API serving our trained YOLOv8 detection model
Streamlit web app with our integrated fire&smoke detector for emergency services

WildfireApp is an application designed to help users detect and report wildfires quickly and reliably. It uses state-of-the-art computer vision technology to detect fire and smoke in images, providing crucial information to emergency services.

• File Upload: Users can upload images containing potential wildfire scenes.
• Camera Input: Users can use their phone's camera to capture and analyze images in real-time.
• Fire and Smoke Detection: Our application uses a custom-trained YOLOv8 model to detect fire and smoke in images.
• Geolocation: If available, the application displays the GPS coordinates of the image, helping emergency services locate the fire.
• Weather Information: Users can access potentially crucial weather data related to the detected fire's location, including wind speed and direction.
• User-Friendly Interface: The user interface is simple and intuitive, making it easy for anyone to use.

Contributions from the community are welcome! If you'd like to contribute to this project, please follow these guidelines:

1. Fork the repository on GitHub.
2. Clone your forked repository to your local machine.
3. Make your changes and test them thoroughly.
4. Create a pull request with a clear description of your changes.

Thanks to the open-source providers for the tools and libraries that made this project possible.

• D-Fire Dataset, built by: Pedro Vinícius Almeida Borges de Venâncio, Adriano Chaves Lisboa, Adriano Vilela Barbosa: An automatic fire detection system based on deep convolutional neural networks for low-power, resource-constrained devices. In: Neural Computing and Applications, 2022.

• The WildfireApp detector is built around a custom-trained YOLOv8-L model