Unorganized 3-D Points Data Registration with Local Geometric Feature Based on CUDA

Qi Ming Wei; Wei Yong Wu

doi:10.4028/www.scientific.net/AMR.433-440.4725

Paper Titles

An Agile Process Model Based on the Third-Party Testing Agencies
p.4698

Research and Design on Intranet Security File System
p.4704

Study on a New Industrial Control Protocol – Ethernet/IP and its Implementation
p.4710

A Novel Intelligent Load Control Switch Based on Dynamic Compensation Method for Current Zero-Crossing Point
p.4717

Unorganized 3-D Points Data Registration with Local Geometric Feature Based on CUDA
p.4725

The Design and Realization of Multi-COM Protocol Switch Server Based on ARM and FPGA
p.4730

The Design of Course-Oriented Online Judge
p.4736

Main Points of Environmental Protection in Three Jiang Yuan Area
p.4741

Optimization of Mixed-Cultivation Conditions of Methanotrophs from the Aged Refuse
p.4746

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 433-440Unorganized 3-D Points Data Registration with...

Unorganized 3-D Points Data Registration with Local Geometric Feature Based on CUDA

Abstract:

Automatic Automatic 3-D unorganized point data registration technique,which maps 3-D datas measured from multiple viewpoints into a common coordinate space, is a key technique for reverse engineering.In order to improve data matching speed, a parallel detecting algorithm with local geometric feature based on CUDA architechure was proposed.Firstly,local geometric feature points were extracted from original data sets,and then the correspondence between them are computed, at last this registration algorithm was implemented in parallel pattern on CUDA.The comparison experiments show that this algorithm is efficient and robust against noise.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 433-440)

Pages:

4725-4729

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.433-440.4725

Citation:

Cite this paper

Online since:

January 2012

Authors:

Qi Ming Wei, Wei Yong Wu

Keywords:

CUDA, Data registration, Feature Points, Parallel Compulation, Unorganized Points

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] P. Yufei, G. Chenghui . Registration of scanning beam data on surface based on genetic algorithm and quaternion method. Journal of Fuzhou University(NaturalScience), Vol 36, pp.1202-1204, April (2008).

Google Scholar

[2] Luo Xianbo, Chong Yuexian. Data registration in 3-D scanning systems. Journal of TsingHua University(NaturalScience), Vol 44, pp.1104-1106 , Aug 2004 (In Chinese).

Google Scholar

[3] Xu Jinting, Liu Weijun. Algorithm for Free-Form Surface Matching Based on Curvatures [J]. Journal of Computer-Aided Design & Computer Graphics , Vol 19, pp.196-197, Feb 2007 (In Chinese).

Google Scholar

[4] Shen Haiping, Da Feipeng, Lei Jiayong. Research ofPoint-cloudsRegistration Based on Least-square Method[J]. Journal of Image and Graphics, Vol 10, pp.1112-1116, Sep 2005 (In Chinese).

Google Scholar

[5] Besl P, McKay N. A method for registration two 3-D shapes[J]. IEEE Trans Pattern Analysis and Machine Intelligence, Vol 14, pp.232-256, Jan (1992).

DOI: 10.1109/34.121791

Google Scholar

[6] HelmutP, HuangQ X, HuY L. Geometry and convergence analysis of algorithms for registration of 3D shapes[J]. International Journal of Computer Vision, Vol 67, pp.277-296, Mar (2006).

Google Scholar

[7] Anshuman Razdan, MyungSoo Bae. Curvature Estimation Scheme for Triangle Meshes Using Biquadratic Bezier Patches[J]. Computer Aided Design , 2005, Vol. 37, Issue 14, pp.1481-1491.

DOI: 10.1016/j.cad.2005.03.003

Google Scholar

[8] NVIDIA Corporation. NVIDIA CUDA computationalunified device ar-chitecture programming guide version 2. 0[K]. (2008).

Google Scholar

[9] QIN An, XU JiaGUOHui. Fast3D rigidmedical image registration based on GPU. Application Research of Computers[J], Vol 27 , pp.1198-1200, Mar (2010).

Google Scholar