期刊文献+

一种基于相位一致性相关的多源遥感影像配准方法

A New Multi-source Remote Sensing Image Registration Method Based on Correlation of Phase Congruency
下载PDF
导出
摘要 针对几何校正过程中多源遥感影像同名点匹配率低的问题,提出一种基于相位一致性相关的遥感影像配准方法。该方法首先使用多尺度Harris提取出不受高斯平滑影响、位置稳定的角点,而后以金字塔分层映射为搜索策略,在参考影像上预测可能包含同名点的子区域,通过计算该子区域与待匹配点领域的相位一致性,同时引入相关系数作为相似性度量获取同名点对,最终实现不同光谱影像间的配准。实验表明,该方法的误匹配率较低,精度和稳定性高于传统原始影像灰度相关及同类配准方法,适用于不同传感器或不同光谱通道间影像的匹配。 This paper provides a new image registration method based on the correlation of phase congruency to solve the problem that the matching ratio of the tie points of multi-source remote sensing images is rather low during geometric correction course.In this method,the corners of stable positions without influence of Gaussian smoothing are firstly filtered by multi-scale Harris,and then layered pyramid structure is utilized as the searching strategy to predict the subregion of reference image in which the tie point maybe locates.So,by calculating the phase congruency between this subregion and that of point to be matched,and by introducing the correlation coefficient as the similarity measurement to obtain the tie point-pairs,the image registration between different spectrums can be achieved.Experiment results showed that this method got low mismatching ratio but high accuracy and high stability in contrast to the traditional grayscale correlation method of original image and other similar methods,and could be suitable for the image matching between different sensors or different spectral channels.
出处 《铁道标准设计》 北大核心 2012年第2期118-123,共6页 Railway Standard Design
基金 国家973项目支持"高分辨率遥感数据精处理和空间信息智能转化的理论与方法"(2012CB719905)
关键词 影像配准 多尺度卷积 相位一致性 相关系数 image registration multi-scale convolution phase congruency correlation coefficient
  • 相关文献

参考文献12

  • 1Zitová B,Flusser J. Image registration methods:A survey[J].Image and Vision Computing,2003,(11):977-1000.
  • 2Lowe D G. Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,(02):91-110.doi:10.1023/B:VISI.0000029664.99615.94.
  • 3Ke Y,Sukthankar R. PCA-SIFT:A more distinctive representation for local image descriptor[A].2004.506-513.
  • 4Abdel-Hakim A E,Farag A A. CSIFT:A SIFT descriptor with color invariant characteristics[A].2006.1978-1983.
  • 5Yi Z,Zhiguo C,Yang X. Multi-spectral remote image registration based on SIFT[J].Electronics Letters,2008,(02):107-108.doi:10.1049/el:20082477.
  • 6Gao F,Masek J,Wolfe R E. Automated registration and orthorectification package for Landsat and Landsat-like data processing[J].Journal of Applied Remote Sensing,2009,(01).
  • 7Bunting P,Labrosse F,Lucas R. A multi-resolution area-based technique for automatic multi-modal image registration[J].Image and Vision Computing,2010,(08):1203-1219.
  • 8Suri S,Reinartz P. Mutual-information-based registration of TerraSAR-X and Ikonos imagery in urban area[J].IEEE Transactions on Geoscience and Remote Sensing,2010,(02):939-949.
  • 9Harris C,Stephens M K. A combined corner and edge detector[A].1988.147-152.
  • 10Rosten E,Drummond T. Machine learning for high-speed corner detection[A].2006.430-443.

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部