| 基于SIFT匹配的全局运动估计方法 |
| |
| 引用本文： | 顾广华,姜思宇,王成儒. 基于SIFT匹配的全局运动估计方法[J]. 光学技术, 2011, 37(1): 85-90 |
| |
| 作者姓名： | 顾广华 姜思宇 王成儒 |
| |
| 作者单位： | 燕山大学信息科学与工程学院,河北,秦皇岛,066004 |
| |
| 摘 要： | 提出了一种基于SIFT(Scale invariant feature transform)匹配的全局运动估计算法.在SIFT初匹配的基础上,对每一个原始匹配特征点,利用所在尺度的邻域灰度信息,对其加权平均后再进行匹配,进而去除误配点.精炼后的匹配点集合作为求解全局运动参数模型的对应数据,采用最小二乘法计算模型参数.在...
|
| 关 键 词： | SIFT匹配 参数模型 全局运动估计 |
A global motion estimation algorithm based on SIFT matching |
| |
| GU Guanghua,JIANG Siyu,WANG Chengru. A global motion estimation algorithm based on SIFT matching[J]. Optical Technique, 2011, 37(1): 85-90 |
| |
| Authors: | GU Guanghua JIANG Siyu WANG Chengru |
| |
| Affiliation: | (School of Information Science and Engineering,Yanshan University,Qinhuangdao 066004,China) |
| |
| Abstract: | A GME(Global motion estimation) algorithm based on SIFT(Scale invariant feature transform) matching is proposed.For each original SIFT matching key-point,the weighted average gray information of its neighbor area on its scale is first utilized to eliminate the error key-points.The sets of the refining key-points are used to solve the motion model by the least squares method.The proposed method is a new attempt on GME.Experimental results show that the GME method combined with SIFT matching achieves the satisfactory results. |
| |
| Keywords: | SIFT matching parameter model global motion estimation |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
