Azadi-Khavaran Object Detection Dataset and Pre-Trained Model by Thesis

Images

3568 images

Explore Dataset

Here are a few use cases for this project:

Infrastructure Maintenance: City governments or transport departments can leverage the "Azadi-Khavaran" model for road surface health assessments and identifying areas for road repair. The model may be linked with GIS systems to pinpoint exact locations of pavement distress.
Construction Quality Assurance: Construction companies can use the model to assess the quality of newly paved streets or surfaces. The timely identification of rutting or corrugation can help avoid future costly repairs.
Urban Planning: The model can provide valuable data for urban planning purposes. With the ability to identify pavement distresses, urban planners can make informed decisions regarding road infrastructure improvement and development.
Autonomous Vehicles: Self-driving car companies can utilize the model in their sensor suite to detect road damages, helping to improve navigation, planning alternative routes, and ensuring safety.
Mobile Application: A mobile application could use this model to help the public report infrastructure faults. Users can snap a photo of the street, and the application can then classify the type of distress and automatically report it to the appropriate municipality or city council.

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{ azadi-khavaran_dataset,
    title = { Azadi-Khavaran Dataset },
    type = { Open Source Dataset },
    author = { Thesis },
    howpublished = { \url{ https://universe.roboflow.com/thesis-x90jz/azadi-khavaran } },
    url = { https://universe.roboflow.com/thesis-x90jz/azadi-khavaran },
    journal = { Roboflow Universe },
    publisher = { Roboflow },
    year = { 2023 },
    month = { jan },
    note = { visited on 2023-12-08 },
}