基于高光谱图像的改进SIFT特征提取与匹配

丁国绅; 易维宁; 杜丽丽; 方薇

doi:10.3788/OPE.20202804.0954

您当前的位置：

首页 >

文章列表页 >

基于高光谱图像的改进SIFT特征提取与匹配

信息科学 | 更新时间：2020-08-13

- 基于高光谱图像的改进SIFT特征提取与匹配
- Improved SIFT feature extraction and matching technology based on hyperspectral image
- 光学精密工程 2020年28卷第4期页码：954-962
- 作者机构：
  
  1.中国科学院安徽光学精密机械研究所通用光学定标与表征技术重点实验室，安徽合肥 230031
  2.中国科学技术大学，安徽合肥 230026
- 作者简介：
  
  [ "丁国绅(1992-)，男，安徽怀宁人，博士研究生，2015年于，2018年于安徽大学分别获得学士、硕士学位，主要从事计算机视觉与遥感图像处理方面的研究。E-mail:guoshenahu@163.com" ]
  方薇(1977-)，女，安徽合肥人，副研究员，1999年，2012年于中国科学技术大学分别获得学士、硕士学位，主要研究方向为计算机信息处理与遥感智能应用。E-mail:fwei@aiofm.ac.cn FANG Wei, E-mail:fwei@aiofm.ac.cn
- 基金信息：
  
  中国科学院创新基金资助项目(No.CXJJ-19S002)
- DOI：10.3788/OPE.20202804.0954
  中图分类号： TP391.41
- 收稿日期：2019-10-31，
  
  修回日期：2019-12-20，
  
  录用日期：2019-12-20，
  
  纸质出版日期：2020-04-15
- 稿件说明：
移动端阅览
丁国绅, 易维宁, 杜丽丽, 等. 基于高光谱图像的改进SIFT特征提取与匹配[J]. 光学精密工程, 2020,28(4):954-962.

Guo-shen DING, Wei-ning YI, Li-li DU, et al. Improved SIFT feature extraction and matching technology based on hyperspectral image[J]. Optics and precision engineering, 2020, 28(4): 954-962.
丁国绅, 易维宁, 杜丽丽, 等. 基于高光谱图像的改进SIFT特征提取与匹配[J]. 光学精密工程, 2020,28(4):954-962. DOI： 10.3788/OPE.20202804.0954.

Guo-shen DING, Wei-ning YI, Li-li DU, et al. Improved SIFT feature extraction and matching technology based on hyperspectral image[J]. Optics and precision engineering, 2020, 28(4): 954-962. DOI： 10.3788/OPE.20202804.0954.

摘要

针对尺度不变特征变换(SIFT)算法所提取图像特征点数量少、误匹率高的问题，提出了一种基于高光谱图像的改进SIFT算法。首先，依据传统SIFT算法中高斯金字塔的构造思想，结合在不同波段下的高光谱图像具有相同宏观特征的特点，首次用高光谱图像作为原始算法中经高斯变换产生的图像，使得检测到的具有实际意义的特征点数量大幅增加；其次，传统SIFT算法以及大量的改进方法都只通过目标象元邻域范围内的像素信息来构造特征描述符，而忽略了像素点的位置信息，文中将目标象元的位置信息纳入了特征描述符，在特征描述符的匹配阶段，在利用邻域范围内的像素信息进行粗匹配之后，利用特征描述符中的位置信息进行精细匹配。仿真实验结果表明：在限定最优值与次优值之比的情况下，采用高光谱图像构造高斯金字塔的方式能显著增加特征点的提取数量，更多地挖掘出图像中的极值点；在特征描述符中加入目标象元的位置信息作为特征点匹配第二阶段的判断依据，正确匹配数量达到原方法的59倍以上，极大提升了算法的匹配性能。

