|
|
|
Abstract
Automated construction of 3D building Models of urban area from LiDAR Digital surface models
Senthil Selvaraj
Senior Research Engineer
PASCO Geomatics India,
Email: selvaraj.senthil@gmail.com
A computer vision based automated method for 3D building modeling by using hough transformation and stable planar regions extracted from Digital Surface Model (DSM) is presented. These DSM's are produced from low-spatial-resolution airborne laser scanner (ALS) data or by the Stereo images of Airborne Digital Scanner (ADS40). It is an automated algorithm for construction of 3D Building models of the urban area from the DSM by using a Hough transformation and stable planar extraction. The Hough transformation which is applied after the non-linear resampling, reduces the error due to discontinuity in the edges and it is unaffected by the noise in the acquired data. Then with these edges resulting from the hough transformation, different planes are being constructed by stable planar region extraction. After the stable planar extraction, the roof edges formed by adjoining planes are computed by using the topologic relations and geometries of the extracted planar regions. Finally, a polyhedral description of the data is derived using the geometries of the stable planar regions, line segments of jump and/or boundary edges, and roof edges. Thus with this approach we would be able to construct and study each and every building in our study area individually. Also this approach relatively performs faster and yields a better accurate 3D models.
|
|
|