基于兴趣点的遥感影像可匹配性度量

巨西诺; 郭文普; 孙继银; 高晶

doi:10.3788/OPE.20142204.1071

您当前的位置：

首页 >

文章列表页 >

基于兴趣点的遥感影像可匹配性度量

信息科学 | 更新时间：2020-08-13

- 基于兴趣点的遥感影像可匹配性度量
- Matching probability metric for remote sensing image based on interest points
- 光学精密工程 2014年22卷第4期页码：1071-1077
- 作者机构：
  
  第二炮兵工程大学,陕西西安,710025
- 作者简介：
- 基金信息：
  
  部委基金资助项目（No.5132202XX）()
- DOI：10.3788/OPE.20142204.1071
  中图分类号： TP391;TP752
- 收稿日期：2013-07-12，
  
  修回日期：2013-09-10，
  
  纸质出版日期：2014-04-25
- 稿件说明：
移动端阅览
巨西诺, 郭文普, 孙继银等. 基于兴趣点的遥感影像可匹配性度量[J]. 光学精密工程, 2014,22(4): 1071-1077

JU Xi-nuo, GUO Wen-pu, SUN Ji-yin etc. Matching probability metric for remote sensing image based on interest points[J]. Editorial Office of Optics and Precision Engineering, 2014,22(4): 1071-1077
巨西诺, 郭文普, 孙继银等. 基于兴趣点的遥感影像可匹配性度量[J]. 光学精密工程, 2014,22(4): 1071-1077 DOI： 10.3788/OPE.20142204.1071.

JU Xi-nuo, GUO Wen-pu, SUN Ji-yin etc. Matching probability metric for remote sensing image based on interest points[J]. Editorial Office of Optics and Precision Engineering, 2014,22(4): 1071-1077 DOI： 10.3788/OPE.20142204.1071.

摘要

为了提高基准图制备的有效性，研究了遥感影像的可匹配性，并针对点特征提出了基于兴趣点度量遥感影像可匹配性的度量指标。首先，利用非下采样Contourlet变换的高频系数提取图像的局部极值点作为兴趣点；然后，利用兴趣点的高频系数和方向特性定义兴趣点的幅值特性和结构特性。最后，分析兴趣点幅值特性和结构特性与实际匹配概率的关系，构建可匹配性度量指标。实验结果表明，可匹配性度量指标与实际匹配概率的线性相关性高于0.9，Spearman相关系数高于0.85，评估结果准确性高、单调性好。利用该指标对图像可匹配区域进行筛选，其制备的基准图的平均匹配概率大于95%，比传统方法提高了15.4%，改善了基准图制备的效率和可靠性。

Abstract

To improve the effectiveness of reference map preparation

the matching probability of a remote sensing image was investigated. A matching probability metric for the remote sensing image was proposed based on interest points. Firstly

the local extreme points obtained from high frequency coefficients of non-subsampled Contourlet transform were set as interest points. Then

the amplitude and structure properties of interest points were defined by the frequency coefficients and direction information. Finally

the matching metric was established based on the analysis of the relationship between amplitude and structure properties and real matching probability. Experiments show that the correlation coefficient of the metric and real matching probability is greater than 0.9 and the Spearman rank order correlation coefficient is greater than 0.85 with high accuracy and consistency. Matching region extraction by using the proposed index gives the average matching probability of more than 95% for reference maps

increasing 15.4% more than traditional methods. It improves the efficiency and the reliability of reference map preparation.

关键词

Keywords

references

ZHANG X CH, HE ZH W, LIANG Y H, et al. Selection method for scene matching area based on information entropy. 2012 Fifth International Symposium on Computational Intelligence and Design (ISCID)[C], 2012, 1:364-368.

