Samats – Texture Extraction Explained

The creation of detailed 3D buildings models, and to a greater extent the creation of entire city models, has become an area of considerable research over the last couple of decades. The accurate modeling of buildings has LBS (Location Based Services) applications in entertainment, planning, tourism and e-commerce to name just a few. Many modeling systems deployed to date require manual correspondences to be made across the image set in order to determine the models 3D structure. This paper describes SAMATS, a Semi-Automated Modelling and Texturing System, which has the capability of producing geometrically accurate and photorealistic building models without the need for manual correspondences from a set of geo-referenced terrestrial images. This paper is the third in a trilogy of publications describing the entire SAMATS system, and describes the third of three components that comprise the full functionality of the complete SAMATS implementation. It focuses on the texture extraction step in detail, while providing an overview only of SAMATS’ other two components.