Dynamic Multi-Behaviour, Orientation-Invariant Re-Identification of Holstein-Friesian Cattle
Open Access
Abstract
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.Keywords
Funding Information
- Fonds Wetenschappelijk Onderzoek (1131821N)
- Flemish Government (1131821N)
This publication has 31 references indexed in Scilit:
- FRCE: Transformer-based feature reconstruction and cross-enhancement for occluded person re-identificationExpert Systems with Applications, 2024
- Recognition of European mammals and birds in camera trap images using deep neural networksIET Computer Vision, 2024
- The interconnection of hierarchy, affiliative behaviours, and social play shapes social dynamics in Maremmana beef cattleApplied Animal Behaviour Science, 2023
- Classification of pig calls produced from birth to slaughter according to their emotional valence and context of productionScientific Reports, 2022
- Cow identification in free-stall barns based on an improved Mask R-CNN and an SVMComputers and Electronics in Agriculture, 2022
- Unsupervised Pre-training for Person Re-identification2021
- Visual identification of individual Holstein-Friesian cattle via deep metric learningComputers and Electronics in Agriculture, 2021
- Plant species classification using deep convolutional neural networkBiosystems Engineering, 2016
- Scalable Person Re-identification: A Benchmark2015
- Social relationships in domestic cattle under modern management techniquesBolletino di zoologia, 1980