Segmentation of building fa ades from vehicle-borne laser scanning data based on mathematical morphology

Recently vehicle-borne laser scanning system equipped with linear array laser scanner, GPS and INS has played an important role on the acquisition of urban spatial data. In this paper, a method was proposed for the segmentation of building facades from vehicle-borne laser scanning data in the outdoor urban environment, which contains five steps including 1) preliminary filtering with depth histogram analysis; 2) binarization of point cloud; 3) mathematical morphology processing of binary image; 4) segmentation of binary image and 5) extracting building facades with the mapping relationships of vehicle-borne laser scanning data and binary image. Depth histogram analysis, calculation of grid size and determination of the number of dilation were described in detail. Finally, an experimental study was made to demonstrate the feasibility of the proposed method for the segmentation of urban building facades.