MillionTrees: A global benchmark for tree detection across geography, sensor, and annotation geometry
Year: 2026
Type: preprint
Abstract: Airborne tree monitoring using remotely sensed data, combined with the growth of computer vision models for object detection and segmentation, can facilitate broad scale assessment of tree health, ecology and ecosystem function. However, datasets for airborne tree detection have been largely limited to a single geography, resolution, or annotation approach, making it difficult to develop general models and benchmark their utility for broad applications. We compile existing and newly published annotation datasets to create a comprehensive dataset for training and evaluating airborne tree detection in RGB imagery. The MillionTrees dataset has over a million individual trees from a broad range of forest types, tree species, and geographic locations. In addition, it has six million weakly supervised annotations from a range of sources including airborne LiDAR and photogrammetry, arborist surveys, and simulated landscapes. An evaluation standard is provided to facilitate rapid model development. We benchmark several existing tree detection algorithms and demonstrate that while current open-source models do not generalize across the diverse datasets in the benchmark, training on MillionTrees improves both within-domain and out-of-domain performance. Held-out validation datasets using ground truth derived from terrestrial LiDAR paired with overhead RGB show that overfitting to test data is common and hyperparameter tuning is an underappreciated challenge towards a global zero shot tree detection method. We discuss the limitations of the currently available data for airborne RGB tree detection, how to create more robust evaluation data and the need for better understanding of the uncertainty and utility of tree detection from airborne remote sensing.
Authors: Ben G. Weinstein, Josh Veitch-Michaelis, Matt J. Allen, Adison Altamirano, Sarah Anacleto, Rasmus Astrup, James G. C. Ball, Hugo Baudchon, Sara Beery, Stephanie A. Bohlman, John Brandt, Myriam Cloutier, Simon-Olivier Duguay, Jessica Ertel, Zhengpeng Feng, Adnan Firoze, Julian Frey, G. Andrew Fricker, Dimitri Gominski, Sarah Graves, Stuart W. D. Grieve, Sander de Haas, Sebastian H. M. Hickman, Tobias D. Jackson, Andrew Jansen, Teja Kattenborn, Taimur Khan, Ryoungseob Kwon, Kyaw Kyaw Htoo, Etienne Laliberté, Isabelle Lefebvre, Emily R. Lines, Moritz Lucas, Alejandro Miranda, Blas Mola-Yudego, Maurice Mugabowindekwe, Jaylen Nicholson, Masanori Onishi, Yusuke Onoda, Arthur Ouaknine, Harry J. F. Owen, Camille Pawlak, Stefano Puliti, Md. Farhadur Rahman, David J. Russell, Oliver Schütte, Henry Senyondo, Yihang She, Ying Sun, Ryuichi Takeshige, Jonas Troles, Vicente Vasquez, Jonathan Ventura, Benjamin Wagner, Qinchuan Xin, Qiue Xu, Derek J. N. Young, Pedro Zamboni, Ethan P. White
Institutions: University of Florida, University of Cambridge, Universidad de La Frontera, Norwegian Institute of Bioeconomy Research, Université de Montréal, Massachusetts Institute of Technology, World Resources Institute, Purdue University West Lafayette, University of Freiburg, California Polytechnic State University, University of Copenhagen, University of Wisconsin–Madison, Queen Mary University of London, University of Bristol, Helmholtz Centre for Environmental Research, Seoul National University, Kyoto University, Osnabrück University, University of Eastern Finland, Australian National University, Mila - Quebec Artificial Intelligence Institute, University of California, Los Angeles, University of California, Davis, Sun Yat-sen University, University of Bamberg, The University of Melbourne, Chinese Academy of Sciences, Institute of Subtropical Agriculture, Technische Universität Dresden
Language: English
Subfield: Environmental Engineering
Field: Environmental Science
Domain: Physical Sciences
SDG: Life on land
Open Access status: green
OpenAlex ID: W7225128084