Automatic Classification and Segmentation of Tunnel Cracks Based on Deep Learning and Visual Explanations

2025-07-18

AI Summary

Tunnel lining crack detection faces challenges in balancing detection accuracy and computational efficiency, alongside poor model interpretability. This paper proposes a two-stage deep learning framework integrating classification and segmentation: first, DenseNet-169 performs binary crack classification; second, DeepLabV3+ executes pixel-wise semantic segmentation. Notably, we introduce a novel score-weighted visualization technique to enhance decision traceability and model interpretability—first applied in this domain. Experimental results demonstrate a classification accuracy of 92.23% at 39.80 FPS, segmentation IoU of 57.01%, and F1-score of 67.44%, all surpassing state-of-the-art methods. The framework significantly improves the reliability and real-time capability of quantitative tunnel health assessment. Moreover, it establishes a new paradigm for explainable AI (XAI) deployment in civil engineering applications, bridging the gap between high-performance deep learning and domain-specific interpretability requirements.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Transparent, Interpretable, Explainable ML
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Tunnel lining crack is a crucial indicator of tunnels' safety status. Aiming to classify and segment tunnel cracks with enhanced accuracy and efficiency, this study proposes a two-step deep learning-based method. An automatic tunnel image classification model is developed using the DenseNet-169 in the first step. The proposed crack segmentation model in the second step is based on the DeepLabV3+, whose internal logic is evaluated via a score-weighted visual explanation technique. Proposed method combines tunnel image classification and segmentation together, so that the selected images containing cracks from the first step are segmented in the second step to improve the detection accuracy and efficiency. The superior performances of the two-step method are validated by experiments. The results show that the accuracy and frames per second (FPS) of the tunnel crack classification model are 92.23% and 39.80, respectively, which are higher than other convolutional neural networks (CNN) based and Transformer based models. Also, the intersection over union (IoU) and F1 score of the tunnel crack segmentation model are 57.01% and 67.44%, respectively, outperforming other state-of-the-art models. Moreover, the provided visual explanations in this study are conducive to understanding the "black box" of deep learning-based models. The developed two-stage deep learning-based method integrating visual explanations provides a basis for fast and accurate quantitative assessment of tunnel health status.

Problem

• Classify tunnel cracks accurately using deep learning
• Segment tunnel cracks efficiently with visual explanations
• Improve tunnel safety assessment via two-step deep learning

Innovation

• Uses DenseNet-169 for crack image classification
• Employs DeepLabV3+ for precise crack segmentation
• Integrates visual explanations to interpret model logic