TERRESTRIAL LASER SCANNING IN ARCHITECTURAL HERITAGE – DEFORMATION ANALYSIS AND THE AUTOMATIC GENERATION OF 2D CROSS-SECTIONS

Thanks to its speed and accuracy, terrestrial laser scanning is gaining importance in the field of architectural and cultural heritage. Laser scanners are field-of-view devices that offer a dense point-wise sampling of an object’s geometry. The first part of this article addresses the question whether laser scanning produces sufficiently accurate results to be used for deformation monitoring of historical structures. A test setup using a masonry arch was prepared in which different scenarios were simulated. The structure was scanned at different times while moving one of its legs and the influence of different scan resolutions on the accuracy and the detectability of deformations were tested. Using a different setup, the influence on accuracy of different targets configurations, in particular orientations and distances to the scanner were tested. In a second part, two prototype algorithms are presented for the automatic generation of cross sections based on point clouds. The first method is based on point splats. Point splats are an alternative for meshes for the surface-like reconstruction of point clouds. Their main advantages are the low computational cost and the ability to give an accurate representation of sharp edges and details. The cross sections obtained from our algorithm are compared to similar cross sections obtained from a mesh based surface representation. The second proposed method segments a sliced point cloud into outlier-free clusters based on techniques from robust statistics. The cluster is grown by fitting a parametric model and computing the residuals using a moving least squares approach. This procedure generates a piecewise smooth cross-section with sharp discontinuity representations. In order to prove the usability of the algorithm, the cross sections obtained from this algorithm are compared to similar cross sections obtained from a mesh based surface representation.status: publishe