“The system comprises an input unit operable to obtain images of a passive non-luminous object held by a user as a video game controller. The system also comprises an object detector and an object pose detector to detect the object and its respective pose in the images obtained. The pose detector is configured to detect the pose of the object based on at least one of a contour detection operation and the output of a machine learning model that has been trained to detect the poses of passive non-luminous objects in images. ” it reads in the patent.