基于未标定多幅图的三维重建算法  

Three dimensional reconstruction algorithm based on uncalibrated multiple images

作　　者：赵璐璐[1] 耿国华[1] 王小凤[1] 刘倩[1] 

机构地区：[1]西北大学信息科学与技术学院,西安710127

出　　处：《计算机应用》2012年第10期2802-2805,共4页journal of Computer Applications

基　　金：国家自然科学基金资助项目(61172170;61170203);973计划前期研究专项(2011CB311802);教育部博士点基金资助项目(200806970014);陕西省自然科学基金资助项目(2011JQ8001;2010JQ8011);虚拟现实应用教育部工程研究中心开放基金资助项目(MEOBNUEVRA200903);陕西省教育厅项目(09JK738;12JK0730)

摘　　要：为得到鲁棒的三维重建效果,提出了一种基于未标定多幅图像的三维重建算法。该算法首先采用Harris算法检测特征点,针对双向匹配算法匹配速度慢的缺点,使用改进的双向匹配算法进行特征点匹配,在已知摄像机参数的情况下进行两幅图的三维重建;接着采用四元数算法进行坐标转换,将由每两幅图得到的不同部分的重建结果转移到同一坐标系下,实现了多幅图像的三维重建;最后利用集束调整优化重建结果。实验结果证明,该算法能获得比较满意的重建效果。This paper proposed an algorithm for 3D reconstruction based on uncalibrated images. First, this algorithm detected the feature points by using Harris corners, and presented an improved bidirectional matching to match these feature points. Under the condition of the known camera parameters, the authors carried out 3D reconstruction of two images. Then the quateruion algorithm was adopted to transform coordinate. The results coming from different subsets were brought into a common coordinate frame, achieving 3D reconstruction of multiple images. Finally, bundle adjustment was used to optimize the results. The experimental results show that object structure can be well reconstructed by using this algorithm.

关 键 词：未标定图像 双向匹配 三维重建 图像序列 四元数 

分 类 号：TP391.413[自动化与计算机技术—计算机应用技术]