Fitted Plane Automatic Extraction Algorithm of 3-D Laser Scanning

Abstract:

On the basis of deep research on existing point cloud segmentation and fitting algorithms, shortages of these algorithms are pointed out. Fully utilizing the intrinsic characteristics of scanned line data, new algorithms are proposed. RANSAC algorithm is improved. The improved algorithm is more robust and efficient compared with existing robust algorithms. Using the improved algorithm, better extraction result and more rational segmentation result can be obtained. A weight determining algorithm for ends of fitted line segments used in plane fitting is proposed, which solves the problem existing in traditional algorithms that ends of line segments can’t be used in plane fitting directly because of their different weights. Besides, a set of integral invalid plane removing algorithm is proposed. Experiments indicate that better plane extraction results of point cloud can be achieved using the proposed algorithm.