Crack segmentation in high-resolution images using cascaded deep convolutional neural networks and Bayesian data fusion
Journal
Smart Structures and Systems
Journal Volume
29
Journal Issue
1
Pages
221-235
Date Issued
2022
Author(s)
Abstract
Manual inspection of steel box girders on long span bridges is time-consuming and labor-intensive. The quality of inspection relies on the subjective judgements of the inspectors. This study proposes an automated approach to detect and segment cracks in high-resolution images. An end-to-end cascaded framework is proposed to first detect the existence of cracks using a deep convolutional neural network (CNN) and then segment the crack using a modified U-Net encoder-decoder architecture. A Naïve Bayes data fusion scheme is proposed to reduce the false positives and false negatives effectively. To generate the binary crack mask, first, the original images are divided into 448 × 448 overlapping image patches where these image patches are classified as cracks versus non-cracks using a deep CNN. Next, a modified U-Net is trained from scratch using only the crack patches for segmentation. A customized loss function that consists of binary cross entropy loss and the Dice loss is introduced to enhance the segmentation performance. Additionally, a Naïve Bayes fusion strategy is employed to integrate the crack score maps from different overlapping crack patches and to decide whether a pixel is crack or not. Comprehensive experiments have demonstrated that the proposed approach achieves an 81.71% mean intersection over union (mIoU) score across 5 different training/test splits, which is 7.29% higher than the baseline reference implemented with the original U-Net. Copyright © 2022 Techno-Press, Ltd.
Subjects
Bayesian data fusion; crack detection; deep learning; semantic segmentation; structural health monitoring
SDGs
Other Subjects
Bayesian networks; Box girder bridges; Convolution; Convolutional neural networks; Crack detection; Deep neural networks; Semantic Segmentation; Semantics; Bayesian data fusions; Crack segmentations; Deep learning; High-resolution images; Image patches; Long-span bridge; Manual inspection; Naive bayes; Semantic segmentation; Steel box girders; Structural health monitoring
Type
journal article