21 July 2017 3D reconstruction from non-uniform point clouds via local hierarchical clustering
Author Affiliations +
Proceedings Volume 10420, Ninth International Conference on Digital Image Processing (ICDIP 2017); 1042038 (2017); doi: 10.1117/12.2281528
Event: Ninth International Conference on Digital Image Processing (ICDIP 2017), 2017, Hong Kong, China
Abstract
Raw scanned 3D point clouds are usually irregularly distributed due to the essential shortcomings of laser sensors, which therefore poses a great challenge for high-quality 3D surface reconstruction. This paper tackles this problem by proposing a local hierarchical clustering (LHC) method to improve the consistency of point distribution. Specifically, LHC consists of two steps: 1) adaptive octree-based decomposition of 3D space, and 2) hierarchical clustering. The former aims at reducing the computational complexity and the latter transforms the non-uniform point set into uniform one. Experimental results on real-world scanned point clouds validate the effectiveness of our method from both qualitative and quantitative aspects.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jiaqi Yang, Ruibo Li, Yang Xiao, Zhiguo Cao, "3D reconstruction from non-uniform point clouds via local hierarchical clustering", Proc. SPIE 10420, Ninth International Conference on Digital Image Processing (ICDIP 2017), 1042038 (21 July 2017); doi: 10.1117/12.2281528; http://dx.doi.org/10.1117/12.2281528
PROCEEDINGS
5 PAGES


SHARE
KEYWORDS
3D modeling

Clouds

RELATED CONTENT

RADIUS common development environment
Proceedings of SPIE (April 01 1992)
Road Boundary Detection for Autonomous Vehicle Navigation
Proceedings of SPIE (December 11 1985)
Seeing In Depth
Proceedings of SPIE (December 29 1977)
On two heuristic viewpoints concerning the study of light
Proceedings of SPIE (February 19 2015)

Back to Top