Dynamic Multi-Behaviour, Orientation-Invariant Re-Identification of Holstein-Friesian Cattle

To perform reliable animal re-identification, most available algorithms require standardised animal poses. However, this lack of versatility prevents widespread application of these algorithms in behavioural research and commercial environments. To circumvent this, we incorporated information about...

Full description

Saved in:
Bibliographic Details
Main Authors: Maarten Perneel, Ines Adriaens, Jan Verwaeren, Ben Aernouts
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/10/2971
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849719616720338944
author Maarten Perneel
Ines Adriaens
Jan Verwaeren
Ben Aernouts
author_facet Maarten Perneel
Ines Adriaens
Jan Verwaeren
Ben Aernouts
author_sort Maarten Perneel
collection DOAJ
description To perform reliable animal re-identification, most available algorithms require standardised animal poses. However, this lack of versatility prevents widespread application of these algorithms in behavioural research and commercial environments. To circumvent this, we incorporated information about the orientation and behaviour of the animals in an embedding-based algorithm to re-identify Holstein-Friesian cattle. After all, the orientation and behaviour of an animal determine which body parts of an animal are visible from the camera’s perspective. We evaluated our approach using a dataset with more than 11,000 instance segments of Holstein-Friesian cattle, but our methodology is readily generalisable to different animal species. Our results show that incorporation of informative metadata parameters in the re-identification procedure increases the rank-1 re-identification accuracy from 0.822 to 0.894, corresponding to a 40% reduction in the number of incorrectly identified animals.
format Article
id doaj-art-7b2688eefa2f47a29f1b2a486e4d202f
institution DOAJ
issn 1424-8220
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-7b2688eefa2f47a29f1b2a486e4d202f2025-08-20T03:12:07ZengMDPI AGSensors1424-82202025-05-012510297110.3390/s25102971Dynamic Multi-Behaviour, Orientation-Invariant Re-Identification of Holstein-Friesian CattleMaarten Perneel0Ines Adriaens1Jan Verwaeren2Ben Aernouts3Department of Biosystems, Division of Animal and Human Health Engineering, KU Leuven, Campus Geel, Kleinhoefstraat 4, 2440 Geel, BelgiumDepartment of Biosystems, Division of Animal and Human Health Engineering, KU Leuven, Campus Geel, Kleinhoefstraat 4, 2440 Geel, BelgiumDepartment of Data Analysis and Mathematical Modelling, Faculty of Bioscience Engineering, Ghent University, Coupure Links 653, 9000 Ghent, BelgiumDepartment of Biosystems, Division of Animal and Human Health Engineering, KU Leuven, Campus Geel, Kleinhoefstraat 4, 2440 Geel, BelgiumTo perform reliable animal re-identification, most available algorithms require standardised animal poses. However, this lack of versatility prevents widespread application of these algorithms in behavioural research and commercial environments. To circumvent this, we incorporated information about the orientation and behaviour of the animals in an embedding-based algorithm to re-identify Holstein-Friesian cattle. After all, the orientation and behaviour of an animal determine which body parts of an animal are visible from the camera’s perspective. We evaluated our approach using a dataset with more than 11,000 instance segments of Holstein-Friesian cattle, but our methodology is readily generalisable to different animal species. Our results show that incorporation of informative metadata parameters in the re-identification procedure increases the rank-1 re-identification accuracy from 0.822 to 0.894, corresponding to a 40% reduction in the number of incorrectly identified animals.https://www.mdpi.com/1424-8220/25/10/2971re-identificationpose estimationbehaviour classificationcattle
spellingShingle Maarten Perneel
Ines Adriaens
Jan Verwaeren
Ben Aernouts
Dynamic Multi-Behaviour, Orientation-Invariant Re-Identification of Holstein-Friesian Cattle
Sensors
re-identification
pose estimation
behaviour classification
cattle
title Dynamic Multi-Behaviour, Orientation-Invariant Re-Identification of Holstein-Friesian Cattle
title_full Dynamic Multi-Behaviour, Orientation-Invariant Re-Identification of Holstein-Friesian Cattle
title_fullStr Dynamic Multi-Behaviour, Orientation-Invariant Re-Identification of Holstein-Friesian Cattle
title_full_unstemmed Dynamic Multi-Behaviour, Orientation-Invariant Re-Identification of Holstein-Friesian Cattle
title_short Dynamic Multi-Behaviour, Orientation-Invariant Re-Identification of Holstein-Friesian Cattle
title_sort dynamic multi behaviour orientation invariant re identification of holstein friesian cattle
topic re-identification
pose estimation
behaviour classification
cattle
url https://www.mdpi.com/1424-8220/25/10/2971
work_keys_str_mv AT maartenperneel dynamicmultibehaviourorientationinvariantreidentificationofholsteinfriesiancattle
AT inesadriaens dynamicmultibehaviourorientationinvariantreidentificationofholsteinfriesiancattle
AT janverwaeren dynamicmultibehaviourorientationinvariantreidentificationofholsteinfriesiancattle
AT benaernouts dynamicmultibehaviourorientationinvariantreidentificationofholsteinfriesiancattle