Deep learning-based automated damage detection in concrete structures using images from earthquake events

2025-10-23

AI Summary

Manual identification of critical post-earthquake damage features—such as exposed reinforcement, cracking, and spalling—in concrete structures suffers from low efficiency and high subjectivity. Method: This paper proposes a hybrid deep learning framework based on YOLOv11, integrating object detection with fine-grained classification to enable end-to-end automatic detection and severity grading of multiple damage types. The framework incorporates transfer learning, adaptive data augmentation, and multi-model ensemble strategies, trained and validated on a real-world earthquake image dataset with expert annotations. Contribution/Results: Experimental results demonstrate superior detection accuracy (mAP@0.5 = 89.3%) and strong generalization capability under complex disaster scenarios. The method significantly improves the efficiency and objectivity of post-disaster structural safety assessment, providing reliable technical support for emergency response and decision-making.

Technology Category

• Machine Learning: Structured Learning
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Bridging structured and unstructured data

Abstract

Timely assessment of integrity of structures after seismic events is crucial for public safety and emergency response. This study focuses on assessing the structural damage conditions using deep learning methods to detect exposed steel reinforcement in concrete buildings and bridges after large earthquakes. Steel bars are typically exposed after concrete spalling or large flexural or shear cracks. The amount and distribution of exposed steel reinforcement is an indication of structural damage and degradation. To automatically detect exposed steel bars, new datasets of images collected after the 2023 Turkey Earthquakes were labeled to represent a wide variety of damaged concrete structures. The proposed method builds upon a deep learning framework, enhanced with fine-tuning, data augmentation, and testing on public datasets. An automated classification framework is developed that can be used to identify inside/outside buildings and structural components. Then, a YOLOv11 (You Only Look Once) model is trained to detect cracking and spalling damage and exposed bars. Another YOLO model is finetuned to distinguish different categories of structural damage levels. All these trained models are used to create a hybrid framework to automatically and reliably determine the damage levels from input images. This research demonstrates that rapid and automated damage detection following disasters is achievable across diverse damage contexts by utilizing image data collection, annotation, and deep learning approaches.

Problem

• Automated detection of structural damage in concrete buildings after earthquakes
• Identifying exposed steel reinforcement through deep learning image analysis
• Developing hybrid framework to classify damage levels from input images

Innovation

• Uses YOLOv11 model for crack and bar detection
• Fine-tunes YOLO model for damage level classification
• Creates hybrid framework combining multiple trained models