An information processing apparatus detects an object queue from a video frame and generates tracking information indicating a position of each tracking target object, where each object included in the object queue is the tracking target object. The information processing apparatus generates queue behavior information related to a behavior of the object queue at a first time point using the tracking information at the first time point. The information processing apparatus computes an estimated position of each tracking target object at a second time point later than the first time point based on the tracking information and the queue behavior information at the first time point. The information processing apparatus updates the tracking information based on the position of each object detected from the video frame at the second time point and the estimated position of each tracking target object at the second time point.