EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Using Deep Learning to Automate Orangutan Nest Detections on Aerial Images Collected With Drones

Serge Wich iD, Marc Ancrenaz, Benoit Goossens iD, Molly Hennekam, Sol Milne, David Burslem iD, Cheryl Knott iD, Julien Martin iD, Paul Fergus

American Journal of Primatology · 2025

DOI: 10.1002/ajp.70100 ↗

Kurz gefasst

Fachartikel in der Zeitschrift American Journal of Primatology, 2025. Verfasst von Serge Wich und 8 weiteren Autor:innen. Beteiligte Einrichtung: School of Biological and Environmental Sciences, Liverpool John Moores University, Liverpool, UK. Hauptthemen laut MEDLINE: Deep Learning, Nesting Behavior, Unmanned Aerial Devices, Pongo. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The authors thank USFWS for providing funding for this study (GA1977)..

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Traditional orangutan distribution and density monitoring requires costly line transect methods on the ground to detect their nests. Recently researchers have started to use unoccupied aerial vehicles, hereafter referred to as drones, to collect such data faster. However, manually inspecting the images acquired by the drone is time‐consuming and hence costly. This study explored a deep learning method for the automated detection of orangutan nests in drone‐captured aerial images, which can significantly improve the efficiency of orangutan monitoring efforts. The YOLO v10 model was trained using 868 images containing 1568 annotated orangutan nests collected from sites in Sabah, Malaysia, and Sumatra, Indonesia. Images were captured using multirotor and fixed‐wing drones at varying altitudes. The model was trained using a transfer learning approach and achieved a mean Average Precision (mAP) of 0.831. The model was subsequently tested on two independent data sets with results showing a precision of 0.98 and recall of 0.88 for a multirotor drone and precision of 0.98 and a recall of 0.71 for a fixed‐wing drone which has the benefit of being able to have longer duration flights. The high precision values indicate the model's accuracy in identifying true nest locations, while the recall values demonstrate its ability to detect a significant portion of the nests present in the images. The study highlights how using drones for data collection can reduce survey times compared to ground surveys, and the automation of nest detection further enhances the efficiency of drone surveys. However, the model's recall, especially for fixed‐wing drone data, could be improved to ensure accurate population trend analyses. Further research should focus on expanding training data sets and refining models to account for different camera systems and environmental conditions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningNesting BehaviorUnmanned Aerial DevicesPongoAnimalsIndonesiaMalaysia

Stichwörter der Autor:innen

IndonesiaMalaysiagreat apesline transectsmonitoring

Autor:innen und Institutionen

  • School of Biological and Environmental Sciences, Liverpool John Moores University, Liverpool, UK.
  • HUTAN, Sandakan, Malaysia.
  • Borneo Futures, Bandar Seri Begawan, Brunei.
  • c/o Sabah Wildlife Department, Danau Girang Field Centre, Wisma MUIS, Kota Kinabalu, Sabah, Malaysia.
  • Cardiff School of Biosciences, Organisms and Environment Division, Cardiff University, Cardiff, UK.
  • Sabah Wildlife Department, Wisma MUIS, Kota Kinabalu, Malaysia.

ORCID-Profile: Serge Wich, Benoit Goossens, David Burslem, Cheryl Knott, Julien Martin

Förderung

  • The authors thank USFWS for providing funding for this study (GA1977).

Zitieren

APA

Wich, S., Ancrenaz, M., Goossens, B., Hennekam, M., Milne, S., Burslem, D., Knott, C., Martin, J., & Fergus, P. (2025). Using Deep Learning to Automate Orangutan Nest Detections on Aerial Images Collected With Drones. American Journal of Primatology. https://doi.org/10.1002/ajp.70100

Vancouver

Wich S, Ancrenaz M, Goossens B, Hennekam M, Milne S, Burslem D, et al. Using Deep Learning to Automate Orangutan Nest Detections on Aerial Images Collected With Drones. American Journal of Primatology. 2025. doi:10.1002/ajp.70100

BibTeX
@article{Wich2025,
  author = {Wich, Serge and Ancrenaz, Marc and Goossens, Benoit and Hennekam, Molly and Milne, Sol and Burslem, David and Knott, Cheryl and Martin, Julien and Fergus, Paul},
  title = {Using Deep Learning to Automate Orangutan Nest Detections on Aerial Images Collected With Drones},
  journal = {American Journal of Primatology},
  year = {2025},
  doi = {10.1002/ajp.70100}
}
Kostenlos starten →