Building extraction from oblique airborne imagery based on robust façade detection

A large number of applications and research fields rely on up-to-date and accurate representation of existing buildings, for example in GIS or 3D city models. Besides verification of existing building datasets, the detection of new objects from remote sensing data is a major task in digital photogrammetry. This paper presents a new approach on building detection and simple reconstruction using airborne oblique images only. Façades are detected in oblique images using edge and height information. The latter is extracted from the same images using a dense image matching technique, implying the need for stereo overlap at the particular façade. The façades are represented as vertical planes in object space and are used to define building hypotheses. These initial buildings are then verified and refined employing the point cloud as derived from multiple image dense matching. The method has been tested on almost 400 buildings in two areas which include different building structures. The results show that the detection rate depends on the number of viewing directions available at a particular building. A building is considered to be detected as soon as any portion of it is detected by our algorithm. Accordingly the correctness is constant above 90%, demonstrating the robustness of the approach. The completeness varies from 67% to 95%, while the geometric accuracy is limited because only box models are fitted to façades. Thus, the next step in the research will be to adapt the outline delineation to irregular buildings.