###

计算机系统应用英文版:2016,25(10):205-208

View/Add Comment 过刊浏览高级检索 HTML

←前一篇 | 后一篇→

码上扫一扫！

下载全文

基于联合特征匹配的多视角三维重建方法

李硕明¹, 陈越^1,2

(1.中山职业技术学院信息工程学院, 中山 528404;2.华南理工大学电子与信息学院, 广州 510641)

Multiple-View 3D Reconstruction Approach Based on Hybrid Feature Matching

LI Shuo-Ming¹, CHEN Yue^1,2

(1.School of information Engineering, Zhongshan Polytechnic, Zhongshan 528404, China;2.School of information and electronics, South China University of Technology, Guangzhou 510641, China)

摘要

图/表

参考文献

相似文献

本文已被：浏览 1354次下载 1682次
Received:February 13, 2016 Revised:April 14, 2016

中文摘要: 本研究提出了一种基于角点与直线联合特征的三阶段匹配算法，依次经过相关匹配、松弛迭代匹配和最小平方中值法匹配三个步骤，并与此同时加入限定图像匹配区域、添加手工匹配点对以及局部直线匹配三个人机交互环节，将局部坐标系中得到的数据点进行三维数据融合到一个坐标系中，能较好解决视差不连续区域和遮挡区域的误匹配问题.实验证明该算法具有良好的运行效率和稳定性，能够对非平面物体进行精确三维重建并实现多视角显示.

中文关键词: 联合特征匹配多视角三维重建三维数据融合

Abstract:In this research, an approach of three-phase 3D corresponding algorithm based on hybrid feature of Harris and line feature points matching is proposed, in which relative matching, relaxation matching and LMedS matching are implemented respectively. At the mean time there Human-machine interaction processes are added, namely limitation of matching area, adding feature points by hand as well as line matching. Through coordinated transformation between views, 3D data of scene form different views integrated into a uniform reference coordinate frame, which can solve the false matching problem caused by inconsistent or shadowed areas. Experiment demonstrates the efficiency and robustness of this corresponding method, in which the 3D model of the targeted object can be displayed on all views.

keywords: hybrid feature matching multiple-views 3D reconstruction 3D data integration

文章编号： 中图分类号： 文献标志码：

基金项目:广东省自然科学基金联合基金（U0835001）

Author Name	Affiliation
LI Shuo-Ming	School of information Engineering, Zhongshan Polytechnic, Zhongshan 528404, China
CHEN Yue	School of information Engineering, Zhongshan Polytechnic, Zhongshan 528404, China School of information and electronics, South China University of Technology, Guangzhou 510641, China

Author Name	Affiliation
LI Shuo-Ming	School of information Engineering, Zhongshan Polytechnic, Zhongshan 528404, China
CHEN Yue	School of information Engineering, Zhongshan Polytechnic, Zhongshan 528404, China School of information and electronics, South China University of Technology, Guangzhou 510641, China

引用文本：
李硕明,陈越.基于联合特征匹配的多视角三维重建方法.计算机系统应用,2016,25(10):205-208
LI Shuo-Ming,CHEN Yue.Multiple-View 3D Reconstruction Approach Based on Hybrid Feature Matching.COMPUTER SYSTEMS APPLICATIONS,2016,25(10):205-208