Road Safety Object Detection Dataset and Pre-Trained Model by Pothole Detection

Images

3319 images

Explore Dataset

Here are a few use cases for this project:

Predictive Road Maintenance: This use case involves using the "Road Safety" CV model to scan and analyze roads for potholes, bumps, and road hazards. The findings can be used to prioritize road repair schedules.
Autonomous Vehicle Navigation: The model can be implemented in self-driving cars to detect and navigate around potholes and road hazards, ensuring a safer, smoother ride.
Bicycle Route Planning: Cyclists and bikers can use this computer vision model to plan safer, smoother bicycle routes by avoiding roads with potholes and bumps.
Municipal Reporting: City government can employ this technology in a mobile application, where citizens take pictures of problematic roads, then the application uses the "Road Safety" model to identify the issue and forward the information to the appropriate department.
Insurance Claims: The model can assist insurance companies in assessing the validity of vehicle damage claims related to roads' conditions, reducing fraud by verifying the presence of damaging potholes in submitted images or videos.

Trained Model API

This project has a trained model available that you can try in your browser and use to get predictions via our Hosted Inference API and other deployment methods.

Cite This Project

If you use this dataset in a research paper, please cite it using the following BibTeX:

@misc{
                            road-safety-nhzti_dataset,
                            title = { Road Safety Dataset },
                            type = { Open Source Dataset },
                            author = { Pothole Detection },
                            howpublished = { \url{ https://universe.roboflow.com/pothole-detection-fkzac/road-safety-nhzti } },
                            url = { https://universe.roboflow.com/pothole-detection-fkzac/road-safety-nhzti },
                            journal = { Roboflow Universe },
                            publisher = { Roboflow },
                            year = { 2022 },
                            month = { nov },
                            note = { visited on 2024-04-29 },
                            }