PatBall1/detectree2

Python package for automatic tree crown delineation based on the Detectron2 implementation of Mask R-CNN

73
/ 100
Verified

Supports both RGB and multispectral aerial imagery with pre-trained models available in the model garden. Built on Detectron2's Mask R-CNN architecture, it performs instance segmentation to delineate individual tree crowns in dense forests through a tiling workflow for large orthomosaics. Integrates with geospatial libraries (GDAL, rasterio) and PyTorch/Detectron2, with GPU acceleration recommended for training custom models on labeled crown datasets.

238 stars and 249 monthly downloads. Available on PyPI.

Maintenance 10 / 25
Adoption 16 / 25
Maturity 25 / 25
Community 22 / 25

How are scores calculated?

Stars

238

Forks

58

Language

Python

License

MIT

Last pushed

Feb 14, 2026

Monthly downloads

249

Commits (30d)

0

Dependencies

11

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/PatBall1/detectree2"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.