Recording behaviour of indoor-housed farm animals automatically using machine vision technology: a systematic review

Kaitlin Wurtz, Irene Camerlink, RB D'Eath, Alberto Peña Fernández, Tomas Norton, Juan Steibel, Janice Siegford

Research output: Contribution to journalLiterature review

Abstract

Large-scale phenotyping of animal behaviour traits is time consuming and has led to increased demand for technologies that can automate these procedures. Automated tracking of animals has been successful in controlled laboratory settings, but recording from animals in large groups in highly variable farm settings presents challenges. The aim of this review is to provide a systematic overview of the advances that have occurred in automated, high throughput image detection of farm animal behavioural traits with welfare and production implications. Peer-reviewed publications written in English were reviewed systematically following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. After identification, screening, and assessment for eligibility, 108 publications met these specifications and were included for qualitative synthesis. Data collected from the papers included camera specifications, housing conditions, group size, algorithm details, procedures, and results. Most studies utilized standard digital colour video cameras for data collection, with increasing use of 3D cameras in papers published after 2013. Papers including pigs (across production stages) were the most common (n = 63). The most common behaviours recorded included activity level, area occupancy, aggression, gait scores, resource use, and posture. Our review revealed many overlaps in methods applied to analysing behaviour, and most studies started from scratch instead of building upon previous work. Training and validation sample sizes were generally small (mean±s.d. groups = 3.8±5.8) and in data collection and testing took place in relatively controlled environments. To advance our ability to automatically phenotype behaviour, future research should build upon existing knowledge and validate technology under commercial settings and publications should explicitly describe recording conditions in detail to allow studies to be reproduced.
Original languageEnglish
Article numbere0226669
JournalPLoS ONE
Volume14
Issue number12
Early online date23 Dec 2019
DOIs
Publication statusFirst published - 23 Dec 2019

Fingerprint

computer vision
Domestic Animals
systematic review
farmed animal species
Farms
Computer vision
Publications
Animals
Technology
cameras
phenotype
Controlled Environment
Animal Behavior
Aptitude
video cameras
Cameras
gait
peers
posture
Aggression

Cite this

Wurtz, Kaitlin ; Camerlink, Irene ; D'Eath, RB ; Peña Fernández, Alberto ; Norton, Tomas ; Steibel, Juan ; Siegford, Janice. / Recording behaviour of indoor-housed farm animals automatically using machine vision technology: a systematic review. In: PLoS ONE. 2019 ; Vol. 14, No. 12.
@article{ad4723ddf1a74d3bac9903cac16982c1,
title = "Recording behaviour of indoor-housed farm animals automatically using machine vision technology: a systematic review",
abstract = "Large-scale phenotyping of animal behaviour traits is time consuming and has led to increased demand for technologies that can automate these procedures. Automated tracking of animals has been successful in controlled laboratory settings, but recording from animals in large groups in highly variable farm settings presents challenges. The aim of this review is to provide a systematic overview of the advances that have occurred in automated, high throughput image detection of farm animal behavioural traits with welfare and production implications. Peer-reviewed publications written in English were reviewed systematically following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. After identification, screening, and assessment for eligibility, 108 publications met these specifications and were included for qualitative synthesis. Data collected from the papers included camera specifications, housing conditions, group size, algorithm details, procedures, and results. Most studies utilized standard digital colour video cameras for data collection, with increasing use of 3D cameras in papers published after 2013. Papers including pigs (across production stages) were the most common (n = 63). The most common behaviours recorded included activity level, area occupancy, aggression, gait scores, resource use, and posture. Our review revealed many overlaps in methods applied to analysing behaviour, and most studies started from scratch instead of building upon previous work. Training and validation sample sizes were generally small (mean±s.d. groups = 3.8±5.8) and in data collection and testing took place in relatively controlled environments. To advance our ability to automatically phenotype behaviour, future research should build upon existing knowledge and validate technology under commercial settings and publications should explicitly describe recording conditions in detail to allow studies to be reproduced.",
author = "Kaitlin Wurtz and Irene Camerlink and RB D'Eath and {Pe{\~n}a Fern{\'a}ndez}, Alberto and Tomas Norton and Juan Steibel and Janice Siegford",
year = "2019",
month = "12",
day = "23",
doi = "10.1371/journal.pone.0226669",
language = "English",
volume = "14",
journal = "PLoS ONE",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "12",

