EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Assessment of Pine Tree Crown Delineation Algorithms on UAV Data: From K-Means Clustering to CNN Segmentation

Ali Hosingholizade, Yousef Erfanifard, Seyed Kazem Alavipanah, Virginia Elena Garcia Millan, Miłosz Mielcarek, Saied Pirasteh, Krzysztof Stereńczak

Forests · 24.01.2025 · 16 (2) · 228

DOI: 10.3390/f16020228 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Forests, online erschienen am 24.01.2025. Verfasst von Ali Hosingholizade und 6 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 81 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Iran National Science Foundation (INSF), Iran.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The crown area is a critical metric for evaluating tree growth and supporting various ecological and forestry analyses. This study compares three approaches, i.e., unsupervised clustering, region-based, and deep learning, to estimate the crown area of Pinus eldarica Medw. using UAV-acquired RGB imagery (2 cm ground sampling distance) and high-density point clouds (1.27 points/cm3). The first approach applied unsupervised clustering techniques, such as Mean-shift and K-means, to directly estimate crown areas, bypassing tree top detection. The second employed a region-based approach, using Template Matching and Local Maxima (LM) for tree top identification, followed by Marker-Controlled Watershed (MCW) and Seeded Region Growing for crown delineation. The third approach utilized a Convolutional Neural Network (CNN) that integrated Digital Surface Model layers with the Visible Atmospheric Resistance Index for enhanced segmentation. The results were compared against field measurements and manual digitization. The findings reveal that CNN and MCW with LM were the most effective, particularly for small and large trees, though performance decreased for medium-sized crowns. CNN provided the most accurate results overall, with a relative root mean square error (RRMSE) of 8.85%, a Nash–Sutcliffe Efficiency (NSE) of 0.97, and a bias score (BS) of 1.00. The CNN crown area estimates showed strong correlations (R2 = 0.83, 0.62, and 0.94 for small, medium, and large trees, respectively) with manually digitized references. This study underscores the value of advanced CNN techniques for precise crown area and shape estimation, highlighting the need for future research to refine algorithms for improved handling of crown size variability.

Förderung

  • Iran National Science Foundation (INSF), Iran

Zitieren

APA

Hosingholizade, A., Erfanifard, Y., Alavipanah, S. K., Millan, V. E. G., Mielcarek, M., Pirasteh, S., & Stereńczak, K. (2025). Assessment of Pine Tree Crown Delineation Algorithms on UAV Data: From K-Means Clustering to CNN Segmentation. Forests, 16(2), 228. https://doi.org/10.3390/f16020228

Vancouver

Hosingholizade A, Erfanifard Y, Alavipanah SK, Millan VEG, Mielcarek M, Pirasteh S, et al. Assessment of Pine Tree Crown Delineation Algorithms on UAV Data: From K-Means Clustering to CNN Segmentation. Forests. 2025;16(2):228. doi:10.3390/f16020228

BibTeX
@article{Hosingholizade2025,
  author = {Hosingholizade, Ali and Erfanifard, Yousef and Alavipanah, Seyed Kazem and Millan, Virginia Elena Garcia and Mielcarek, Miłosz and Pirasteh, Saied and Stereńczak, Krzysztof},
  title = {Assessment of Pine Tree Crown Delineation Algorithms on UAV Data: From K-Means Clustering to CNN Segmentation},
  journal = {Forests},
  year = {2025},
  volume = {16},
  number = {2},
  pages = {228},
  doi = {10.3390/f16020228}
}
Kostenlos starten →