| 条件理论控制下良态特征的匹配算法 |
| |
| 引用本文： | 雷明,杨丹,张小洪.条件理论控制下良态特征的匹配算法[J].光电工程,2008,35(5):124-129. |
| |
| 作者姓名： | 雷明 杨丹 张小洪 |
| |
| 作者单位： | 1. 重庆大学数理学院,重庆,400044
2. 重庆大学软件工程学院,重庆,400030 |
| |
| 摘 要： | 使用多尺度Harris算子检测图像的角点作为初始兴趣点.针对自适应非极大值抑制排除了大量潜在匹配点的缺陷,引入条件理论对初始兴趣点进行控制,排除病态点,减少后续过程的计算量,提高算法效率,同时最大限度的保留了匹配点.满足条件理论控制下的特征称为良态特征.由于初始Harris角点的位置会发生偏移以及有伪角点产生,所以利用亚像素定位技术进行精确定位,并排除伪角点和不稳定的角点.使用PCA-SIFT对特征点及其邻域进行描述获得特征向量.最后通过向量之间的欧几里德距离判断特征点是否匹配.实验结果表明算法效率改进明显,匹配效果良好,对图像的几何变换、噪声及光照变化等具有较强的鲁棒性.
|
| 关 键 词： | 特征匹配 条件理论 良态特征 自适应非极大值抑制 亚像素定位 条件理论 控制 态特征 匹配算法 Theory Condition Control Features Algorithm 鲁棒性 光照变化 噪声 几何变换 匹配效果 效率改进 结果 实验 距离判断 欧几里德 特征向量 |
| 文章编号： | 1003-501X(2008)05-0124-05 |
| 收稿时间： | 2007/7/6 |
| 修稿时间： | 2007年7月6日 |
Matching Algorithm of Well Conditioned Features under the Control of Condition Theory |
| |
| LEI Ming,YANG Dan,ZHANGXiao-hong.Matching Algorithm of Well Conditioned Features under the Control of Condition Theory[J].Opto-Electronic Engineering,2008,35(5):124-129. |
| |
| Authors: | LEI Ming YANG Dan ZHANGXiao-hong |
| |
| Affiliation: | LEI Ming1,YANG Dan2,ZHANG Xiao-hong2 ( 1. College of Mathematics & Physics,Chongqing University,Chongqing 400044,China,2. School of Software Engineering,Chongqing 400030,China ) |
| |
| Abstract: | Corners in an image were detected by multi-scale Harris operator,and they were taken as initial interest points. Since adaptive non-maximal suppression eliminated lots of potential matching points,condition theory was applied to control the number of initial interest points. The bad conditioned points were eliminated,so the computational complexity of the following process was decreased and the efficiency of the algorithm was improved. Meanwhile,matching points were mostly kept. Features under the control o... |
| |
| Keywords: | feature matching condition theory well conditioned feature adaptive non-maximal suppression sub-pixel localization |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
