Automated long-term monitoring of stereotypical movement in polar bears under human care using machine learning

The welfare of animals under human care is often assessed by observing behaviours indicative of stress or discomfort, such as stereotypical behaviour (SB), which often shows as repetitive, invariant pacing. Traditional behaviour monitoring methods, however, are labour-intensive and subject to observ...

Full description

Saved in:
Bibliographic Details
Main Authors: Matthias Zuerl, Philip Stoll, Ingrid Brehm, Jonas Sueskind, René Raab, Jan Petermann, Dario Zanca, Ralph Simon, Lorenzo von Fersen, Bjoern Eskofier
Format: Article
Language:English
Published: Elsevier 2024-11-01
Series:Ecological Informatics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1574954124003820
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850266215654621184
author Matthias Zuerl
Philip Stoll
Ingrid Brehm
Jonas Sueskind
René Raab
Jan Petermann
Dario Zanca
Ralph Simon
Lorenzo von Fersen
Bjoern Eskofier
author_facet Matthias Zuerl
Philip Stoll
Ingrid Brehm
Jonas Sueskind
René Raab
Jan Petermann
Dario Zanca
Ralph Simon
Lorenzo von Fersen
Bjoern Eskofier
author_sort Matthias Zuerl
collection DOAJ
description The welfare of animals under human care is often assessed by observing behaviours indicative of stress or discomfort, such as stereotypical behaviour (SB), which often shows as repetitive, invariant pacing. Traditional behaviour monitoring methods, however, are labour-intensive and subject to observer bias. Our study presents an innovative automated approach utilising computer vision and machine learning to non-invasively detect and analyse SB in managed populations, exemplified by a longitudinal study of two polar bears. We designed an animal tracking framework to localise and identify individual animals in the enclosure. After determining their position on the enclosure map via homographic transformation, we refined the resulting trajectories using a particle filter. Finally, we classified the trajectory patterns as SB or normal behaviour using a lightweight random forest approach with an accuracy of 94.9 %. The system not only allows for continuous, objective monitoring of animal behaviours but also provides insights into seasonal variations in SB, illustrating its potential for improving animal welfare in zoological settings. Ultimately, we analysed 607 days for the occurrence of SB, allowing us to discuss seasonal patterns of SB in both the male and female polar bear monitored. This work advances the field of animal welfare research by introducing a scalable, efficient method for the long-term, automated detection and monitoring of stereotypical behaviour, paving the way for its application across various settings and species that can be continuously monitored with cameras. We made the code publicly available at https://github.com/team-vera/stereotypy-detector.
format Article
id doaj-art-3aab6734b80346bbadff98b5a74f66a4
institution OA Journals
issn 1574-9541
language English
publishDate 2024-11-01
publisher Elsevier
record_format Article
series Ecological Informatics
spelling doaj-art-3aab6734b80346bbadff98b5a74f66a42025-08-20T01:54:15ZengElsevierEcological Informatics1574-95412024-11-018310284010.1016/j.ecoinf.2024.102840Automated long-term monitoring of stereotypical movement in polar bears under human care using machine learningMatthias Zuerl0Philip Stoll1Ingrid Brehm2Jonas Sueskind3René Raab4Jan Petermann5Dario Zanca6Ralph Simon7Lorenzo von Fersen8Bjoern Eskofier9Machine Learning and Data Analytics Lab, Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen 91052, Germany; Corresponding author.Machine Learning and Data Analytics Lab, Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen 91052, GermanyAnimal Physiology, Department of Biology, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen 91058, GermanyMachine Learning and Data Analytics Lab, Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen 91052, GermanyMachine Learning and Data Analytics Lab, Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen 91052, GermanyMachine Learning and Data Analytics Lab, Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen 91052, GermanyMachine Learning and Data Analytics Lab, Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen 91052, GermanyBehavioral Ecology and Conservation Lab, Nuremberg Zoo, Nuremberg 90480, GermanyBehavioral Ecology and Conservation