多尺度、多角度异源遥感影像配准方法研究

计算机工程与应用 ›› 2012, Vol. 48 ›› Issue (30): 5-9.

多尺度、多角度异源遥感影像配准方法研究

王瑞瑞1，2，3，马建文4

1.北京林业大学省部共建森林培育与保护教育部重点实验室，北京 100083
2.北京林业大学测绘与3S技术研究中心，北京 100083
3.中国科学院遥感应用研究所，北京 100101
4.中国科学院对地观测与数字地球科学中心，北京 100094

出版日期:2012-10-21 发布日期:2012-10-22

Registration method for heterogenous remote sensing images with multi-scale and multi-angle

WANG Ruirui1，2，3, MA Jianwen4

1.Key Lab for Silviculture and Conservation, Ministry of Education, Beijing Forestry University, Beijing 100083, China
2.Center of 3S Technology and Mapping, Beijing Forestry University, Beijing 100083, China
3.Institute of Remote Sensing Applications, Chinese Academy of Sciences, Beijing 100101, China
4.Center for Earth Observation and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China

Online:2012-10-21 Published:2012-10-22

摘要/Abstract

摘要： 针对具有显著尺度和角度差异的异源遥感影像配准中存在的问题，引入具有角度不变性和同一尺度的空间辅助圆，克服角度和尺度偏差；选取对异源影像的光谱差异具有高鲁棒性的归一化互信息测度，基于空间辅助圆提取统计特征进行区域配准。该方法还将同名特征点的搜索范围限制在辅助圆内，在保证算法搜索效率的同时提高了配准的精度。选取具有较大尺度和角度偏差的异源遥感影像进行实验，通过与基于空间辅助面的配准方法相比较，证明基于空间辅助圆的归一化互信息配准方法对角度和光谱偏差具有较高的鲁棒性，配准模型的精度小于一个像素。

关键词: 多尺度多角度的异源遥感影像配准, 空间辅助圆, 角度不变性, 归一化互信息

Abstract: Aiming to the high accuracy registration between heterogenous images with differences in angles and scales, the spatially assistant circles with invariant angle and same scale are introduced, and the normalized mutual information robust to spectrum differences is adopted to compute the statistical features in the assistant circles. It confines the searching range to the assistant circle, which increases the registration precision while the searching efficiency is guaranteed. Optical and SAR images with considerable differences in scale and angle are tested, and the registration method based on spatial assistant plane is used for comparison. The experimental results indicate that the registration method based on spatially assistant circle and normalized mutual information is robust to differences in angle and spectrum. Moreover, the registration model’s error is lower than one pixel.

Key words: heterogenous images registration with multi-angle and multi-scale, spatially assistant circle, invariant angle, normalized mutual information

王瑞瑞1，2，3，马建文4. 多尺度、多角度异源遥感影像配准方法研究[J]. 计算机工程与应用, 2012, 48(30): 5-9.

WANG Ruirui1，2，3, MA Jianwen4. Registration method for heterogenous remote sensing images with multi-scale and multi-angle[J]. Computer Engineering and Applications, 2012, 48(30): 5-9.

[1]	邱云飞，高华聪. 混合Filter与改进自适应GA的特征选择方法[J]. 计算机工程与应用, 2021, 57(11): 95-102.
[2]	张晓琴，刘莉楠. 基于亲密度和吸引力的二分网络社区发现算法[J]. 计算机工程与应用, 2019, 55(23): 170-176.
[3]	胡顺波. 图像配准中同条件非均匀抽样原则的对比研究[J]. 计算机工程与应用, 2012, 48(3): 158-161.
[4]	李伟1，何鹏举1，杨恒2，陈明1. 遗传算法对Powell图像配准方法的改进[J]. 计算机工程与应用, 2012, 48(20): 1-5.
[5]	王丽，孙丰荣，王奕琨，刘炜，姜威，秦通，李新彩. 基于互信息的颅脑MR影像序列的三维配准[J]. 计算机工程与应用, 2011, 47(31): 160-163.
[6]	王广泰¹，胡顺波¹，刘常春²，邵鹏³，杨吉宏⁴. 基于归一化互信息向量熵的多幅图像配准方法[J]. 计算机工程与应用, 2009, 45(22): 172-174.
[7]	黎燕,樊晓平,李刚,黄芳. 尺度空间图像的互信息与配准[J]. 计算机工程与应用, 2008, 44(23): 178-182.
[8]	徐东，李升辉 . 互信息医学图像配准研究与局部极值的克服[J]. 计算机工程与应用, 2007, 43(3期): 217-217.