Pyrovision: wildfire early detection

The increasing adoption of mobile phones have significantly shortened the time required for firefighting agents to be alerted of a starting wildfire. In less dense areas, limiting and minimizing this duration remains critical to preserve forest areas.

Pyrovision aims at providing the means to create a wildfire early detection system with state-of-the-art performances at minimal deployment costs.

Quick Tour

Automatic wildfire detection in PyTorch

You can use the library like any other python package to detect wildfires as follows:

from pyrovision.models import rexnet1_0x
from torchvision import transforms
import torch
from PIL import Image


# Init
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])

tf = transforms.Compose([transforms.Resize(size=(448)), transforms.CenterCrop(size=448),
                         transforms.ToTensor(), normalize])

model = rexnet1_0x(pretrained=True).eval()

# Predict
im = tf(Image.open("path/to/your/image.jpg").convert('RGB'))

with torch.no_grad():
    pred = model(im.unsqueeze(0))
    is_wildfire = torch.sigmoid(pred).item() >= 0.5

Setup

Python 3.6 (or higher) and pip/conda are required to install PyroVision.

Stable release

You can install the last stable release of the package using pypi as follows:

pip install pyrovision

or using conda:

conda install -c pyronear pyrovision

Developer installation

Alternatively, if you wish to use the latest features of the project that haven't made their way to a release yet, you can install the package from source:

git clone https://github.com/pyronear/pyro-vision.git
pip install -e pyro-vision/.

What else

Documentation

The full package documentation is available here for detailed specifications.

Demo app

The project includes a minimal demo app using Gradio

You can check the live demo, hosted on :hugs: HuggingFace Spaces :hugs: over here :point_down:

Docker container

If you wish to deploy containerized environments, a Dockerfile is provided for you build a docker image:

docker build . -t <YOUR_IMAGE_TAG>

Minimal API template

Looking for a boilerplate to deploy a model from PyroVision with a REST API? Thanks to the wonderful FastAPI framework, you can do this easily. Follow the instructions in ./api to get your own API running!

Reference scripts

If you wish to train models on your own, we provide training scripts for multiple tasks! Please refer to the ./references folder if that's the case.

Citation

If you wish to cite this project, feel free to use this BibTeX reference:

@misc{pyrovision2019,
    title={Pyrovision: wildfire early detection},
    author={Pyronear contributors},
    year={2019},
    month={October},
    publisher = {GitHub},
    howpublished = {\url{https://github.com/pyronear/pyro-vision}}
}

Contributing

Please refer to CONTRIBUTING to help grow this project!

License

Distributed under the Apache 2 License. See LICENSE for more information.