Camera self-calibration from video sequences with changing focal length

Camera self-calibration techniques make it possible to compute three-dimensional measurements of an observed scene from video sequences without prior knowledge of the camera intrinsic parameters. However, most previous techniques make the overly constraint assumption that camera intrinsic parameters remain constant throughout the image sequence. The self-calibration method described in this article generalises the camera model by adding into the intrinsic parameter set a variable focal length, whose change is approximated by a cubic B-spline. The modified intrinsic parameters are then calculated with adapted Kruppa equations, together with an initialization procedure that utilizes the genetic algorithm. Results obtained using synthetic image sequences are presented. It shows the algorithm's ability to trade the changing focal length (zooming) even under noisy conditions.