View in EDS

Automated 24-h cattle feeding behaviour analysis using Raspberry Pi, infrared imaging, and deep learning-based head position and ID classification.

Saved in:
Bibliographic Details
Title: Automated 24-h cattle feeding behaviour analysis using Raspberry Pi, infrared imaging, and deep learning-based head position and ID classification.
Authors: Wager-Jones, G.1 (AUTHOR), Butler, M.1 (AUTHOR), Harris, W.E.1 (AUTHOR), Rutter, M.1 (AUTHOR), Bleach, E.1 (AUTHOR), Behrendt, K.1 (AUTHOR) kbehrendt@harper-adams.ac.uk
Source: Biosystems Engineering. Jul2026, Vol. 267, pN.PAG-N.PAG. 1p.
Subjects: Cattle feeding & feeds, Deep learning, Precision farming, Infrared imaging, Raspberry Pi, Identification of animals
Abstract: Monitoring cattle feeding behaviour is essential for assessing animal wellbeing. While recent vision-based systems advance behavioural analysis, many cannot link behaviour to feed intake, operate day and night, or detect interactions like muzzle-to-feed contact. They also rely on small, unrepresentative datasets and complex architectures that hinder collaboration. This study presents a low-cost, scalable framework using infrared imaging and motion-triggered video capture to identify cattle feeding behaviours and presence at the feed bunk. Using a Raspberry Pi with an infrared camera and open-source motion detection software, 503 video recordings were collected across varied light conditions. From these, two supervised models were trained: a convolutional neural network (CNN) for head-position classification, including muzzle-to-feed contact (test accuracy: 94.86%, loss = 0.17) and another for individual identification. Trained on 10,103 frames, the animal identification model distinguished feeder occupancy and specific individuals with high test-set accuracy (98.52%, loss = 0.05), dropping to 89.5% when evaluated on an external dataset of 25,453 manually annotated frames. This discrepancy highlights challenges in generalising to real-world conditions. Together, the models link feeding events to individual animals and feed bin weights to estimate intake. Future work will refine ingestion behaviour detection, while modularity allows potential deployment on edge or server-based farm management platforms. Findings show simple systems enable robust behavioural monitoring and interdisciplinary collaboration by lowering technical barriers for animal scientists. The framework supports scalable, data-driven livestock management and integration with precision farming systems. • 24hr (day and night) feeding behaviour camera monitoring system. • 93.2% accuracy for detecting muzzle to feed contact. • Methodology for linking high granularity feed weight data with feeding behaviours. • Simple multi-image classification for scalability and ease of use. [ABSTRACT FROM AUTHOR]
Copyright of Biosystems Engineering is the property of Academic Press Inc. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 194170991
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Automated 24-h cattle feeding behaviour analysis using Raspberry Pi, infrared imaging, and deep learning-based head position and ID classification.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Wager-Jones%2C+G%2E%22">Wager-Jones, G.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Butler%2C+M%2E%22">Butler, M.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Harris%2C+W%2EE%2E%22">Harris, W.E.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Rutter%2C+M%2E%22">Rutter, M.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Bleach%2C+E%2E%22">Bleach, E.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Behrendt%2C+K%2E%22">Behrendt, K.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> kbehrendt@harper-adams.ac.uk</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Biosystems+Engineering%22">Biosystems Engineering</searchLink>. Jul2026, Vol. 267, pN.PAG-N.PAG. 1p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Cattle+feeding+%26+feeds%22">Cattle feeding & feeds</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Precision+farming%22">Precision farming</searchLink><br /><searchLink fieldCode="DE" term="%22Infrared+imaging%22">Infrared imaging</searchLink><br /><searchLink fieldCode="DE" term="%22Raspberry+Pi%22">Raspberry Pi</searchLink><br /><searchLink fieldCode="DE" term="%22Identification+of+animals%22">Identification of animals</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Monitoring cattle feeding behaviour is essential for assessing animal wellbeing. While recent vision-based systems advance behavioural analysis, many cannot link behaviour to feed intake, operate day and night, or detect interactions like muzzle-to-feed contact. They also rely on small, unrepresentative datasets and complex architectures that hinder collaboration. This study presents a low-cost, scalable framework using infrared imaging and motion-triggered video capture to identify cattle feeding behaviours and presence at the feed bunk. Using a Raspberry Pi with an infrared camera and open-source motion detection software, 503 video recordings were collected across varied light conditions. From these, two supervised models were trained: a convolutional neural network (CNN) for head-position classification, including muzzle-to-feed contact (test accuracy: 94.86%, loss = 0.17) and another for individual identification. Trained on 10,103 frames, the animal identification model distinguished feeder occupancy and specific individuals with high test-set accuracy (98.52%, loss = 0.05), dropping to 89.5% when evaluated on an external dataset of 25,453 manually annotated frames. This discrepancy highlights challenges in generalising to real-world conditions. Together, the models link feeding events to individual animals and feed bin weights to estimate intake. Future work will refine ingestion behaviour detection, while modularity allows potential deployment on edge or server-based farm management platforms. Findings show simple systems enable robust behavioural monitoring and interdisciplinary collaboration by lowering technical barriers for animal scientists. The framework supports scalable, data-driven livestock management and integration with precision farming systems. • 24hr (day and night) feeding behaviour camera monitoring system. • 93.2% accuracy for detecting muzzle to feed contact. • Methodology for linking high granularity feed weight data with feeding behaviours. • Simple multi-image classification for scalability and ease of use. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Biosystems Engineering is the property of Academic Press Inc. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=194170991
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.biosystemseng.2026.104465
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 1
        StartPage: N.PAG
    Subjects:
      – SubjectFull: Cattle feeding & feeds
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Precision farming
        Type: general
      – SubjectFull: Infrared imaging
        Type: general
      – SubjectFull: Raspberry Pi
        Type: general
      – SubjectFull: Identification of animals
        Type: general
    Titles:
      – TitleFull: Automated 24-h cattle feeding behaviour analysis using Raspberry Pi, infrared imaging, and deep learning-based head position and ID classification.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Wager-Jones, G.
      – PersonEntity:
          Name:
            NameFull: Butler, M.
      – PersonEntity:
          Name:
            NameFull: Harris, W.E.
      – PersonEntity:
          Name:
            NameFull: Rutter, M.
      – PersonEntity:
          Name:
            NameFull: Bleach, E.
      – PersonEntity:
          Name:
            NameFull: Behrendt, K.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 07
              Text: Jul2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 15375110
          Numbering:
            – Type: volume
              Value: 267
          Titles:
            – TitleFull: Biosystems Engineering
              Type: main
ResultId 1