曹菲, 杨小冈, 缪栋, 等. 景象匹配制导基准图选定准则研究[J]. 计算机应用研究, 2005, (5): 137-139. CAO F, YANG X G, MIU D, et al. Study on reference image selection roles for scene matching guidance[J]. Application Research of Computers, 2005, (5): 137-139. (in Chinese)

杨小冈, 曹菲, 黄先祥, 等. 景象匹配仿真中基准图的制备方法研究[J]. 系统仿真学报, 2010, 22(4): 850-852. YANG X G, CAO F, HUANG X X, et al. Reference image preparation approach for scene matching simulation[J]. Journal of System Simulation, 2010, 22(4): 850-852. (in Chinese)

赵锋伟, 沈振康, 刘扬, 等. 景象匹配评估系统中图像特征指标的选择(一)图像统计特征[J]. 红外与激光工程, 2001, 30(4): 187-191. ZHAO F W, SHEN ZH K, LIU Y, et al. Selection of image feature set in performance evaluation system of scene matching algorithm (Part 1: image statistic feature)[J]. Infrared and Laser Engineering, 2001, 30(4):187-191. (in Chinese)

HARRIS C, STEPHENS M. A combined corner and edge detector[C]. In Proceedings of the Alvey Vision Conference, 1988, 147-151.

LOWE D G. Distinctive image features from scale invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.

BAY H, ESS A, TUYTELAARS T, et al. Speeded-Up Robust Features(SURF)[J]. International Journal on Computer Vision and Image Understanding, 2008, 110(3): 346-359.

丘文涛, 赵建, 刘杰. 结合区域分割的SIFT图像匹配方法[J]. 液晶与显示, 2012, 27(6):827-831. QIU W T, ZHAO J, LIU J. Image matching algorithm combining SIFT with region segmentation[J]. Chinese Journal of Liquial Crystals and Displays, 2012, 27(6):827-831. (in Chinese)

唐永鹤, 卢焕章. 基于灰度差分不变量的快速局部特征描述算法[J]. 光学精密工程, 2012, 20(2): 447-454. TANG Y H, LU H ZH. Fast local feature description algorithm based on grey value differential invariants[J]. Opt. Precision Eng., 2012, 20(2): 447-454. (in Chinese)

贾平, 徐宁, 张叶. 基于局部特征提取的目标自动识别[J]. 光学精密工程, 2013, 21(7): 1898-1905. JIA P, XU N, ZHANG Y. Automatic target recognition based on local feature extraction[J]. Opt. Precision Eng., 2013, 21(7): 1898-1905. (in Chinese)

PANG Y W, LI W, YUAN Y, et al.. Fully affine invariant SURF for image matching[J]. Neurocomputing, 2012, 85: 6-10.

DA CUNHA A L, ZHOU J P, DO M N. The nonsubsampled Contourlet transform: theory, design and applications[J]. IEEE Transaction on Image Processing, 2006, 15(10): 3089-3101

DO M N, VETTERLI M. The Contourlet transform: an efficient directional multiresolution image representation[J]. IEEE Transactions on Image Processing, 2005, 14(12): 2091-2106.

SCHMID C, MOHR R, BAUCKHAGE C. Evaluation of interest point detectors[J]. International Journal of Computer Vision, 2000, 37(2): 151-172.

杨小冈, 左森, 黄先祥, 等. 图像匹配综合实验与仿真系统研究[J]. 系统仿真学报, 2010, 22(6):1360-1364. YANG X G, ZUO S, HUANG X X, et al. Integral experiment and simulation system for image matching[J]. Journal of System Simulation, 2010, 22(6):1360-1364. (in Chinese)

WU J M, JING Z L, WU Z, et al. Study on an improved Hausdorff distance for multi-sensor image matching[J]. Communications in Nonlinear Science and Numerical Simulation, 2012, 17(2): 513-520.

LIU X Z, TIAN Z, CHAI C Y, et al. Multiscale registration of remote sensing image using robust SIFT features in steerable-domain[J]. The Egyptian Journal of Remote Sensing and Space Science, 2011, 14(2): 63-72.

Final report from the video quality experts group on the validation of objective models of video quality assessment[OL]. (2003-07-01), http:// www.vqeg.org

浏览量

564

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向单幅遥感图像超分辨率的空间自适应及频率融合网络

融合边缘增强与非局部模块的遥感图像超分辨率重建生成对抗网络

融合CNN和Transformer的遥感图像建筑物快速提取

融合分形几何特征Resnet遥感图像建筑物分割

多尺度特征融合空洞卷积ResNet遥感图像建筑物分割