DetecTree

DetecTree: Tree detection from aerial imagery in Python - Published in JOSS (2020)

https://github.com/martibosch/detectree

Science Score: 93.0%

This score indicates how likely this project is to be science-related based on various indicators:

○
CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
✓
DOI references
Found 11 DOI reference(s) in README and JOSS metadata
✓
Academic publication links
Links to: joss.theoj.org, zenodo.org
○
Committers with academic emails
○
Institutional organization owner
✓
JOSS paper metadata
Published in Journal of Open Source Software

Keywords

image-segmentation python remote-sensing tree-canopy tree-detection tree-pixels

Scientific Fields

Mathematics Computer Science - 84% confidence

Last synced: 4 months ago · JSON representation

Repository

Tree detection from aerial imagery in Python

Basic Info

Host: GitHub
Owner: martibosch
License: gpl-3.0
Language: Python
Default Branch: main
Homepage: https://doi.org/10.21105/joss.02172
Size: 4.93 MB

Statistics

Stars: 267
Watchers: 6
Forks: 35
Open Issues: 6
Releases: 10

Topics

image-segmentation python remote-sensing tree-canopy tree-detection tree-pixels

Created over 6 years ago · Last pushed 4 months ago

Metadata Files

Readme Changelog Contributing License

DetecTree

Overview

DetecTree is a Pythonic library to perform semantic segmentation of aerial imagery into tree/non-tree pixels, following the methods of Yang et al. [1]. A pre-trained model is available at Hugging Face hub, which can be used as follows:

```python from urllib import request

import detectree as dtr import matplotlib.pyplot as plt import rasterio as rio from rasterio import plot

download a tile from the SWISSIMAGE WMS

tileurl = ( "https://wms.geo.admin.ch/?SERVICE=WMS&REQUEST=GetMap&VERSION=1.3.0&" "FORMAT=image/png&LAYERS=ch.swisstopo.images-swissimage&CRS=EPSG:2056" "&BBOX=2532980,1152150,2533380,1152450&WIDTH=800&HEIGHT=600" ) tilefilename = "tile.png" request.urlretrieve(tileurl, tilefilename)

use the pre-trained model to segment the image into tree/non-tree-pixels

ypred = dtr.Classifier().predictimg(tile_filename)

side-by-side plot of the tile and the predicted tree/non-tree pixels

figwidth, figheight = plt.rcParams["figure.figsize"] fig, axes = plt.subplots(1, 2, figsize=(2 * figwidth, figheight)) with rio.open(tilefilename) as src: plot.show(src, ax=axes[0]) axes[1].imshow(ypred) ```

Pre-trained example

Alternatively, you can use detectree to train your own model on your aerial imagery dataset:

```python import detectree as dtr import matplotlib.pyplot as plt import rasterio as rio from rasterio import plot

select the training tiles from the tiled aerial imagery dataset

ts = dtr.TrainingSelector(imgdir='data/tiles') splitdf = ts.traintestsplit(method='cluster-I')

train a tree/non-tree pixel classifier

clf = dtr.ClassifierTrainer().trainclassifier( splitdf=splitdf, responseimgdir='data/responsetiles')

use the trained classifier to predict the tree/non-tree pixels

testfilepath = splitdf[~splitdf['train'].sample(1).iloc[0]['img_filepath'] ypred = dtr.Classifier(clf=clf).classifyimg(testfilepath)

side-by-side plot of the tile and the predicted tree/non-tree pixels

figwidth, figheight = plt.rcParams['figure.figsize'] fig, axes = plt.subplots(1, 2, figsize=(2 * figwidth, figheight))

with rio.open(imgfilepath) as src: plot.show(src.read(), ax=axes[0]) axes[1].imshow(ypred) ```

Example

A full example application of DetecTree to predict a tree canopy map for the Aussersihl district in Zurich is available as a Jupyter notebook. See also the API reference documentation and the examples repository for more information on the background and some example notebooks.

The target audience is researchers and practitioners in GIS that are interested in two-dimensional aspects of trees, such as their proportional abundance and spatial distribution throughout a region of study. These measurements can be used to assess important aspects of urban planning such as the provision of urban ecosystem services. The approach is of special relevance when LIDAR data is not available or it is too costly in monetary or computational terms.

