Deep learning based individual tree crown delineation from panchromatic aerial imagery

Accurate delineation of individual tree crowns (ITC) enables a better understanding of tree-level growth dynamics and evaluating tree vitality. In recent year, researches have introduced deep learning techniques in this field. However, the precise segmentation relies on high quality annotated datase...

Full description

Saved in:
Bibliographic Details
Main Authors: J. Tian, D. Panangian, W. Fan, B. Siegmann, X. Yuan
Format: Article
Language:English
Published: Copernicus Publications 2025-07-01
Series:ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://isprs-annals.copernicus.org/articles/X-G-2025/885/2025/isprs-annals-X-G-2025-885-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849432399128035328
author J. Tian
J. Tian
D. Panangian
W. Fan
B. Siegmann
X. Yuan
author_facet J. Tian
J. Tian
D. Panangian
W. Fan
B. Siegmann
X. Yuan
author_sort J. Tian
collection DOAJ
description Accurate delineation of individual tree crowns (ITC) enables a better understanding of tree-level growth dynamics and evaluating tree vitality. In recent year, researches have introduced deep learning techniques in this field. However, the precise segmentation relies on high quality annotated dataset and test images with limited domain gaps between the training data. Under the framework of the Helmholtz project, panchromatic airborne images are captured over a mixed European forest. In this research, we adopt a UAV benchmark dataset as training data. To close the domain gaps, a deep learning based colorization step is added, for which two deep learning frameworks are compared to achieve an improved ITC delineation result in a dense forest area.
format Article
id doaj-art-01bf389535b444fb9c368451dae6cd32
institution Kabale University
issn 2194-9042
2194-9050
language English
publishDate 2025-07-01
publisher Copernicus Publications
record_format Article
series ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj-art-01bf389535b444fb9c368451dae6cd322025-08-20T03:27:22ZengCopernicus PublicationsISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences2194-90422194-90502025-07-01X-G-202588589210.5194/isprs-annals-X-G-2025-885-2025Deep learning based individual tree crown delineation from panchromatic aerial imageryJ. Tian0J. Tian1D. Panangian2W. Fan3B. Siegmann4X. Yuan5Remote Sensing Technology Institute, German Aerospace Center (DLR), Oberpfaffenhofen, GermanyInstitute of Forest Management, TUM School of Life Sciences Weihenstephan, Technical University of Munich, Freising, GermanyRemote Sensing Technology Institute, German Aerospace Center (DLR), Oberpfaffenhofen, GermanyInstitute of Forest Management, TUM School of Life Sciences Weihenstephan, Technical University of Munich, Freising, GermanyInstitute for Bio- and Geosciences, Forschungszentrum Jülich GmbH, Jülich, GermanyRemote Sensing Technology Institute, German Aerospace Center (DLR), Oberpfaffenhofen, GermanyAccurate delineation of individual tree crowns (ITC) enables a better understanding of tree-level growth dynamics and evaluating tree vitality. In recent year, researches have introduced deep learning techniques in this field. However, the precise segmentation relies on high quality annotated dataset and test images with limited domain gaps between the training data. Under the framework of the Helmholtz project, panchromatic airborne images are captured over a mixed European forest. In this research, we adopt a UAV benchmark dataset as training data. To close the domain gaps, a deep learning based colorization step is added, for which two deep learning frameworks are compared to achieve an improved ITC delineation result in a dense forest area.https://isprs-annals.copernicus.org/articles/X-G-2025/885/2025/isprs-annals-X-G-2025-885-2025.pdf
spellingShingle J. Tian
J. Tian
D. Panangian
W. Fan
B. Siegmann
X. Yuan
Deep learning based individual tree crown delineation from panchromatic aerial imagery
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title Deep learning based individual tree crown delineation from panchromatic aerial imagery
title_full Deep learning based individual tree crown delineation from panchromatic aerial imagery
title_fullStr Deep learning based individual tree crown delineation from panchromatic aerial imagery
title_full_unstemmed Deep learning based individual tree crown delineation from panchromatic aerial imagery
title_short Deep learning based individual tree crown delineation from panchromatic aerial imagery
title_sort deep learning based individual tree crown delineation from panchromatic aerial imagery
url https://isprs-annals.copernicus.org/articles/X-G-2025/885/2025/isprs-annals-X-G-2025-885-2025.pdf
work_keys_str_mv AT jtian deeplearningbasedindividualtreecrowndelineationfrompanchromaticaerialimagery
AT jtian deeplearningbasedindividualtreecrowndelineationfrompanchromaticaerialimagery
AT dpanangian deeplearningbasedindividualtreecrowndelineationfrompanchromaticaerialimagery
AT wfan deeplearningbasedindividualtreecrowndelineationfrompanchromaticaerialimagery
AT bsiegmann deeplearningbasedindividualtreecrowndelineationfrompanchromaticaerialimagery
AT xyuan deeplearningbasedindividualtreecrowndelineationfrompanchromaticaerialimagery