Saved in:
Bibliographic Details
Main Authors: Gominski, Dimitri, Ortiz-Gonzalo, Daniel, Brandt, Martin, Mugabowindekwe, Maurice, Fensholt, Rasmus
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.15816
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910580946763776
author Gominski, Dimitri
Ortiz-Gonzalo, Daniel
Brandt, Martin
Mugabowindekwe, Maurice
Fensholt, Rasmus
author_facet Gominski, Dimitri
Ortiz-Gonzalo, Daniel
Brandt, Martin
Mugabowindekwe, Maurice
Fensholt, Rasmus
contents Individual tree species labels are particularly hard to acquire due to the expert knowledge needed and the limitations of photointerpretation. Here, we present a methodology to automatically mine species labels from public forest inventory data, using available pretrained tree detection models. We identify tree instances in aerial imagery and match them with field data with close to zero human involvement. We conduct a series of experiments on the resulting dataset, and show a beneficial effect when adding noisy or even unlabeled data points, highlighting a strong potential for large-scale individual species mapping.
format Preprint
id arxiv_https___arxiv_org_abs_2408_15816
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Mining Field Data for Tree Species Recognition at Scale
Gominski, Dimitri
Ortiz-Gonzalo, Daniel
Brandt, Martin
Mugabowindekwe, Maurice
Fensholt, Rasmus
Computer Vision and Pattern Recognition
Individual tree species labels are particularly hard to acquire due to the expert knowledge needed and the limitations of photointerpretation. Here, we present a methodology to automatically mine species labels from public forest inventory data, using available pretrained tree detection models. We identify tree instances in aerial imagery and match them with field data with close to zero human involvement. We conduct a series of experiments on the resulting dataset, and show a beneficial effect when adding noisy or even unlabeled data points, highlighting a strong potential for large-scale individual species mapping.
title Mining Field Data for Tree Species Recognition at Scale
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.15816