Citation

Bosch M. 2020. “DetecTree: Tree detection from aerial imagery in Python”. Journal of Open Source Software, 5(50), 2172. doi.org/10.21105/joss.02172

Note that DetecTree is based on the methods of Yang et al. [1], therefore it seems fair to reference their work too. An example citation in an academic paper might read as follows:

The classification of tree pixels has been performed with the Python library DetecTree (Bosch, 2020), which is based on the approach of Yang et al. (2009).

Installation

With conda

The easiest way to install detectree is with conda as in:

bash conda install -c conda-forge detectree

With pip

You can install detectree with pip as in:

bash pip install detectree

If you want to be able to read compressed LAZ files, you will need the Python bindings for laszip. Note that the latter require [laszip], which can be installed using conda (which is automatically handled when installing detectree with conda as shown above) or downloaded from laszip.org. Then, detectree and the Python bindings for laszip can be installed with pip as in:

bash pip install detectree[laszip]

Development install

To install a development version of detectree, you can first use conda to create an environment with all the dependencies - with the environment-dev.yml file - and activate it as in:

bash conda env create -f environment-dev.yml conda activate detectree-dev

and then clone the repository and use pip to install it in development mode

bash git clone git@github.com:martibosch/detectree.git cd detectree/ pip install -e .

This will also install the dependencies required for running tests, linting the code and building the documentation. Additionally, you can activate pre-commit so that the latter are run as pre-commit hooks as in:

bash pre-commit install

Acknowledgments

With the support of the École Polytechnique Fédérale de Lausanne (EPFL)

References

Yang, L., Wu, X., Praun, E., & Ma, X. (2009). Tree detection from aerial imagery. In Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (pp. 131-137). ACM.

Owner

Name: Martí Bosch
Login: martibosch
Kind: user
Location: Lausanne
Company: EPFL

Website: https://fosstodon.org/@martibosch
Twitter: mortybosch
Repositories: 83
Profile: https://github.com/martibosch

Doctor in civil and environmental engineering. Urban sprawl, Python, and a bit of landscape ecology and complexity

JOSS Publication

DetecTree: Tree detection from aerial imagery in Python

Published

June 25, 2020

DOI

10.21105/joss.02172

Volume 5, Issue 50, Page 2172

Authors

Martí Bosch

Urban and Regional Planning Community, École Polytechnique Fédérale de Lausanne, Switzerland

Editor

Kristen Thyng

GitHub Events

Total

Create event: 4
Issues event: 2
Release event: 2
Watch event: 33
Issue comment event: 1
Push event: 74
Fork event: 5

Last Year

Create event: 4
Issues event: 2
Release event: 2
Watch event: 33
Issue comment event: 1
Push event: 74
Fork event: 5

Committers

Last synced: 5 months ago

All Time

Total Commits: 130
Total Committers: 2
Avg Commits per committer: 65.0
Development Distribution Score (DDS): 0.008

Past Year

Commits: 41
Committers: 1
Avg Commits per committer: 41.0
Development Distribution Score (DDS): 0.0

Top Committers

Name	Email	Commits
Martí Bosch	m**h@p**m	129
Kristen Thyng	k**g@g**m	1

Issues and Pull Requests

Last synced: 4 months ago

All Time

Total issues: 13
Total pull requests: 21
Average time to close issues: 2 months
Average time to close pull requests: 6 days
Total issue authors: 9
Total pull request authors: 4
Average comments per issue: 2.92
Average comments per pull request: 0.43
Merged pull requests: 5
Bot issues: 0
Bot pull requests: 19

Past Year

Issues: 1
Pull requests: 0
Average time to close issues: 3 months
Average time to close pull requests: N/A
Issue authors: 1
Pull request authors: 0
Average comments per issue: 1.0
Average comments per pull request: 0
Merged pull requests: 0
Bot issues: 0
Bot pull requests: 0

View more stats

Top Authors

Issue Authors

rmsare (3)
MisterB92 (2)
easz (2)
jehontan (1)
ligaofeng0901 (1)
wittylife (1)
Ayushri (1)
tadolphi (1)
pedromarcolin (1)

