Fusion of registered images of night scenery that are obtained from cameras tuned to different band-widths will be a significant component of future night-vision devices. A new algorithm for such multispectral image fusion is described. The algorithm performs gray-scale image fusion using a method based on principal components. The monochrome fused image is then colored by means of a suitable pseudocoloring technique to produce the fused color output image. The approach can easily be used for any number of bandwidths. Examples illustrate the algorithms use to fuse an intensified low-light visible image with another image obtained from a single forward-looking infrared camera. The algorithm may be implemented readily in hardware for use in night-vision devices as an important aid to surveillance and navigation in total darkness. The applicability of the technology to transportation is also discussed.