Non-intrusive automated measurement of dairy cow body condition using 3D video

Mark Hansen, Melvyn Smith, Lyndon Smith, Ian Hales and Duncan Forbes

Abstract

Regular scoring of a dairy herd in terms of various physical metrics such as Body Condition Score (BCS), mobility and weight are essential for maintaining high animal welfare. This paper presents preliminary results of an automated system capable of nonintrusively measuring BCS automatically as the cow walks uninhibited beneath a 3D camera. The system uses a ’rolling ball’ algorithm on the depth map which simulates how well a ball of a set radius fits the surface. In this way a measure of angularity is generated which is shown to be inversely related to BCS on 95 cows. The measurements are shown to be highly repeatable with 14 out of 15 cows being scored within one quarter BCS score repeatedly and seven of those being scored within an eighth of a BCS score.

Session

Workshop: Machine Vision of Animals and their Behaviour (MVAB 2015)

Files

Paper (PDF, 3M)

DOI

10.5244/C.29.MVAB.1
https://dx.doi.org/10.5244/C.29.MVAB.1

Citation

Bibtex

@inproceedings{MVAB2015_1,
	title={Non-intrusive automated measurement of dairy cow body condition using 3D video},
	author={Mark Hansen and Melvyn Smith and Lyndon Smith and Ian Hales and Duncan Forbes},
	year={2015},
	month={September},
	pages={1.1-1.8},
	articleno={1},
	numpages={8},
	booktitle={Proceedings of the Machine Vision of Animals and their Behaviour (MVAB)},
	publisher={BMVA Press},
	editor={T. Amaral, S. Matthews, T. Plötz, S. McKenna, and R. Fisher},
	doi={10.5244/C.29.MVAB.1},
	isbn={1-901725-57-X},
	url={https://dx.doi.org/10.5244/C.29.MVAB.1}
}