An algorithm is described for the automated registration of remotely sensed imagery that registers 6000 × 6000-pixel images in 8–18 minutes on an IBM RISC System/6000® workstation. The resulting registration is accurate to the subpixel level even in the presence of noise and large areas of change in the images. It is shown that the registration- mapping function for parallel projections has the form F(x,y) = A(x,y) + h(x,y)e, where A(x,y) is an affine transformation, h(x,y) is a function that depends on the topographic heights, and e is a vector that defines the epipolar lines. The algorithm determines the parameters of this equation using only the image data, without knowledge of the viewing orientations or scene point coordinates. The search for match points is then a one-dimensional search along the epipolar lines, which greatly increases the speed and accuracy of the registration.

Automated subpixel image registration of remotely sensed imagery

This paper describes a technique to align or register tWO overlapping images using only the contents of the images. A set of minuria features are computed for each image where the minutiae are defined as unique changes in direction in constant image intensity lines or small closed segmented regions. The resulting minutia patterns are then matched or correlated with the location of the correlation peak being the necessary translation needed to align the two images. The images must be approximately to the same scale. Rotations can be handled by successive application of the translation algorithm using specified rotations for one of the images. Motion of an object is detected from a simple comparison of its registered cwrdinates in the two images. The technique has been applied to many infrared and video images and works well where there is sufficient scene richness.

http://ieeexplore.ieee.org/iel5/8547/27033/01201014.pdf

J.C. Fisey

Papers

A technique for image registration and motion detection