Mosaics of images from architectural and heritage structures

This paper presents an automatic robust system which relies only on the information contained within the original images for the construction of massive composite mosaic images from close-range and high-resolution originals, such as those obtained when imaging architectural and heritage structures. We first apply the Harris Corner Detector to extract a selection of corners and, then, employ both the intensity correlation and the spatial correlation between the corresponding corners for matching them. We estimate the lens distortion parameter and the eight-parameter planar projective transformation matrix via the Levenberg-Marquardt algorithm. After the pairwise registration stage, we used a global optimization strategy, solving a linear system of equations to produce a globally consistent alignment of the entire set of original images. Lastly, image fusion using a weighted blending function together with intensity compensation produces an effective seamless mosaic image. Comparisons with current commercial image-mosaic software are favourable.