Plane extraction for indoor place recognition

In this paper, we present an image based plane extraction method well suited for real-time operations. Our approach exploits the assumption that the surrounding scene is mainly composed by planes disposed in known directions. Planes are detected from a single image exploiting a voting scheme that takes into account the vanishing lines. Then, candidate planes are validated and merged using a region grow- ing based approach to detect in real-time planes inside an unknown in- door environment. Using the related plane homographies is possible to remove the perspective distortion, enabling standard place recognition algorithms to work in an invariant point of view setup. Quantitative Ex- periments performed with real world images show the effectiveness of our approach compared with a very popular method.