基于多幅图像序列的三维重建

基于多幅图像序列的三维重建

崔晓青¹, 李谊¹, 韩东峰¹, 李远¹, 李宗承²

1. 吉林大学计算机科学与技术学院, 长春 130012； 2. 山东理工大学工程技术学院, 山东淄博 255000

收稿日期:2007-01-28 修回日期:1900-01-01 出版日期:2008-01-26 发布日期:2008-01-26
通讯作者: 韩东峰

Three Dimensional Reconstruction Method Based on Image Sequence of Multiple Images

CUI Xiaoqing¹, LI Yi¹, HAN Dongfeng¹, LI Yuan¹, LI Zongcheng²

1. College of Computer Science and Technology, Jilin University, Changchun 130012, China；2. School of Engineering Technology, Shandong University of Technology, Zibo 255000, Shandong Province, China

Received:2007-01-28 Revised:1900-01-01 Online:2008-01-26 Published:2008-01-26
Contact: HAN Dongfeng

摘要/Abstract

摘要： 基于多幅图像序列的三维重建技术, 以两幅图像的三维重建算法为基础, 采用由运动中恢复校准的结构方法, 在已知摄像机参数的情况下, 利用KLT特征点跟踪算法, 实现了多幅图像的三维重建, 并利用集束调整优化了重建结果.

关键词: 随机采样算法, 三维重建, 图像序列

Abstract: We presented a three dimensional reconstruction method based on image sequence of multiple images. Under the condition of the known camera parameters, we used the KarhunenLoeve Transform algorithm tracking feature to reconstruct three dimensional model based on the algorithm of reconstruction for two images, and also used bundle adjustment to optimize the result. The experiment shows an encouraging resultand the system is convenient, lowcost and easy to use.

Key words: random sample consensus (RANSAC), 3D reconstrction, image sequence

中图分类号:

TP39

崔晓青, 李谊, 韩东峰, 李远, 李宗承. 基于多幅图像序列的三维重建[J]. J4, 2008, 46(01): 75-80.

CUI Xiaoqing, LI Yi, HAN Dongfeng, LI Yuan, LI Zongcheng. Three Dimensional Reconstruction Method Based on Image Sequence of Multiple Images[J]. J4, 2008, 46(01): 75-80.