Simultaneous feature tracking and three-dimensional object reconstruction from an image sequence

Most existing work on the recovery of scene structure from an image sequence assume prior knowledge of the camera or do not attempt to recover metric geometry, and that feature points have been extracted with the required correspondences established, often by human operators. This paper presents a scheme that removed the above assumptions. Using an extended Kalman filter (EKF) framework the scheme performs simultaneous corner feature tracking with correspondence analysis, and the reconstruction of three-dimensional (3D) rigid objects. The paper introduces the concept of individual global rotation quaternions and translational offset vectors so that it is not necessary for all features associated with an object to be present in the first frame of the image sequence. Experiments on two image sequences containing a soccer ball and a model house show the potential and effectiveness of the scheme.