The detectree2_2023 from 0scarj1ang

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.

Detectree2是一个基于Mask R-CNN的自动树冠检测与分割的Python包。您可以在model_garden中选择预训练模型。这里提供了如何准备数据、训练模型和进行预测的教程。如果有任何问题，合作提案或者需要样例数据，可以邮件联系James Ball。一些示例数据可以在这里下载。

_{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.
MRes project repo available here.}

Warning
Due to an influx of new users we have been hitting bandwidth limits. This is primarily from the file size of the pre-trained models. If you are using these models please aim to save them locally and point to them when you need them rather than downloading them each time they are required. We will move to a more bandwidth friendly set up soon. In the meantime, if installing the package is failing please raise it as an issue or notify me directly on [email protected].

Please cite

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. https://doi.org/10.1002/rse2.332

Requirements

Python 3.8+
gdal geospatial libraries
PyTorch ≥ 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.

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.

Independent validation

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, Yi, Quan Wang, and Atsuhiro Iio. (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

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

├── LICENSE
├── Makefile
├── README.md
├── detectree2
│   ├── data_loading
│   ├── models
│   ├── preprocessing
│   ├── R
│   └── tests
├── docs
│   └── source
├── model_garden
├── notebooks
│   ├── colab
│   ├── colabJB
│   ├── colabJH
│   ├── colabKoay
│   ├── colabPan
│   ├── colabSeb
│   ├── exploratory
│   ├── mask_rcnn
│   │   ├── testing
│   │   └── training
│   ├── reports
│   └── turing
├── report
│   ├── figures
│   └── sections
└── 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.

0scarj1ang / detectree2_2023 Goto Github PK

detectree2_2023's Introduction