Cracks in Steel Bridges (CSB) dataset: data underlying the publication: Deep Learning for Segmentation of Cracks in High-Resolution Images of Steel Bridges

The presented dataset used for the experiments is described in the article "Deep Learning for Segmentation of Cracks in High-Resolution Images of Steel Bridges" (doi:https://doi.org/10.48550/arXiv.2403.17725). The dataset consists of images of steel bridge structures and pixel-wise fatigue crack annotations. Some of the images contain bridge structures with cracks or corrosion, while others capture structures without any defect. <br>The images are provided by bridge infrastructure owners "Rijkswatersaat" and "ProRail" and by "Nebest" engineering company. The annotation of images was made using a semi-automatic annotation tool described in the article "Segmentation Tool for Images of Cracks" (doi:https://doi.org/10.1007/978-3-031-35399-4_8) and which implementation is available at https://github.com/akomp22/crack-segmentation-tool.<br>The dataset consists of high-resolution images and is stored in the folder "entire images". The images are divided into test and train sets. Images that capture cracks are stored in the folder "crack_train" and "crack_test". Images capturing structure without a crack are stored in folders "nocrack_train" and "nocrack_test". For each image, a .json file is stored in the same folder and under the same name as the corresponding image. The .json file stores the position (x,y) of pixels on the image, which lie in a crack region. An example of a code to generate a binary segmentation map from the .json files is given in the "read_json_annotation.py" file.Additional patch datasets were generated from the entire images. The patch datasets are stored in the “patch dataset” folder. The multiple patch datasets differ by the patch size, number of patches, and fraction of patches that do not contain cracks among all patches of the particular dataset. Furthermore, we provide segmentation maps in file "predictions.rar" for entire test images which are given by the method proposed in our research article.<br>For more explanations, please refer to the article: https://doi.org/10.48550/arXiv.2403.17725

本实验所用数据集已在论文《用于钢桥高分辨率图像裂缝分割的深度学习》（Deep Learning for Segmentation of Cracks in High-Resolution Images of Steel Bridges）（DOI：https://doi.org/10.48550/arXiv.2403.17725）中进行了详细阐述。该数据集包含钢桥结构图像以及逐像素疲劳裂缝标注。部分图像拍摄了带有裂缝或锈蚀的桥体结构，其余图像则拍摄了无任何缺陷的桥体结构。
本数据集的图像由桥梁基础设施所有者Rijkswatersaat、ProRail以及工程公司Nebest提供。图像标注工作采用了论文《裂缝图像分割工具》（Segmentation Tool for Images of Cracks）（DOI：https://doi.org/10.1007/978-3-031-35399-4_8）中介绍的半自动标注工具完成，该工具的实现代码可在https://github.com/akomp22/crack-segmentation-tool获取。
数据集包含高分辨率图像，存储于名为"entire images"（完整图像）的文件夹中。图像被划分为训练集与测试集：带有裂缝的图像分别存储于"crack_train"（裂缝训练集）与"crack_test"（裂缝测试集）文件夹中；无裂缝的桥体结构图像则分别存储于"nocrack_train"（无裂缝训练集）与"nocrack_test"（无裂缝测试集）文件夹中。针对每张图像，对应文件夹中会存储一个与图像同名的.json文件，该文件记录了图像中属于裂缝区域的像素的坐标(x,y)。"read_json_annotation.py"文件中提供了一段用于从.json文件生成二进制分割掩码的示例代码。
此外，我们从完整图像中生成了多个补丁数据集（patch dataset），这些补丁数据集存储于"patch dataset"（补丁数据集）文件夹中。不同补丁数据集的区别在于补丁尺寸、补丁数量，以及特定数据集中无裂缝补丁所占的比例。我们还在"predictions.rar"文件中提供了本研究论文所提方法生成的全部测试图像的分割掩码结果。
如需更多详细说明，请参阅论文：https://doi.org/10.48550/arXiv.2403.17725