Texture extraction for building models from IR sequences of urban areas

Focus of the paper lies on automated texturing of 3d building modelswith images recorded with infrared (IR) cameras. Therefore, a datafusion of given 3d models provided by a GIS and recorded IR imagesequences is performed. Two concepts are presented to project the2d images into the 3d object space. In the first concept, the polygenesof the faces of the 3d model are projected into the IR image andmatched to the edges for assigning the correct parts of the imageto the corresponding faces of the model. These image parts are thenprojected onto the faces and stored as surface textures. The secondconcept uses homography to detect surface planes in two subsequentimages and matches theses planes to the 3d model. Because one imagedoes not show complete building facades, the extracted textures ofthe images are combined to create complete textures for the modelsurfaces. These textures can be used for feature extraction and objectrecognition for analyzing buildings.     «

Focus of the paper lies on automated texturing of 3d building modelswith images recorded with infrared (IR) cameras. Therefore, a datafusion of given 3d models provided by a GIS and recorded IR imagesequences is performed. Two concepts are presented to project the2d images into the 3d object space. In the first concept, the polygenesof the faces of the 3d model are projected into the IR image andmatched to the edges for assigning the correct parts of the imageto the corresponding faces of the mo...     »