EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

YOLO ‐Behaviour: A simple, flexible framework to automatically quantify animal behaviours from videos

Alex Hoi Hang Chan, Prasetia Putra, Harald Schupp, Johanna Köchling, Jana Straßheim, Britta Renner, Julia Schroeder, William D. Pearse, Shinichi Nakagawa, Terry Burke, Michael Griesser, Andrea Meltzer und 2 weitere

Methods in Ecology and Evolution · 2025-04 · 16 (4) · 760-774

DOI: 10.1111/2041-210x.14502 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Methods in Ecology and Evolution, online erschienen am 12.02.2025. Verfasst von Alex Hoi Hang Chan und 13 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deutsche Forschungsgemeinschaft.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Manually coding behaviours from videos is essential to study animal behaviour but it is labour‐intensive and susceptible to inter‐rater bias and reliability issues. Recent developments of computer vision tools enable the automatic quantification of behaviours, supplementing or even replacing manual annotation. However, widespread adoption of these methods is still limited, due to the lack of annotated training datasets and domain‐specific knowledge required to optimize these models for animal research. Here, we present YOLO‐Behaviour, a flexible framework for identifying visually distinct behaviours from video recordings. The framework is robust, easy to implement, and requires minimal manual annotations as training data. We demonstrate the flexibility of the framework with case studies for event‐wise detection in house sparrow nestling provisioning, Siberian jay feeding, human eating behaviours and frame‐wise detections of various behaviours in pigeons, zebras and giraffes. Our results show that the framework reliably detects behaviours accurately and retrieve comparable accuracy metrics to manual annotation. However, metrics extracted for event‐wise detection were less correlated with manual annotation, and potential reasons for the discrepancy between manual annotation and automatic detection are discussed. To mitigate this problem, the framework can be used as a hybrid approach of first detecting events using the pipeline and then manually confirming the detections, saving annotation time. We provide detailed documentation and guidelines on how to implement the YOLO‐Behaviour framework, for researchers to readily train and deploy new models on their own study systems. We anticipate the framework can be another step towards lowering the barrier of entry for applying computer vision methods in animal behaviour.

Förderung

  • Deutsche Forschungsgemeinschaft

Zitieren

APA

Chan, A. H. H., Putra, P., Schupp, H., Köchling, J., Straßheim, J., Renner, B., Schroeder, J., Pearse, W. D., Nakagawa, S., Burke, T., Griesser, M., Meltzer, A., Lubrano, S., & Kano, F. (2025). YOLO ‐Behaviour: A simple, flexible framework to automatically quantify animal behaviours from videos. Methods in Ecology and Evolution, 16(4), 760-774. https://doi.org/10.1111/2041-210x.14502

Vancouver

Chan AHH, Putra P, Schupp H, Köchling J, Straßheim J, Renner B, et al. YOLO ‐Behaviour: A simple, flexible framework to automatically quantify animal behaviours from videos. Methods in Ecology and Evolution. 2025;16(4):760-774. doi:10.1111/2041-210x.14502

BibTeX
@article{Chan2025,
  author = {Chan, Alex Hoi Hang and Putra, Prasetia and Schupp, Harald and Köchling, Johanna and Straßheim, Jana and Renner, Britta and Schroeder, Julia and Pearse, William D. and Nakagawa, Shinichi and Burke, Terry and Griesser, Michael and Meltzer, Andrea and Lubrano, Saverio and Kano, Fumihiro},
  title = {YOLO ‐Behaviour: A simple, flexible framework to automatically quantify animal behaviours from videos},
  journal = {Methods in Ecology and Evolution},
  year = {2025},
  volume = {16},
  number = {4},
  pages = {760--774},
  doi = {10.1111/2041-210x.14502}
}
Kostenlos starten →