Constructing a Real-World Benchmark for Early Wildfire Detection with the New PYRONEAR-2025 Dataset

TL;DR

The paper introduces PYRONEAR-2025, a comprehensive wildfire detection dataset with images and videos from multiple countries, designed to improve early wildfire detection models and benchmarks.

Contribution

It presents a large, diverse, and challenging dataset for wildfire detection, including both images and videos, and demonstrates its utility for training and evaluating detection models.

Findings

The dataset surpasses existing datasets in size and diversity.

The dataset is particularly challenging, with an F1 score of around 70%.

Using the dataset with public datasets improves overall detection results.

Abstract

Early wildfire detection (EWD) is of the utmost importance to enable rapid response efforts, and thus minimize the negative impacts of wildfire spreads. To this end, we present PYRONEAR-2025, a new dataset composed of both images and videos, allowing for the training and evaluation of smoke plume detection models, including sequential models. The data is sourced from: (i) web-scraped videos of wildfires from public networks of cameras for wildfire detection in-the-wild, (ii) videos from our in-house network of cameras, and (iii) a small portion of synthetic and real images. This dataset includes around 150,000 manual annotations on 50,000 images, covering 640 wildfires, PYRONEAR-2025 surpasses existing datasets in size and diversity. It includes data from France, Spain, Chile and the United States. Finally, it is composed of both images and videos, allowing for the training and evaluation of smoke plume detection models, including sequential models. We ran cross-dataset experiments using a lightweight state-of-the-art object detection model, as the ones used in-real-life, and found out the proposed dataset is particularly challenging, with F1 score of around 70\%, but more stable than existing datasets. Finally, its use in concordance with other public datasets helps to reach higher results overall. Last but not least, the video part of the dataset can be used to train a lightweight sequential model, improving global recall while maintaining precision for earlier detections. [We make both our code and data available online](https://github.com/joseg20/wildfires2025).