Machine-Learning-Based Activity Tracking for Individual Pig Monitoring in Experimental Facilities for Improved Animal Welfare in Research
Sensors · 28.01.2025 · 25 (3) · 785
DOI: 10.3390/s25030785 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 28.01.2025. Verfasst von Frederik Deutch und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Clinical Medicine, Aarhus University, 8000 Aarhus, Denmark. Hauptthemen laut MEDLINE: Machine Learning, Animal Welfare. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The A.P. Moeller Foundation for Medical Research.
Abstract (Originalsprache)
In experimental research, animal welfare should always be of the highest priority. Currently, physical in-person observations are the standard. This is time-consuming, and results are subjective. Video-based machine learning models for monitoring experimental pigs provide a continuous and objective observation method for animal misthriving detection. The aim of this study was to develop and validate a pig tracking technology, using video-based data in a machine learning model to analyze the posture and activity level of experimental pigs living in single-pig pens. A research prototype was created using a microcomputer and a ceiling-mounted camera for live recording based on the obtained images from the experimental facility, and a combined model was created based on the Ultralytics YOLOv8n for object detection trained on the obtained images. As a second step, the Lucas–Kanade sparse optical flow technique for movement detection was applied. The resulting model successfully classified whether individual pigs were lying, standing, or walking. The validation test showed an accuracy of 90.66%, precision of 90.91%, recall of 90.66%, and correlation coefficient of 84.53% compared with observed ground truth. In conclusion, the model demonstrates how machine learning can be used to monitor experimental animals to potentially improve animal welfare.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Clinical Medicine, Aarhus University, 8000 Aarhus, Denmark.
- Department of Urology, Aarhus University Hospital, 8000 Aarhus, Denmark.
- Department of Electro- and Computer technology, Section for Biomedical Engineering, Aarhus University, 8000 Aarhus, Denmark.
- Institute of Transfusion Medicine and Transplant Engineering, Hannover Medical School, 30625 Hannover, Germany.
- Department of Surgery, University Medical Center Groningen, 9713 GZ Groningen, The Netherlands.
ORCID-Profile: Frederik Deutch, Marc Gjern Weiss, Stefan Rahr Wagner, Constanca Figueiredo, Cyril Moers
Förderung
- The A.P. Moeller Foundation for Medical Research
Zitieren
APA
Deutch, F., Weiss, M. G., Wagner, S. R., Hansen, L. S., Larsen, F., Figueiredo, C., Moers, C., & Keller, A. K. (2025). Machine-Learning-Based Activity Tracking for Individual Pig Monitoring in Experimental Facilities for Improved Animal Welfare in Research. Sensors, 25(3), 785. https://doi.org/10.3390/s25030785
Vancouver
Deutch F, Weiss MG, Wagner SR, Hansen LS, Larsen F, Figueiredo C, et al. Machine-Learning-Based Activity Tracking for Individual Pig Monitoring in Experimental Facilities for Improved Animal Welfare in Research. Sensors. 2025;25(3):785. doi:10.3390/s25030785
BibTeX
@article{Deutch2025,
author = {Deutch, Frederik and Weiss, Marc Gjern and Wagner, Stefan Rahr and Hansen, Lars Schmidt and Larsen, Frederik and Figueiredo, Constanca and Moers, Cyril and Keller, Anna Krarup},
title = {Machine-Learning-Based Activity Tracking for Individual Pig Monitoring in Experimental Facilities for Improved Animal Welfare in Research},
journal = {Sensors},
year = {2025},
volume = {25},
number = {3},
pages = {785},
doi = {10.3390/s25030785}
}
EUVIMED