Home › AI & machine learning › BatiScan IA
BatiScan IA QGIS 4 compatibility
Not QGIS 4 ready Active
Not yet — the latest version declares max QGIS version 3.99.0, so it is not offered to QGIS 4 users.
AI building mapping for QGIS: detect building footprints on satellite imagery (no points needed), or turn field-collected building points into footprints with Segment Anything.
About
BatiScan maps buildings from satellite or aerial imagery with AI. The automatic mode uses the BatiScan Sahel v6 model, a U-Net trained on villages of Mali and on open building footprints from West Africa (30 cm/px), from round huts to rectangular metal and earth roofs. It separates adjacent buildings, draws straight footprints that never overlap, and flags objects that look like the surrounding ground for review. On 20 hand-checked test zones in two villages kept out of training, it found about 89 percent of the buildings, and about 94 percent of its objects were correct. The model (98 MB) is downloaded on first use and is provided for research and testing, not for commercial use. BatiScan also turns building points collected in the field into footprints with Segment Anything (MobileSAM in ONNX, no PyTorch needed), offers a click-to-map tool, a points-versus-footprints quality report, and export of image/mask tiles to train a model for your own area. Any Deepness-compatible ONNX segmentation model can be added. Works with GeoTIFF orthophotos and XYZ/WMS basemaps (Google, Bing, Esri...). Requires the Python packages onnxruntime and opencv, which the plugin offers to install on first use. Less accurate on dense urban areas and very large buildings. Walled yards and flat earth roofs can be confused at this resolution.
| Author | Allaye GUINDO |
|---|---|
| Downloads | 146 |
| Latest version | 0.5.1 |
| Last updated | 2026-11-05 (7 days ago) |
| Min QGIS | 3.38.0 |
| Max QGIS | 3.99.0 |
| QGIS 4 ready | No |
| Maintenance | Active |
| Category | AI & machine learning |
| Tags | building, buildings, footprint, ai, deep learning, segment anything, sam, onnx, segmentation, remote sensing, africa, sahel, mali, bâtiment |
Homepage · Repository · Issue tracker · Official page
Alternatives in AI & machine learning
Raster classification in QGIS with 11 machine learning algorithms, Optuna hyperparameter search, SHAP explanations, class imbalance handling
- ArcGeek CalculatorQGIS 4 ready
ArcGeek Calculator is a QGIS plugin that provides a comprehensive set of tools for coordinate calculations, conversions, spatial operations,
- Bunting Labs AI VectorizerQGIS 4 ready
Autocomplete for vectorizing and georeferencing raster maps.
Related plugins
- AITracer by LADQGIS 4 ready
Click any feature on a georeferenced raster and SAM2 segments it instantly. Refine with positive/negative prompts, then accept to create a v
- GeoOSAMQGIS 4 ready
AI-powered segmentation for QGIS - SAM2.1 & SAM3 with text prompts, similar object detection, vector ROI, and professional GIS workflow feat
- TreeEyedNot QGIS 4 ready
TreeEyed is a QGIS plugin for tree monitoring using AI.
- SamGeoQGIS 4 ready
Segment remote sensing images using SAM (Segment Anything Model) with text, point, and box prompts.
- Geo SAMQGIS 4 ready
Segment Landform with Segment-Anything AI Model (SAM)
- AI Segmentation by TerraLabQGIS 4 ready
AI segmentation in QGIS 3.22 to 4. Draw a zone, name an object and get every building footprint, tree or solar panel as vector polygons, or
Maintenance: Active = updated within 1 year, Quiet = 1–3 years, Likely abandoned = over 3 years.