Image registration in stereo-based multi-modal imaging systems

This paper describes an imaging system for the acquisition of physically disparate images, such as visible and infrared wavelength range images, together with an image registration algorithm. The algorithm makes use of 3D scene data obtained from stereo and integrates local and global registration methods in order to obtain registrations that have good positional accuracy and dense, gap-less image regions. The registration result has the resolution of the image with the highest resolution. Experimental results with a color CCD camera and a far-infrared thermal imager indicated that the proposed method is effective and accurate.