Corrosion Condition State Semantic Segmentation Dataset

<p>The data was collected from the Virginia Department of
Transportation (VDOT) Bridge Inspection Reports. The data was semantically
annotated following the corrosion condition state guidelines stated in the
American Association of State Highway and Transportation Officials (AASHTO) and
Bridge Inspector's Reference Manual (BIRM). There were four corrosion class
categories: [good, fair, poor, severe]. The dataset consisted of 440 finely
annotated images and was randomly split into 396 training images and 44 testing
images. The images were resized to 512x512 for training and testing the
DeeplabV3+ model. The original and resized images are included. After training
with the DeeplabV3+ model (DOI: 10.7294/16628668), we were able to receive an
F1 score of 86.67. More details of the training, the results, the dataset, and
the code may be referenced in the journal article. The GitHub repository
information may be found in the journal article.</p><p><br>If you are using the dataset in your work, please include <b>both </b>the journal article and the dataset citation. <br></p>

本数据集采集自弗吉尼亚州交通运输厅（Virginia Department of Transportation, VDOT）的桥梁检测报告。数据依据美国国家公路与运输协会（American Association of State Highway and Transportation Officials, AASHTO）及《桥梁检测员参考手册》（Bridge Inspector's Reference Manual, BIRM）中规定的腐蚀状态分级准则完成语义标注。本次标注共设置四类腐蚀等级：[良好、尚可、较差、严重]。数据集包含440张精细标注图像，并通过随机划分策略拆分为396张训练图像与44张测试图像。为适配DeepLabV3+模型的训练与测试流程，所有图像均被统一调整至512×512分辨率，原始图像与调整尺寸后的图像均已包含在数据集中。依托DeepLabV3+模型开展训练（DOI: 10.7294/16628668）后，模型获得了86.67的F1分数。更多关于训练细节、实验结果、数据集详情及代码的相关信息，可查阅配套期刊论文，GitHub仓库的相关信息亦可在该期刊论文中获取。

若您的研究工作中使用本数据集，请同时引用该期刊论文与数据集的引用信息。

搜集汇总

背景与挑战

背景概述

该数据集包含440张桥梁腐蚀状况的语义分割图像，标注类别为[good, fair, poor, severe]，用于训练和测试DeeplabV3+模型，F1得分为86.67。数据来源于弗吉尼亚交通部桥梁检查报告，并按照AASHTO和BIRM指南进行标注。