Automatic 3d reconstruction and texture extraction for 3d building models from thermal infrared image sequences

This paper discusses the automatic texturing of building facades from thermal infrared image sequences. A fully automatic method is presented to refine GPS based positions using a relative orientation of the image sequence and preknowledge of a given building model in a bundle adjustment process. The resulting refined orientation parameters are used to project the infrared images of the sequence onto the building façade. The resulting partial textures are combined to get complete façade textures in the thermal infrared domain. The quality of the presented method is evaluated using RGB textures as ground truth and stochastic parameters from the adjustment process.     «

This paper discusses the automatic texturing of building facades from thermal infrared image sequences. A fully automatic method is presented to refine GPS based positions using a relative orientation of the image sequence and preknowledge of a given building model in a bundle adjustment process. The resulting refined orientation parameters are used to project the infrared images of the sequence onto the building façade. The resulting partial textures are combined to get complete façade textures...     »