A system to capture an image and determine a position of an object utilizes a camera. A first processing module recognizes a set of predetermined landmarks, including a first landmark and remainder landmarks, in the image. A second processing module determines an actual location of the first landmark in the image, and applies at least one filtering scheme to estimate positions of the remainder landmarks in the image. A third processing module determines a pose of the object based on the actual location of the first landmark and the estimated positions of the remainder landmarks.