For access to this article, please select a purchase option:
Buy conference paper PDF
Buy Knowledge Pack
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
An outline is provided of a research programme at a national mapping agency, that aims to use computer vision tools modelled upon the theories of vision perception to improve the efficiency of the update of topographic maps. Based upon the underlying principles of top-down and bottom-up influences on image interpretation, case studies are presented that illustrate results produced after the application of robust algorithms for extracting low-level `primitive' information from aerial photography. In addition to contributing to research that aims to produce automatic mapping systems, it is intended that algorithms for producing these primitives will form the basis of semi-automated tools that help photogrammetric operators update maps in an increasingly efficient manner. The work presented here is an outline of research programme, upon which the author gratefully acknowledges the contributions of Panja Sai-Ui (2003), Paolo Gamba et al. (2004), Padraig Corcoran and Nick Donnelly.