Abstract
In response to the lack of data samples for highway diseases both in China and abroad,this paper established a disease dataset that included 2D images and 3D morphologies of highways and clarified the principles of data collection,data processing methods,sample description,data quality control,and validation.The dataset contained 11 types of highway pavement diseases such as cracks,block cracks,longitudinal cracks,transverse cracks,subsidence,rutting,wave congestion,and potholes,in a total of 576 subdivided scenarios with different lanes,different light backgrounds,and different road structures.The dataset also comprised six types of traffic signs:warning signs,prohibition signs,directional signs,guide signs,tourist area signs,and road construction safety signs.This dataset could provide a large number of training samples for neural network models for defect detection on various highways and be used for small sample training of the YOLOV 7 model,verifying the effectiveness of the dataset.The results of the study show that establishing an image dataset based on highway scenarios can effectively deepen the understanding of highway diseases and pavement scenarios,provide an intelligent information-based solution to highway pavement disease detection,and lay a solid foundation for the training of relevant algorithmic models and the subsequent construction of the dataset.
Publication Date
4-10-2025
DOI
10.14048/j.issn.1671-2579.2025.02.027
First Page
238
Last Page
246
Submission Date
April 2025
Recommended Citation
Zijian, WANG; Han, ZHANG; Xinpeng, YAO; Dongdong, XIE; and Songhua, FAN
(2025)
"Construction of Disease Dataset Comprising 2D Images and 3D Morphologies of Highways,"
Journal of China & Foreign Highway: Vol. 45:
Iss.
2, Article 27.
DOI: 10.14048/j.issn.1671-2579.2025.02.027
Available at:
https://zwgl1980.csust.edu.cn/journal/vol45/iss2/27
Reference
[1]高建贞.基于图像分析的道路病害自动检测研究 [D].南京:南京理工大学,2003.GAO Jianzhen.Research on automatic pavement distress detection based on image analysis [D].Nanjing:Nanjing University of Science and Technology,2003.
[2]刘宪明,辛公锋.国内基于深度学习的道路路面病害检测研究综述 [J].电子世界,2021 (8):96-98.LIU Xianming,XIN Gongfeng.Summary of domestic research on pavement disease detection based on deep learning [J].Electronics World,2021 (8):96-98.
[3] 刘宪明,夏晗,胡冬平,等.公路路面损坏与内部隐伏病害的关联性研究 [J].中外公路,2024,44(5):75-82.LIU Xianming,XIA Han,HU Dongping,et al.Correlation between pavement distress and structural hidden distress[J].Journal of China & Foreign Highway,2024,44(5):75-82.
[4]田杨,邱玲.一种基于 Fast-RCNN 的道路病害检测算法[J].市政技术,2020,38(增刊 1):123-127.TIAN Yang,QIU Ling.A road disease detection algorithm based on Fast-RCNN [J].Journal of Municipal Technology,2020,38(sup 1):123-127.
[5]ZHOU W,ZHAN Y F,ZHANG H C,et al.Road defect detection from on-board cameras with scarce and cross-domain data [J].Automation in Construction,2022,144:104628.
[6]ZHU Z M,LI M C,ZHOU F Q,et al.Stable 3D measurement method for high dynamic range surfaces based on fringe projection profilometry [J].Optics and Lasers in Engineering,2023,166:107542.
[7]ZHU Z M,DONG Y W,YOU D D,et al.Accurate three-dimensional measurement based on polarization-defocused encoded structured light [J].Measurement,2022,205:112128.
[8]杨东霖.基于深度学习的离焦条纹投影三维测量方法研究[D].南京:南京理工大学,2021.YANG Donglin.Research on 3D measurement method of defocused fringe projection based on deep learning [D].Nanjing:Nanjing University of Science and Technology,2021.
[9]郑瑞卿.基于弱监督的单视图三维重构方法及应用研究[D].北京:北京交通大学,2020.ZHENG Ruiqing.Research on single view 3D reconstruction based on weak supervision and its application [D].Beijing:Beijing Jiaotong University,2020.
[10]ZHU Z M,DONG Y W,XIANG P,et al.Rapid exposure time estimation method for high-dynamic range surface [J].Optik,2023,273:170467.
