电子与控制

基于控制线方法的机载SAR和可见光图像匹配应用研究

  • 刘中杰 ,
  • 曹云峰 ,
  • 庄丽葵 ,
  • 丁萌
展开
  • 1. 南京航空航天大学 自动化学院, 江苏 南京 210016;
    2. 空军驻京昌地区军事代表室, 北京 100041;
    3. 南京航空航天大学 高新技术研究院, 江苏 南京 210016;
    4. 南京航空航天大学 民航学院, 江苏 南京 210016
刘中杰 男, 博士研究生。主要研究方向: 无人机飞行控制与导航、图像处理。Tel: 010-58871169 E-mail: liuzhongjie1123@163.com;曹云峰 男, 硕士, 教授, 博士生导师。主要研究方向: 无人机飞行控制与导航、微型飞行器飞行控制、计算机视觉、控制系统数字化设计。Tel: 025-84890902 E-mail: cyfac@nuaa.edu.cn;庄丽葵 女, 讲师。主要研究方向: 无人机飞行控制。Tel: 025-84890902 E-mail: lkzhuang@nuaa.edu.cn;丁萌 男, 博士, 副教授。主要研究方向: 计算机视觉。Tel: 025-52119071 E-mail: nuaa_dm@hotmail.com

收稿日期: 2013-03-29

  修回日期: 2013-06-17

  网络出版日期: 2013-06-20

基金资助

国家自然科学基金(61203170);航空科学基金(20110752005);江苏省普通高校研究生科研创新计划;中央高校基本科研业务费专项资金(CXLX12_0160);中国博士后基金特别资助(2013T60539)

Applied Research on Airborne SAR and Optical Image Registration Based on Control Line Method

  • LIU Zhongjie ,
  • CAO Yunfeng ,
  • ZHUANG Likui ,
  • DING Meng
Expand
  • 1. College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China;
    2. Air Force Military Representative Office in Jingchang District, Beijing 100041, China;
    3. Academy of Frontier Science, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China;
    4. College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China

Received date: 2013-03-29

  Revised date: 2013-06-17

  Online published: 2013-06-20

Supported by

National Natural Science Foundation of China (61203170);Aeronautical Science Foundation of China (20110752005);Funding of Jiangsu Innovation Program for Graduate Education;Fundamental Research Funds for the Central Universities (CXLX12_0160);Special Foundation of China Postdoctoral Science (2013T60539)

摘要

根据无人机(UAV)景象匹配导航的现实需求,对具有典型人造场景的机载合成孔径雷达(SAR)图像与可见光图像,提出一种基于直线特征的SAR图像与可见光图像配准方法。首先,利用改进的直线段检测(LSD)方法提取图像直线特征;其次,构造控制线并设计了一种基于控制线的图像配准方法;最后,依据仿射变换模型实现了待配准图像的精确自动配准。实验表明,在SAR和可见光图像存在较大灰度差异、旋转和平移的情况下,该算法仍能精确配准图像,且运算时间大幅减少,能够满足一些实时性较强的应用。

本文引用格式

刘中杰 , 曹云峰 , 庄丽葵 , 丁萌 . 基于控制线方法的机载SAR和可见光图像匹配应用研究[J]. 航空学报, 2013 , 34(9) : 2194 -2201 . DOI: 10.7527/S1000-6893.2013.0309

Abstract

According to the realistic needs of the unmanned aerial vehicle (UAV) scene matching navigation, image registration method is proposed, based on linear features of the airborne synthetic aperture radar (SAR) and optical images containing typical man-made objects. Firstly, improved line segment detection (LSD) method is proposed to extract linear features of the image; Secondly, we construct the control lines and design an image registration method. Finally, precise automatic image registration is achieved based on the affine transformation model. The experimental results show that the proposed method has high registration accuracy for the SAR image and optical image, which is different in intensive, rotation and translation. The computation time is substantially reduced, and it is possible to meet some of the real-time applications.

