2 March 2016 Automatic registration of laser-scanned point clouds based on planar features
Author Affiliations +
Proceedings Volume 9901, 2nd ISPRS International Conference on Computer Vision in Remote Sensing (CVRS 2015); 990103 (2016) https://doi.org/10.1117/12.2234791
Event: 2015 ISPRS International Conference on Computer Vision in Remote Sensing, 2015, Xiamen, China
Abstract
Automatic multistation registration of laser-scanned point clouds is a research hotspot in laser-scanned point clouds registration. Some targets such as common buildings have plenty of planar features, and using these features as constraints properly can bring about high accuracy registration results. Starting from this, a new automatic multistation registration method using homologous planar features of two scan stations was proposed. In order to recognize planes from different scan stations and get plane equations in corresponding scan station coordinate systems, k-means dynamic clustering method was improved to be adaptive and robust. And to match the homologous planes of the two scan stations, two different procedures were proposed, respectively, one of which was based on the “common” relationship between planes and the other referenced RANSAC algorithm. And the transformation parameters of the two scan station coordinate systems were calculated after homologous plane matching. Finally, the transformation parameters based on the optimal match of planes was adopted as the final registration result. Comparing with ICP algorithm in experiment, the method is proved to be effective.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Minglei Li, Minglei Li, Xinyuan Gao, Xinyuan Gao, Li Wang, Li Wang, Guangyun Li, Guangyun Li, } "Automatic registration of laser-scanned point clouds based on planar features", Proc. SPIE 9901, 2nd ISPRS International Conference on Computer Vision in Remote Sensing (CVRS 2015), 990103 (2 March 2016); doi: 10.1117/12.2234791; https://doi.org/10.1117/12.2234791
PROCEEDINGS
7 PAGES


SHARE
Back to Top