19 August 2011 Fragmentary area repairing on the edge of 3D laser point cloud based on edge extracting of images and LS-SVM
Author Affiliations +
Abstract
In the process of hole-repairing in point cloud, it's difficult to repair by the indeterminate boundary of fragmentary area in the edge of point cloud. In view of this condition, the article advances a method of Fragmentary area repairing on the edge of point cloud based on edge extracting of image and LS-SVM. After the registration of point cloud and corresponding image, the sub-pixel edge can be extracted from the image. Then project the training points and sub-pixel edge to the characteristic plane that has being constructed to confirm the bound and position for re-sampling. At last get the equation of fragmentary area to accomplish the repairing by Least-Squares Support Vector Machines. The experimental results demonstrate that the method guarantees accurate fine repairing.
© (2011) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ziming Zhao, Ziming Zhao, Xiangyang Hao, Xiangyang Hao, Songlin Liu, Songlin Liu, Song Zhao, Song Zhao, "Fragmentary area repairing on the edge of 3D laser point cloud based on edge extracting of images and LS-SVM", Proc. SPIE 8192, International Symposium on Photoelectronic Detection and Imaging 2011: Laser Sensing and Imaging; and Biological and Medical Applications of Photonics Sensing and Imaging, 81922V (19 August 2011); doi: 10.1117/12.900779; https://doi.org/10.1117/12.900779
PROCEEDINGS
8 PAGES


SHARE
Back to Top