A multi-scale residual encoding network for concrete crack segmentation

• Published in: Journal of intelligent & fuzzy systems Vol. 46; no. 1; pp. 1379 - 1392
• Main Authors: Liu, Die, Xu, MengDie, Li, ZhiTing, He, Yingying, Zheng, Long, Xue, Pengpeng, Wu, Xiaodong
• Format: Journal Article
• Language: English
• Published: Amsterdam IOS Press BV 10.01.2024
• Subjects: Coding; Cracks; Datasets; Edge detection; Feature maps; Semantic segmentation; State-of-the-art reviews; Surface cracks
• ISSN: 1064-1246; 1875-8967
• DOI: 10.3233/JIFS-231736

Concrete surface crack detection plays a crucial role in ensuring concrete safety. However, manual crack detection is time-consuming, necessitating the development of an automatic method to streamline the process. Nonetheless, detecting concrete cracks automatically remains challenging due to the heterogeneous strength of cracks and the complex background. To address this issue, we propose a multi-scale residual encoding network for concrete crack segmentation. This network leverages the U-NET basic network structure to merge feature maps from different levels into low-level features, thus enhancing the utilization of predicted feature maps. The primary contribution of this research is the enhancement of the U-NET coding network through the incorporation of a residual structure. This modification improves the coding network’s ability to extract features related to small cracks. Furthermore, an attention mechanism is utilized within the network to enhance the perceptual field information of the crack feature map. The integration of this mechanism enhances the accuracy of crack detection across various scales. Furthermore, we introduce a specially designed loss function tailored to crack datasets to tackle the problem of imbalanced positive and negative samples in concrete crack images caused by data imbalance. This loss function helps improve the prediction accuracy of crack pixels. To demonstrate the superiority and universality of our proposed method, we conducted a comparative evaluation against state-of-the-art edge detection and semantic segmentation methods using a standardized evaluation approach. Experimental results on the SDNET2018 dataset demonstrate the effectiveness of our method, achieving mIOU, F1-score, Precision, and Recall scores of 0.862, 0.941, 0.945, and 0.9394, respectively.