Autonomous Driving Challenge


Instance Segmentation

Racetrack Computer Vision Project

Drop an image or


4163 images
Explore Dataset

Here are a few use cases for this project:

  1. Autonomous Vehicle Navigation: The "Racetrack" could be used in the development of self-driving cars for navigating racetracks. This could be especially useful for companies developing autonomous racing cars for competitions like Roborace. The system could identify cars, pitlane entry & exit, and obstacles, informing the autonomous systems on the appropriate actions to take.

  2. Racing Game Development: Game developers could use the "Racetrack" model to generate realistic and dynamic environments for racing video games, by accurately interpreting and simulating real-world racing conditions like free/occupied parking and racer positions based on the pitlane.

  3. Race Analytics: Sports broadcasters or racing teams could use this model for real-time or post-racing analysis. By identifying different elements like vehicles, obstacles, or the finish line, it could provide insightful data such as obstacle avoidance tactics, pitlane entry & exit strategies, or the precise moment a race was won.

  4. Race Event Management: Event organizers could use this model to monitor and manage large racetrack events. The system could keep track of parking occupation, the position of staff, and vehicles, thus improving the accuracy and efficiency of event management.

  5. Surveillance & Security: Racetrack authorities could use this model to enhance their overall security by identifying unauthorized persons or vehicles, detecting suspicious activities around the pitlane or in the parking areas, and maintaining traffic flow by recognizing obstacles and blocked routes.

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:

                            title = { Racetrack Dataset },
                            type = { Open Source Dataset },
                            author = { Autonomous Driving Challenge },
                            howpublished = { \url{ } },
                            url = { },
                            journal = { Roboflow Universe },
                            publisher = { Roboflow },
                            year = { 2024 },
                            month = { jan },
                            note = { visited on 2024-03-04 },

Connect Your Model With Program Logic

Find utilities and guides to help you start using the Racetrack project in your project.

Last Updated

2 months ago

Project Type

Instance Segmentation




car cross_parking_free cross_parking_occupied ego_vehicle finish_line obstacle person pitlane pitlane_entry pitlane_exit racetrack vertical_parking_free vertical_parking_occupied

Views: 531

Views in previous 30 days: 22

Downloads: 13

Downloads in previous 30 days: 0


CC BY 4.0