卫星图像配准及匹配曲线特征评估法

李京娜; 邓嘉兴; 王刚

doi:doi:10.3969/j.issn.1003-501x.2014.03.012

光电工程, 2014, 41 (3): 73, 网络出版: 2014-04-09

卫星图像配准及匹配曲线特征评估法

Satellite Image Registration and Matching Curves Feature Assessment Method

论文大纲

李京娜 ^*邓嘉兴王刚

作者单位

鲁东大学信息与电气工程学院, 山东烟台 264025

图像配准匹配曲线特征评估法修正的结构相似度傅里叶-梅林变换 images registration matching curve feature evaluation (MCfe) method modified structural similarity (MSSIM) Fourier-mellin transform

摘要

由于卫星图像来自于不同的传感器、由不同的视角和光谱、在不同的时间获得, 图像间存在较大差异。为了有效配准图像, 提出一种“先粗后精”的配准算法, 首先采用Fourier-Mellin 变换算法实施快速的粗配准, 然后采用以修正的结构相似度为测度的优化算法实施精确配准。对于真实的卫星图像配准, 由于没有准确的衡量标准, 很难给出定量的评估结果。本文提出一种新的配准评估方法——匹配曲线特征评估法, 以匹配曲线的峰度、峰偏、峰值以及峰值间均方根误差(RMSE)为定量评估指标, 以峰值间RMSE 最小为准则自动调整配准参数。结果表明, “先粗后精”的配准算法能够实现相当精确的配准; 匹配曲线特征评估法不仅能够从曲线的光滑度、尖锐度等特性直观描述配准性能, 并能由曲线的特征指标定量评估配准效果, 而且还能自动调整配准参数, 使配准更加精确。

Abstract

The registration of satellite imagery is challenging task because of considerable differences between the image pairs captured by different sensors, view angles, spectrum or at different times. To align the images effectively, a coarse-to-fine registration algorithm is proposed. First, Fourier-Mellin transform algorithm is used to implement a fast coarse registration. Then, the optimization algorithm based on MSSIM measure is used to implement a fine registration. Because there is no accurate measure standard, it is very difficult to give a quantitative assessment of the registration results for real satellite images. A novel registration evaluation method is proposed, called Catching Curve Feature Evaluation (MCfe) method. In MCfe, kurtosis, peak deviation, peak maximum and Root Mean Square Error (RMSE) among peak maxima are extracted as the quantitative evaluation indexes, and the minimizing on RMSE is used as a registration criterion. The results demonstrate that the coarse-to-fine registration algorithm can achieve an extremely accurate registration for satellite imagery. The MCfe method can intuitively describe the registration performance from the curve features such as smoothness and sharpness, and also to be used to quantitatively assess the registration results, but also to automatically adjust the registration parameters to obtain a more accurate registration.

参考文献

[1] Zitova B, Flusser J. Image registration methods: a survey [J]. Image and Vision Computing(S0262-8856), 2003, 21: 977–1000.

[2] ZHAO Zengshun, FENG Xiang, TENG Shenghua, et al. Multiscale Point Correspondence Using Feature Distribution and Frequency Domain Alignment [J]. Mathematical Problems in Engineering(S1024-123X), 2012.

[3] 韩雨, 王卫卫, 冯象初. 基于迭代重加权的非刚性图像配准 [J]. 自动化学报, 2011, 37(9): 1059-1066.

HAN Yu, WANG Weiwei, FENG Xiangchu. Iteratively Reweighted Method Based Nonrigid Image Registration [J]. Acta Automatica Sinica, 2011, 37 (9): 1059-1066.

[4] 王婕妤, 王加俊, 张静亚. 基于改进光流场和尺度不变特征变换的非刚性医学图像配准 [J]. 电子与信息学报, 2013, 35(5): 1222-1228.

