A three-stage detection algorithm for automatic crack-width identification of fine concrete cracks

Abstract

Semantic image segmentation is extensively used for automatic concrete crack detection. In previous studies on semantic image segmentation, concrete images were usually labeled as crack and noncrack zones, and recognition models were then trained using artificial neural networks. However, there is not enough edge information in concrete images for the trained model to identify effectively fine concrete cracks (widths < 0.1 mm). Furthermore, complex backgrounds in concrete images can cause false detections. To improve efficiency and reduce false detections, this study develops a three-stage automatic crack-width identification method for fine concrete cracks. First, a full crack skeleton information identification based on image segmentation is proposed. The performance of the mainstream image segmentation architectures, PSP-Net, Seg-Net, U-Net, and Res-Unet, are compared and analyzed, demonstrating that the Res-Unet-based crack skeleton segmentation is the most accurate at fine-crack detection and able to solve the information loss problem that occurs when learning the imbalanced data of fine concrete cracks. Second, a fractal dimension (FD)-based false detection removal process is applied to discriminate true cracks and false detections. The results show that false detections (line-like curves, shadows, and surface stains) can be removed, increasing the matching rate from 0.6476 to 0.8351. Finally, the FD features of the crack skeleton with maximum widths < 0.1 mm, crack widths in the range of 0.1–0.2 mm, and crack widths > 0.2 mm are calculated. Findings illustrate that the values of the FD feature for the three crack-width ranges are suitable for quantitative characterization of identified crack widths.