Precise image registration and occlusion labeling

Image registration has traditionally been performed by estimating parametric transformation between two images. In this paper, we extend the standard approach to multiple images and adopt the photogrammetric process to improve accuracy of registration. In particular, we use a multi-head camera mount providing multiple non-overlapping images per time epoch and use multiple epochs which increase the number of images to be considered during the estimation process. The existence of a dominant scene plane in 3-space visible in all the images acquired from the multi-head platform formulated in a bundle block adjustment framework in the image space provides precise registration between the images.