StructDamage:A Large Scale Unified Crack and Surface Defect Dataset for Robust Structural Damage Detection

2026-03-11

AI Summary

This study addresses the limitations of existing crack and surface defect datasets—particularly their insufficient geographic diversity, material coverage, scale, and annotation consistency—which hinder model generalization in real-world scenarios. To overcome these challenges, the authors present StructDamage, a unified large-scale structural damage dataset that systematically integrates 78,093 images from 32 publicly available datasets, spanning nine distinct material types. The dataset employs consistent annotation protocols and a hierarchical organization scheme, enabling, for the first time, standardized cross-material and cross-scenario fusion of multi-source crack data. StructDamage is compatible with mainstream architectures, including CNNs and Vision Transformers. Baseline experiments with 15 models demonstrate strong performance, with 12 achieving macro F1-scores above 0.96; the best-performing model, DenseNet201, attains an accuracy of 98.62%, establishing a highly consistent and reproducible benchmark for structural damage recognition.

Technology Category

• Machine Learning: Structured Learning
• Computer Vision: Adversarial Attacks & Robustness
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Bridging structured and unstructured data

Abstract

Automated detection and classification of structural cracks and surface defects is a critical challenge in civil engineering, infrastructure maintenance, and heritage preservation. Recent advances in Computer Vision (CV) and Deep Learning (DL) have significantly improved automatic crack detection. However, these methods rely heavily on large, diverse, and carefully curated datasets that include various crack types across different surface materials. Many existing public crack datasets lack geographic diversity, surface types, scale, and labeling consistency, making it challenging for trained algorithms to generalize effectively in real world conditions. We provide a novel dataset, StructDamage, a curated collection of approximately 78,093 images spanning nine surface types: walls, tile, stone, road, pavement, deck, concrete, and brick. The dataset was constructed by systematically aggregating, harmonizing, and reannotating images from 32 publicly available datasets covering concrete structures, asphalt pavements, masonry walls, bridges, and historic buildings. All images are organized in a folder level classification hierarchy suitable for training Convolutional Neural Networks (CNNs) and Vision Transformers. To highlight the practical value of the dataset, we present baseline classification results using fifteen DL architectures from six model families, with twelve achieving macro F1-scores over 0.96. The best performing model DenseNet201 achieves 98.62% accuracy. The proposed dataset provides a comprehensive and versatile resource suitable for classification tasks. With thorough documentation and a standard structure, it is designed to promote reproducible research and support the development and fair evaluation of robust crack damage detection approaches.

Problem

• structural damage detection
• crack dataset
• surface defects
• dataset diversity
• generalization

Innovation

• StructDamage
• crack detection
• surface defect dataset
• deep learning benchmark
• data harmonization