[1]张皓,李娜,王陆.基于多尺度结构特征的快速异源图像匹配[J].红外技术,2020,42(5):420-425.[doi:10.11846/j.issn.1001_8891.202005002]
 ZHANG Hao,LI Na,WANG Lu.Fast Multi-sensor Image Matching Algorithm Based on a Multi-scale Dense Structure Feature[J].Infrared Technology,2020,42(5):420-425.[doi:10.11846/j.issn.1001_8891.202005002]
点击复制

基于多尺度结构特征的快速异源图像匹配
分享到:

《红外技术》[ISSN:1001-8891/CN:CN 53-1053/TN]

卷:
42卷
期数:
2020年第5期
页码:
420-425
栏目:
出版日期:
2020-05-23

文章信息/Info

Title:
Fast Multi-sensor Image Matching Algorithm Based on a Multi-scale Dense Structure Feature

文章编号:
1001-8891(2020)05-0420-06
作者:
张皓1李娜1王陆2
1. 河南工学院 计算机科学与技术学院;2. 北京邮电大学 电子工程学院
Author(s):
ZHANG Hao1LI Na1WANG Lu2
1. College of Computer Science and Technology, Henan Institute of Technology;
2. School of Electronic Engineering, Beijing University of Posts and Telecommunications

关键词:
异源图像匹配卷积定理快速傅里叶变换密集特征Gabor滤波器
Keywords:
multi-sensor image matching convolution theorem fast Fourier transform dense feature Gabor filter
分类号:
TP391
DOI:
10.11846/j.issn.1001_8891.202005002
文献标志码:
A
摘要:
针对异源图像提出一种基于多尺度密集结构特征的快速匹配算法。算法首先利用Gabor滤波器逐像素提取图像中的结构响应,再根据主方向响应对多尺度结构特征融合,然后使用快速傅里叶变换在频域计算各特征分量图像之间的卷积,最后将卷积生成的系数矩阵求和计算出图像之间的相似性并选择相似性最大位置作为匹配结果输出。本文算法能有效适应异源图像间的非线性灰度变化和噪声干扰问题。测试使用可见光、红外、雷达图像组成的异源图像数据集对本文算法和现有算法进行测试比较,结果表明:本文算法的平均误匹配率最低,并且计算速度有明显优势。
Abstract:
A fast image matching algorithm based on a multiscale dense structure feature has been proposed for matching multi-sensor images. In this method, the Gabor filter is employed for generating the structure response of the image. Then, the multiscale structure feature is combined on the basis of the major orientation response. Subsequently, fast Fourier transform is employed to calculate the convolution for each feature component image in the frequency domain. Finally, the similarity between images is estimated based on the sum of the convolutions, and the position with maximum similarity is outputted as the matching result. The proposed algorithm can effectively adapt to non-linear intensity variation between a multi-sensor image and noise distortion. In the experiments, a dataset consisting of optical, infrared, and synthetic aperture radar images was used for evaluating the proposed algorithm and other existing algorithms. The results indicate that the average error matching rate of the proposed algorithm is the lowest among the investigated algorithms and it has a distinct advantage in terms of computational performance.?

参考文献/References:

[1] 靳珍璐, 潘泉, 赵春晖, 等. 基于局部精确直方图匹配的无人机景象匹配导航色彩恒常算法[J]. 中国惯性技术学报, 2015, 23(5): 674-680.?
JIN Zhenlu, PAN Quan, ZHAO Chunhui, et al. Color constancy algorithm based on local exact histogram matching for scene matching navigation of UAVs[J]. Journal of Chinese Inertial Technology, 2015, 23(5): 674-680.
[2] 杜江, 杨建华, 石静. 景象匹配定位制导中误匹配消除方法[J]. 导航定位学报, 2017, 5(3): 5-8.?
DU Jiang, YANG Jianhua, SHI Jing. Mismatching eliminating method of scene matching, positioning and guidance[J]. Journal of Navigation and Positioning, 2017, 5(3): 5-8.
[3] 李海波, 曹云峰, 丁萌, 等. 基于异源图像特征的显著性融合检测方法[J]. 计算机技术与发展, 2018, 28(3): 1-5.?
LI Haibo, CAO Yunfeng, DING Meng, et al. A saliency fusion detection method based on image features from different sensors[J]. Computer Technology and Development, 2018, 28(3): 1-5.
[4] Hel-Or Y, Hel-Or H, David E. Fast template matching in non-linear tone-mapped images[C]//IEEE International Conference on Computer Vision, 2011: 1355-1362.?
[5] Brunelli R. Template Matching Techniques in Computer Vision: Theory and Practice[M]. Wiley, 2009.?
[6] Maes F, Vandermeulen D, Suetens P. Medical image registration using mutual information[J]. Proceedings of IEEE, 2003, 91(10): 1699-1722.?
[7] Heo Y S, Lee K M, Lee S U. Robust Stereo Matching Using Adaptive Normalized Cross-correlation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(4): 807-822.?
[8] Keshavarz H, Tajeripour F, Faghihi R, et al. Developing a new approach for registering LWIR and MWIR images using local transformation function[J]. Signal, Image and Video Processing, 2012, 9: 29-37.?
[9] Sibiryakov A. Fast and high-performance template matching method[C]//IEEE Conference on Computer Vision and Pattern Recognition, 2011: 1417-1424.?
[10] Mellor M, Brady M. Phase Mutual Information as a similarity measure for registration[J]. Medical Image Analysis, 2005, 9(4): 330-343.
[11] YE Y, SHEN L. Hopc: a novel similarity metric based on geometric structural properties for multi-modal remote sensing image matching[J]. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, 2016, 3(1): 9-16.?
[12] 蔡鸣, 孙秀霞, 徐嵩, 等. 视觉技术辅助的无人机自主着陆组合导航研究[J]. 应用光学, 2015, 36(3): 343-350.?
CAI Ming. SUN Xiuxia, XU Song, et al. Vision/INS integrated navigation for UAV autonomous landing[J]. Journal of Applied Optics, 2015, 36(3): 343-350.
[13] 闫明, 杜佩, 王惠林, 等. 机载光电系统的地面多目标定位算法[J]. 应用光学, 2012, 33(4): 717-720.?
YAN Ming, DU Pei, WANG Huilin, et al. Ground multi-target positioning algorithm for airborne optoelectronic system[J]. Journal of Applied Optics, 2012, 33(4): 717-720.
[14] 张宝辉, 张俊举, 苗壮, 等. 远距离多源图像融合系统实时配准设计[J]. 应用光学, 2013, 34(3): 436-441.?
ZHANG Baohui, ZHANG Junju, MIAO Zhuang, et al. Real time registration for long-distance multi-source image fusion system[J]. Journal of Applied Optics, 2013, 34(3): 436-441.

备注/Memo

备注/Memo:
收稿日期:2019-09-17;修订日期:2020-03-03.
作者简介:张皓(1983-),男,河北保定人,硕士,实验师,研究方向:智能算法及数据处理。E-mail:vvtiq83@163.com。
基金项目:国家自然科学基金项目(61802116),河南省高等学校重点科研项目(19A520019)。

更新日期/Last Update: 2020-05-19