EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Individual Urban Tree Detection from Multispectral Satellite Imagery via Point-Supervised Deep Learning

Thomas Martinoli, Luca Morandini, Piero Fraternali

Remote Sensing · 17.06.2026 · 18 (12) · 2021

DOI: 10.3390/rs18122021 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 17.06.2026. Verfasst von Thomas Martinoli und 2 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union-Next Generation EU, Italian Ministry of University and Research.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Monitoring urban biodiversity is essential for designing resilient and sustainable cities. Urban trees provide a wide range of ecosystem services (ESs), including air pollution reduction, urban heat island mitigation, and psychological benefits for citizens. Accurate and updated tree inventories are therefore essential tools for urban environmental monitoring. However, existing urban tree inventories are often incomplete or outdated, especially in private areas, limiting accurate ES assessment and urban planning. Earth observation satellite missions, particularly very-high-resolution multispectral (VHR-MS) imagery, offer a valuable alternative to field surveys for gathering information on urban environments. This work proposes a deep learning (DL) framework based on VHR-MS satellite imagery for the automatic generation of accurate urban tree inventories. DL models reduce human effort and save operational time by automatically learning complex representations and patterns from satellite imagery. The proposed encoder–decoder architecture extends prior point-based detection approaches by integrating a ResNet-50 backbone and a percentile-based threshold calibration procedure. Given the lack of suitable training data covering heterogeneous and densely vegetated urban environments, a dedicated dataset was constructed from VHR-MS satellite imagery acquired over the Lombardy region (Italy). The dataset encompasses a wide range of land uses and land covers, including residential and industrial zones, public parks, private gardens, and agricultural areas. Through the photointerpretation of more than 2800 images, precise coordinates for more than 50,000 manually annotated trees were obtained. The DL model is trained with point-level annotations, enabling precise localization of individual trees while reducing annotation ambiguity in dense urban contexts. On the Lombardy dataset at 30 cm/px resolution, the proposed framework achieves 86.72% Precision, 66.92% Recall, an F1-score of 75.54%, and a localization error of 1.473 m.

Förderung

  • European Union-Next Generation EU
  • Italian Ministry of University and Research

Zitieren

APA

Martinoli, T., Morandini, L., & Fraternali, P. (2026). Individual Urban Tree Detection from Multispectral Satellite Imagery via Point-Supervised Deep Learning. Remote Sensing, 18(12), 2021. https://doi.org/10.3390/rs18122021

Vancouver

Martinoli T, Morandini L, Fraternali P. Individual Urban Tree Detection from Multispectral Satellite Imagery via Point-Supervised Deep Learning. Remote Sensing. 2026;18(12):2021. doi:10.3390/rs18122021

BibTeX
@article{Martinoli2026,
  author = {Martinoli, Thomas and Morandini, Luca and Fraternali, Piero},
  title = {Individual Urban Tree Detection from Multispectral Satellite Imagery via Point-Supervised Deep Learning},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {12},
  pages = {2021},
  doi = {10.3390/rs18122021}
}
Kostenlos starten →