A complete paper appears in CVPR 94.
We describe a system for detection and description of buildings in aerial scenes. This is a difficult task as the aerial images con tain a variety of objects. Low-level segmentation processes give highly fragmented segments due to a number of reasons. We use a perceptual grouping approach to collect these fragments and dis card those that come from other sources. We use shape properties of the buildings for this. We use shadows to help form and verify the hypotheses generated by the grouping process. This latter step also provides 3-D descriptions of the buildings. Our system has been tested on a number of examples and is able to work with overhead or oblique views.
For example, starting from an image, we extract line segments. These are collapsed into Linear structures and Junctions. A large number of (parallelgram) hypotheses are generated from these structures and a small number are selected. By analyzing the shadows, we verify several parallelgrams. From this result, we compute the heigth of the building and can construct an alternative display.