This project aims at the advancement of the ability to extract spatial information from digital aerial imagery by taking advantage of geospatial databases to support and guide object extraction operations. It deals with aerial images representing scenes for which prior or complementary information already exists. Examples of such information are pre-existing digital maps, digital terrain models, and spatial information systems in general. The research plan involves: (1) matching images to existing databases for change detection; (2) analysis of scale differences between database information and image; and (3) developing metadata structures to convey accuracy information for objects contained in geospatial databases. By embedding object extraction processes within the framework of spatial information systems, digital image analysis will be able to exploit the advantages offered by the availability of spatial data from various sources and in diverse formats, and, in turn, contribute to the improvement of the temporal and quantitative quality and completeness of the data contained in those sources. The educational aspect of the project includes initiatives designed to take advantage of and incorporate the project research advancements in the graduate and undergraduate curriculum, as well as in the high-school outreach program of the Department of Spatial Information Engineering. A 3-day workshop, with participation of U.S. and international experts is also planned. Combined, the issues addressed in this project will substantially advance science in digital image processing and analysis, and will complement parallel advancements in a variety of related disciplines, most notably digital libraries, geographic information systems, and remote sensor technology.
