Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 2.65 MB
Add to list
  1. Search results
  2. Dynamic multi-behaviour, orientation-...

Dynamic multi-behaviour, orientation-invariant re-identification of Holstein-Friesian cattle

Maarten Perneel (UGent) , Ines Adriaens (UGent) , Jan Verwaeren (UGent) and Ben Aernouts
(2025) SENSORS. 25(10).
Author
Organization
Project
Abstract
To perform reliable animal re-identification, most available algorithms require standardised animal poses. However, this lack of versatility prevents widespread application of these algorithms in behavioural research and commercial environments. To circumvent this, we incorporated information about the orientation and behaviour of the animals in an embedding-based algorithm to re-identify Holstein-Friesian cattle. After all, the orientation and behaviour of an animal determine which body parts of an animal are visible from the camera's perspective. We evaluated our approach using a dataset with more than 11,000 instance segments of Holstein-Friesian cattle, but our methodology is readily generalisable to different animal species. Our results show that incorporation of informative metadata parameters in the re-identification procedure increases the rank-1 re-identification accuracy from 0.822 to 0.894, corresponding to a 40% reduction in the number of incorrectly identified animals.
Keywords
re-identification, pose estimation, behaviour classification, cattle

Downloads

  • Download
    publisher version.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 2.65 MB

Citation

Please use this url to cite or link to this publication:

MLA
Perneel, Maarten, et al. “Dynamic Multi-Behaviour, Orientation-Invariant Re-Identification of Holstein-Friesian Cattle.” SENSORS, vol. 25, no. 10, 2025, doi:10.3390/s25102971.
APA
Perneel, M., Adriaens, I., Verwaeren, J., & Aernouts, B. (2025). Dynamic multi-behaviour, orientation-invariant re-identification of Holstein-Friesian cattle. SENSORS, 25(10). https://doi.org/10.3390/s25102971
Chicago author-date
Perneel, Maarten, Ines Adriaens, Jan Verwaeren, and Ben Aernouts. 2025. “Dynamic Multi-Behaviour, Orientation-Invariant Re-Identification of Holstein-Friesian Cattle.” SENSORS 25 (10). https://doi.org/10.3390/s25102971.
Chicago author-date (all authors)
Perneel, Maarten, Ines Adriaens, Jan Verwaeren, and Ben Aernouts. 2025. “Dynamic Multi-Behaviour, Orientation-Invariant Re-Identification of Holstein-Friesian Cattle.” SENSORS 25 (10). doi:10.3390/s25102971.
Vancouver
1.
Perneel M, Adriaens I, Verwaeren J, Aernouts B. Dynamic multi-behaviour, orientation-invariant re-identification of Holstein-Friesian cattle. SENSORS. 2025;25(10).
IEEE
[1]
M. Perneel, I. Adriaens, J. Verwaeren, and B. Aernouts, “Dynamic multi-behaviour, orientation-invariant re-identification of Holstein-Friesian cattle,” SENSORS, vol. 25, no. 10, 2025.
@article{01JYPB617TMKDKHSX2VV01RP8X,
  abstract     = {{To perform reliable animal re-identification, most available algorithms require standardised animal poses. However, this lack of versatility prevents widespread application of these algorithms in behavioural research and commercial environments. To circumvent this, we incorporated information about the orientation and behaviour of the animals in an embedding-based algorithm to re-identify Holstein-Friesian cattle. After all, the orientation and behaviour of an animal determine which body parts of an animal are visible from the camera's perspective. We evaluated our approach using a dataset with more than 11,000 instance segments of Holstein-Friesian cattle, but our methodology is readily generalisable to different animal species. Our results show that incorporation of informative metadata parameters in the re-identification procedure increases the rank-1 re-identification accuracy from 0.822 to 0.894, corresponding to a 40% reduction in the number of incorrectly identified animals.}},
  articleno    = {{2971}},
  author       = {{Perneel, Maarten and Adriaens, Ines and Verwaeren, Jan and Aernouts, Ben}},
  issn         = {{1424-8220}},
  journal      = {{SENSORS}},
  keywords     = {{re-identification,pose estimation,behaviour classification,cattle}},
  language     = {{eng}},
  number       = {{10}},
  pages        = {{23}},
  title        = {{Dynamic multi-behaviour, orientation-invariant re-identification of Holstein-Friesian cattle}},
  url          = {{http://doi.org/10.3390/s25102971}},
  volume       = {{25}},
  year         = {{2025}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: