Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Jun 25;19(6):e0305671.
doi: 10.1371/journal.pone.0305671. eCollection 2024.

Automated monitoring of brush use in dairy cattle

Negar Sadrzadeh  1 , Borbala Foris  1 , Joseph Krahn  1 , Marina A G von Keyserlingk  1 , Daniel M Weary  1
Affiliations

Automated monitoring of brush use in dairy cattle

Negar Sadrzadeh et al. PLoS One. .

Abstract

Access to brushes allows for natural scratching behaviors 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 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 identify 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 behavior in a group setting; this approach could be applied to develop automated measures of other behaviors with the potential to better assess welfare and improve the care for farm animals.

PubMed Disclaimer

Conflict of interest statement

The authors have declared that no competing interests exist.

Figures

Fig 1
Fig 1. Overview of pen layout and monitoring system design.
Freestall pen layout on the left, showing the location of the automated brush. Pen dimensions are shown in m. On the right, an outline of the system used to monitor cow presence near the brush (shown as red circles): two RFID antennas (shown as blue bars) and a webcam above the brush were used to detect cow ear tags and fiducial markers, respectively. A wider view of the brush area (3 m × 5 m) was captured by a CCTV camera, allowing human observers to record brush use. Illustration by Ann Sanderson (independent illustrator, Canada).
Fig 2
Fig 2. Tagged cattle.
Unique ArUco tags assigned to each of the 24 cows in the group. Six identical tags were printed on Vinyl waterproof paper and attached to the collar of each cow. (Photo credit UBC Animal Welfare Program).
Fig 3
Fig 3. Data processing schematic.
Four approaches to combine the rotation data (each green line represents a rotation event and red boxes indicate bouts (i.e., consecutive sequences of rotation events in which the brush was used by the same cows) of a mechanical brush with the identification data of cows detected by the brush (each letter represents an individual). (A, C) The "proximity" approach assigns the cow detected closest in time to the brush use event/bout as the user. (B, D) The “predictive model” approach selects the user(s) from among 4 individuals detected closest in time to each event/bout.
Fig 4
Fig 4. Daily brush use estimation: Observer vs. automated method.
Correlation between the total daily brush use duration of 24 lactating dairy cows as determined by human video observation and an algorithm combining brush rotation data and cow detections based on a computer vision system with fiducial markers and using proximity method for integration (r = 0.84).
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Wilson SC, Mitlöhner FM, Morrow-Tesch J, Dailey JW, McGlone JJ. An assessment of several potential enrichment devices for feedlot cattle. Appl Anim Behav Sci. 2002;76: 259–265. doi: 10.1016/S0168-1591(02)00019-9 - DOI
    1. DeVries TJ, Vankova M, Veira DM, Von Keyserlingk MAG. Short Communication: Usage of Mechanical Brushes by Lactating Dairy Cows. J Dairy Sci. 2007;90: 2241–2245. doi: 10.3168/JDS.2006-648 - DOI - PubMed
    1. McConnachie E, Smid AMC, Thompson AJ, Weary DM, Gaworski MA, Von Keyserlingk MAG. Cows are highly motivated to access a grooming substrate. Biol Lett. 2018;14. doi: 10.1098/RSBL.2018.0303 - DOI - PMC - PubMed
    1. Val-Laillet D, Veira DM, Von Keyserlingk MAG. Short Communication: Dominance in Free-Stall—Housed Dairy Cattle Is Dependent upon Resource. J Dairy Sci. 2008;91: 3922–3926. doi: 10.3168/JDS.2008-1332 - DOI - PubMed
    1. Mandel R, Nicol C, Whay H, Klement E. Short communication: Detection and monitoring of metritis in dairy cows using an automated grooming device. 2017. doi: 10.3168/jds.2016-12201 - DOI - PubMed

Grants and funding

DMW received funding for this project from the Investment Agriculture Foundation of BC (#INV174; https://iafbc.ca/). The funders played no role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript.