Early detection of wildfires

Pyronear is an open-source project for the common good

More information

Who are we?

Pyronear is a non-profit NGO whose objective is to democratize open and low-tech solutions for fighting wildfires, for the benefit of the ecosystems and the citizens. To achieve this goal, we are co-building an early detection solution that is open source, efficient, automatic, energy-efficient, economical and modular

Card icon

Open source

All our code is available for free and co-developed by our volunteers. We believe that collective intelligence is the best way to solve a complex problem.

Card icon

Early detection

To fight effectively against wildfires, it is important to detect them early in order to allow a quick intervention of fire and rescue services and thus limit their impact.

Card icon


Our AI experts actively follow the news in this fast-moving field in order to make Pyronear benefit from its latest advances.

Card icon


We offer a fully automated solution to free up firefighters' time.

Card icon

Energetically sober

We are in a so-called low-tech approach, we have built a low-consumption device allowing an easier deployment and a more reasoned use of our precious resources.

Card icon


Our R&D is done by volunteers, our device is sober and the non-profit object of our association, which allows us to propose very competitive prices to facilitate a deployment on the territory.

Card icon


We offer a complete detection pipeline but our system has been designed to work with existing equipment (use of cameras already in place, connection with existing software ...)

How does it work?

Pyronear is a complete fire risk management solution. It consists of an early wildfire detection algorithm, implemented on a microcomputer, connected to cameras positioned on high spots with a view on the forest. Our detectors communicate fire alerts to a database that is connected to a supervision platform for the fire department.


Our detection towers consist of 4/5 high resolution cameras and a micro computer. We capture one image per camera at regular intervals and then analyze it locally using our wildfire detection model. In case of detection, the alert mode is activated, all the images coming from the camera having detected the fire are then sent to our database via our api, the communication protocol we have developed.


How to deploy it?

To get more information, reach us by email or on social networks. We will get back to you as soon as possible.

Contact us

Who do we work with?

SDIS 07-logo


Our first partner for requirements gathering and field experimentation

Engie Green-logo

Engie Green

Our first private partner, with whom we are conducting an experiment in Gironde



The Chilean National Center of Artificial Intelligence with whom we are working for our first deployment abroad

ADF Subirats-logo

ADF Subirats

Our catalan partner for the adaptation of our device to existing cameras

FORCE 06-logo


Our partner in the department of Alpes Maritimes to diversify field tests

Who supports us?

Data for Good-logo

Data for Good

Part of the 6th, 8th and 10th acceleration seasons of Data for Good, it is the birth place of Pyronear



A stakeholder for rescue innovation, and our point of contact with firefighters

Fondation M33-logo

Fondation M33

Who supports us humanly and financially through corporate sponsorship



Which helps us with its human resources and its connection with the academic world



Who supports us through Etalab and the Citizen Initiative Accelerator



Which supports us financially via its endowment fund and provides its financial expertise

They talk about us

Follow the Pyronear adventure

To stay updated about our progress or to join the adventure, you can also reach us on social media!