Search

Initial building footprint extraction as well as inventory update are still achieved via manual, labor-consuming digitizing from imagery. An extraction methodology is presented that integrates automatic and manual processes. This integration provides the advantage of a repetitive action accomplished by a computer and superior human decision making. The suggested approach incorporates readily available GIS parcels layers to provide an easily replicable simplification process that can precede any extraction procedure. The results emphasize a great savings in time (and subsequently in cost) by using parcel-based partitioning during the image preprocessing and integrating with current common extraction workflows, including manual digitizing. We present a quantitative comparison between the suggested methodology and both an automatic and a fully manual extraction procedure. The approach shows consistent savings of more than 30 percent in time, extracting buildings for both commercial and residential parcels. [ABSTRACT FROM AUTHOR]

One of the most challenging problems in digital photogrammetry todayis automatic extraction of cartographic features from large-scale aerial images. Automatic detection of such features in general, and buildings in particular, will significantly improve the map compilation process as well as other tasks, such as DEM and orthophoto generation. This paper presents a semiautomatic approach for the extraction of buildings from large-scale images. The main goal is to recover three-dimensional (3D) outlines of buildings. The extraction should be sufficiently accurate, reliable, and efficient in order to comply with the high standards set by the photogrammetric community. In order to obtain a 3D description, the approach comprises stereo analysis for extracting building heights, along with a general knowledge of building geometry and shadow information. The paper explains the approach, presents experiments, and discusses the results. [ABSTRACT FROM AUTHOR]