| 基于视觉约束能量最小化的特征点匹配算法 |
| |
| 引用本文： | 刘朝霞,邵峰,景雨,祁瑞华.基于视觉约束能量最小化的特征点匹配算法[J].计算机科学,2018,45(5):228-231, 254. |
| |
| 作者姓名： | 刘朝霞 邵峰 景雨 祁瑞华 |
| |
| 作者单位： | 大连外国语大学软件学院 辽宁 大连116044,大连海事大学信息科学技术学院 辽宁 大连116026,大连外国语大学软件学院 辽宁 大连116044,大连外国语大学软件学院 辽宁 大连116044 |
| |
| 基金项目： | 本文受国家自然科学基金青年科学基金项目(61201454,2),大连外国语大学创新团队资助 |
| |
| 摘 要： | 为了解决海上目标航空遥感图像重复特征较多导致的匹配不一致问题,并简化匹配过程,文中提出了基于SIFT视觉约束能量最小化的匹配算法(CEM-SIFT)。该算法将约束能量最小化模型应用于特征点的匹配,通过构造有限脉冲响应线性滤波器,采用视觉信息计算其能量值,使得待匹配的点集经过滤波之后的平均输出能量在一定约束下达到最小值,最终实现含重复信息的特征精确匹配。采用10组航空遥感海冰图像对算法进行测试,结果表明,相对于采用SIFT欧氏距离(ED-SIFT),在匹配重复特征比较多、点集规模比较大的图像时,CEM-SIFT算法的匹配精度更高,能够达到100%。
|
| 关 键 词： | 特征匹配 SIFT 约束能量最小化 视觉特征 |
| 收稿时间： | 2018/3/28 0:00:00 |
| 修稿时间： | 2018/4/16 0:00:00 |
Feature Matching Algorithm Based on Visual Feature Constrained Energy Minimization |
| |
| LIU Zhao-xi,SHAO Feng,JING Yu and QI Rui-hua.Feature Matching Algorithm Based on Visual Feature Constrained Energy Minimization[J].Computer Science,2018,45(5):228-231, 254. |
| |
| Authors: | LIU Zhao-xi SHAO Feng JING Yu and QI Rui-hua |
| |
| Affiliation: | School of Software,Dalian University of Foreign Languages,Dalian,Liaoning 116044,China,Faculty of Information Science & Technology,Dalian Maritime University,Dalian,Liaoning 116026,China,School of Software,Dalian University of Foreign Languages,Dalian,Liaoning 116044,China and School of Software,Dalian University of Foreign Languages,Dalian,Liaoning 116044,China |
| |
| Abstract: | The aerial remote sensing image captured on the sea has the characteristics of monotonous and similar patterns,which may result in mismatches in feature matching.In order to remove the mismatches and simplify the matching process,a novel feature matching algorithm based on the constrained energy minimization of SIFT feature(CEM-SIFT) was proposed.In the algorithm,a finite-impulse response filter is designed and visual information is used to compute the output energy.In the constraints imposed by desired signature,the filter output energy is minimized.Ten pairs of seaice aerial images were utilized to evaluate the performance.The experimental results show that the proposed algorithm CEM-SIFT is more accurate than the euclidean distance of SIFT feature(ED-SIFT) when matching an image with many repetitive features and large point set scale. |
| |
| Keywords: | Feature matching SIFT Constrained energy minimization(CEM) Visual feature |
|
|
点击此处可从《计算机科学》下载全文 |
|