Abstract

Aiming at the small number of feature points and high error rate in the traditional Scale Invariant Feature Transform(SIFT) algorithm

an improved SIFT algorithm was improved based on hyperspectral images. First

hyperspectral images were used as the images generated by Gaussian transformation based on the Gaussian pyramid construction in the traditional SIFT algorithmand the characteristics of hyperspectral images with the same macro-characteristics in different wavebands.This considerably increased the number of real significant feature points detected. Second

the traditional SIFT algorithm and several improved methods only construct the feature descriptor through the pixel information in the neighborhood of the target pixeland ignore the position information of the pixel. In this study

the position information of the target pixel was included in the feature descriptor. The pixel information in the neighborhood was first used for coarse matching

and the position information in the feature descriptor was subsequently used for fine matching. The simulation results showed that by limiting the ratio of the suboptimal value

the method of constructing Gaussian pyramid with hyperspectral images significantly increased the number of feature points extracted

and more extreme points in the image could be extracted.Furthermore

the position information of the target pixel was added to the feature descriptor as the judgment basis of the second stage of feature point matching. Consequently

the number of correct matching was at least 59 times that of the original method

which greatly improved the matching performance of the algorithm.

关键词

Keywords

references

陈斌 , 东一舟 , 朱晋宁 . 非控场景下主成分稀疏表示与低秩分解的人脸识别 . 液晶与显示 , 2019 . 34 ( 8 ): 816 - 824 . http://d.old.wanfangdata.com.cn/Periodical/yjyxs201908012 http://d.old.wanfangdata.com.cn/Periodical/yjyxs201908012 .

B CHEN , Y ZH DONG , J N ZHU . Face recognition based on sparse representation of principal components and low rank decomposition in uncontrolled scenes . Chinese Journal of Liquid Crystals and Displays , 2019 . 34 ( 8 ): 816 - 824 . http://d.old.wanfangdata.com.cn/Periodical/yjyxs201908012 http://d.old.wanfangdata.com.cn/Periodical/yjyxs201908012 .

X S XU , Z Y YUE , T ZHANG , 等 . Method on underwater assisted navigation system using two-dimensional terrain feature matching based on Hu moments . Journal of Chinese Inertial Technology , 2015 . 23 ( 3 ): 363 - 368 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zggxjsxb201503015 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zggxjsxb201503015 .

SH YUAN , T ZHENG . 3D reconstruction based on spatial vanishing information . Chinese Optics Letters , 2005 . 3 ( 3 ): 146 http://cn.bing.com/academic/profile?id=81693206400d67d626031cc6448fe958&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=81693206400d67d626031cc6448fe958&encoded=0&v=paper_preview&mkt=zh-cn .

朱述龙 , 钱曾波 . 基于小波包特征的纹理影像分割 . 中国图象图形学报 , 2018 . 3 ( 8 ): 662 - 665 . http://www.cnki.com.cn/Article/CJFDTotal-ZGTB808.009.htm http://www.cnki.com.cn/Article/CJFDTotal-ZGTB808.009.htm .

SH L ZHU , Z B QIAN . Textured image segmentation using wavelet packet transform . Journal of Image and Graphics , 2018 . 3 ( 8 ): 662 - 665 . http://www.cnki.com.cn/Article/CJFDTotal-ZGTB808.009.htm http://www.cnki.com.cn/Article/CJFDTotal-ZGTB808.009.htm .

D MARR , E HILDRETH . Theory of edge detection . Proceedings of the Royal Society of London. Series B, Biological Sciences , 1980 . 207 ( 1167 ): 187 - 217 . DOI: 10.1098/rspb.1980.0020 http://doi.org/10.1098/rspb.1980.0020 .

DALAL N. Finding People in Images and Videos [D]. Grenoble, France: The French National Institute for Research in Computer Science and Control, 2006.

D LOWE . Distinctive image features from scale-invariant keypoints . International Journal of Computer Vision , 2004 . 160 ( 2 ): 91 - 110 . http://d.old.wanfangdata.com.cn/NSTLQK/NSTL_QKJJ025429678/ http://d.old.wanfangdata.com.cn/NSTLQK/NSTL_QKJJ025429678/ .

MORAVEC H P. Obstacle Avoidance and Navigation in the Real World by A Seeing Robot Rover [M]. INSPIRE-HEP, 1980.

