Segmentation of Building Models From Dense 3D Point-Clouds
|Authors||Bauer Joachim, Karner Konrad, Schindler K., Klaus Andreas, Zach Christopher|
27th Workshop of the Austrian Association for Pattern Recognition 2003, Laxenburg
This paper proposes an approach for the detection and partition of planar structures in dense 3D point clouds from facades. The aim is the creation of a polygonal model with a considerably lower complexity than the original data set. We perform a robust detection of the dominant facade planes and apply a sweep based scheme in order to detect structures like windows, doors, balconies in those planes.