Lab, Nuremberg Zoo, Nuremberg 90480, GermanyMachine Learning and Data Analytics Lab, Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen 91052, GermanyThe welfare of animals under human care is often assessed by observing behaviours indicative of stress or discomfort, such as stereotypical behaviour (SB), which often shows as repetitive, invariant pacing. Traditional behaviour monitoring methods, however, are labour-intensive and subject to observer bias. Our study presents an innovative automated approach utilising computer vision and machine learning to non-invasively detect and analyse SB in managed populations, exemplified by a longitudinal study of two polar bears. We designed an animal tracking framework to localise and identify individual animals in the enclosure. After determining their position on the enclosure map via homographic transformation, we refined the resulting trajectories using a particle filter. Finally, we classified the trajectory patterns as SB or normal behaviour using a lightweight random forest approach with an accuracy of 94.9 %. The system not only allows for continuous, objective monitoring of animal behaviours but also provides insights into seasonal variations in SB, illustrating its potential for improving animal welfare in zoological settings. Ultimately, we analysed 607 days for the occurrence of SB, allowing us to discuss seasonal patterns of SB in both the male and female polar bear monitored. This work advances the field of animal welfare research by introducing a scalable, efficient method for the long-term, automated detection and monitoring of stereotypical behaviour, paving the way for its application across various settings and species that can be continuously monitored with cameras. We made the code publicly available at https://github.com/team-vera/stereotypy-detector.http://www.sciencedirect.com/science/article/pii/S1574954124003820Animal welfareAnimal trackingBehaviour classificationDeep learningComputer visionCoping
spellingShingle Matthias Zuerl
Philip Stoll
Ingrid Brehm
Jonas Sueskind
René Raab
Jan Petermann
Dario Zanca
Ralph Simon
Lorenzo von Fersen
Bjoern Eskofier
Automated long-term monitoring of stereotypical movement in polar bears under human care using machine learning
Ecological Informatics
Animal welfare
Animal tracking
Behaviour classification
Deep learning
Computer vision
Coping
title Automated long-term monitoring of stereotypical movement in polar bears under human care using machine learning
title_full Automated long-term monitoring of stereotypical movement in polar bears under human care using machine learning
title_fullStr Automated long-term monitoring of stereotypical movement in polar bears under human care using machine learning
title_full_unstemmed Automated long-term monitoring of stereotypical movement in polar bears under human care using machine learning
title_short Automated long-term monitoring of stereotypical movement in polar bears under human care using machine learning
title_sort automated long term monitoring of stereotypical movement in polar bears under human care using machine learning
topic Animal welfare
Animal tracking
Behaviour classification
Deep learning
Computer vision
Coping
url http://www.sciencedirect.com/science/article/pii/S1574954124003820
work_keys_str_mv AT matthiaszuerl automatedlongtermmonitoringofstereotypicalmovementinpolarbearsunderhumancareusingmachinelearning
AT philipstoll automatedlongtermmonitoringofstereotypicalmovementinpolarbearsunderhumancareusingmachinelearning
AT ingridbrehm automatedlongtermmonitoringofstereotypicalmovementinpolarbearsunderhumancareusingmachinelearning
AT jonassueskind automatedlongtermmonitoringofstereotypicalmovementinpolarbearsunderhumancareusingmachinelearning
AT reneraab automatedlongtermmonitoringofstereotypicalmovementinpolarbearsunderhumancareusingmachinelearning
AT janpetermann automatedlongtermmonitoringofstereotypicalmovementinpolarbearsunderhumancareusingmachinelearning
AT dariozanca automatedlongtermmonitoringofstereotypicalmovementinpolarbearsunderhumancareusingmachinelearning
AT ralphsimon automatedlongtermmonitoringofstereotypicalmovementinpolarbearsunderhumancareusingmachinelearning
AT lorenzovonfersen automatedlongtermmonitoringofstereotypicalmovementinpolarbearsunderhumancareusingmachinelearning
AT bjoerneskofier automatedlongtermmonitoringofstereotypicalmovementinpolarbearsunderhumancareusingmachinelearning