The Centre for Machine Vision (CMV) at UWE Bristol have recently won funding to investigate towards a Holistic Assessment of Animal Welfare using Emotion and Deep Learning, building on prior work from CMV.
The project aims to develop technology for automated assessment of animal emotional wellbeing through the interpretation of body language, informed by work in human activity and emotion recognition using AI. Body posture and movement, which together characterise a wider body language, manifest as varying body shapes/poses and movements. The team will utilise human eye tracking to identify holistic spatial temporal animal features linked to perceived animal emotional states, then apply this knowledge via a novel form of supervised machine learning.
The project comprises of five partners including BOKU University, Scotland’s Rural College, University College Dublin, Linnaeus University and UWE Bristol.
The call was run by the European Partnership on Animal Health and Welfare with each partner funded by their national funder, DEFRA in UWE Bristol’s case.
The total grant is €1,459,800, with €492,000 allocated to CMV/UWE. There has also been a spinout InnovateUK project, “Pig Health Station” aimed at realising a commercial product, arising from the work.
The interdisciplinary team will explore computer vision-based machine learning techniques to train machine models with numerous examples of pig body language corresponding to different animal emotional states (ground truth), such as positive emotions associated with reward or negative emotions caused by unfamiliar environments. With extensive examples including structured treatments and environments to create a spectrum of emotional experiences, they aim to correlate specific animal stances and movements with given emotions and levels of arousal.
Through a system of detected trends and alerts, AI enabled automation could offer a powerful means to identify animals needing follow-up interventions in a timely manner, ensuring animal wellbeing, reducing production costs (e.g. treatments, morbidity) and antimicrobial usage (e.g. fewer blanket treatments).
The project will be led by Associate Professor of Computer Vision and Machine Learning Dr Wenhao Zhang, Lecturer in Robotics and Machine Vision Dr Disi Chen and Professor of Machine Vision Professor Melvyn Smith.