Python package for automatic tree crown delineation based on Mask R-CNN. Pre-trained models can be picked in the model_garden
.
A tutorial on how to prepare data, train models and make predictions is available here. For questions, collaboration proposals and requests for data email James Ball. Some example data is available for download here.
Detectree2ๆฏไธไธชๅบไบMask R-CNN็่ชๅจๆ ๅ ๆฃๆตไธๅๅฒ็Pythonๅ
ใๆจๅฏไปฅๅจmodel_garden
ไธญ้ๆฉ้ข่ฎญ็ปๆจกๅใ่ฟ้ๆไพไบๅฆไฝๅๅคๆฐๆฎใ่ฎญ็ปๆจกๅๅ่ฟ่ก้ขๆต็ๆ็จใๅฆๆๆไปปไฝ้ฎ้ข๏ผๅไฝๆๆกๆ่
้่ฆๆ ทไพๆฐๆฎ๏ผๅฏไปฅ้ฎไปถ่็ณปJames Ballใไธไบ็คบไพๆฐๆฎๅฏไปฅๅจ่ฟ้ไธ่ฝฝใ
Code developed by James Ball, Seb Hickman, Thomas Koay, Oscar Jiang, Luran Wang, Panagiotis Ioannou, James Hinton and Matthew Archer in the Forest Ecology and Conservation Group at the University of Cambridge. The Forest Ecology and Conservation Group is led by Professor David Coomes and is part of the University of Cambridge Conservation Research Institute. |
---|
Note
To save bandwidth trained models have been moved to Zenodo. Download models directly with wget
or equivalent.
Citation
Please cite this article if you use detectree2 in your work:
Ball, J.G.C., Hickman, S.H.M., Jackson, T.D., Koay, X.J., Hirst, J., Jay, W., Archer, M., Aubry-Kientz, M., Vincent, G. and Coomes, D.A. (2023), Accurate delineation of individual tree crowns in tropical forests from aerial RGB imagery using Mask R-CNN. Remote Sens Ecol Conserv. 9(5):641-655. https://doi.org/10.1002/rse2.332
Independent validation
Independent validation has been performed on a temperate deciduous forest in Japan.
Detectree2 (F1 score: 0.57) outperformed DeepForest (F1 score: 0.52)
Detectree2 could estimate tree crown areas accurately, highlighting its potential and robustness for tree detection and delineation
Gan, Y., Wang, Q., and Iio, A. (2023). Tree Crown Detection and Delineation in a Temperate Deciduous Forest from UAV RGB Imagery Using Deep Learning Approaches: Effects of Spatial Resolution and Species Characteristics. Remote Sensing. 15(3):778. https://doi.org/10.3390/rs15030778
Requirements
- Python 3.8+
- gdal geospatial libraries
- PyTorch โฅ 1.8 and torchvision versions that match
- For training models GPU access (with CUDA) is recommended
e.g.
pip3 install torch torchvision torchaudio
Installation
pip
pip install git+https://github.com/PatBall1/detectree2.git
Currently works on Google Colab (Pro version recommended). May struggle on clusters if geospatial libraries are not configured. See Installation Instructions if you are having trouble.
conda
Under development
Getting started
Detectree2, based on the Detectron2 Mask R-CNN architecture, locates trees in aerial images. It has been designed to delineate trees in challenging dense tropical forests for a range of ecological applications.
This tutorial takes you through the key steps. Example Colab notebooks are also available but are not updated frequently so functions and parameters may need to be adjusted to get things working properly.
The standard workflow includes:
- Tile the orthomosaics and crown data (for training, validation and testing)
- Train (and tune) a model on the training tiles
- Evaluate the model performance by predicting on the test tiles and comparing to manual crowns for the tiles
- Using the trained model to predict the crowns over the entire region of interest
Training crowns are used to teach the network to delineate tree crowns.
Here is an example image of the predictions made by Detectree2.
Applications
Tracking tropical tree growth and mortality
Counting urban trees (Buffalo, NY)
Multi-temporal tree crown segmentation
Liana detection and infestation mapping
In development
Tree species identification and mapping
In development
To do
- Functions for multiple labels vs single "tree" label
Project Organization
โโโ LICENSE
โโโ Makefile
โโโ README.md
โโโ detectree2
โย ย โโโ data_loading
โย ย โโโ models
โย ย โโโ preprocessing
โย ย โโโ R
โย ย โโโ tests
โโโ docs
โย ย โโโ source
โโโ model_garden
โโโ notebooks
โย ย โโโ colab
โย ย โโโ colabJB
โย ย โโโ colabJH
โย ย โโโ colabKoay
โย ย โโโ colabPan
โย ย โโโ colabSeb
โย ย โโโ exploratory
โย ย โโโ mask_rcnn
โย ย โย ย โโโ testing
โย ย โย ย โโโ training
โย ย โโโ reports
โย ย โโโ turing
โโโ report
โย ย โโโ figures
โย ย โโโ sections
โโโ requirements
Code formatting
To automatically format your code, make sure you have black
installed (pip install black
) and call
black .
from within the project directory.
Copyright (c) 2022, James G. C. Ball