Horizontal Plane Detection from 3D Point Clouds of Buildings

Meng Zhang, Guang Jiang, Chengke Wu and Long Quan

Electronics Letters


The detection of the horizontal plane or its normal direction is important in the processing of 3D point clouds of buildings. Generally, the horizontal plane is detected from clues of vanishing points of visual images or from the border detection of 3D point data. However, these methods are not fit for most building structures of various kinds. Presented is a novel detection method to extract directly the horizontal plane from 3D point clouds of buildings. This method makes use of the fact that the exterior sides of the buildings perpendicular to the ground and its normal direction must lie on the horizontal plane. Thus the horizontal plane can be detected according to the normal vector. Experimental results demonstrate that the method is simple andd robust.



@ARTICLE{6222090, author={M. Zhang and G. Jiang and C. Wu and L. Quan}, journal={Electronics Letters}, title={Horizontal plane detection from 3D point clouds of buildings}, year={2012}, volume={48}, number={13}, pages={764-765}, keywords={object detection;horizontal plane detection;3D point clouds;vanishing points;visual images;border detection;building structures}, doi={10.1049/el.2012.0126}, ISSN={0013-5194}, month={June}}