孔明 , 郝玲 , 刘维 , 等 . 数字全息中基于优化Harris角点的相位拼接算法 . 红外与激光工程 , 2019 . 48 ( 11 ): 1126002 http://d.old.wanfangdata.com.cn/Periodical/hwyjggc201911037 http://d.old.wanfangdata.com.cn/Periodical/hwyjggc201911037 .

M KONG , L HAO , W LIU , 等 . Phase splicing algorithm based on optimized Harris corner in digital holography . Infrared and Laser Engineering , 2019 . 48 ( 11 ): 1126002 http://d.old.wanfangdata.com.cn/Periodical/hwyjggc201911037 http://d.old.wanfangdata.com.cn/Periodical/hwyjggc201911037 .

LOWE D G. Object Recognition from Local Scale-Invariant Features[C]. IEEE Computer Society , 1999: 1150-1157.

曾峦 , 王元钦 , 谭久彬 . 改进的SIFT特征提取和匹配算法 . 光学精密工程 , 2011 . 19 ( 6 ): 1391 - 1397 . http://www.eope.net/CN/abstract/abstract10825.shtml http://www.eope.net/CN/abstract/abstract10825.shtml .

L ZENG , Y Q WANG , J B TAN . Improved algorithm for SIFT feature extraction and matching . Opt. Precision Eng , 2011 . 19 ( 6 ): 1391 - 1397 . http://www.eope.net/CN/abstract/abstract10825.shtml http://www.eope.net/CN/abstract/abstract10825.shtml .

Q ZENG , J ADU , J LIU , 等 . Real-time adaptive visible and infrared image registration based on morphological gradient and C_SIFT . Journal of Real-Time Image Processing , 2019 . 1 - 13 . https://link.springer.com/article/10.1007/s11554-019-00858-x https://link.springer.com/article/10.1007/s11554-019-00858-x .

耿庆田 , 赵浩宇 , 王宇婷 , 等 . 基于改进SIFT特征提取的车标识别 . 光学精密工程 , 2018 . 26 ( 5 ): 269 - 276 . http://www.eope.net/CN/abstract/abstract17623.shtml http://www.eope.net/CN/abstract/abstract17623.shtml .

Q T GENG , H Y ZHAO , Y T WANG , 等 . A vehicle logo recognition algorithm based on the improved SIFT feature . Opt. Precision Eng , 2018 . 26 ( 5 ): 269 - 276 . http://www.eope.net/CN/abstract/abstract17623.shtml http://www.eope.net/CN/abstract/abstract17623.shtml .

Y ZHAO , Y ZHAI , E DUBOIS , 等 . Image matching algorithm based on SIFT using color and exposure information . Journal of Systems Engineering and Electronics , 2016 . 27 ( 3 ): 691 - 699 . DOI: 10.1109/JSEE.2016.00072 http://doi.org/10.1109/JSEE.2016.00072 .

Q YU , S ZHOU , Y JIANG , 等 . High-performance SAR image matching using improved SIFT framework based on rolling guidance filter and ROEWA-powered feature . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2019 . 12 ( 3 ): 1 - 14 . DOI: 10.1109/JSTARS.2019.2903004 http://doi.org/10.1109/JSTARS.2019.2903004 .

SIMO-SERRA E, TRULLS E, FERRAZ L, et al . Discriminative Learning of Deep Convolutional Feature Point Descriptors [C]. IEEE International Conference on Computer Vision , 2015: 118-126.

BIAN J, LIN W Y, MATSUSHITA Y, et al . GMS: Grid-Based Motion Statistics for Fast, Ultra-Robust Feature Correspondence[C]. IEEE Conference on Computer Vision and Pattern Recognition , 2017: 2828-2837.

浏览量

351

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

3D-CNN与Transformer混合结构的高光谱图像空谱联合分类

CNN-Transformer结合对比学习的高光谱与LiDAR数据协同分类

同质区共享端元变异性的高光谱混合像元分解

利用光谱解混合的目标检测

面向领域自适应的部分最优传输高光谱图像分类