CAMERA CALIBRATION WITHOUT FEATURE-EXTRACTION

This paper presents an original approach to the problem of camera cali bration using a calibration pattern, It consists of directly searching for the camera parameters that best project three-dimensional points of a calibration pattern onto intensity edges in an image of this patt ern, without explicitly extracting the edges. Based on a characterizat ion of image edges as maxima of the intensity gradient or zero-crossin gs of the Laplacian, we express the whole calibration process as a one -stage optimization problem. A classical iterative optimization techni que is used in order to solve it. Our approach is different from the c lassical calibration techniques which involve two consecutive stages: extraction of image features and computation of the camera parameters. Thus, our approach is easier to implement and to use, less dependent on the type of calibration pattern that is used, and more robust. Firs t, we describe the details of the approach, Then, we show some experim ents in which two implementations of our approach and two classical tw o-stage approaches are compared, Tests on real and synthetic data allo w us to characterize our approach in terms of convergence, sensitivity to the initial conditions, reliability, and accuracy. (C) 1996 Academ ic Press, Inc.