -- Periodicals; Strength of materials -- Periodicals; Nondestructive testing -- Periodicals; Constructions -- Stabilité -- Périodiques; Résistance des matériaux -- Périodiques; Contrôle non destructif -- Périodiques; Electronic journals; 624.17
• DOI: 10.1177/14759217221109496
• Languages: English
• ISSNs: 1475-9217

Abstract

Concrete crack detection is a significant research problem in structural safety. However, the traditional manual inspection is a laborious and time-consuming method, and the detection accuracy is greatly limited by the work experience of engineers. Hence, automatic image-based crack detection has attracted wide attention from both academia and industry. In this study, a novel crack detection method using attention convolution neural networks, ATCrack, is proposed for automatic crack identification. ATCrack uses a symmetric structure consisting of an encoder and a decoder by imposing channel-spatial attention to achieve end-to-end crack prediction. Channel attention module is introduced in the encoder to improve the effective utilization of crack features, and spatial attention is added in the decoder to suppress the background features. Combining with channel and spatial attention modules, the codec network will be more sensitive to the characteristics of cracks and increase detection accuracy and robustness. Moreover, a complex crack dataset of buildings and pavements is collected to verify the effectiveness and feasibility of ATCrack. Finally, experiment results are tested on several public datasets and self-collected (CBCrack) database, and it shows that the proposed method during the five-fold cross-validation can achieve state-of-the-art performance compared with other existing methods in terms of precision, recall, F1-score, and mIoU.