Visual Identification of Individual Holstein-Friesian Cattle via Deep Metric Learning

Abstract

Holstein-Friesian cattle exhibit individually-characteristic black and white coat patterns visually akin to those arising from Turing's reaction-diffusion systems.This work takes advantage of these natural markings in order to automate visual detection and biometric identification of individual Holstein-Friesians via convolutional neural networks and deep metric learning techniques. Existing approaches rely on markings, tags or wearables with a variety of maintenance requirements, whereas we present a totally hands-off method for the automated detection, localisation, and identification of individual animals from overheadimaging in an open herd setting, i.e. where new additions to the herd are identified without re-training. We propose the use of SoftMax-based reciprocal triplet loss to address the identification problem and evaluate the techniques in detail against fixed herd paradigms. We find that deep metric learning systems show strong performance even when many cattle unseen during system training are to be identified and re-identified -achieving 98.2% accuracy when trained on just half of the population. This work paves the way for facilitating the non-intrusive monitoring of cattle applicable to precision farming and surveillance for automated productivity, health and welfare monitoring, and to veterinary research

Towards Self-Supervision for Video Identification of Individual Holstein-Friesian Cattle: The Cows2021 Dataset

“…Considering that 182 classes were used and absolutely no training labelling was provided, results of 57.0% Top-1 accuracy and 76.9% Top-4 accuracy are an encouraging and practically relevant first step towards self-supervision in this domain. We know that individual Holstein-Friesian identification via supervised deep learning is a widely solved task with systems achieving near-perfect benchmarks when using multi-frame LRCNs [7] and good results even in partial annotation settings [5]. However, labelling efforts are laborious for supervised systems of larger herds; they require days if not weeks of manual annotation effort using visual dictionaries of animal ground truth.…”

“…4) images that contain the correct individual with a chance better than 3-in-4. As part of a toolchain, the approach presented can potentially dramatically reduce labelling times and help bootstrap production systems via combinations of self-supervised learning followed by open set fine-tuning [5].…”

“…Existing multi-object single-frame cattle detectors [11,7,5] produce image-aligned bounding-boxes that cannot avoid capturing several individuals in crowded scenes (see Fig. 3), which is problematic for subsequent identity assignment.…”

“…The last can conveniently operate from a distance above and has recently been implemented via supervised deep learning [6,3]. However, research into reducing manual labelling efforts for creating and maintaining such ID systems is in its infancy [5,44]. Particularly, unsupervised learning for coat pattern identification of Holstein-Friesians has not been tried and public datasets [4] are small to date.…”

Perspectives on individual animal identification from biology and computer vision

“…For the purposes of this review, we forgo discussion of individual identification in the context of the agricultural sciences, as circumstances differ greatly in those environments. However, we note that there is an emerging body of computer vision for the identification of livestock(76,77).…”