Detection of Calving Activity in Dairy Cows Through Computer Vision

Calving is a critical event in dairy farming, as abnormal calving can lead to calf mortality, health complications for the cow, and economic losses for farmers. These risks can be minimized by the timely detection of calving onset, which can be determined from animal behaviour. Ear position is a behavioural indicator of cows’ emotional states and a novel indicator of calving onset. However, computer vision models are needed for continuous monitoring of these behaviours and to validate their usefulness in determining calving onset. The objective of this project is to develop computer vision models to monitor dairy cow behaviour before calving, particularly focusing on ear positions, and to investigate the potential of these behavioural indicators for detecting the onset of calving. The host group at Vetmeduni Vienna has developed research on calving monitoring and has previously explored other behavioural indicators. Adding ear position analysis will strengthen their research, while the intern from the University of Manitoba will gain hands-on experience with new feature-extraction approaches using computer vision models. The project will establish research collaborations and strengthen the research capacity of both groups through the exchange of knowledge and methodologies for digital livestock monitoring.

Faculty Supervisor:

Gabriel Dallago

Student:

Partner:

University of Veterinary Medicine Vienna

Discipline:

Life Sciences

Sector:

Agriculture and Food; Artificial Intelligence

University:

University of Manitoba

Program: