Objects trail-based analysis and control of video

Systems and methods for analyzing scenes from cameras imaging an event, such as a sporting event broadcast, are provided. Systems and methods include detecting and tracking patterns and trails. This may be performed with intra-frame processing and without knowledge of camera parameters. A system for analyzing a scene may include an object characterizer, a foreground detector, an object tracker, a trail updater, and a video annotator. Systems and methods may provide information regarding centers and spans of activity based on object locations and trails, which may be used to control camera field of views such as a camera pose and zoom level. A magnification may be determined for images in a video sequence based on the size of an object in the images. Measurements may be determined from object trails in a video sequence based on an effective magnification of images in the video sequence.

TECHNICAL FIELD (1) Embodiments of this invention are directed to object tracking, video and the field of augmented reality. BACKGROUND (2) Automatic tracking of objects from one or more cameras is a prominent area within the field of computer vision. Typically, it involves calibrating the camera, modeling the scene background, detecting the foreground regions, and employing a known tracking algorithm to derive the instantaneous location of objects within the field of view of the camera. Tracking systems are widely employed for applications such as defense and civil surveillance, traffic control, and game enhancement. In the case of game enhancement, player tracking systems in a sporting event can provide game statistics that may be presented to viewers, coaches, or players during a live broadcast or later for offline analysis and storage. Another use for player tracking from a video of a sporting event is annotation—the location of players may be highlighted and their maneuvers on the court or field may be trailed. Throughout this disclosure “court” will be used to encompass a court such as a basketball court, a field such as a football field, a rink such as a hockey rink, or any other defined area on which a sport may be played. (3) Tracking of objects or image patterns is generally achieved through an analysis of their corresponding image-regions in each video frame. Based on a metric measured between an object's model and the image-regions' (foregrounds') descriptors, the