视觉驱动的变分配准方法

王慧贤; 靳惠佳; 雷呈强; 江万寿; 王艳

doi:10.11947/j.AGCS.2015.20140281

测绘学报 >

2015 , Vol. 44 >Issue 8: 893 - 899

DOI: https://doi.org/10.11947/j.AGCS.2015.20140281

摄影测量学与遥感

视觉驱动的变分配准方法

王慧贤 ,
靳惠佳 ,
雷呈强 ,
江万寿 ,
王艳

展开

1. 中国科学院电子学研究所空间信息处理与应用系统技术重点实验室, 北京 100190;
2. 武汉大学测绘遥感信息工程国家重点实验室, 湖北武汉 430079;
3. 军械工程学院电子与光学工程系, 河北石家庄 050003;
4. 北京市遥感信息研究所, 北京 100192

王慧贤(1985-),女,博士,助理研究员,研究方向为遥感影像处理与分析。E-mail:hxwang@mail.ie.ac.cn

收稿日期: 2014-05-27

修回日期: 2014-11-19

网络出版日期: 2015-09-02

基金资助

国家973计划(2011CB707105);国家863计划(2013AA12A301);高分重大专项(GFZX0404040904);长江学者和创新团队发展计划(IRT1278)

收起

A Visually Inspired Variational Method for Automatic Image Registration

WANG Huixian ,
JIN Huijia ,
LEI Chengqiang ,
JIANG Wanshou ,
WANG Yan

Expand

1. Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China;
2. State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China;
3. Electronic & Optical Engineering Department, Mechanical Engineering College, Shijiazhuang 050003, China;
4. Institute of Information in Remote Sensing in Beijing, Beijing 100192, China

Received date: 2014-05-27

Revised date: 2014-11-19

Online published: 2015-09-02

Supported by

The National Basic Research Program(973 program)(No.2011CB707105);The National High Technology Research and Development Program(863 Program) of China(No.2013AA12A301);National Science and Technology Major Project of the Ministry of Science and Technology of China in High Resolution Earth Observation Systems(No.GFZX0404040904);Program for Changjiang Scholars and Innovative Research Team in University(No.IRT1278)

Fold

摘要

针对传统整体配准模型不能充分顾及局部变形的问题,提出了一种视觉驱动的变分配准方法。该方法在变分模型建立中综合考虑了局部变换、整体平滑和视觉约束,同时兼顾了亮度和对比度差异。首先,基于灰度均方根误差建立配准模型的数据项;其次,为了保证整体平滑,模型采用H¹半范数进行自适应约束;最后,为了保证影像中的空间属性满足视觉的要求,不能出现扭曲变形,采用直线特征进行先验约束。在变分模型求解过程中先利用整个影像估计影像之间的整体变换参数,然后采用小的邻域范围进行局部估计。整个过程在多水平差分框架下迭代求解变换参数,进而兼顾了整体平滑和局部变形。笔者利用ZY-3卫星数据进行了试验,采用目视和量化指标进行了评价,验证了本文方法的优越性。

关键词： 视觉驱动; 变分理论; 局部变形; 影像配准

本文引用格式

王慧贤 , 靳惠佳 , 雷呈强 , 江万寿 , 王艳 . 视觉驱动的变分配准方法[J]. 测绘学报, 2015 , 44(8) : 893 -899 . DOI: 10.11947/j.AGCS.2015.20140281

Abstract

A visually inspired variational method for automatic image registration is proposed to solve local deformation which traditional global registration model cannot well satisfy. The variational model considers local transformation, global smoothness and visual constraints. To account for intensity variations, we incorporate change of local contrast and brightness into our model. Firstly, the data entry of registration model is built according to the root-mean-square error of intensity; secondly, adaptive constraint using H¹ half norm is used to ensure the global smooth in the model; finally, in order to make sure that the spatial attributes of the image satisfy the visual requirements and without distortion, the linear features are used as priori constraints. During the solution of model parameters, the whole image is used to globally estimate the transformation parameters, and then local estimation of the parameters is taken in a small neighbor. The entire procedure is built upon a multi-level differential framework, and the transformation parameters are calculated iteratively, which can consider both global smoothness and local distortion. To assess the quality of the proposed method, ZY-3 satellite images were used. Visual and quantitative analysis proved that the proposed method can significantly improve the registration precision.

