面向目标检测的空间观测图像精确配准

沈同圣; 张健; 娄树理

doi:10.3788/OPE.20142208.2205

您当前的位置：

首页 >

文章列表页 >

面向目标检测的空间观测图像精确配准

信息科学 | 更新时间：2020-08-13

- 面向目标检测的空间观测图像精确配准
- Precise registration of space observation images for target detection
- 光学精密工程 2014年22卷第8期页码：2205-2213
- 作者机构：
  
  1. 海军航空工程学院控制工程系,山东烟台,中国,264001
  2. 中国国防科技信息中心北京,100142
- 作者简介：
- 基金信息：
  
  国家自然科学基金资助项目（No.61302008）()
- DOI：10.3788/OPE.20142208.2205
  中图分类号： TP75;TP391.4
- 收稿日期：2013-12-12，
  
  修回日期：2014-01-09，
  
  纸质出版日期：2014-08-25
- 稿件说明：
移动端阅览
沈同圣, 张健, 娄树理. 面向目标检测的空间观测图像精确配准[J]. 光学精密工程, 2014,22(8): 2205-2213

SHEN Tong-sheng, ZHANG Jian, LOU Shu-li. Precise registration of space observation images for target detection[J]. Editorial Office of Optics and Precision Engineering, 2014,22(8): 2205-2213
沈同圣, 张健, 娄树理. 面向目标检测的空间观测图像精确配准[J]. 光学精密工程, 2014,22(8): 2205-2213 DOI： 10.3788/OPE.20142208.2205.

SHEN Tong-sheng, ZHANG Jian, LOU Shu-li. Precise registration of space observation images for target detection[J]. Editorial Office of Optics and Precision Engineering, 2014,22(8): 2205-2213 DOI： 10.3788/OPE.20142208.2205.

摘要

针对空间目标检测对图像配准精度的要求，本文组合Fourier-Mellin变换和加速鲁棒特征变换（SURF）算法来实现对空间观测图像的精确配准，并研究了该配准算法所涉及的变换模型、特征提取、特征匹配和配准精度等问题。该算法首先利用Fourier-Mellin变换计算图像旋转角度的整数值，根据整数角度将待配准图像反向旋转；然后利用SURF算法检测两幅图像的匹配特征点；最后利用最小二乘方法计算旋转角度的浮点值和平移量，而整数角度与浮点角度之和就是待配准图像的实际旋转角度。文中分析了SURF特征点检测与图像尺寸、DoH响应阈值以及尺度空间层数之间的关系。实验结果表明：提出的算法对图像旋转角度估计值的均方误差为0.0077°，50组实拍图像中星点质心均方误差的平均值为0.1353 pixel，能够满足空间目标检测对图像配准的精度要求。

Abstract

For the requirements of space target detection for image registration

an observation image registration algorithm based on Fourier-Mellin trans-form and Speed Up Robust Feature(SURF) transform was proposed. The transform model

feature detection

feature matching and the matching accuracy related to the algorithm were all discussed. Firstly

the Fourier-Mellin transform was used to calculate the rotation angle

the image to be matched was reversely rotated according to the integer angle of the image. Then

the SURF was used to detect the matching feature points between two images. Finally

the floating point rotation angle and offset were calculated with the least square method. The sum of integer angle and floating point angle is an actual rotation angle of the image to be matched. Furthermore

the relationships between SURF feature point detection and image size

DoH response threshold and scale space decompose layers were analyzed. The experimental results show that the Root Mean Square Error(RMSE) of rotation angle estimation is 0.0077°

and the average value of RMSE of 50 groups of star centroids is 0.1353 pixel. The algorithm can meet the requirements of space target detection.

关键词

Keywords

references

CHU P L. Efficient detection of small moving objects[R]. Lexington, Massachusetts: Lincoln Laboratory, Massachusetts Institute of Technology, 1989.

POHLIG S C. Maximum likelihood detection of electro-optic moving targets[R]. Lexington, Massachusetts: Lincoln Laboratory, Massachusetts Institute of Technology, 1992.

张玉叶, 王春歆. 基于改进DPA的空间小目标检测算法[J]. 电子学报, 2010, 38 (3): 556-560. ZHANG Y Y, WANG CH X. Space small targets detection based on improved DPA[J]. Acta Electronica Sina, 2010, 38 (3): 556-560. (in Chinese)

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

LOWE D G. Local feature view clustering for 3D object recognition[C]. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2001, 1: 682-688.

何敬, 李永树, 鲁恒, 等. 基于SIFT 特征点的无人机影像拼接方法研究[J]. 光电工程, 2011, 38 (2): 122-126. HE J, LI Y SH, HU H, et al.. Research of UAV aerial image mosaic based on SIFT[J]. Opto-Electronic Engineering, 2011, 38(2):122-126. (in Chinese)

傅卫平,秦川,刘佳, 等. 基于SIFT算法的图像目标匹配与定位[J]. 仪器仪表学报, 2011, 32 (1): 163-169. FU W P, QIN CH, LIU J, et al.. Matching and location of image object based on SIFT algorithm[J]. Chinese Journal of Scientific Instrument, 2011, 32 (1):163-169. (in Chinese)

王梅, 屠大维, 周许超. SIFT特征匹配和差分相乘融合的运动目标检测[J]. 光学精密工程, 2011, 19 (4): 892-899. WANG M, TU D W, ZHOU X CH. Moving object detection by combining SIFT and differetial multiplication[J]. Opt. Precision Eng., 2011, 19 (4): 892-899. (in Chinese)

BAY H, ESS A, TUYTELAARS T. Speeded-up robust features (SURF)[J]. Computer Vision and Image Understanding, 2008, 110 (3): 346-359.

