Automatic assessment of dairy cattle body condition score using thermal imaging

Authors:
I. Halachmi;M. Klopčič;P. Polak;D. J. Roberts;J. M. Bewley
Affiliations:
Agricultural Research Organization, ARO, the Volcani Center, Israel;Dept. of Animal Science, Biotechnical Faculty, University of Ljubljana, Domzale, Slovenia;Inst. for Animal Production, Slovak Agricultural Research Center, Nitra, Slovakia;SAC Dairy Research Centre, Hestan House, The Crichton, Dumfries, Scotland, UK;Dept. of Animal and Food Sciences, University of Kentucky, Lexington, KY, USA
Venue:
Computers and Electronics in Agriculture
Year:
2013

Citing 1
Cited 0

Comparison of segmentation algorithms for cow contour extraction from natural barn background in side view images

Computers and Electronics in Agriculture

Quantified Score

Hi-index	0.00

Visualization

Abstract

Automatic and objective dairy cow body condition scoring has the potential to be used as a feed, reproduction, health and longevity management tool. The feasibility of including a body shape measurement in automatic monitoring of body condition was evaluated. The hypothesis tested was that the body shape of a fatter cow is more round than that of a thin cow and, therefore, may better fit a parabolic shape. The more prominent hooks and the tailhead depressions of a thin cow tended to diverge from the parabolic shape. An image-processing model appraised body shape. The novelties in this study compared to the previous ones (Halachmi et al., 2008; Bewley et al., 2008) were: (1) completing the full-automation of the system and (2) more accurate reference, not ultrasound. The model was implemented and its outputs were validated against manual body condition scoring (BCS) of 186 Holstein-Friesian cows. Pearson correlation between the thermally sensed BCS and the manual BCS was 0.94.