Datasets
Standard Dataset
Pavement defect data set under complex background
- Citation Author(s):
- Submitted by:
- Pei Huang
- Last updated:
- Thu, 06/20/2024 - 06:49
- DOI:
- 10.21227/6yhm-kz11
- License:
62 Views- Categories:
- Keywords:
Abstract
This study is based on the image data of cement concrete pavement diseases collected by myself. The mobile phone is fixed on the sun visor of the passenger seat of the vehicle, and all kinds of diseases on the road are photographed along with the vehicle. Based on 1,595 images, each image is expanded to 4 by using the data enhancement method. After screening, a total of 2,925 images are obtained, including 2,125 defective images with shadow occlusion and uneven illumination. In order to improve the robustness of the algorithm, 800 images are defect images collected in normal light, and 2925 photos are labeled by an opensource image LabelImg tool, and the defect images are divided into training set, verification set and test set with a ratio of 8: 1: 1, including 2340 training sets, 292 verification sets and 293 test sets.
This study is based on the image data of cement concrete pavement diseases collected by myself. The mobile phone is fixed on the sun visor of the passenger seat of the vehicle, and all kinds of diseases on the road are photographed along with the vehicle. Based on 1,595 images, each image is expanded to 4 by using the data enhancement method. After screening, a total of 2,925 images are obtained, including 2,125 defective images with shadow occlusion and uneven illumination. In order to improve the robustness of the algorithm, 800 images are defect images collected in normal light, and 2925 photos are labeled by an opensource image LabelImg tool, and the defect images are divided into training set, verification set and test set with a ratio of 8: 1: 1, including 2340 training sets, 292 verification sets and 293 test sets.
Comments
本研究基于我自己收集的水泥混凝土路面病害图像数据。手机固定在车辆乘客座椅的遮阳板上，随车辆一起拍摄道路上的各种疾病。基于1,595张图像，使用数据增强方法将每张图像扩展为4张。筛选后共获得2,925张图像，其中阴影遮挡和照明不均匀的缺陷图像2,125张。为了提高算法的鲁棒性，将800张图像为在正常光下采集的缺陷图像，并通过开源图像LabelImg工具对2925张照片进行标记，并将缺陷图像按8：1：1的比例分为训练集、验证集和测试集，包括2340个训练集、292个验证集和293个测试集。
This study is based on the image data of cement concrete pavement diseases collected by myself. The mobile phone is fixed on the sun visor of the passenger seat of the vehicle, and all kinds of diseases on the road are photographed along with the vehicle. Based on 1,595 images, each image is expanded to 4 by using the data enhancement method. After screening, a total of 2,925 images are obtained, including 2,125 defective images with shadow occlusion and uneven illumination. In order to improve the robustness of the algorithm, 800 images are defect images collected in normal light, and 2925 photos are labeled by an opensource image LabelImg tool, and the defect images are divided into training set, verification set and test set with a ratio of 8: 1: 1, including 2340 training sets, 292 verification sets and 293 test sets.