CMU-CS-98-158
Computer Science Department
School of Computer Science, Carnegie Mellon University


CMU-CS-98-158

Research in Image Understanding and Automated Cartography:
1997-1998

David M. McKeown, Jr., G. Edward Bulwinkle,
Steven Douglas Cochran, Wilson A. Harvey, Chris McGlone,
Jeff McMahill, Michael F. Polis, Jefferey A. Shufelt

September 1998

This paper was presented at the
1998 DARPA Image Understanding Workshop
20-23 November 1998, Monterey, California.

Available by request only at Digital Mapping Laboratory Publications Archive


Keywords: Automated cartographic feature extraction, automated phototexturing, automated road detection, building detection, data fusion, performance evaluation, selection and generalization, scene registration, spatial databases, stereo, synthetic environments


This technical report presents an overview of our research in image understanding and automated cartography to support efficient representation and rapid construction of virtual world databases. Topics discussed include the use of aerial and terrestrial imagery to phototexture site models for visualization using photogrammetric principles, the refinement of multi-image stereo for DEM generation, and experiments towards the development of rigorous metrics and methods to evaluate cartographic feature extraction systems. Extensions to cartographic feature generalization, particularly to consider the effect of the terrain (3D) and proximity to other features (2D) are presented. Analysis of areal drainage to support integration into a simulation database using Voroni tessellation is also described.

28 pages

Return to: SCS Technical Report Collection
School of Computer Science homepage

This page maintained by reports@cs.cmu.edu