EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Applicability of Machine Learning in Behavioural Monitoring of the Red Panda (Ailurus fulgens) in Zoos

Amalie M Worup, Anne S Sonne, Jeppe Kudahl, Johanne H Jacobsen iD, Sussie Pagh iD, Thea L Faddersbøll iD, Cino Pertoldi iD

Animals · 10.04.2026 · 16 (8) · 1165

DOI: 10.3390/ani16081165 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Animals, online erschienen am 10.04.2026. Verfasst von Amalie M Worup und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemistry and Bioscience, Aalborg University, Frederik Bajers Vej 7H, 9220 Aalborg, Denmark. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Welfare assessment for the endangered red panda (Ailurus fulgens) in captivity requires systematic behaviour monitoring, yet traditional direct observation is often limited by observer subjectivity and time constraints. This study evaluates the feasibility of employing machine learning (ML) to automate behavioural monitoring of a red panda in a complex, mixed-species enclosure at Aalborg Zoo, Denmark. Using video data from cameras in the enclosure of the red panda, and the ML model LabGym for animal detection and behavioural categorisation, models were trained to analyse activity patterns of the red panda. The results demonstrate that, while the behaviour categorizer is a promising tool with high classification confidence, the overall system effectiveness is currently limited by the object detector’s performance in a naturalistic environment. Challenges such as environmental obstructions (e.g., rocks, foliage, and trees) and the animal’s camouflage contributed to a significant amount of unclassified time, which may affect the overall assessment of behavioural distribution. We conclude that, while ML holds potential for non-invasive behaviour monitoring, its application in complex zoo settings requires improved detection capabilities to be fully reliable. Future iterations of this system could be enhanced by complementing standard object detection with pose estimation frameworks. Implementing alternative labelling strategies or background subtraction methods could additionally mitigate the detection challenges posed by environmental obstruction.

Schlagwörter

Stichwörter der Autor:innen

LabGymbehaviour categorizationobject detection

Autor:innen und Institutionen

  • Department of Chemistry and Bioscience, Aalborg University, Frederik Bajers Vej 7H, 9220 Aalborg, Denmark.
  • Aalborg Zoo, Mølleparkvej 63, 9000 Aalborg, Denmark.

ORCID-Profile: Johanne H Jacobsen, Sussie Pagh, Thea L Faddersbøll, Cino Pertoldi

Zitieren

APA

Worup, A. M., Sonne, A. S., Kudahl, J., Jacobsen, J. H., Pagh, S., Faddersbøll, T. L., & Pertoldi, C. (2026). Applicability of Machine Learning in Behavioural Monitoring of the Red Panda (Ailurus fulgens) in Zoos. Animals, 16(8), 1165. https://doi.org/10.3390/ani16081165

Vancouver

Worup AM, Sonne AS, Kudahl J, Jacobsen JH, Pagh S, Faddersbøll TL, et al. Applicability of Machine Learning in Behavioural Monitoring of the Red Panda (Ailurus fulgens) in Zoos. Animals. 2026;16(8):1165. doi:10.3390/ani16081165

BibTeX
@article{Worup2026,
  author = {Worup, Amalie M and Sonne, Anne S and Kudahl, Jeppe and Jacobsen, Johanne H and Pagh, Sussie and Faddersbøll, Thea L and Pertoldi, Cino},
  title = {Applicability of Machine Learning in Behavioural Monitoring of the Red Panda (Ailurus fulgens) in Zoos},
  journal = {Animals},
  year = {2026},
  volume = {16},
  number = {8},
  pages = {1165},
  doi = {10.3390/ani16081165}
}
Kostenlos starten →