3D Point Cloud Optimization Based on a Random Walk Model Using SBA

Author

Chunmei Duan

Author_Institution

Sch. of Manage. Sci. & Eng., Shandong Normal Univ., Jinan, China

fYear

2013

fDate

26-28 July 2013

Firstpage

667

Lastpage

672

Abstract

In this paper, we propose a new algorithm for optimizing coarse 3D point cloud obtained from multiview images. We start firstly with the 3D geometry acquired from images taken from multiviews by structure from motion (SFM) approach. Then, the 3D point data is regarded as the input of the sparse bundle adjustment (SBA) technique in a RANSAC framework. A random walk model is proposed to relocate the back projections of 3D points which are also one of the inputs of the optimization algorithm, so as to improve the optimization results further. Experimental results in the end of the paper prove the effectiveness of the proposed approach.

Keywords

image reconstruction; optimisation; solid modelling; 3D geometry; 3D point cloud optimization; RANSAC framework; SBA technique; SFM approach; multiview images; optimization algorithm; random walk model; sparse bundle adjustment; structure-from-motion approach; Algorithm design and analysis; Cameras; Computer vision; Image reconstruction; Optimization; Solid modeling; Three-dimensional displays; 3D point cloud; 3D reconstruction; RANSAC; SBA; random walk model;

fLanguage

English

Publisher

ieee

Conference_Titel

Image and Graphics (ICIG), 2013 Seventh International Conference on

Conference_Location

Qingdao

Type

conf

DOI

10.1109/ICIG.2013.137

Filename

6643754