Feature preserving method for creating visual appearance models and virtual views from collective images

Abstract

With respect to satellite and aerial RGB images, ground-based acquisitions can provide a more detailed representation of a natural landscape, especially for steep slopes. Moreover, for some applications the generation of a new `virtual' view-point can provide a valuable visualization tool. Using such a technique, the visual appearance of a landscape (generated from one or several geo-registered images) can be seen from a new, specified vantage point. In this paper, we propose a method of generating a visual appearance model and subsequent virtual views, through a direct re-projection of visual content from source geo-registered images.