An Iterative Image Registration Technique with an Application to Stereo Vision (DARPA)

Abstract

Image registration finds a variety of applications in computer vision. Unfortunately, traditional image registration techniques tend to be costly. We present a new image registration technique that makes use of the spatial intensity gradient of the images to find a good match using a type of Newton-Raphson iteration. Our technique is faster because it examines far fewer potential matches between the images than existing techniques. Furthermore, this registration technique can be generalized to handle rotation, scaling and shearing. We show how our technique can be adapted for use in a stereo vision system. Note: Essentially the same, but shorter version of this paper was presented and included in the Proc. 7th International Joint Conference on Artificial Intelligence (IJCAI) 1981, August 24-28, Vancouver, British Columbia, pp.674-679. When you refer to the work, please refer to the IJCAI paper.