Reconstructing the 3D thermal model of indoor environment from unorganized data set acquired by 3D laser scans and thermal imaging camera

After recording data sets using a 3D laser scanner, the logical step would be to reconstruct 3D model from given points. This paper proposes one solution to the reconstruction of 3D model. It combines splatting methods with polygonalization to achieve most accurate 3D model of an indoor mobile robot environment with fast execution and rendering time. The main objective of the work, which was done as a part of ThermalMapper project, was to generate an accurate mesh of the indoor environment based on laser scans with added temperature scalars acquired by 6D SLAM method. This is useful for generating meshes of museums, buildings, tunnels, etc. which can be used for inspection and different analyses. A series of experiments demonstrate the usefulness and effectiveness of the proposed 3D surface reconstruction methods.