| 基于SIFT特征匹配的全自动辐射归一化算法 |
| |
| 引用本文： | 孙韬,方俊永,刘学,王晋年,童庆禧.基于SIFT特征匹配的全自动辐射归一化算法[J].红外与毫米波学报,2012,31(4):355-359. |
| |
| 作者姓名： | 孙韬 方俊永 刘学 王晋年 童庆禧 |
| |
| 作者单位： | 1. 中国科学院遥感应用研究所遥感科学国家重点实验室,北京100101;中国科学院研究生院,北京100049
2. 中国科学院遥感应用研究所遥感科学国家重点实验室,北京,100101 |
| |
| 基金项目： | 北京市科技计划“高性能航空光学传感器的研制”(D08080103760802)；国家重大科技基础设施建设项目 “多模态数字相机” |
| |
| 摘 要： | 分析了辐射归一化在遥感、航测领域中的重要性,针对辐射归一化线性校正法进行了研究,并提出了一种非人工干预、自动化程度高的基于SIFT(尺度不变特征Scale-Invariant Feature Transform)特征匹配的辐射归一化新方法。通过实验发现,基于SIFT特征匹配的辐射归一化方法能够减少由于大气、照度和传感器差异带来的辐射误差,与传统的方法相比具有结果稳定、自动化程度高的特点.
|
| 关 键 词： | 辐射归一化 尺度不变特征 线性校正法 均方根误差 |
| 收稿时间： | 8/9/2011 12:00:00 AM |
| 修稿时间： | 2012/3/13 0:00:00 |
Automatic relative radiometric normalization method based on SIFT feature matching |
| |
| SUN Tao,FANG Jun-Yong,LIU Xue,WANG Jin-Nian and TONG Qing-Xi.Automatic relative radiometric normalization method based on SIFT feature matching[J].Journal of Infrared and Millimeter Waves,2012,31(4):355-359. |
| |
| Authors: | SUN Tao FANG Jun-Yong LIU Xue WANG Jin-Nian and TONG Qing-Xi |
| |
| Affiliation: | State Key Laboratory of Remote Sensing Science, Institute of Remote Sensing Applications,Chinese Academy of Sciences,State Key Laboratory of Remote Sensing Science, Institute of Remote Sensing Applications,Chinese Academy of Sciences,State Key Laboratory of Remote Sensing Science, Institute of Remote Sensing Applications,Chinese Academy of Sciences,State Key Laboratory of Remote Sensing Science, Institute of Remote Sensing Applications, Chinese Academy of Sciences and State Key Laboratory of Remote Sensing Science, Institute of Remote Sensing Applications,Chinese Academy of Sciences |
| |
| Abstract: | This paper analyzed the importance of relative radiometric normalization(RRN) in remote sensing and aerophotogrammetry filed. The linear correction method of RRN was studied. A high automatic RRN method was proposed based on the scale-invariant feature transform(SIFT).It was found that the RRN can minimize radiometric difference among images caused by inconsistencies of acquisition conditions (such as weather, season, etc.) rather than in surface reflectance. Compared with the traditional ways, the new method is more robust and automatic. |
| |
| Keywords: | Relative Radiometric Normalization Scale-invariant feature transform linear correction method RMS error |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《红外与毫米波学报》浏览原始摘要信息 |
|
点击此处可从《红外与毫米波学报》下载全文 |
|
