Two- and Three-Dimensional Computer Vision Techniques for More Reliable Body Condition Scoring
Niall O’Mahony,
Lenka Krpalkova,
Gearoid Sayers,
Lea Krump,
Joseph Walsh,
Daniel Riordan
Affiliations
Niall O’Mahony
IMaR Research Centre, Department of Agricultural and Manufacturing Engineering, School of Science Technology Engineering and Maths (STEM), Munster Technological University, Kerry Campus, V92 CX88 Tralee, Ireland
Lenka Krpalkova
IMaR Research Centre, Department of Agricultural and Manufacturing Engineering, School of Science Technology Engineering and Maths (STEM), Munster Technological University, Kerry Campus, V92 CX88 Tralee, Ireland
Gearoid Sayers
IMaR Research Centre, Department of Agricultural and Manufacturing Engineering, School of Science Technology Engineering and Maths (STEM), Munster Technological University, Kerry Campus, V92 CX88 Tralee, Ireland
Lea Krump
IMaR Research Centre, Department of Agricultural and Manufacturing Engineering, School of Science Technology Engineering and Maths (STEM), Munster Technological University, Kerry Campus, V92 CX88 Tralee, Ireland
Joseph Walsh
IMaR Research Centre, Department of Agricultural and Manufacturing Engineering, School of Science Technology Engineering and Maths (STEM), Munster Technological University, Kerry Campus, V92 CX88 Tralee, Ireland
Daniel Riordan
IMaR Research Centre, Department of Agricultural and Manufacturing Engineering, School of Science Technology Engineering and Maths (STEM), Munster Technological University, Kerry Campus, V92 CX88 Tralee, Ireland
This article identifies the essential technologies and considerations for the development of an Automated Cow Monitoring System (ACMS) which uses 3D camera technology for the assessment of Body Condition Score (BCS). We present a comparison of a range of common techniques at the different developmental stages of Computer Vision including data pre-processing and the implementation of Deep Learning for both 2D and 3D data formats commonly captured by 3D cameras. This research focuses on attaining better reliability from one deployment of an ACMS to the next and proposes a Geometric Deep Learning (GDL) approach and evaluating model performance for robustness from one farm to another in the presence of background, farm, herd, camera pose and cow pose variabilities.
