[1]施文灶,毛政元.采用非线性尺度空间滤波和SIFT的遥感影像配准方法[J].华侨大学学报(自然科学版),2016,37(1):38-42.[doi:10.11830/ISSN.1000-5013.2016.01.0038]
　SHI Wenzao,MAO Zhengyuan.Remotely Sensed Imagery Registration Based on Nonlinear Scale-Space Filtering and SIFT[J].Journal of Huaqiao University(Natural Science),2016,37(1):38-42.[doi:10.11830/ISSN.1000-5013.2016.01.0038]
点击复制

采用非线性尺度空间滤波和SIFT的遥感影像配准方法()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第37卷
期数:
2016年第1期
页码:
38-42
栏目:
出版日期:
2016-01-03

文章信息/Info

Title:
Remotely Sensed Imagery Registration Based on Nonlinear Scale-Space Filtering and SIFT
文章编号:
1000-5013(2016)01-0038-05
作者:
施文灶1; 2; 3; 4;  毛政元1; 3; 4
1. 福州大学 空间数据挖掘与信息共享教育部重点实验室, 福建 福州 350002;2. 福建师范大学 光电与信息工程学院, 福建 福州 350108;3. 福州大学 地理空间信息技术国家地方联合工程研究中心, 福建 福州 350002;4. 福州大学 福建省空间信息工程研究中心, 福建 福州 350002
Author(s):
SHI Wenzao1; 2; 3; 4;  MAO Zhengyuan1; 3; 4
1. Key Lab of Spatial Data Mining and Information Sharing of Ministry of Education, Fuzhou University, Fuzhou 350002, China; 2. College of Photonic and Electronic Engineering, Fujian Normal University, Fuzhou 350108, China; 3. National Engineering Research Centre of Geospatial Information Technology, Fuzhou University, Fuzhou 350002, China; 4. Spatial Information Engineering Research Centre of Fujian Province, Fuzhou University, Fuzhou 350002, China
关键词:
遥感影像;  非线性尺度空间滤波;  尺度不变特征转换;  配准;  仿射变换
Keywords:
remotely sensed imagery;  nonlinear scale-space filtering;  scale-invariant feature transform;  registration;  affine transformation
分类号:
P237
DOI:
10.11830/ISSN.1000-5013.2016.01.0038
文献标志码:
A
摘要:
针对传统点特征匹配算法存在运算时间长和配准精度低的问题,提出一种基于非线性尺度空间滤波和尺度不变特征转换(SIFT)点特征配准算法.首先,通过非线性尺度空间滤波对基准影像和待配准影像分别进行预处理,保留其边缘信息并去除噪声.其次,采用SIFT算法对预处理后的两幅影像进行特征点提取,通过最近邻和次近邻的欧式距离比值法进行双向匹配,得到匹配特征点.最后,对待配准影像进行仿射变换.结果表明:该方法的总体运行时间比传统SIFT点特征配准算法降低63.2%,且配准精度大幅提高.
Abstract:
To solve the problems of long executing time and low registration accuracy of the traditional point feature matching algorithm, this article proposed an improved scale-invariant feature transform(SIFT)point feature matching approach based on the nonlinear scale-space filtering. Firstly, the reference image and the to-be-registered one were respectively preprocessed with the nonlinear scale-space filter filtering. Secondly, feature points were extracted from the two images by means of the SIFT algorithm. Then, matched feature points were obtained through a bilateral matching by the ratio of Euclidean distances of the nearest neighbor to that of the next nearest one. Finally, an affine transformation was carried out to the to-be-registered image. Experimental results show that the executing time of the proposed method reduces 63.2% compared with the traditional SIFT point feature matching algorithm, and the registration accuracy is significantly improved.

参考文献/References:

[1] BROWN L G.A survey of image registration techniques[J].Acm Computing Surveys,1992,24(4):325-376.
[2] ZITOVA B,FLUSSER J.Image registration methods: A survey image vis comput[J].Image and Vision Computing,2003,21(11):977-1000.
[3] POHL C,Van GENDEREN J L.Review article multisensor image fusion in remote sensing: Concepts, methods and applications[J].International Journal of Remote Sensing,1998,19(5):823-854.
[4] HOLDEN M.A review of geometric transformations for nonrigid body registration[J].IEEE Transactions on Medical Imaging,2008,27(1):111-128.
[5] 张迁,刘政凯,庞彦伟,等.基于SUSAN算法的航空影像的自动配准[J].测绘学报,2003,32(3):245-250.
[6] 罗楠,孙权森,耿蕾蕾,等.一种扩展 SURF 描述符及其在遥感图像配准中的应用[J].测绘学报,2013,42(3):383-388.
[7] YAN Weidong,SHE Hongwei,YUAN Zhanbin.Robust registration of remote sensing image based on SURF and KCCA[J].Journal of the Indian Society of Remote Sensing,2014,42(2):291-299.
[8] TEKE M,TEMIZEL A.Multi-spectral satellite image registration using scale-restricted SURF[C]//20th International Conference on Pattern Recognition.Istanbul:IEEE Press,2010:2310-2313.
[9] SONG Zhili,ZHANG Junping.Remote sensing image registration based on retrofitted SURF algorithm and trajectories generated from Lissajous figures[J].Geoscience and Remote Sensing Letters,2010,7(3):491-495.
[10] KIM A L,SONG J H,KANG S L,et al.Matching and geometric correction of multi-resolution satellite SAR images using SURF technique[J].Korean Journal of Remote Sensing,2014,30(4):431-440.
[11] 岳春宇,江万寿.几何约束和改进 SIFT 的 SAR 影像和光学影像自动配准方法[J].测绘学报,2012,41(4):570-576.
[12] YU Le,ZHANG Dengrong,HOLDEN E J.A fast and fully automatic registration approach based on point features for multi-source remote-sensing images[J].Computers and Geosciences,2008,34(7):838-848.
[13] ZHENG Yi,CAO Zhiguo,XIAO Yang.Multi-spectral remote image registration based on SIFT[J].Electronics Letters,2008,44(2):107-108.
[14] GONCALVES H,CORTE-REAL L,GONCALVES J A.Automatic image registration through image segmentation and SIFT[J].IEEE Transactions on Geoscience and Remote Sensing,2011,49(7):2589-2600.
[15] HASAN M,JIA X,ROBLES-KELLY A,et al.Multi-spectral remote sensing image registration via spatial relationship analysis on sift keypoints[C]//Geoscience and Remote Sensing Symposium.Honolulu:IEEE Press, 2010:1011-1014.
[16] LOWE D G.Object recognition from local scale-invariant features[C]//The Proceedings of the Seventh IEEE International Conference on Computer Vision.Kerkyra:IEEE Press,1999:1150-1157.
[17] LOWE D G.Distinctive image feature from scaleinvariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.

备注/Memo

备注/Memo:
收稿日期: 2015-09-10
通信作者: 施文灶(1982-),男,讲师,博士研究生,主要从事高空间分辨率遥感影像信息提取的研究.E-mail:swz@fjnu.edu.cn.
基金项目: 国家自然科学基金资助项目(61275006, 41201427); “十二五”国家科技支撑计划项目(2013BAC08B02-01); 国家重点基础研究发展计划项目(2006CB708306); 福建省教育厅科研基金资助项目(JB14038)
更新日期/Last Update: 2016-01-20