Development of a computer vision system to monitor pig locomotion

Abstract

Avoiding lameness or leg weakness in pig pro-duction is crucial to reduce cost, improve animal welfare and meat quality. Detection of lameness detection by the use of vision systems may as-sist the farmer or breeder to obtain a more ac-curate and robust measurement of lameness. The paper presents a low-cost vision system for measuring the locomotion of moving pigs based on motion detection, frame-grabbing and multi-variate image analysis. The first step is to set up a video system based on web camera technol-ogy and choose a test area. Secondly, a motion detection and data storage system are used to build a processing system of video data. The video data are analyzed measuring the proper-ties of each image, stacking them for each ani-mal and then analyze these stacks using multi-variate image analysis. The system was able to obtain and decompose information from these stacks, where components could be extracted, representing a particular motion pattern. These components could be used to classify or score animals according to this pattern, which might be an indicator of lameness. However, further improvement is needed with respect to stan-dardization of herding, test area and tracking of animals in order to have a robust system to be used in a farm environment.