IGN BdOrtho imagery was used to train a YOLO large model for solar panel detection. The resulting model is available on Hugging Face and its performance can be seen on a MapRoulette project. The dataset author is listed as Cyrille37.
Use Cases
- Train object detection models based on satellite imagery mentioned in the description
- Benchmark solar panel detection algorithms based on the described YOLO model results
- Map renewable energy infrastructure based on the detection of solar panels
- Validate remote sensing models based on the MapRoulette project results
Strengths
- Model trained on the dataset is described as having 'very good results'
- A YOLO large model was successfully trained using this dataset
- Results are publicly available for review on a MapRoulette project
Limitations
- Description metadata is limited; actual data quality requires manual inspection after download
- Column-level documentation is absent; field semantics must be inferred after download
- Row count is unknown, which may limit suitability assessment
Provenance
- Source
- huggingface
- Collection Method
- A YOLO large model was trained with this dataset on IGN BdOrtho imagery.
- Freshness
- Last updated 2026-03-26 22:05:08; freshness should be verified
- Geography
- Likely France, based on the use of IGN (Institut National de l'Information Géographique et Forestière) BdOrtho imagery.