Production System for Autonomous 3-dimensional Modeling with Lidar, Ifsar, and Photogrammetric Dsm Data

We describe an autonomous production system that utilizes Computational Fluid Dynamics (CFD) techniques and Partial Differential Equations (PDEs) to create accurate textured 3D site models with LiDAR, IFSAR, and stereo imagery. LiDAR is the data set of choice for specific urban scenes. IFSAR or stereo imagery is used for broad areas to mitigate cost. A high resolution Digital Surface Model (DSM) from any of these sources is input into the Harris’ LiteSiteTM toolkit. A DSM and high resolution imagery are all that are required to create an autonomously textured site model. Initially a DSM is input and an inpainting algorithm is used to autonomously repair voids due to low returns, system malfunctions, and coverage issues, for a DSM derived from IFSAR, LiDAR or optical data. PDE inpainting is derived from the Geometric Heat Equation (GHE) and the Navier-Stokes’ equation. Once system errors and coverage issues in the DSM are repaired, a surface based anisotropic diffusion algorithm is applied to remove system noise from the DSM. The anisotropic diffusion algorithm has its origins in the isotropic heat equation. The LiteSiteTM toolkit uses an autonomous PDE inpainting algorithm to fill voids in a bare-earth product where vegetation and building features have been extracted. The sides of the buildings are autonomously textured with oblique imagery while filling obscured areas with a 3D PDE or exemplar inpainting algorithm. A high quality textured urban 3D model derived from LiDAR is produced for specific areas merged with a broad area site model derived from correlated imagery or IFSAR DSM.