MDMCS: A Benchmark Dataset for Multi-Damage Monitoring of Concrete Structures

Concrete structures deteriorate over time due to environmental exposure and mechanical stress, leading to various types of damage such as cracking, spalling, corrosion, and exposed rebar. Automated detection using deep learning-based computer vision techniques is limited by the lack of high-quality, annotated datasets. To address this challenge, this paper presents MDMCS (Multi-Damage Monitoring of Concrete Structures), a dataset of 1,200 images with precise pixel-wise annotations involving four types of damage (cracking, spalling, corrosion, and exposed rebar) and diverse lighting conditions and material textures. The dataset has been evaluated using six state-of-the-art segmentation models, validating the efficacy of the dataset and providing benchmarks for damage detection models. MDMCS will facilitate advances in artificial intelligence-powered structural monitoring and robot-assisted automatic inspection for improving the operation and maintenance of concrete structures.

混凝土结构会因环境侵蚀与机械应力随时间发生劣化，进而产生开裂、剥落、锈蚀以及钢筋外露等多种损伤类型。基于深度学习的计算机视觉技术在自动化检测领域的应用，却因高质量标注数据集的匮乏而受到限制。为应对这一挑战，本研究提出了MDMCS（混凝土结构多损伤监测，Multi-Damage Monitoring of Concrete Structures）数据集：该数据集包含1200张图像，针对四类损伤（开裂、剥落、锈蚀与钢筋外露）进行了精准的像素级标注，且涵盖了多样化的光照条件与材料纹理。本研究采用六种当前前沿的语义分割模型对该数据集进行了评估，验证了数据集的有效性，并为损伤检测模型提供了基准测试标准。MDMCS数据集将助力基于人工智能的结构监测技术发展，以及机器人辅助自动巡检技术的进步，从而优化混凝土结构的运维工作。