WANG Jieyu, WANG Jiajun, ZHANG Jingya. Non-rigid Medical Image Registration Based on Improved Optical Flow Method and Scale-invariant Feature Transform [J]. Journal of Electronics & Information Technology, 2013, 35(5): 1222-1228.

[5] Sánchez-Ferrero G V, Vega A T, Grande L C, et al. Strain Rate Tensor Estimation in Cine Cardiac MRI Based on Elastic Image Registration: Tensors in Image Processing and Computer Vision [M]. Springer London, 2009: 355-379.

[6] WANG Zhou, Bovik A C. A universal image quality index [J]. Signal Processing Letters(S1070-9908), 2002, 9(3): 81-84.

[7] WANG Zhou, Bovik A C, Sheikh H R, et al. Image quality assessment: From error visibility to structural similarity [J]. IEEE Transactions on Image Processing(S1057-7149), 2004, 13(4): 600-612.

[8] Aja-Fernandez S, Estepar R S J, Alberola-Lopez C, et al. Image quality assessment based on local variance [C]// IEEE 28th Annual International Conference of the Engineering in Medicine and Biology Society, New York City, USA, Aug 30-Sept 3, 2006: 4815-4818.

[9] 罗述谦, 周果宏. 医学图像处理与分析 [M]. 北京: 科学出版社, 2003: 140-201.

LUO Shuqian, ZHOU Guohong. Medical Image Processing and Analysis [M]. Beijing: Science Press, 2003: 140-201.

[10] West J, Fitzpatrick J M, Wang M Y, et al. Comparison and evaluation of retrospective intermodality brain image registration techniques [J]. Journal of Computer Assisted Tomography(S0363-8715), 1997, 21(4): 554-568.

[11] DeCarlo L T. On the meaning and use of kurtosis [J]. Psychological Methods (S1082-989X), 1997, 2(3): 292-307.

[12] 李京娜, 王国宏, 孙少燕, 等. 基于修改后的结构相似度的三维图像配准 [J]. 光电工程, 2012, 39(12): 70-76.

LI Jingna, WANG Guohong, SUN Shaoyan, et al. 3-Dimension Image Registration Based on Modified Structural Similarity [J]. Opto-Electronic Engineering, 2012, 39(12): 70-76.

[13] CHEN Qinsheng, Defrise M, Deconinck F. Symmetric phaseonly matched filtering of fourier-mellin transforms for image registration and recognition [J]. IEEE Transactions Pattern Analysis and Machine Intelligence(S0162-8828), 1994, 16(12): 1156–1168.

[14] Reddy B S, Chatterji B N. An FFT-based technique for translation, rotation, and scale-invariant image registration [J]. IEEE Transactions Pattern Analysis and Machine Intelligence(S0162-8828), 1996, 5(8): 1266–1270.

[15] Kim K B, Kim J S, Choi J S. Fourier Based Image Registration for Sub-Pixel Using Pyramid Edge Detection and Line Fitting [C]// IEEE First International Conference on Intelligent Networks and Intelligent Systems, Nov 1- 3, 2008: 535-538.

[16] 唐焕文, 秦学志. 实用最优化方法: 三版 [M]. 大连: 大连理工大学出版社, 2004: 147-149.

TANG Huanwen, QIN Xuezhi. Practical methods of optimization: Third-edition [M]. Dalian: Dalian University of Technology Press, 2004: 147-149.

[17] http: //vision.ece.ucsb.edu/registration/satellite/multispectral.htm.

李京娜, 邓嘉兴, 王刚. 卫星图像配准及匹配曲线特征评估法[J]. 光电工程, 2014, 41(3): 73. LI Jingna, DENG Jiaxing, WANG Gang. Satellite Image Registration and Matching Curves Feature Assessment Method[J]. Opto-Electronic Engineering, 2014, 41(3): 73.

卫星图像配准及匹配曲线特征评估法

关于本站 Cookie 的使用提示

全站搜索

卫星图像配准及匹配曲线特征评估法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索