metadata
license: mit
language:
- en
Tree Crown Detection in RGB Airborne Imagery
The model was initially described in Remote Sensing on a single site. The prebuilt model uses a semi-supervised approach in which millions of moderate quality annotations are generated using a LiDAR unsupervised tree detection algorithm, followed by hand-annotations of RGB imagery from select sites. Comparisons among geographic sites were added to Ecological Informatics. The model was further improved, and the Python package was released in Methods in Ecology and Evolution.
- Repository: https://github.com/weecology/DeepForest
- Paper : https://www.sciencedirect.com/science/article/pii/S157495412030011X
- Demo : https://huggingface.co/spaces/weecology/deepforest-demo
How to Get Started with the Model
Use the code below to get started with the model.
from deepforest import main
from deepforest import get_data
from deepforest.visualize import plot_results
# Initialize the model class
model = main.deepforest()
# Load a pretrained tree detection model from Hugging Face
model.load_model(model_name="weecology/deepforest-tree", revision="main")
sample_image_path = get_data("OSBS_029.png")
img = model.predict_image(path=sample_image_path)
plot_results(img)
Citation
@article{WEINSTEIN2020101061,
title = {Cross-site learning in deep learning RGB tree crown detection},
journal = {Ecological Informatics},
volume = {56},
pages = {101061},
year = {2020},
issn = {1574-9541},
doi = {https://doi.org/10.1016/j.ecoinf.2020.101061},
url = {https://www.sciencedirect.com/science/article/pii/S157495412030011X},
author = {Ben G. Weinstein and Sergio Marconi and Stephanie A. Bohlman and Alina Zare and Ethan P. White},
Model Card Authors
Ben G. Weinstein, Sergio Marconi, Stephanie A. Bohlman, Alina Zare and Ethan P. White