metadata

title: CEA List FrugalAI Challenge
emoji: 🔥
colorFrom: red
colorTo: yellow
sdk: docker
pinned: false

YOLO for Early Fire Detection

Team

Renato Sortino
Aboubacar Tuo
Charles Villard
Nicolas Allezard
Nicolas Granger
Angélique Loesch
Quoc-Cuong Pham

Model Description

YOLO model for early fire detection in forests, proposed as a solution for the Frugal AI Challenge 2025, image task.

Intended Use

Primary intended uses:
Primary intended users:
Out-of-scope use cases:

Training Data

The model uses the pyronear/pyro-sdis dataset:

Size: ~33000 examples
Split: 80% train, 20% test
Images annotated with bounding boxes in correspondence of wildfire instances

Labels

Smoke

Performance

Metrics

Accuracy: ~83%
Environmental Impact:
- Emissions tracked in gCO2eq
- Energy consumption tracked in Wh

Model Architecture

The model is a YOLO-based object detection model, that does not depend on NMS in inference. Bypassing this operation allows for further optimization at inference time via tensor decomposition and quantization

Environmental Impact

Environmental impact is tracked using CodeCarbon, measuring:

Carbon emissions during inference
Energy consumption during inference

This tracking helps establish a baseline for the environmental impact of model deployment and inference.

Limitations

It may fail to generalize to night scenes or foggy settings
It is subject to false detections, especially at low confidence thresholds