This paper describes a system for analysis of aerial images of urban areas using multiple images from different viewpoints and its evaluation. The proposed approach combines bottom-up and top-down processing. In this paper the emphasis is on the discussion of the experimental evaluation. To evaluate statistically the performance of the system, a set of 100 realisations of 5 images from different viewpoints was used, which was generated by combining real and ray-traced images. The experiments show a significant improvement of reliability and accuracy if multi-view imagery is used instead of single-view.
|Title of host publication||Proceedings of the 2nd Ascona Workshop 1997, Automatic Extraction of Man-Made Objects from Aerial and Images II|
|Place of Publication||Basel|
|Number of pages||10|
|Publication status||Published - 1997|
|Event||Automatic Extraction of Man-Made Objects from Aerial and Images (II): 2nd Ascona Workshop 1997 - Ascona, Switzerland|
Duration: 5 May 1997 → 5 May 1997
|Workshop||Automatic Extraction of Man-Made Objects from Aerial and Images (II)|
|Period||5/05/97 → 5/05/97|
Spreeuwers, L. J., Schutte, K., Schutte, K., & Houkes, Z. (1997). A model driven approach to extract buildings from multi-view aerial imagery. In Proceedings of the 2nd Ascona Workshop 1997, Automatic Extraction of Man-Made Objects from Aerial and Images II (pp. 109-118). Basel: Birkhäuser.