True orthoimage generation by mutual recovery of occlusion areas

摘要

Demand for orthoimages is increasing as a crucial component of geographic information systems (GISs). Orthoimages are geometrically equivalent to planimetric maps, which show true geographic locations of terrain features. To produce orthoimages, geometric distortions from camera tilt and relief displacement from perspective images must be corrected. Traditionally, removing such distortions has been accomplished by differential rectification in a pixel-by-pixel fashion. However, this method cannot produce true orthoimages because of the double-mapping problem. We propose a method of generating patch-based true orthoimages for surface patches in buildings. The proposed method utilizes three-dimensional (3D) building model data. Patches from the data were projected onto aerial images to extract image patches and analysis of the superstructures was performed. Because orthoimages are generated for each building, the orthoimage quality is enhanced when using building data with a high level of detail. Instead of performing the complex visibility analysis of existing approaches, this article identifies occlusion areas based on unit surfaces of buildings and presents mutual recovery of occlusions using multiple images. To evaluate the feasibility of the method, experiments were performed with real datasets: (1) a building with a dome superstructure, (2) high-rise buildings close to each other, and (3) buildings with various shapes.