Creating a 4D atlas of body composition and gait with 3D cameras and deep learning to inform next generation cattle health and welfare developments University of Bristol in United Kingdom

Background: High animal welfare and health practices are more important than ever to satisfy societal demands for the livestock sector. The use of precision monitoring instrumentation for dairy cattle is key to optimising animal health and welfare. During a successful ongoing collaboration between Bristol Robotics Laboratory (University of the West of England) and the John Oldacre Centre farm research platform at Bristol Veterinary School [1], we have established a new intensive monitoring testbed of six 3D depth cameras which each day provides unobtrusive stress-free recording of the dynamic 3D structure of each cow in our herd. Together with this, we have developed novel deep learning methods for identifying each individual purely through their distinctive body shape [2].

Aims and objectives: In this PhD project, the student will harness the massive amount of data our testbed produces over long time periods (>1 year) for each of our 180 cows to develop a deep learning powered 3D atlas over time that learns the main modes of variation in their body composition and gait as the cows mature as well as go through pregnancy and milk production.

Methods: Particular attention will be paid to both measuring and biomechanically modelling dynamic gait as they walk through the testbed in order to capture both healthy mobility as well as the early signs of disease such as lameness. The resulting model will be used as a research tool to develop further disease understanding and welfare interventions, and we will also investigate how the approach can be translated into commercial farm environments. For the later, it is expected that novel methods fitting the atlas to limited and low-cost camera configurations will be investigated. The studentship would suit either a mathematical or computational student interested in sustainable food production, or someone with veterinary or biosciences expertise who wishes to build up artificial intelligence skills – in either case a tailored training package will be developed to suit.

Key references:

[1] https://www.bristol.ac.uk/vet-school/research/john-oldacre-centre/

[2] https://arxiv.org/abs/2404.00172

Supervisors: The student will be based 50%/50% at two leading, geographically close institutes, and will benefit from a broad cross-disciplinary supervision team, led by Prof Andrew Dowsey (One Health Data Science) and Prof Mark Hansen (Machine Vision), who has published and commercialised state-of-the-art work in this area (HerdVision), and supported by welfare expert Prof Siobhan Mullan (University College Dublin).

Start date: Sept 2025

How to apply: See How to apply – SWBiosciences Doctoral Training Partnership

Candidate requirements:

See Eligibility – SWBiosciences Doctoral Training Partnership .

Standard University of Bristol eligibility rules for PhD admissions also apply. Please visit PhD Veterinary Sciences

Contacts: Contact the lead supervisor [email protected] if you have queries about the project. For queries about the SWBio DTP scheme contact [email protected]