| 一种基于SIFT特征的快速逐层遥感图像配准方法 |
| |
| 引用本文： | 侯鹏洋,季艳,高峰,胡蕾.一种基于SIFT特征的快速逐层遥感图像配准方法[J].遥感技术与应用,2014,29(5):873-877. |
| |
| 作者姓名： | 侯鹏洋 季艳 高峰 胡蕾 |
| |
| 作者单位： | (1.北京航空航天大学计算机学院数字媒体北京市重点实验室,北京100191;;
2.北京遥感信息研究所,北京100011;
3.江西师范大学计算机信息工程学院,江西 南昌330022) |
| |
| 基金项目： | 国家杰出青年科学基金项目(61125206)和国家自然科学基金项目（61262036）资助。 |
| |
| 摘 要： | 当前SIFT特征分层配准方法中存在特征点匹配复杂度高以及不同时相地物变化导致特征点误匹配等问题,提出一种基于SIFT特征的“低分辨率配准\,高分辨率验证”快速逐层遥感图像配准方法。该方法针对同源同分辨率不同时相的遥感图像,通过在金字塔的低分辨率图层匹配特征点对并建立仿射变换模型,在金字塔的高分辨率图层评估并修正模型。实验表明：提出的方法在保证配准精度的前提下,有效提高了配准算法的效率。
|
| 关 键 词： | 遥感图像 图像配准 SIFT 变化检测 |
Fast Hierarchical Registration Method for Remote Sensing Image based on SIFT |
| |
| Hou Pengyang,Ji Yan,Gao Feng,Hu Lei.Fast Hierarchical Registration Method for Remote Sensing Image based on SIFT[J].Remote Sensing Technology and Application,2014,29(5):873-877. |
| |
| Authors: | Hou Pengyang Ji Yan Gao Feng Hu Lei |
| |
| Affiliation: | (1.Beijing Key Laboratory of Digital Media,School of Computer Science and Engineering,;
Beihang University,Beijing 100191,China;;
2.Beijing Institute of Remote Sensing Information,Beijing 100011,China;;
3.School of Computer Information Engineering,Jiangxi Normal University,Nanchang 330022,China) |
| |
| Abstract: | For the current automatic image registration based on SIFT,feature point matching algorithm is time\|consuming,in addition,the changes of multi\|temporal images affect the accuracy of registration,this paper proposes a SIFT\|based feature of the “low\|resolution matching,high resolution authentication” hierarchical image registration algorithm to improve the above issues.In the proposed algorithm,affine transformation model is established in low\|resolution pyramid images and sequentially evaluated and revised by match points in high resolution pyramid images.Experimental results show that the improved SIFT algorithm can reduce the time complexity with rather considerable accuracy. |
| |
| Keywords: | Remote sensing image Image registration SIFT Change detection |
|
| 点击此处可从《遥感技术与应用》浏览原始摘要信息 |
|
点击此处可从《遥感技术与应用》下载全文 |
|
