By Berckmans, Daniel and Leroy, Toon and Maertens, Willem and Sonck, Bart and Song, Xiangyu and Vranken, Erik, Computers and Electronics in Agriculture, 2008
Research Paper Web Link / URL:
http://www.sciencedirect.com/science/article/pii/S0168169908001440
http://www.sciencedirect.com/science/article/pii/S0168169908001440
Description
The occurrence of lameness in dairy cattle is of increasing importance in herd health management and herd productivity. Current practice, involves visual observation by human experts to score cow's locomotion in order to estimate the lameness in the herd. The trackway defined as “hind hoof compared to fore hoof position” is one of the main components to score the locomotion. However, because of the time-consuming observation method, lame cows are undiagnosed until the problem has become severe. Up till now there is no automatic (visual) method for detecting lameness in dairy cattle. The objective of our study was to make an automatic system for continuous on-farm detection and prediction of lameness in the farm by using vision techniques. The current focus was on demonstrating the possibility of capturing cow's hoof locations by vision and strong correlation between automatically calculated hoof trackway and visual locomotion scores. Fifteen selected lactating cows were scored visually by four trained observers at the Gent University Research Farm. Scoring varied from 1 (normal walking) to 5 (extremely lame). Side-view images with resolution of 1024 × 768 pixels were recorded when cows passed an experimental set-up freely. Recorded videos were split into sequences of bitmap images. After background subtraction, binary image operations, calibration and hoof separation, the trackway information containing hoof location in the real world and its related time in the video was calculated. The accuracy of automatically captured results was checked by comparing with the output from manually labeled hoof locations. The mean correlation coefficient of all measurements was 94.8%. Hence, the results suggest that the automatic method by vision analysis is feasible to present the cows’ real locomotion situations. The first result showed a positive linear relationship between cows’ trackways overlap and locomotion scores by human visualization. This research proved that vision techniques have great potential to be used for continuous quantification of lameness in cows.
The occurrence of lameness in dairy cattle is of increasing importance in herd health management and herd productivity. Current practice, involves visual observation by human experts to score cow's locomotion in order to estimate the lameness in the herd. The trackway defined as “hind hoof compared to fore hoof position” is one of the main components to score the locomotion. However, because of the time-consuming observation method, lame cows are undiagnosed until the problem has become severe. Up till now there is no automatic (visual) method for detecting lameness in dairy cattle. The objective of our study was to make an automatic system for continuous on-farm detection and prediction of lameness in the farm by using vision techniques. The current focus was on demonstrating the possibility of capturing cow's hoof locations by vision and strong correlation between automatically calculated hoof trackway and visual locomotion scores. Fifteen selected lactating cows were scored visually by four trained observers at the Gent University Research Farm. Scoring varied from 1 (normal walking) to 5 (extremely lame). Side-view images with resolution of 1024 × 768 pixels were recorded when cows passed an experimental set-up freely. Recorded videos were split into sequences of bitmap images. After background subtraction, binary image operations, calibration and hoof separation, the trackway information containing hoof location in the real world and its related time in the video was calculated. The accuracy of automatically captured results was checked by comparing with the output from manually labeled hoof locations. The mean correlation coefficient of all measurements was 94.8%. Hence, the results suggest that the automatic method by vision analysis is feasible to present the cows’ real locomotion situations. The first result showed a positive linear relationship between cows’ trackways overlap and locomotion scores by human visualization. This research proved that vision techniques have great potential to be used for continuous quantification of lameness in cows.
We welcome and encourage discussion of our linked research papers. Registered users can post their comments here. New users' comments are moderated, so please allow a while for them to be published.