Open Collections

Sadrzadeh Ahmadi, Negar

University of British Columbia

Access to brushes allows for natural scratching behaviours in cattle, especially in confined indoor settings. Cattle are motivated to use brushes, but brush use varies with multiple factors including social hierarchy and health. Brush use might serve as an indicator of cow health or welfare, but practical application of these measures requires accurate and automated monitoring tools. This study describes a machine learning approach to monitor brush use by dairy cattle. We aimed to capture the daily brush use by integrating data on the rotation of a mechanical brush with data on cow identification derived from either 1) low-frequency radio frequency identification or 2) a computer vision system using fiducial markers. We found that the computer vision system outperformed the RFID system in accuracy, and that the machine learning algorithms enhanced the precision of the brush use estimates. This study presents the first description of a fiducial marker-based computer vision system for monitoring individual cattle behaviour in a group setting; this approach could be applied to develop automated measures of other behaviours with the potential to better assess welfare and improve the care for farm animals.

Text

2024-07-24

Attribution-NonCommercial-NoDerivatives 4.0 International

http://hdl.handle.net/2429/88691

Applied Animal Biology

University of British Columbia

UBCV

http://creativecommons.org/licenses/by-nc-nd/4.0/