Mosaicing a Large Number of Widely Dispersed, Noisy, and Distorted Images: A Bayesian Approach

Abstract

In this paper we extend existing mosaicing algorithms to deal with image se-quences that are captured over a wide spatial area, exhibit large geometric and photometric distortions, and contain significant additive noise and other contami-nations, such as light reflections. The paper focuses on three main contributions. (1) We extend the camera model used for mosaicing to deal, not only with geomet-ric lens distortion, but with vignetting and permanent occluders as well. (2) We introduce a novel method for global image alignment based on a technique from the robotics literature, together with a novel optimization strategy, the folding al-gorithm, to guarantee global convergence. (3) We utilize techniques developed in the super-resolution literature for restoration of the final image mosaic from the contaminated input images. The estimation of camera parameters, the global alignment and the final mosaic are all derived within a unifying Bayesian frame-work, starting with the single objective of obtaining the maximum a posteriori estimate of the final mosaic, given the input images. Our approach is illustrated with results on a complex and challenging image sequence obtained from a state of the art robotics application.