A technique for monitoring the health of dairy cattle with a high degree of accuracy uses a camera and artificial intelligence (AI) to achieve a “smart” cowhouse. Detailed observation by AI-powered image analysis could enable early detection of injuries and illnesses that could impact the quantity and quality of milk production. Smart cowhouse. Courtesy of Osaka University. Researchers at Osaka University established a method for early detection of lameness in cows with an accuracy of 99 percent or higher by applying a technique developed for human gait analysis. The researchers waterproofed and dustproofed Microsoft Kinect, a camera-based sensor capable of measuring distance to an object, and set it in a cowshed. Based on a large number of cow gait images taken by the sensor, the team was able to characterize cow gaits, detecting cows with lameness through machine learning. Depth sensor installed in a cowhouse. Courtesy of Osaka University. “Our achievements will mark the start of techniques for monitoring cows using AI-powered image analysis,” said professor Yagi Yasushi. “This will contribute largely to realizing a smart cowhouse interlocked with an automatic milking machine and feeding robot, both of which have already been introduced to some dairy farms, as well as wearable sensors attached to cows under study. Gait feature. Courtesy of Osaka University. “By . . . showing farmers cow conditions in detail through automatic analysis of cow conditions, we can realize a new era of dairy farming in which farmers can focus entirely on health management of their cows and delivering high-quality dairy products,” Yasushi said. The research was presented at IPSJ SIG-CVIM: Computer Vision and Image Media Academic Conference, March 10-11, 2017, National Institute of Informatics, Tokyo.