[11]揭强,符锌砂.高速公路小间距互通立交连接段改造方案研究：以中江高速公路新隆枢纽 ‒港口互通为例 [J/OL].中外公路,1-7[2024 -11-28].https://kns.cnki.net/kcms/detail/ 43.1363.U.20241128.1521.006.html.JIE Qiang,FU Xinsha.Study on reconstruction scheme of expressway small-spacing interchange connecting section:Taking Xinlong hub-port interchange of Zhongjiang Expressway as an example [J/OL ].Journal of China & Foreign Highway,1-7[2024 -11-28].https://kns.cnki.net/kcms/detail/ 43.1363.U.20241128.1521.006.html.
[12]孙朝云,邹鹏,李伟,等.基于 OpenGL 路面裂缝三维重构技术研究 [J].中外公路,2014,34(5):73-76.SUN Zhaoyun,ZOU Peng,LI Wei,et al.Research on 3D reconstruction technology of pavement cracks based on OpenGL [J].Journal of China & Foreign Highway,2014,34(5):73-76.
[13]郝雪丽,孙朝云,李伟,等.基于结构光的路面三维重构技（a） 定检识别的纵向裂纹（b） 定检识别的横向裂纹（c） 定检识别的块修（d） 定检识别的条修图9 道路 数据缺陷 样式图Figure 9 Road data defect styles术[J].计算机工程与设计,2015,36(8):2303 -2307.HAO Xueli,SUN Zhaoyun,LI Wei,et al.3D road reconstruction research based on structured light [J].Computer Engineering and Design,2015,36(8):2303 -2307.
[14]李智,刘健,苏冠宇.基于激光轮廓仪的沥青路面轮廓特征的三维重构技术 [J].公路工程,2019,44(5):47-52.LI Zhi,LIU Jian,SU Guanyu.Three-dimension reconstruction of asphalt pavement contour features based on laser profiler [J].Highway Engineering,2019,44(5):47-52.
[15]黄中文,周飞,王元元.基于改进光度立体技术的路面三维纹理重构测量 [J].公路,2022,67(1):14-18.HUANG Zhongwen,ZHOU Fei,WANG Yuanyuan.Measurement of pavement 3D texture based on improved photometric stereo technique [J].Highway,2022,67(1):14-18.
[16]WANG X Y,ZHU Z M,ZHOU F Q,et al.Complete calibration of a structured light stripe vision sensor through a single cylindrical target [J].Optics and Lasers in Engineering,2020,131:106096.
[17]PAN J W,SHI Z S,MENG X,et al.Reflection characteristics of typical road defects in 3D GPR images for collapse mitigation [J].Journal of Applied Geophysics,2023,217:105166.
[18]金红杰,钟岳,臧利国,等.基于三次样条插值谐波叠加技术的随机路面重构方法研究 [J].振动与冲击,2023,42(10):23-30,143.JIN Hongjie,ZHONG Yue,ZANG Liguo,et al.A study on harmonic superposition method based on cubic spline interpolation of random road reconstruction [J].Journal of Vibration and Shock,2023,42(10):23-30,143.
[19]李晓霞,陈强.三维场景分割中多模态数据融合的 2D-3D耦合网络 [J].计算机时代,2023 (1):17-20,25.LI Xiaoxia,CHEN Qiang.A joint 2D-3D network based on multimodal data fusion for 3D scene semantic segmentation [J].Computer Era,2023 (1):17-20,25.
[20]曾永强,张永华,赵辉,等.高速路侧雷达和相机融合的目标检测与跟踪 [J/OL ].中外公路,1-8[2025 -01-22].https://kns.cnki.net/kcms/detail/ 43.1363.U.20250122.1717.010.html.ZENG Yongqiang,ZHANG Yonghua,ZHAO Hui,et al.Target detection and tracking based on high-speed roadside radar and camera fusion [J/OL ].Journal of China & Foreign Highway,1-8[2025 -01-22].https://kns.cnki.net/kcms/detail/ 43.1363.U.20250122.1717.010.html.
[21]白宇,梁晓玉,安胜彪.深度学习的 2D-3D融合深度补全综述 [J].计算机工程与应用,2023,59(13):17-32.BAI Yu,LIANG Xiaoyu,AN Shengbiao.Review of 2D-3D fusion deep completion of deep learning [J].Computer Engineering and Applications,2023,59(13):17-32.
[22]杨凤满,孙玲,宋向辉,等.面向智慧高速公路数据管理需求的数据元提取方法 [J].公路交通科技,2022,39(增刊 1):116-122.YANG Fengman,SUN Ling,SONG Xianghui,et al.Data element extraction method for data management requirements of smart expressway [J].Journal of Highway and Transportation Research and Development,2022,39(sup 1):116-122.