Monitoring the position of animals in the outdoors can provide useful information in ecology and in agriculture. A common method is to use active sensors, such as GPS, to record their positions at constant intervals of time. But using active sensors can rapidly become expensive when several animals have to be monitored at the same time. Another method is to use a passive sensor to monitor the entire flock of animals. In this article, we propose a method to process images taken by a commercial drone in order to automate the tracking of animal activities. We developed a method that automatically detects goats from the images and tracks their activity using a combination of thresholding and supervised classification methods. We tested our method on 571 drone images taken over 11 days and found a sensitivity of 74% for animal detection and 78.3% for activity detection.