Online lameness detection in dairy cattle using Body Movement Pattern (BMP)

In this paper a method for real time lameness detection in dairy cattle based on back posture analysis is presented. The system utilizes image processing techniques to automatically detect lameness based on new definition called Body Movement Pattern (BMP). The traditional Locomotion Scoring (LS) system that is widely used for manual lameness detection by expert people failed to classify the selected cows from a commercial farm in Estonia. The proposed system not only performs the detection in automatic way but also categorizes the level of lameness with high accuracy. Two ellipses are fitted on the back posture and the parameters of the ellipses in relation to the head position are used as features for classification of the lameness degree. The new method has been tested on more than 1200 cows with success rate of 92%.