Cover Image

Benchmarking tree species classification from proximally-sensed laser scanning data: introducing the FOR-species20K dataset

Show other versions (1)

Proximally-sensed laser scanning presents new opportunities for automated forest data capture and offers profound insights into forest ecosystems. However, a gap remains in automatically deriving ecologically pertinent forest information, such as tree species, without relying on additional ground da...

Full description

Saved in:
Bibliographic Details
Main Authors: Puliti, Stefano (Author) , Lines, Emily R. (Author) , Müllerová, Jana (Author) , Frey, Julian (Author) , Schindler, Zoe (Author) , Straker, Adrian (Author) , Allen, Matthew J. (Author) , Winiwarter, Lukas (Author) , Rehush, Nataliia (Author) , Hristova, Hristina (Author) , Murray, Brent (Author) , Calders, Kim (Author) , Coops, Nicholas (Author) , Höfle, Bernhard (Author) , Irwin, Liam (Author) , Junttila, Samuli (Author) , Krůček, Martin (Author) , Krok, Grzegorz (Author) , Král, Kamil (Author) , Levick, Shaun R. (Author) , Luck, Linda (Author) , Missarov, Azim (Author) , Mokroš, Martin (Author) , Owen, Harry J. F. (Author) , Stereńczak, Krzysztof (Author) , Pitkänen, Timo P. (Author) , Puletti, Nicola (Author) , Saarinen, Ninni (Author) , Hopkinson, Chris (Author) , Terryn, Louise (Author) , Torresan, Chiara (Author) , Tomelleri, Enrico (Author) , Weiser, Hannah (Author) , Astrup, Rasmus (Author)
Format: Article (Journal) Chapter/Article
Language:English
Published: 12 August 2024
In: Arxiv
Year: 2024, Pages: [1-24]
DOI:10.48550/arXiv.2408.06507
Online Access:Resolving-System, kostenfrei, Volltext: https://doi.org/10.48550/arXiv.2408.06507
Get full text
Author Notes:Stefano Puliti, Emily R. Lines, Jana Müllerová, Julian Frey, Zoe Schindler, Adrian Straker, Matthew J. Allen, Lukas Winiwarter, Nataliia Rehush, Hristina Hristova, Brent Murray, Kim Calders, Louise Terryn, Nicholas Coops, Bernhard Höfle, Samuli Junttila, Martin Krůček, Grzegorz Krok, Kamil Král, Shaun R. Levick, Linda Luck, Azim Missarov, Martin Mokroš, Harry J. F. Owen, Krzysztof Stereńczak, Timo P. Pitkänen, Nicola Puletti, Ninni Saarinen, Chris Hopkinson Chiara Torresan, Enrico Tomelleri, Hannah Weiser, and Rasmus Astrup
Description
Summary:Proximally-sensed laser scanning presents new opportunities for automated forest data capture and offers profound insights into forest ecosystems. However, a gap remains in automatically deriving ecologically pertinent forest information, such as tree species, without relying on additional ground data. Artificial intelligence approaches, particularly deep learning (DL), have shown promise toward automation. However, progress has been limited by the lack of large, diverse, and, most importantly, openly available labelled single tree point cloud datasets. This has hindered both 1) the robustness of the DL models across varying data types (platforms and sensors), and 2) the ability to effectively track progress in DL model development, thereby slowing the convergence towards best practice for species classification.
Item Description:Gesehen am 29.04.2026
Physical Description:Online Resource
DOI:10.48550/arXiv.2408.06507

Similar Items