Key words： visually inspired; variational theory; local distortion; image registration

参考文献

[1] DAWN S, SAXENA V, SHARMA B. Remote Sensing Image Registration Techniques: A Survey[C]//ELMOATAZ A, LEZORAY O, NOUBOUD F, et al. Image and Signal Processing. Lecture Notes in Computer Science Volume 6134. Berlin, Heidelberg: Springer, 2010: 103-112.
[2] YU Xianchuan, LÜ Zhonghua, HU Dan. Review of Remote Sensing Image Registration Techniques[J]. Optics and Precision Engineering, 2013, 21(11): 2960-2972. (余先川, 吕中华, 胡丹. 遥感图像配准技术综述[J]. 光学精密工程, 2013, 21(11): 2960-2972.)
[3] FÖRSTNER W, GVLCH E. A Fast Operator for Detection and Precise Location of Distinct Points, Corners and Centres of Circular Features[C]//ISPRS Intercommission Workshop. Interlaken:[s.n.], 1987.
[4] HARRIS C, STEPHENS M. A Combined Corner and Edge Detection[C]//Proceedings of the Fourth Alvey Vision Conference. Manchester:[s.n.], 1988: 147-151.
[5] ZHANG Qian, LIU Zhengkai, PANG Yanwei, et al. Automatic Registration of Aerophotos Based on SUSAN Operator[J]. Acta Geodaetica et Cartographica Sinica, 2003, 32(3): 245-250. (张迁, 刘政凯, 庞彦伟, 等. 基于SUSAN算法的航空影像的自动配准[J]. 测绘学报, 2003, 32(3): 245-250.)
[6] LOWE D G. Distinctive Image Features from Scale-invariant Keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.
[7] LUO Nan, SUN Quansen, GENG Leilei, 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. (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.)
[8] VON GIOI R G, JAKUBOWICZ J, MOREL J M, et al. LSD: a Line Segment Detector[J/OL]. Image Processing on Line, 2012, http://www.ipol.im/pub/art/2012/gjmr-lsd/.
[9] MEER P, GEORGESCU B. Edge Detection with Embedded Confidence[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(12): 1351-1365.
[10] ZHANG Kaihua, ZHOU Wengang, ZHANG Zhen,et al. Improved C-V Active Contour Model[J]. Opto-Electronic Engineering, 2008, 35(12): 112-116. (张开华, 周文罡, 张振, 等. 一种改进的C-V主动轮廓模型[J]. 光电工程, 2008, 35(12): 112-116.)
[11] BOUMAN C A, SHAPIRO M. A Multiscale Random Field Model for Bayesian Image Segmentation[J]. IEEE Transactions on Image Processing, 1994, 3(2): 162-177.
[12] MARTINEZ A, GARCIA-CONSUEGRA J, ABAD F.A Correlation-Symbolic Approach to Automatic Remotely Sensed Image Rectification[C]//IEEE 1999 International Geoscience and Remote Sensing Symposium. Hamburg: IEEE, 1999: 336-338.
[13] EMERY W J, BALDWIN D, MATTHEWS D. Maximum Cross Correlation Automatic Satellite Image Navigation and Attitude Corrections for Open-Ocean Image Navigation[J]. IEEE Transactions on Geoscience and Remote Sensing, 2003, 41(1): 33-42.
[14] CHEN H M, VARSHNEY P K, ARORA M K. Performance of Mutual Information Similarity Measure for Registration of Multitemporal Remote Sensing Images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2003, 41(11): 2445-2454.
[15] HEL-OR Y, HEL-OR H, DAVID E. Fast Template Matching in Non-Linear Tone-Mapped Images[C]//2011 IEEE International Conference on Computer Vision. Barcelona: IEEE, 2011: 1355-1362.
[16] YE Yuanxin. Multi-Source Remote Sensing Image Registration Based on Phase Congruency[D]. Wuhan: Wuhan University, 2013. (叶沅鑫. 基于相位一致性的异源遥感影像配准[D]. 武汉: 武汉大学, 2013.)
[17] RUDIN L I, OSHER S, FATEMI E. Nonlinear Total Variation Based Noise Removal Algorithms[J]. Physica D: Nonlinear Phenomena, 1992, 60(1-4): 259-268.
[18] CHUMCHOB N, CHEN K. Improved Variational Image Registration Model and a Fast Algorithm for Its Numerical Approximation[J]. Numerical Methods for Partial Differential Equations, 2012, 28(6): 1966-1995.
[19] WU C C. SiftGPU: A GPU Implementation of Scale Invariant Feature Transform (SIFT)[J/OL]. http://cs.unc.edu/~ccwu/siftgpu/, 2007.
[20] WANG H X, JIANG W S, LEI C Q, et al. A Robust Image Fusion Method Based on Local Spectral and Spatial Correlation[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 11(2): 454-458.
[21] ZHOU J, CIVCO D L, SILANDER J A. A Wavelet Transform Method to Merge Landsat TM and SPOT Panchromatic Data[J]. International Journal of Remote Sensing, 1998, 19(4): 743-757.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献