}

Wurtz, K, Camerlink, I, D'Eath, RB, Peña Fernández, A, Norton, T, Steibel, J & Siegford, J 2019, 'Recording behaviour of indoor-housed farm animals automatically using machine vision technology: a systematic review', PLoS ONE, vol. 14, no. 12, e0226669. https://doi.org/10.1371/journal.pone.0226669

Recording behaviour of indoor-housed farm animals automatically using machine vision technology: a systematic review. / Wurtz, Kaitlin; Camerlink, Irene; D'Eath, RB; Peña Fernández, Alberto; Norton, Tomas; Steibel, Juan; Siegford, Janice.

In: PLoS ONE, Vol. 14, No. 12, e0226669, 23.12.2019.

Research output: Contribution to journalLiterature review

TY - JOUR

T1 - Recording behaviour of indoor-housed farm animals automatically using machine vision technology: a systematic review

AU - Wurtz, Kaitlin

AU - Camerlink, Irene

AU - D'Eath, RB

AU - Peña Fernández, Alberto

AU - Norton, Tomas

AU - Steibel, Juan

AU - Siegford, Janice

PY - 2019/12/23

Y1 - 2019/12/23

N2 - Large-scale phenotyping of animal behaviour traits is time consuming and has led to increased demand for technologies that can automate these procedures. Automated tracking of animals has been successful in controlled laboratory settings, but recording from animals in large groups in highly variable farm settings presents challenges. The aim of this review is to provide a systematic overview of the advances that have occurred in automated, high throughput image detection of farm animal behavioural traits with welfare and production implications. Peer-reviewed publications written in English were reviewed systematically following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. After identification, screening, and assessment for eligibility, 108 publications met these specifications and were included for qualitative synthesis. Data collected from the papers included camera specifications, housing conditions, group size, algorithm details, procedures, and results. Most studies utilized standard digital colour video cameras for data collection, with increasing use of 3D cameras in papers published after 2013. Papers including pigs (across production stages) were the most common (n = 63). The most common behaviours recorded included activity level, area occupancy, aggression, gait scores, resource use, and posture. Our review revealed many overlaps in methods applied to analysing behaviour, and most studies started from scratch instead of building upon previous work. Training and validation sample sizes were generally small (mean±s.d. groups = 3.8±5.8) and in data collection and testing took place in relatively controlled environments. To advance our ability to automatically phenotype behaviour, future research should build upon existing knowledge and validate technology under commercial settings and publications should explicitly describe recording conditions in detail to allow studies to be reproduced.

AB - Large-scale phenotyping of animal behaviour traits is time consuming and has led to increased demand for technologies that can automate these procedures. Automated tracking of animals has been successful in controlled laboratory settings, but recording from animals in large groups in highly variable farm settings presents challenges. The aim of this review is to provide a systematic overview of the advances that have occurred in automated, high throughput image detection of farm animal behavioural traits with welfare and production implications. Peer-reviewed publications written in English were reviewed systematically following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. After identification, screening, and assessment for eligibility, 108 publications met these specifications and were included for qualitative synthesis. Data collected from the papers included camera specifications, housing conditions, group size, algorithm details, procedures, and results. Most studies utilized standard digital colour video cameras for data collection, with increasing use of 3D cameras in papers published after 2013. Papers including pigs (across production stages) were the most common (n = 63). The most common behaviours recorded included activity level, area occupancy, aggression, gait scores, resource use, and posture. Our review revealed many overlaps in methods applied to analysing behaviour, and most studies started from scratch instead of building upon previous work. Training and validation sample sizes were generally small (mean±s.d. groups = 3.8±5.8) and in data collection and testing took place in relatively controlled environments. To advance our ability to automatically phenotype behaviour, future research should build upon existing knowledge and validate technology under commercial settings and publications should explicitly describe recording conditions in detail to allow studies to be reproduced.

UR - http://www.scopus.com/inward/record.url?scp=85077194414&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0226669

DO - 10.1371/journal.pone.0226669

M3 - Literature review

C2 - 31869364

VL - 14

JO - PLoS ONE

JF - PLoS ONE

SN - 1932-6203

IS - 12

M1 - e0226669

ER -