Urban Position Estimation from One Dimensional Visual Cues

Abstract

We consider the problem of vision-based position estimation in urban environments. In particular, we are interested in position estimation from visual cues, but using only limited computational resources. Our particular solution to this problem is based on representing the variability of the "horizon" of the cityscape when seen from within the city; that is, the outlines of the rooftops of adjacent buildings. By encoding the image using only such a one-dimensional contour, we obtain an image encoding that is exceedingly compact. This, in turn, allows us to both efficiently transmit this representation to a remote "recognition engine" as well as allowing for an efficient storage and matching process. We outline our approach and representation, and provide experimental data supporting its feasibility.