Pull Request Authors

dependabot[bot] (15)
pre-commit-ci[bot] (4)
kthyng (1)
martibosch (1)

Top Labels

Issue Labels

Pull Request Labels

dependencies (15)

Packages

Total packages: 3
Total downloads:
- pypi 815 last-month

Total dependent packages: 0
(may contain duplicates)
Total dependent repositories: 4
(may contain duplicates)
Total versions: 30
Total maintainers: 1

proxy.golang.org: github.com/martibosch/detectree

Documentation: https://pkg.go.dev/github.com/martibosch/detectree#section-documentation
License: gpl-3.0
Latest release: v0.8.1
published 5 months ago

Versions: 13
Dependent Packages: 0
Dependent Repositories: 0

Rankings

Stargazers count: 3.8%

Forks count: 4.5%

Average: 4.9%

Dependent packages count: 5.4%

Dependent repos count: 5.7%

Last synced: 4 months ago

pypi.org: detectree

Tree detection from aerial imagery in Python.

Documentation: https://detectree.readthedocs.io/
License: GPL-3.0
Latest release: 0.8.1
published 5 months ago

Versions: 13
Dependent Packages: 0
Dependent Repositories: 3
Downloads: 815 Last month

Rankings

Stargazers count: 5.5%

Dependent packages count: 7.3%

Forks count: 7.6%

Dependent repos count: 9.1%

Average: 10.1%

Downloads: 20.9%

Maintainers (1)

martibosch

Last synced: 4 months ago

conda-forge.org: detectree

Homepage: https://github.com/martibosch/detectree
License: GPL-3.0-or-later
Latest release: 0.4.2
published about 3 years ago

Versions: 4
Dependent Packages: 0
Dependent Repositories: 1

Rankings

Dependent repos count: 24.1%

Stargazers count: 31.4%

Forks count: 35.3%

Average: 35.6%

Dependent packages count: 51.5%

Last synced: 4 months ago

Dependencies

.github/workflows/release.yml actions

actions/checkout v4 composite
actions/download-artifact v3 composite
actions/setup-python v4 composite
actions/upload-artifact v3 composite
heinrichreimer/github-changelog-generator-action v2.1.1 composite
pypa/gh-action-pypi-publish release/v1 composite
softprops/action-gh-release v1 composite

.github/workflows/tests.yml actions

actions/checkout v4 composite
codecov/codecov-action v3 composite
mamba-org/setup-micromamba v1 composite

pyproject.toml pypi

dask [delayed,distributed]
joblib *
laspy >= 2.0.0
numpy >= 1.15
opencv-python >= 4.0.0
pandas >= 0.23
pymaxflow >= 1.0.0
rasterio >= 1.0.0
scikit-image *
scikit-learn *
scipy >= 1.0.0
tqdm *

docs/requirements.txt pypi

m2r2 ==0.3.3
pydata-sphinx-theme ==0.15.2
sphinx ==7.2.6
sphinx_click ==5.01
sphinxcontrib.bibtex ==2.6.2

DetecTree

Science Score: 93.0%

Keywords

Scientific Fields

Repository

Basic Info

Statistics

Topics

Metadata Files

README.md

DetecTree

Overview

download a tile from the SWISSIMAGE WMS

use the pre-trained model to segment the image into tree/non-tree-pixels

side-by-side plot of the tile and the predicted tree/non-tree pixels

select the training tiles from the tiled aerial imagery dataset

train a tree/non-tree pixel classifier

use the trained classifier to predict the tree/non-tree pixels

side-by-side plot of the tile and the predicted tree/non-tree pixels

Citation

Installation

With conda

With pip

Development install

See also

Acknowledgments

References

Owner

JOSS Publication

DetecTree: Tree detection from aerial imagery in Python

Authors

Editor

Tags

GitHub Events

Total

Last Year

Committers

All Time

Past Year

Top Committers

Issues and Pull Requests

All Time

Past Year

Top Authors

Issue Authors

Pull Request Authors

Top Labels

Issue Labels

Pull Request Labels

Packages

proxy.golang.org: github.com/martibosch/detectree

Rankings

pypi.org: detectree

Rankings

Maintainers (1)

conda-forge.org: detectree

Rankings

Dependencies