Edge landmarks in monocular SLAM

While many visual simultaneous localisation and mapping (SLAM) systems use point features as landmarks, few take advantage of the edge information in images. Those SLAM systems that do observe edge features do not consider edges with all degrees of freedom. Edges are difficult to use in vision SLAM because of selection, observation, initialisation and data association challenges. However, a map that includes edge features contains higher-order geometric information useful both during and after SLAM. We define a well-localised edge landmark and present an efficient algorithm for selecting such landmarks. Further, we describe how to initialise new landmarks, observe mapped landmarks in subsequent images, and deal with the data association challenges of edges. Initial operation of these methods in a particle-filter based SLAM system is presented.