参考文献

[1] Candocia F, Adjouadi M. A similarity measure for stereo feature matching. IEEE Transactions on Image Processing, 1997, 6(10): 1460-1464.

[2] Dawn S, Saxena V, Sharma B. Remote sensing image registration techniques: a survey. Image and Signal Processing, 2010, 6134: 103-112.

[3] Chen X, Qiu P H. Intensity-based image registration by nonparametric local smoothing. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(10): 2081-2092.

[4] Yi M, Guo B L. Aerial video image registration method based on invariant feature and mapping restraint. Acta Aeronautica et Astronautica Sinica, 2012, 33(10): 1872-1880. (in Chinese) 易盟, 郭宝龙. 基于不变特征和映射抑制的航拍视频图像配准. 航空学报, 2012, 33(10): 1872-1880.

[5] Liu B Q, Feng D Z, Wu N, et al. An image automatic registration method for InSAR complex images based on point features. Acta Aeronautica et Astronautica Sinica, 2007, 28(1): 161-166. (in Chinese) 刘宝泉, 冯大政, 武楠, 等. 基于点特征的干涉合成孔径雷达复图像自动配准算法. 航空学报, 2007, 28(1): 161-166.

[6] Niu L P, Mao S Y, Chen W. Multi-sensor image registration method adapted for large scale. Acta Aeronautica et Astronautica Sinica, 2006, 27(3): 475-480. (in Chinese) 牛力丕, 毛士艺, 陈炜. 一种适应较大比例变化的多传感器图像配准方法. 航空学报, 2006, 27(3): 475-480.

[7] Stamos I, Leordeanu M. Automated feature-based range registration of urban scenes of large scale.2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003, 2: II-561.

[8] Kim Y S, Lee J H, Ra J B. Multi-sensor image registration based on intensity and edge orientation information. Pattern Recognition, 2008, 41(11): 3356-3365.

[9] Su J, Lin X G, Liu D Z. A multi-sensor image registration algorithm based on structure feature edges. Acta Automatica Sinca, 2009, 35(3): 251-257. (in Chinese) 苏娟, 林行刚, 刘代志. 一种基于结构特征边缘的多传感器图像配准方法. 自动化学报, 2009, 35(3): 251-257.

[10] Li Y, Cui Y Y, Han X Y. Optical image and SAR image registration based on linear features and control points. Acta Automatica Sinca, 2012, 38(12): 1968-1974. (in Chinese) 李映, 崔杨杨, 韩晓宇. 基于线特征和控制点的可见光和SAR图像配准. 自动化学报, 2012, 38(12): 1968-1974.

[11] Ji J, Ang H S, Wang X G, et al. Fast extraction and matching of strait lines on sequential images. Journal of Nanjing University of Aeronautics & Astronautics, 2005, 37(2): 227-231. (in Chinese) 季建,昂海松,王旭刚,等. 序列图像中直线边缘快速提取和匹配. 南京航空航天大学学报, 2005, 37(2): 227-231.

[12] Hu Z L, Sun J P, Yuan Y N, et al. SAR image despeckling in wavelet domain based on α-stable model. Acta Aeronautica et Astronautica Sinica, 2006, 27(5): 928-933. (in Chinese) 胡正磊, 孙进平, 袁运能, 等. 利用α稳定分布的小波域SAR图像降斑算法. 航空学报, 2006, 27(5): 928-933.

[13] Gioi V, Grompone R, Jakubowicz J, Morel J M, et al. LSD: a fast line segment detector with a false detection control. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(4): 722-732.

[14] Desolneux A, Moisan L, Morel J M. Edge detection by Helmholtz principle. Journal of Mathematical Imaging, 2001, 14(3): 271-284.

[15] Desolneux A, Moisan L, Morel J M. Computational gestalts and perception thresholds. Journal of Physiology-Paris, 2003, 97(2): 311-324.

文章导航

/