We use computer vision and AI to provide non-invasive, objective and continuous monitoring of animal behaviour and welfare. Our research spans behaviour recognition, early detection of health problems, and modelling of pain and positive and negative affective states. We address fundamental challenges from data collection and reliable ground truth to interpretable models that generalise across animals and environments. Ultimately, we aim to translate these methods into practical, scalable welfare-monitoring systems for real-world farm environments. 

Selected Publication:

* Guzhva, Oleksiy, Mahmoud, Marwa , Civan Dogan, Ozgur, Berthet, David and Högberg, Niclas (2026) The use of computer vision technologies for monitoring the behavior of dairy cattle. In: Berckmans, Daniel and Norton, Tomás (eds.) Advances in Precision Dairy and Beef Farming Technologies.

* Broomé, Sofia, Feighelstein, Marcelo, Zamansky, Anna, Carreira Lencioni, Gabriel, Haubro Andersen, Pia, Pessanha, Francisca, Mahmoud, Marwa , Kjellström, Hedvig and Salah, Albert Ali (2023) Going deeper than tracking: a survey of computer-vision based recognition of animal pain and emotions. International Journal of Computer Vision.

* Pessanha, Francisca, McLennan, Krista and Mahmoud, Marwa (2020) Towards Automatic Monitoring of Disease Progression in Sheep: a Hierarchical Model for Sheep Facial Expressions Analysis from Video. In: 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020)