Datasets¶

There are three datasets within the MillionTrees package: TreeBoxes, TreePoints, and TreePolygons. These datasets contain many source datasets from dozens of papers and research efforts. Below, each source is briefly described. The images for each dataset are generated directly from the dataloaders to allow rapid verification of the annotation status and are regenerated automatically when a new dataset is released or updated.

Boxes¶

Kwon et al. 2023¶

sample_image

Citation: Ryoungseob Kwon, Youngryel Ryu, Tackang Yang, Zilong Zhong, Jungho Im,
Merging multiple sensing platforms and deep learning empowers individual tree mapping and species detection at the city scale,
ISPRS Journal of Photogrammetry and Remote Sensing, Volume 206, 2023

Location: Suwon, South Korea

Ragadoshi_Sweden¶

sample_image

Link: https://lila.science/datasets/forest-damages-larch-casebearer/

Location: Sweden

Sun et al. 2022¶

sample_image

Link: https://www.sciencedirect.com/science/article/pii/S030324342100369X

Santos et al. 2019¶

sample_image

Link: Dataset Ninja

@Article{s19163595, AUTHOR = {Santos, Anderson Aparecido dos and Marcato Junior, José and Araújo, Márcio Santos and Di Martini, David Robledo and Tetila, Everton Castelão and Siqueira, Henrique Lopes and Aoki, Camila and Eltner, Anette and Matsubara, Edson Takashi and Pistori, Hemerson and Feitosa, Raul Queiroz and Liesenberg, Veraldo and Gonçalves, Wesley Nunes}, TITLE = {Assessment of CNN-Based Methods for Individual Tree Detection on Images Captured by RGB Cameras Attached to UAVs}, JOURNAL = {Sensors}, VOLUME = {19}, YEAR = {2019}, NUMBER = {16}, ARTICLE-NUMBER = {3595}, URL = {https://www.mdpi.com/1424-8220/19/16/3595}, DOI = {10.3390/s19163595} }

Location: Barro Colorado Island, Panama

Velasquez-Camacho et al. 2023¶

sample_image

Link: https://zenodo.org/records/10246449

Location: Spain

Weinstein et al. 2021¶

sample_image

Link: https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1009180

Location NEON sites within the United States

An extension of this published resource was made by the Weecology Lab at the University of Florida

sample_image

World Resources Institute¶

NAIP Imagery from across the United States

sample_image

Zamboni et al. 2022¶

sample_image

Link: https://github.com/pedrozamboni/individual_urban_tree_crown_detection

Location: Mato Grosso do Sul, Brazil

Points¶

Amirkolaee et al. 2023¶

sample_image

Citation: Amirkolaee, Hamed Amini, Miaojing Shi, and Mark Mulligan.
TreeFormer: a Semi-Supervised Transformer-based Framework for Tree Counting from a Single High Resolution Image.
IEEE Transactions on Geoscience and Remote Sensing (2023)

Link: https://github.com/HAAClassic/TreeFormer

Location: London, England

Ventura et al. 2022¶

sample_image

Citation: J. Ventura, C. Pawlak, M. Honsberger, C. Gonsalves, J. Rice, N.L.R. Love, S. Han, V. Nguyen, K. Sugano, J. Doremus, G.A. Fricker, J. Yost, and M. Ritter.
Individual Tree Detection in Large-Scale Urban Environments using High-Resolution Multispectral Imagery.
International Journal of Applied Earth Observation and Geoinformation, 130, 103848 (2024)

Link: https://github.com/jonathanventura/urban-tree-detection-data

Location: Southern California, United States

National Ecological Observatory Network¶

sample_image

Location: Multiple sites across the United States, see NEON Field Sites

Link: https://data.neonscience.org/data-products/DP1.10098.001

Tonga Trees¶

sample_image

Location: Tonga

Link: The provenance of this project is unclear, it was used several times in ArcGIS tutorials, but no citation was given.

https://learn.arcgis.com/en/projects/detect-objects-with-a-deep-learning-pretrained-model/

Polygons¶

Araujo et al. 2020¶

sample_image

Link: [https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0243079][https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0243079]

Location: Manuas, Brazil