Update README.md

README.md

@@ -12,7 +12,7 @@ short_description: YOLO for low-emission Early Fire Detection
 
 # YOLO for Early Fire Detection
 
-## Team
+## Team ([CEA List, LVA](https://kalisteo.cea.fr/index.php/ai/))
 - Renato Sortino
 - Aboubacar Tuo
 - Charles Villard
@@ -23,46 +23,42 @@ short_description: YOLO for low-emission Early Fire Detection
 
 ## 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**: 
+YOLO model for early fire detection in forests, proposed as a solution for the [Frugal AI Challenge 2025](https://frugalaichallenge.org/), image task. 
 
 ## 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
-0. Smoke
+The model uses the following datasets:
+| Dataset | Number of samples | Number of instances | 
+|----------|----------|----------|
+| [pyronear/pyro-sdis](https://huggingface.co/datasets/pyronear/pyro-sdis) | 29,537 | 28,167 |
+| [D-Fire](https://github.com/gaiasd/DFireDataset) | 10,525 | 11,865 |
+| [Wildfire Smoke Dataset](https://www.kaggle.com/datasets/gloryvu/wildfire-smoke-detection/data) | ~12,300 | 11,539  |
+| [Hard Negatives](https://github.com/aiformankind/wildfire-smoke-dataset) | ~5,000 | ~5,000 |
+| Synthetic Dataset | ~5,000 | ~5,000 |
 
 ## 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
+Bypassing this operation allows for further optimization at inference time via tensor decomposition.
 
-## Environmental Impact
+### Metrics
+| Model | Accuracy | Precision | Recall | meanIoU | Wh | gCO2eq
+|----------|----------|----------|----------|----------|----------|----------|
+| YOLOv10s | 0.87 | 0.88 | 0.98 | 0.84 | 6.77 | 0.94 |
+| YOLOv10m | 0.88 | 0.87 | 0.99 | 0.88 | 8.39 | 1.16 |
+| YOLOv10m + Spatial-SVD | 0.85 | 0.86 | 0.97 | 0.82 | 8.24 | 1.14 |
 
-Environmental impact is tracked using CodeCarbon, measuring:
-- Carbon emissions during inference
-- Energy consumption during inference
+Environmental impact is tracked using [CodeCarbon](https://codecarbon.io/), measuring:
+- Carbon emissions during inference (gCO2eq)
+- Energy consumption during inference (Wh)
 
 This tracking helps establish a baseline for the environmental impact of model deployment and inference.
 
-## Limitations
+## Limitations and future work
 - It may fail to generalize to night scenes or foggy settings
 - It is subject to false detections, especially at low confidence thresholds
+- Clouds at ground level can be misinterpreted as smoke
+- It would be better to use temporal-aware models trained on videos
 
 ```