Automation of video-based location tracking tool for dairy cows in their housing stalls using deep learning

Animal welfare research has raised concerns regarding the intensification of farm animal housing systems that offer limited opportunity for movement. Applying deep learning models to location tracking provides an opportunity for accurate and timely measurement of cow movement within the housing envi...

Full description

Bibliographic Details
Main Authors: A. Zambelis, M. Saadati, G.M. Dallago, P. Stecko, V. Boyer, J.-P. Parent, M. Pedersoli, E. Vasseur
Format: Article
Language:English
Published: Elsevier 2021-12-01
Series:Smart Agricultural Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772375521000150
_version_ 1818345079909122048
author A. Zambelis
M. Saadati
G.M. Dallago
P. Stecko
V. Boyer
J.-P. Parent
M. Pedersoli
E. Vasseur
author_facet A. Zambelis
M. Saadati
G.M. Dallago
P. Stecko
V. Boyer
J.-P. Parent
M. Pedersoli
E. Vasseur
author_sort A. Zambelis
collection DOAJ
description Animal welfare research has raised concerns regarding the intensification of farm animal housing systems that offer limited opportunity for movement. Applying deep learning models to location tracking provides an opportunity for accurate and timely measurement of cow movement within the housing environment. The objective of this study is to develop an accurate and low-cost alternative to manual cow tracking of spatial use in their tie-stall by applying deep learning techniques. Twenty-four lactating Holstein cows were video recorded for a continuous 24-h period on weeks 1, 2, 3, 6, 8, and 10. Individual images showing the in-stall position of each cow were extracted from each 24-h recording at a rate of one image per minute. Three coordinates on each cow were manually annotated on the image sequences to track the location of the left hip, the right hip, and the neck. The final dataset used to validate the deep learning approach consisted of 199,100 Red-Green-Blue images with manual coordinate annotations. Leave-one-out cross-validation was used to train 5 variants of different deep residual networks. Model performance was expressed in terms of pixel error for each coordinate annotated from the validation image set. Pixel error was converted to a standard measure in cm using the average pixel/cm ratio for each cow in each week. The average error from all 3 coordinates in the best model was equivalent to a 1.44 cm error for Resnet-18 in the actual physical placement of the coordinates within the stall environment. Based on this high degree of accuracy, this model could be used to analyze the activity patterns of individual cows for optimization of stall spaces and improved ease of movement.
first_indexed 2024-12-13T16:56:41Z
format Article
id doaj.art-cb95537e73f84eba862b6246509f241d
institution Directory Open Access Journal
issn 2772-3755
language English
last_indexed 2024-12-13T16:56:41Z
publishDate 2021-12-01
publisher Elsevier
record_format Article
series Smart Agricultural Technology
spelling doaj.art-cb95537e73f84eba862b6246509f241d2022-12-21T23:37:54ZengElsevierSmart Agricultural Technology2772-37552021-12-011100015Automation of video-based location tracking tool for dairy cows in their housing stalls using deep learningA. Zambelis0M. Saadati1G.M. Dallago2P. Stecko3V. Boyer4J.-P. Parent5M. Pedersoli6E. Vasseur7McGill University, Ste-Anne-de-Bellevue, QC, Canada, H9 × 3V9École de Technologie Supérieure, Montréal, QC, Canada, H3C 1K3McGill University, Ste-Anne-de-Bellevue, QC, Canada, H9 × 3V9McGill University, Ste-Anne-de-Bellevue, QC, Canada, H9 × 3V9McGill University, Ste-Anne-de-Bellevue, QC, Canada, H9 × 3V9Agriculture et Agroalimentaire Canada, Saint-Jean-sur-Richelieu, QC, Canada, J3B 3B6École de Technologie Supérieure, Montréal, QC, Canada, H3C 1K3McGill University, Ste-Anne-de-Bellevue, QC, Canada, H9 × 3V9; Corresponding author.Animal welfare research has raised concerns regarding the intensification of farm animal housing systems that offer limited opportunity for movement. Applying deep learning models to location tracking provides an opportunity for accurate and timely measurement of cow movement within the housing environment. The objective of this study is to develop an accurate and low-cost alternative to manual cow tracking of spatial use in their tie-stall by applying deep learning techniques. Twenty-four lactating Holstein cows were video recorded for a continuous 24-h period on weeks 1, 2, 3, 6, 8, and 10. Individual images showing the in-stall position of each cow were extracted from each 24-h recording at a rate of one image per minute. Three coordinates on each cow were manually annotated on the image sequences to track the location of the left hip, the right hip, and the neck. The final dataset used to validate the deep learning approach consisted of 199,100 Red-Green-Blue images with manual coordinate annotations. Leave-one-out cross-validation was used to train 5 variants of different deep residual networks. Model performance was expressed in terms of pixel error for each coordinate annotated from the validation image set. Pixel error was converted to a standard measure in cm using the average pixel/cm ratio for each cow in each week. The average error from all 3 coordinates in the best model was equivalent to a 1.44 cm error for Resnet-18 in the actual physical placement of the coordinates within the stall environment. Based on this high degree of accuracy, this model could be used to analyze the activity patterns of individual cows for optimization of stall spaces and improved ease of movement.http://www.sciencedirect.com/science/article/pii/S2772375521000150AutomationDairy cowTrackingAnimal behavior
spellingShingle A. Zambelis
M. Saadati
G.M. Dallago
P. Stecko
V. Boyer
J.-P. Parent
M. Pedersoli
E. Vasseur
Automation of video-based location tracking tool for dairy cows in their housing stalls using deep learning
Smart Agricultural Technology
Automation
Dairy cow
Tracking
Animal behavior
title Automation of video-based location tracking tool for dairy cows in their housing stalls using deep learning
title_full Automation of video-based location tracking tool for dairy cows in their housing stalls using deep learning
title_fullStr Automation of video-based location tracking tool for dairy cows in their housing stalls using deep learning
title_full_unstemmed Automation of video-based location tracking tool for dairy cows in their housing stalls using deep learning
title_short Automation of video-based location tracking tool for dairy cows in their housing stalls using deep learning
title_sort automation of video based location tracking tool for dairy cows in their housing stalls using deep learning
topic Automation
Dairy cow
Tracking
Animal behavior
url http://www.sciencedirect.com/science/article/pii/S2772375521000150
work_keys_str_mv AT azambelis automationofvideobasedlocationtrackingtoolfordairycowsintheirhousingstallsusingdeeplearning
AT msaadati automationofvideobasedlocationtrackingtoolfordairycowsintheirhousingstallsusingdeeplearning
AT gmdallago automationofvideobasedlocationtrackingtoolfordairycowsintheirhousingstallsusingdeeplearning
AT pstecko automationofvideobasedlocationtrackingtoolfordairycowsintheirhousingstallsusingdeeplearning
AT vboyer automationofvideobasedlocationtrackingtoolfordairycowsintheirhousingstallsusingdeeplearning
AT jpparent automationofvideobasedlocationtrackingtoolfordairycowsintheirhousingstallsusingdeeplearning
AT mpedersoli automationofvideobasedlocationtrackingtoolfordairycowsintheirhousingstallsusingdeeplearning
AT evasseur automationofvideobasedlocationtrackingtoolfordairycowsintheirhousingstallsusingdeeplearning