Abstract

Recent growth of the geo-spatial information on the web has made it possible to easily access various and high quality geo-spatial datasets, such as road networks and high resolution imagery. Although there exist efficient methods to locate road intersections from road networks for route planning, there are few research activities on detecting road intersections from orthoimagery. Detected road intersections on imagery can be utilized for conflation, cityplanning and other GIS-related applications. In this paper, we describe an approach to automatically and accurately identifying road intersections from high resolution color orthoimagery. We exploit image metadata as well as the color of imagery to classify the image pixels as on-road/off-road. Using these chromatically classified image pixels as input, we locate intersections on the images by utilizing the knowledge inferred from the road network. Experimental results show that the proposed method can automatically identify the road intersections with 76.3% precision and 61.5% recall in the imagery for a partial area of St. Louis, MO.

Date

August 30, 2004

Authors

Ching-Chien Chen, Cyrus Shahabi, Craig A Knoblock

Conference

STDBM

Volume

4

Pages

17-24