Automated activity monitoring using a visual sensor

Automated activity monitoring becomes important in many applications such as healthcare. In this paper, we propose an automated solution for measuring the daily-life activities of livestock by using video data in order to manage the healthcare problem of group-housed pigs. We first extract activity data from the video and then measure the amount of the daily-life activities caused by group-housed pigs. From the experimental results, we believe our method can be either a standalone solution or an additional solution to known methods for detecting abnormal behavior in group-housed pigs accurately.