RDD2020: An Image Dataset for Smartphone-based Road Damage Detection and Classification
收藏资源简介：
The RDD2020 dataset contains 26336 road images collected from India, Japan, and the Czech Republic with more than 31000 instances of road damage. The dataset contains annotation for four damage categories: Longitudinal Cracks(D00), Transverse Cracks(D10), Alligator Cracks(D20), and Potholes(D40); and is intended for developing deep learning-based methods to detect and classify road damage automatically. The images in RDD2020 were captured using vehicle-mounted smartphones, making it useful for municipalities and road agencies to develop methods for low-cost monitoring of road pavement surface conditions. Further, the machine learning researchers can use the datasets for benchmarking the performance of different algorithms for solving other problems of the same type (classification, object detection, etc.). For instance, the Global Road Damage Detection Challenge (GRDDC'2020), organized as an IEEE Big Data Cup in 2020, utilized the dataset RDD2020 to evaluate the road damage detection models proposed by the participants. An overview of the challenge is provided in the video https://www.youtube.com/watch?v=8sh70wjn1aI. The readers may access the latest updates and the articles related to the dataset at https://www.researchgate.net/project/Global-Road-Damage-Detection.
RDD2020数据集共包含26336张道路图像，采集自印度、日本与捷克共和国，涵盖超过31000个道路损伤实例。该数据集标注了四类道路损伤：纵向裂缝（Longitudinal Cracks, D00）、横向裂缝（Transverse Cracks, D10）、龟裂（Alligator Cracks, D20）与坑槽（Potholes, D40），旨在研发基于深度学习的自动化道路损伤检测与分类方法。RDD2020中的图像均通过车载智能手机采集，可帮助市政部门与道路管理机构研发低成本的道路路面状况监测方案。此外，机器学习研究者可利用该数据集对各类算法的性能进行基准测试，以解决同类问题（如分类、目标检测等）。例如，2020年以IEEE大数据杯（IEEE Big Data Cup）形式举办的全球道路损伤检测挑战赛（Global Road Damage Detection Challenge, GRDDC'2020），就采用RDD2020数据集对参赛者提出的道路损伤检测模型进行评估。该挑战赛的概况可通过视频https://www.youtube.com/watch?v=8sh70wjn1aI查看。读者可通过链接https://www.researchgate.net/project/Global-Road-Damage-Detection获取该数据集的最新动态与相关研究文章。
