treeX

Separates individual trees from laser scans without any trained model.

Field
Forestry & vegetation
Method
Classical method
Data it takes
point-cloud
License
MIT

treeX segments trees from terrestrial, personal and drone laser scans using geometric rules rather than learned weights. There is no training step, and no pretrained model whose training data may not match the target forest.

This makes it applicable to stand types the deep learning segmenters have not encountered, and provides a baseline for comparison. Runs on CPU.

Upstream project →

Catalog entry last checked 2026-08-18. All models →

Run treeX on your data

The lab runs this on its own compute, in a container, with the inputs and parameters recorded alongside the result. Initial scoping conversations are free.

Contact the Lab