Python package for automatic tree crown delineation based on the Detectron2 implementation of Mask R-CNN
MIT License
Models moved from repo to Zenodo to resolve bandwidth issues
Published by PatBall1 about 1 year ago
Multi-temporal prediction combination.
Multi-class outputs.
Published by PatBall1 over 1 year ago
Some changes to how the file paths are constructed in tile_data
to allow more flexibility for non-conventional crs
Published by PatBall1 over 1 year ago
to_traintest_function
tweaked to support cases where there is limited available data. It is now possible to not reserve any data for testing (keeping it all for training/validation). Through the strict
argument it is also possible to control whether no overlap in the buffer of training/validation tiles and test tiles is enforced.
This flexibility should help users who have limited data to train on.
Published by PatBall1 over 1 year ago
Minor updates to the clean_crown
function to help handle crs and indexing issues
Published by PatBall1 over 1 year ago
Some fixes to the tile_data_train
function were implemented to stop misalignment on tiles along the edge of a raster scene
Published by PatBall1 over 1 year ago
Some cleaning of the repo to align with publication in Remote Sensing in Ecology and Conservation
Published by PatBall1 over 1 year ago
clean_crowns
function now:
Updated notes in the tutorial help guide clean/useful outputs
Published by PatBall1 over 1 year ago
First full release of detectree2
Full Changelog: https://github.com/PatBall1/detectree2/compare/dtree...1.0