Thermal leakage detection on building facades using infrared textures generated by mobile mapping

Focus of the paper lies on automated texturing of 3d building models with images recorded with infrared (IR) cameras. Therefore, a data fusion of given 3d models and recorded IR image sequences is performed. A relative orientation of the images of the sequence is generated using Nistér's five-point algorithm and image triplets. This results in a point cloud of correspondence points and a relative camera path. The relative oriented image scene is then matched in two steps first to the recoded GPS camera path and then to the given building with least squares minimum distance. Textures are extracted for every image and its according camera position from all visible surfaces. Because one image does not show complete building facades, the extracted textures of the images are combined to create complete textures for the model surfaces. These textures can be used for feature extraction and object recognition for analyzing buildings and assigned 3d coordinates to found features and objects.