%0 Conference Paper
%K Building Footprint
%K Line Extraction
%K Polygonization
%A Mark WuDunn
%A Avideh Zakhor
%A Samir Touzani
%A Jessica Granderson
%B SPIE Geospatial Informatics X
%D 2020
%G eng
%T ​Aerial 3D Building Reconstruction from RGB Drone Imagery
%8 06/2020
%X <p>3D Building Reconstruction is an important problem with applications in urban planning, emergency response,<br />and disaster planning. This paper presents a new pipeline for 3D reconstruction of buildings from RGB imagery<br />captured via a drone. We leverage the commercial software Pix4D to construct a 3D point cloud from RGB<br />drone imagery, which is then used in conjunction with image processing and geometric methods to extract a<br />building footprint. The footprint is then extruded vertically based on the heights of the segmented rooftops.<br />The footprint extraction involves two main steps, line segment detection and polygonization of the lines. To<br />detect line segments, we project the point cloud onto a regular grid, detect preliminary lines using the Hough<br />transform, refine them via RANSAC, and convert them into line segments by checking the density of the points<br />surrounding the line. In the polygonization step, we convert detected line segments into polygons by constructing<br />and completing partial polygons, and then filter them by checking for support in the point cloud. The polygons<br />are then merged based on their respective height profiles. We have tested our system on two buildings of several<br />thousand square feet in Alameda, CA, and obtained an F1 score of 0.93 and 0.95 respectively as compared to<br />the ground truth.</p>