dimas Object Detection Dataset and Pre-Trained Model by new school

Images

646 images

Explore Dataset

Here are a few use cases for this project:

Pothole Detection in Infrastructure Repair Industry: The "dimas" model can be used by public works organizations, construction companies, or driveway repair services to identify different types of potholes in roads or other surfaces. The model can help determine the size and depth, thus aiding in repair planning and cost estimation.
Autonomous Vehicle Navigation: "dimas" can be used in autonomous driving systems to identify and classify holes in roadways, enhancing the safety and operational efficiency. The model will allow the self-driving cars to avoid major holes, adjust speed or maneuver accordingly around minor ones.
Geological and Archaeological Study: Researchers can use this model to study different types of natural and infrastructural anomalies like sinkholes, pits or cave entrances. The model can help scientists and archaeologists to distinguish between different hole classes in their explorations.
Urban Planning and Civil Engineering: The "dimas" model can assist in urban planning and development projects where it's essential to know the type of ground anomalies, helping in designing better infrastructure and determining risk zones.
Drone Surveillance and Inspection: Drones equipped with this model can provide real-time data about holes in difficult-to-access terrains, buildings, or structures. It can be useful in industries like mining, oil and gas extraction, or search and rescue operations.

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{
                            dimas_dataset,
                            title = { dimas Dataset },
                            type = { Open Source Dataset },
                            author = { new school },
                            howpublished = { \url{ https://universe.roboflow.com/new-school/dimas } },
                            url = { https://universe.roboflow.com/new-school/dimas },
                            journal = { Roboflow Universe },
                            publisher = { Roboflow },
                            year = { 2023 },
                            month = { jan },
                            note = { visited on 2024-05-16 },
                            }