Description

The Road Damage Dataset, RDD2022, is released as a part of the Crowdsensing-based Road Damage Detection Challenge (CRDDC'2022), an IEEE BigData Cup. It comprises 47,420 road images from six countries, Japan, India, the Czech Republic, Norway, the United States, and China. The images have been annotated with more than 55,000 instances of road damage. Four types of road damage, namely longitudinal cracks, transverse cracks, alligator cracks, and potholes, are captured in the dataset.

Usage

The annotated dataset is envisioned for developing deep learning-based methods to detect and classify road damage automatically. The municipalities and road agencies may utilize the RDD2022 dataset, and the models trained using RDD2022 for low-cost automatic monitoring of road conditions. Further, computer vision and machine learning researchers may use the dataset to benchmark the performance of different algorithms for other image-based applications of the same type (classification, object detection, etc.).

For further details, please refer to the CRDDC'2022 resources.

RDD2022

## Overview

RDD2022 is a dataset for object detection tasks - it contains Object_detect annotations for 4,804 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

The RDD2022 dataset contains road images from six countries (India, Japan, Czech Republic, Norway, China, and USA). However, in the presented dataset, four damage types were considered. There are many road defects in road networks. The edited and updated dataset is called N-RDD2024. 10 different types of defects were considered in this dataset. The defect classes labeled are longitudinal cracks (D00), transverse cracks (D10), alligator cracks (D20), repaired cracks (D30), potholes (D40), pedestrian crossing blurs (D50), lane line blurs (D60), manhole covers (D70), patchy road sections (D80) and rutting (D90), respectively. The process of detecting and classifying all defects in road pavement will become more robust for institutions/organizations and researchers.

Road damage detection is of great significance to traffic safety and road maintenance. However, the existing target detection technology still has shortcomings in accuracy, real-time and adaptability. In order to meet this challenge, this study constructed SEA-YOLO v8 model for road damage detection. Firstly, the SBS module is constructed to optimize the computational complexity, achieve real-time target detection under limited hardware resources, successfully reduce the model parameters, and make the model more lightweight; Secondly, we integrate the EMA attention mechanism module into the neck component, enabling the model to utilize feature information from different layers, enabling the model to selectively focus on key areas and improve feature representation; Then, an adaptive attention feature pyramid structure is proposed to enhance the feature fusion capability of the network; Finally, lightweight shared convolutional detection head (LSCD-Head) is introduced to improve feature representation and reduce the number of parameters. The experimental results on the RDD2022 dataset show that the SEA-YOLO v8 model has achieved 63.2% mAP50. The performance is better than yolov8 model and mainstream target detection model. This shows that in complex urban traffic scenarios, the model has high detection accuracy and adaptability, can accurately locate and detect road damage, save manpower and material resources, provide guidance for road damage assessment and maintenance, and promote the sustainable development of urban roads.

YOLOv8 Rdd2022

## Overview

YOLOv8 Rdd2022 is a dataset for object detection tasks - it contains Road Damage annotations for 274 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Created from https://github.com/sekilab/RoadDamageDetector
for more details about the dataset you can visit: https://www.researchgate.net/publication/363668453_RDD2022_A_multinational_image_dataset_for_automatic_Road_Damage_Detection

AI Pothole Detection

https://datasetninja.com/road-pothole-images [uploaded] https://datasetninja.com/road-damage https://universe.roboflow.com/intel-unnati-training-program/pothole-detection-bqu6s https://figshare.com/articles/dataset/RDD2022_-_The_multi-national_Road_Damage_Dataset_released_through_CRDDC_2022/21431547

PotholeDetectionRDD2022

## Overview

PotholeDetectionRDD2022 is a dataset for object detection tasks - it contains POTHOLE annotations for 38,384 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [Public Domain license](https://creativecommons.org/licenses/Public Domain).

Dataset

This dataset was created by Khaled Abdelgaber

Contents

rdd raw dataset

The Road Damage Dataset 2020 (RDD-2020) Secondly is a large-scale heterogeneous dataset comprising 26620 images collected from multiple countries using smartphones. The images are collected from roads in India, Japan and the Czech Republic.

RDD2022_China_Drone

## Overview

RDD2022_China_Drone is a dataset for object detection tasks - it contains Road Damage annotations for 2,393 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

RDD2022_Drone

## Overview

RDD2022_Drone is a dataset for object detection tasks - it contains Crack Ngnf annotations for 2,510 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

RDD2022_china_drone 2

## Overview

RDD2022_china_drone 2 is a dataset for object detection tasks - it contains Distress PCJx annotations for 3,030 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Roboscout_rdd2022_subset

## Overview

Roboscout_rdd2022_subset is a dataset for instance segmentation tasks - it contains Potholes annotations for 23,471 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).