| 一种稳健的角点匹配方法 |
| |
| 引用本文： | 杨成胡,赵鸿燕,吴立刚.一种稳健的角点匹配方法[J].南京气象学院学报,2012,4(6):550-554. |
| |
| 作者姓名： | 杨成胡 赵鸿燕 吴立刚 |
| |
| 作者单位： | 广东省电子技术研究所,广州,510630;广东省电子技术研究所,广州,510630;哈尔滨工业大学 航天学院,哈尔滨,150001 |
| |
| 基金项目： | 广东省科技计划资助项目(2010-B010700025) |
| |
| 摘 要： | 在不同的图像之间寻找若干稳健的匹配点是许多计算机视觉算法有效应用的关键.SIFT(Scale Invariant Feature Transforms)算法已经证明了能够实现稳健匹配点提取的任务,然而SIFT算法提取的匹配点往往处于目标内部的某些均匀的区域,并不包括目标的边角点.考虑到角点往往包含了目标关键的结构信息,因此利用SIFT匹配点的稳健性结合角点检测,既能够提高角点匹配的稳健性又能够减小角点匹配搜索范围.匹配实验证明了该方法能够有效抵御噪声的干扰以及尺度和视角变化的影响,具备良好的匹配稳健性.
|
| 关 键 词： | 特征匹配 尺度不变特征变换(SIFT) 角点 |
| 收稿时间： | 2012/5/23 0:00:00 |
A robust approach on corner points matching |
| |
| YANG Chenghu,ZHAO Hongyan and WU Ligang.A robust approach on corner points matching[J].Journal of Nanjing Institute of Meteorology,2012,4(6):550-554. |
| |
| Authors: | YANG Chenghu ZHAO Hongyan and WU Ligang |
| |
| Institution: | Guangdong Electronic Technology Research Institute,Guangzhou 510630;Guangdong Electronic Technology Research Institute,Guangzhou 510630;School of Astronautics,Harbin Institute of Technology,Harbin 150001 |
| |
| Abstract: | To find the robust matching points between different views on the same object is the key step in a computer vision system in practice.The popular SIFT (Scale Invariant Feature Transforms) has showed its power for robust feature points matching.However,the edge and corner points are not included in the SIFT matching points.Considering the fact that the corner points represent the structure information of an object,we hence propose a robust approach for corner matching via SIFT.This new approach improves the robustness while decreases the computing burden in matching.A series of experiments on corner points matching illustrate that the proposed approach is not sensitive to changes in view,rotation or scale,and robust to noise interference. |
| |
| Keywords: | feature matching SIFT corner points |
|
| 点击此处可从《南京气象学院学报》浏览原始摘要信息 |
| 点击此处可从《南京气象学院学报》下载免费的PDF全文 |
|