丁南南,刘艳滢,张叶, 等. 基于SURF-DAISY算法和随机Kd树的快速图像配准[J]. 光电子·激光, 2012, 23 (7): 1395-1402. DING N N, LIU Y Y, ZHANG Y, et al.. Fast image registration based on SURF-DAISY algorithm and randomized Kd trees[J]. Journal of Optoelectronics Laser, 2012, 23 (7):1395-1402. (in Chinese)

罗楠,孙权森,耿蕾蕾, 等. 一种扩展SURF描述符及其在遥感图像配准中的应用[J]. 测绘学报, 2013, 42 (3): 383-388. LUO N, SUN Q SH, GENG L L, et al.. An extended SURF descriptor and its application in remote sensing images registration[J]. Acta Geodaetica et Cartographica Sinica, 2013, 42 (3): 383-388. (in Chinese)

谢雨来, 李醒飞, 吕津玮, 等. 基于SURF算法的水下图像实时配准方法[J]. 计算机辅助设计与图形学学报, 2010, 22 (12): 2215-2220. XIE Y L, LI X F, LV J W, et al.. Underwater images real-time registration method based on SURF[J]. Journal of Computer-Aided Design & Computer Graphics, 2010, 22(12):2215-2220. (in Chinese)

高素青, 谭勋军, 黄承夏. 一种基于SURF的图像配准改进算法[J]. 解放军理工大学学报:自然科学版, 2013, 14 (4): 373-376. GAO S Q, TAN X J, HUANG CH X, et al..Improved algorithm of image registration based on SURF[J]. Journal of PLA University of Science and Technology:Natural Science Edition,2013, 14 (4): 373-376. (in Chinese)

REDDY B S, CHATTERJI B N. An FFT-based technique for translation, rotation and scale in variant image registration [J]. IEEE Transactions on Image Processing, 1996, 5 (8):1266-1271.

CHEN Q S, DEFRISE M, DECONINCK F. Symmetric phase-only matched filtering of Fourier-Mellin transforms for image registration and recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1994,16(12):1156-1168.

王亮,刘蓉,张丽, 等. 基于Fourier-Mellin变换的气象卫星光谱图像配准[J]. 光谱学与光谱分析, 2013, 33 (3): 855-858. WANG L, LIU R, ZHANG L, et al.. The meteorological satellite spectral image registration based on Fourier-Mellin Transform[J]. Spectroscopy and Spectral Analysis, 2013, 33(3):855-858. (in Chinese)

林卉, 梁亮, 杜培军, 等. 利用Fourier-Mellin变换的遥感图像自动配准[J]. 武汉大学学报:信息科学版, 2012, 37(6):649-652. LIN H, LIANG L, DU P J, et al.. Image registration based on Fourier-mellin Transform[J]. Geomatics and Information Science of Wuhan University, 2012, 37(6):649-652. (in Chinese)

石晓进, 张云华. 基于Fourier-Mellin变换和相干系数法的重复轨道干涉SAR图像配准新方法[J]. 电子与信息学报, 2009, 31 (4): 803-807. SHI X J, ZHAGN Y H. A new image registration method for repeat-pass In SAR based on Fourier-Mellin Transformation and Correlation-Coeffcient algorithm[J]. Journal of Electronics & Information Technology, 2009, 31(4):803-807. (in Chinese)

翟优, 曾峦, 熊伟. 基于不变特征描述符实现星点匹配[J]. 光学精密工程, 2012, 20 (11):2532-2539. ZHAI Y, ZENG L, XIONG W. Star matching based on invariant feature descriptor[J]. Opt. Precision Eng., 2012, 20 (11): 2532-2539. (in Chinese)

LIEBE C C. Accuracy performance of star trackers a-tutorial[J]. IEEE Transactions on Aerospace and Electronic System, 2002, 38 (2): 587-599.

焦继超, 赵保军, 唐林波. 一种基于非降采样Contourlet变换和MLESAC的星空图像配准算法[J]. 系统工程与电子技术, 2010, 32 (12): 2686-2690. JIAO J CH, ZHAO B J, TANG L B. Space image registration algorithm based on nonsubsampled Contourlet transform and MLESAC[J]. Systems Engineering and Electronics, 2010, 32 (12): 2686-2690.(in Chinese)

浏览量

575

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

变分近似解算KL散度红外可见光遥感图像配准

多光谱图像融合的IC器件表面缺陷检测

双层平板探测的双能成像检测系统

基于相位特征的可见光和SAR遥感图像自动配准

采用轮廓特征匹配的红外-可见光视频自动配准