{"title":"RDD2022:用于道路损坏自动检测的多国图像数据集","authors":"Deeksha Arya, Hiroya Maeda, Sanjay Kumar Ghosh, Durga Toshniwal, Yoshihide Sekimoto","doi":"10.1002/gdj3.260","DOIUrl":null,"url":null,"abstract":"<p>The data article describes the Road Damage Dataset, RDD2022, encompassing of 47,420 road images from majorly six countries, Japan, India, the Czech Republic, Norway, the United States, and China. The dataset incorporates over 55,000 instances of road damage, specifically longitudinal cracks, transverse cracks, alligator cracks, and potholes. Designed to facilitate the development of deep learning methodologies for automated road damage detection and classification, RDD2022 was unveiled as part of the Crowd sensing-based Road Damage Detection Challenge (CRDDC'2022), with a major contribution from the challenge winners. This challenge garnered global participation, urging researchers to propose solutions for automatic road damage detection in multiple countries. A noteworthy outcome of CRDDC'2022 was the emergence of a top-performing model achieving a remarkable F1 Score of 76.9% for road damage detection in all six countries using RDD2022. This success underscores the dataset's practical applicability for municipalities and road agencies, enabling low-cost, automatic monitoring of road conditions. Beyond its immediate utility, RDD2022 stands as a valuable benchmark for researchers in computer vision, geoscience, and machine learning, offering a rich resource for algorithmic evaluation in diverse image-based applications, including classification and object detection. The latest big data cup, Optimized Road Damage Detection Challenge (ORDDC'2024), is also based on RDD2022, underscoring its continued relevance and pivotal role in current research and development endeavors.</p>","PeriodicalId":54351,"journal":{"name":"Geoscience Data Journal","volume":null,"pages":null},"PeriodicalIF":3.3000,"publicationDate":"2024-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/gdj3.260","citationCount":"0","resultStr":"{\"title\":\"RDD2022: A multi-national image dataset for automatic road damage detection\",\"authors\":\"Deeksha Arya, Hiroya Maeda, Sanjay Kumar Ghosh, Durga Toshniwal, Yoshihide Sekimoto\",\"doi\":\"10.1002/gdj3.260\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>The data article describes the Road Damage Dataset, RDD2022, encompassing of 47,420 road images from majorly six countries, Japan, India, the Czech Republic, Norway, the United States, and China. The dataset incorporates over 55,000 instances of road damage, specifically longitudinal cracks, transverse cracks, alligator cracks, and potholes. Designed to facilitate the development of deep learning methodologies for automated road damage detection and classification, RDD2022 was unveiled as part of the Crowd sensing-based Road Damage Detection Challenge (CRDDC'2022), with a major contribution from the challenge winners. This challenge garnered global participation, urging researchers to propose solutions for automatic road damage detection in multiple countries. A noteworthy outcome of CRDDC'2022 was the emergence of a top-performing model achieving a remarkable F1 Score of 76.9% for road damage detection in all six countries using RDD2022. This success underscores the dataset's practical applicability for municipalities and road agencies, enabling low-cost, automatic monitoring of road conditions. Beyond its immediate utility, RDD2022 stands as a valuable benchmark for researchers in computer vision, geoscience, and machine learning, offering a rich resource for algorithmic evaluation in diverse image-based applications, including classification and object detection. The latest big data cup, Optimized Road Damage Detection Challenge (ORDDC'2024), is also based on RDD2022, underscoring its continued relevance and pivotal role in current research and development endeavors.</p>\",\"PeriodicalId\":54351,\"journal\":{\"name\":\"Geoscience Data Journal\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.3000,\"publicationDate\":\"2024-06-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1002/gdj3.260\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Geoscience Data Journal\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/gdj3.260\",\"RegionNum\":3,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"GEOSCIENCES, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Geoscience Data Journal","FirstCategoryId":"89","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/gdj3.260","RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"GEOSCIENCES, MULTIDISCIPLINARY","Score":null,"Total":0}
RDD2022: A multi-national image dataset for automatic road damage detection
The data article describes the Road Damage Dataset, RDD2022, encompassing of 47,420 road images from majorly six countries, Japan, India, the Czech Republic, Norway, the United States, and China. The dataset incorporates over 55,000 instances of road damage, specifically longitudinal cracks, transverse cracks, alligator cracks, and potholes. Designed to facilitate the development of deep learning methodologies for automated road damage detection and classification, RDD2022 was unveiled as part of the Crowd sensing-based Road Damage Detection Challenge (CRDDC'2022), with a major contribution from the challenge winners. This challenge garnered global participation, urging researchers to propose solutions for automatic road damage detection in multiple countries. A noteworthy outcome of CRDDC'2022 was the emergence of a top-performing model achieving a remarkable F1 Score of 76.9% for road damage detection in all six countries using RDD2022. This success underscores the dataset's practical applicability for municipalities and road agencies, enabling low-cost, automatic monitoring of road conditions. Beyond its immediate utility, RDD2022 stands as a valuable benchmark for researchers in computer vision, geoscience, and machine learning, offering a rich resource for algorithmic evaluation in diverse image-based applications, including classification and object detection. The latest big data cup, Optimized Road Damage Detection Challenge (ORDDC'2024), is also based on RDD2022, underscoring its continued relevance and pivotal role in current research and development endeavors.
Geoscience Data JournalGEOSCIENCES, MULTIDISCIPLINARYMETEOROLOGY-METEOROLOGY & ATMOSPHERIC SCIENCES
CiteScore
5.90
自引率
9.40%
发文量
35
审稿时长
4 weeks
期刊介绍:
Geoscience Data Journal provides an Open Access platform where scientific data can be formally published, in a way that includes scientific peer-review. Thus the dataset creator attains full credit for their efforts, while also improving the scientific record, providing version control for the community and allowing major datasets to be fully described, cited and discovered.
An online-only journal, GDJ publishes short data papers cross-linked to – and citing – datasets that have been deposited in approved data centres and awarded DOIs. The journal will also accept articles on data services, and articles which support and inform data publishing best practices.
Data is at the heart of science and scientific endeavour. The curation of data and the science associated with it is as important as ever in our understanding of the changing earth system and thereby enabling us to make future predictions. Geoscience Data Journal is working with recognised Data Centres across the globe to develop the future strategy for data publication, the recognition of the value of data and the communication and exploitation of data to the wider science and stakeholder communities.