摘要:
A process and a device for the automatic rectification of images, where at least one image is rectified by a mapping function onto a reference image and at least some of the parameters of the mapping function are unknown are disclosed. The process includes at least an extraction of at least three objects from the image; a detennination of at least three control points in the image, where characteristic points of the extracted objects are determined as control points; an assignment of the objects to objects in the reference image, where the objects in the two images are assigned on the basis of the similarity between the objects and/or on the basis of a vector grid, the vector grid being formed by connecting the characteristic object points, and a selection of a suitable mapping function and/or an adjustment of the parameters of the mapping function, where the mapping function is changed by changing the parameters in such a way that the cumulative error with respect to the positional differences between the projected control points and the corresponding points in the reference image is minimized.