CLASSIFICATION OF MOBILE LASER SCANNING POINT CLOUDS OF URBAN SCENES EXPLOITING CYLINDRICAL NEIGHBOURHOODS

Cities developed on compressible soils are susceptible to land deformation. Its spatial and temporal monitoring and analysis are necessary for sustainable development of these cities. Techniques such as remote sensing or predictions based on soil characterization can be used to assess such deformations. The objective of this study is to combine these two using machine learning in an attempt to better predict and understand deformations.