首页 | 本学科首页   官方微博 | 高级检索  
     

基于SIFT图像特征匹配的多视角深度图配准算法
引用本文:韦虎,张丽艳,刘胜兰,石春琴.基于SIFT图像特征匹配的多视角深度图配准算法[J].计算机辅助设计与图形学学报,2010,22(4).
作者姓名:韦虎  张丽艳  刘胜兰  石春琴
作者单位:南京航空航天大学机电学院,南京,210016
基金项目:国家自然科学基金(50875130);;高等学校博士点专项科研基金(200802870016);;江苏省科技支撑计划(BE2008136)
摘    要:为有效地解决多视角深度图配准问题,提出一种新的配准算法.首先给出一种深度图数据图像化方法,根据深度图包含的像素信息和网格顶点处的曲率值创建特征图像;然后通过对特征图像进行SIFT特征检测与匹配来获得特征点与匹配关系,从而得到原始深度图上的特征点与匹配关系;最后采用投票和预配准方法去除误匹配,实现递增式多视角深度图配准.模拟噪声实验和多个实际测量深度图的配准实验结果验证了该算法的鲁棒性和有效性.

关 键 词:双目立体测量  多视角深度图  配准  SIFT算法  特征匹配  

An Algorithm on Registration of Multi-view Range Images Based on SIFT Feature Matching
Wei Hu,Zhang Liyan,Liu Shenglan, Shi Chunqin.An Algorithm on Registration of Multi-view Range Images Based on SIFT Feature Matching[J].Journal of Computer-Aided Design & Computer Graphics,2010,22(4).
Authors:Wei Hu  Zhang Liyan  Liu Shenglan    Shi Chunqin
Affiliation:College of Mechanical and Electronic Engineering/a>;Nanjing University of Aeronautics and Astronautics/a>;Nanjing 210016
Abstract:A novel algorithm on registration of multi-view range images is proposed.Firstly,a method for transferring a range image to a feature image is performed,where the pixel information and the curvature information on the range image is used.Secondly,the keypoints and their matching relationships on the feature images are constructed by using the SIFT algorithm.The matching relationships among the original range images are obtained accordingly.Lastly,false matches are deleted by a voting and pre-registering sch...
Keywords:binocular stereo vision  multi-view range images  registration  SIFT algorithm  feature matching  
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号