Comparison of strategies for automatic video-based detection of piling behaviour in laying hens

This study addresses piling behaviour in laying hens, a concern for producers due to welfare issues. Piling is commonly defined as the intense aggregation of birds into dense clusters, typically occurring in large group-housing systems. This behaviour can lead to severe welfare issues including suff...

Full description

Saved in:
Bibliographic Details
Main Authors: Dan Børge Jensen, Michael Toscano, Esther van der Heide, Matias Grønvig, Franziska Hakansson
Format: Article
Language:English
Published: Elsevier 2025-03-01
Series:Smart Agricultural Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772375524003496
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850041569395081216
author Dan Børge Jensen
Michael Toscano
Esther van der Heide
Matias Grønvig
Franziska Hakansson
author_facet Dan Børge Jensen
Michael Toscano
Esther van der Heide
Matias Grønvig
Franziska Hakansson
author_sort Dan Børge Jensen
collection DOAJ
description This study addresses piling behaviour in laying hens, a concern for producers due to welfare issues. Piling is commonly defined as the intense aggregation of birds into dense clusters, typically occurring in large group-housing systems. This behaviour can lead to severe welfare issues including suffocation for the affected birds, particularly those at the bottom of the pile. This is a preliminary study, using video data from 4 commercial Swiss layer flocks. The long-term goal of our research is to develop a machine learning-based method to automatically detect piling behaviour using a two-step approach: first, a pre-trained convolutional neural network model (VGG-16) is used to extract features from the video data. Second, a secondary model, trained specifically to detect piling, is applied to the extracted features. The specific aim of this preliminary study is to determine which secondary modelling strategy is best suited for the accurate and efficient detection of piling behaviour. Three secondary methods are explored, namely fully connected artificial neural networks (FC-ANN), long-short term memory (LSTM) networks, and convolutional neural networks (CNN).
format Article
id doaj-art-21c9e014780f429ca1606087eb59d88f
institution DOAJ
issn 2772-3755
language English
publishDate 2025-03-01
publisher Elsevier
record_format Article
series Smart Agricultural Technology
spelling doaj-art-21c9e014780f429ca1606087eb59d88f2025-08-20T02:55:45ZengElsevierSmart Agricultural Technology2772-37552025-03-011010074510.1016/j.atech.2024.100745Comparison of strategies for automatic video-based detection of piling behaviour in laying hensDan Børge Jensen0Michael Toscano1Esther van der Heide2Matias Grønvig3Franziska Hakansson4Department of Large Animal Sciences, Faculty of Health and Medical Sciences, University of Copenhagen, Grønnegårdsvej 2, DK-1870, Frederiksberg C, Denmark; Corresponding author.Center for Proper Housing: Laying hens and Rabbits (ZTHZ), Division of Animal Welfare, VPH Institute, University of Bern, Burgerweg 22, 3052, Zollikofen, SwitzerlandDepartment of Large Animal Sciences, Faculty of Health and Medical Sciences, University of Copenhagen, Grønnegårdsvej 2, DK-1870, Frederiksberg C, DenmarkDepartment of Large Animal Sciences, Faculty of Health and Medical Sciences, University of Copenhagen, Grønnegårdsvej 2, DK-1870, Frederiksberg C, DenmarkDepartment of Large Animal Sciences, Faculty of Health and Medical Sciences, University of Copenhagen, Grønnegårdsvej 2, DK-1870, Frederiksberg C, DenmarkThis study addresses piling behaviour in laying hens, a concern for producers due to welfare issues. Piling is commonly defined as the intense aggregation of birds into dense clusters, typically occurring in large group-housing systems. This behaviour can lead to severe welfare issues including suffocation for the affected birds, particularly those at the bottom of the pile. This is a preliminary study, using video data from 4 commercial Swiss layer flocks. The long-term goal of our research is to develop a machine learning-based method to automatically detect piling behaviour using a two-step approach: first, a pre-trained convolutional neural network model (VGG-16) is used to extract features from the video data. Second, a secondary model, trained specifically to detect piling, is applied to the extracted features. The specific aim of this preliminary study is to determine which secondary modelling strategy is best suited for the accurate and efficient detection of piling behaviour. Three secondary methods are explored, namely fully connected artificial neural networks (FC-ANN), long-short term memory (LSTM) networks, and convolutional neural networks (CNN).http://www.sciencedirect.com/science/article/pii/S2772375524003496Automatic monitoringConvolutional neural networkFully-connected neural networkLong short-term memory networkPiling behaviourLaying hens
spellingShingle Dan Børge Jensen
Michael Toscano
Esther van der Heide
Matias Grønvig
Franziska Hakansson
Comparison of strategies for automatic video-based detection of piling behaviour in laying hens
Smart Agricultural Technology
Automatic monitoring
Convolutional neural network
Fully-connected neural network
Long short-term memory network
Piling behaviour
Laying hens
title Comparison of strategies for automatic video-based detection of piling behaviour in laying hens
title_full Comparison of strategies for automatic video-based detection of piling behaviour in laying hens
title_fullStr Comparison of strategies for automatic video-based detection of piling behaviour in laying hens
title_full_unstemmed Comparison of strategies for automatic video-based detection of piling behaviour in laying hens
title_short Comparison of strategies for automatic video-based detection of piling behaviour in laying hens
title_sort comparison of strategies for automatic video based detection of piling behaviour in laying hens
topic Automatic monitoring
Convolutional neural network
Fully-connected neural network
Long short-term memory network
Piling behaviour
Laying hens
url http://www.sciencedirect.com/science/article/pii/S2772375524003496
work_keys_str_mv AT danbørgejensen comparisonofstrategiesforautomaticvideobaseddetectionofpilingbehaviourinlayinghens
AT michaeltoscano comparisonofstrategiesforautomaticvideobaseddetectionofpilingbehaviourinlayinghens
AT esthervanderheide comparisonofstrategiesforautomaticvideobaseddetectionofpilingbehaviourinlayinghens
AT matiasgrønvig comparisonofstrategiesforautomaticvideobaseddetectionofpilingbehaviourinlayinghens
AT franziskahakansson comparisonofstrategiesforautomaticvideobaseddetectionofpilingbehaviourinlayinghens