Research

Understanding animal emotions is an important part of animal welfare. Humans can recognise emotions by synthesising information from facial expressions, body posture, and movements. This ‘holistic approach’ has also been applied to the observation of animals, e.g. combining various body movements and -parts, or applying Qualitative Behavioural Assessment (QBA). However, which observable features in an animal's appearance and movements are used and which combinations of these are most relevant in perceiving differing states of valence and arousal remains unknown. Furthermore, until now the mentioned behavioural observations are very time consuming and therefore application in a commercial context is limited. Therefore, our project aims to explore a novel spatiotemporal form of supervised machine learning for holistic assessment of animal wellbeing by interpretation of body language, which is informed by work in human activity and emotion recognition using AI. Computer vision-based machine learning techniques will be applied, in which models will be trained using many examples of (individual) pig body language when experiencing known differing emotional states (as ground truth), e.g. positive emotions during feeding or negative emotions when in an unfamiliar environment. Over time, it should be possible to correlate the same or a similar animal's stance and/or type of movement with a particular valence and level of arousal. As a part of the model development, eye tracking during experimental observations will allow to explore aspects of human perception of animal body language. The model will be applied and tested under various other situations on-farm, in groups of animals, various husbandry and age situations. Automated detection of body postures and movements offers the possibility for extending welfare monitoring beyond human time limitations to provide monitoring of large numbers of animals. Such a system could both complement welfare monitoring (e.g. on-farm, on abattoirs, experimental situations).

The aim of SOWtrack project is to select animal-based measures (ABMs) and related management-, resource-and environmental-based (so called ‘context’) data for sows and piglets in different housing systems and practices, including slaughter, and then to collect in the field on a large scale and in a harmonised way across EU MSs. These data are to be used to develop a freely accessible prototype database for analysing the correlation between ABMs and related context data. This will enable future quantitative risk assessment of the on-farm welfare of sows and piglets. The database will be essential for keeping track of how welfare standards change over time and in the tracking and mitigation of welfare risks. This project will be based in countries that encompass the diversity of pig farming and management traditions in the EU. All Animal-Based Measures for Tracking Welfare in Sows and Piglets in the major housing systems, based on the EFSA Pig opinion (2022)1 are represented in at least four of the partner countries. This diversity will enable us to test ABMs in very different conditions and to collect context data from all major housing systems within the EU. This is a critical aspect of the SOWtrack proposal as inspectors and policy makers seek standardized protocols for collection of ABM data that scale across husbandry systems, differing management systems and contexts to cover the variation seen in the farms across Europe. At the same time the protocols must remain feasible and efficient to use in practice.