一种具有仿射不变性的倾斜影像快速匹配方法

肖雄武; 郭丙轩; 李德仁; 赵霞; 江万寿; 胡翰; 张春森

doi:10.11947/j.AGCS.2015.20140048

测绘学报 >

2015 , Vol. 44 >Issue 4: 414 - 421

DOI: https://doi.org/10.11947/j.AGCS.2015.20140048

摄影测量学与遥感

一种具有仿射不变性的倾斜影像快速匹配方法

肖雄武 ,
郭丙轩 ,
李德仁 ,
赵霞 ,
江万寿 ,
胡翰 ,
张春森

展开

1. 武汉大学测绘遥感信息工程国家重点实验室, 湖北武汉 430079;
2. 西安科技大学测绘科学与技术学院, 陕西西安 710054

肖雄武(1988—),男,博士生,研究方向为倾斜影像匹配、空三和三维重建.E-mail:xiao_xiongwu@sina.com

收稿日期: 2014-01-21

修回日期: 2014-12-11

网络出版日期: 2015-04-27

基金资助

国家973计划(2012CB719905);国家自然科学基金(61172174);测绘遥感信息工程国家重点实验室开放基金((13)重点项目)

收起

A Quick and Affine Invariance Matching Method for Oblique Images

XIAO Xiongwu ,
GUO Bingxuan ,
LI Deren ,
ZHAO Xia ,
JIANG Wanshou ,
HU Han ,
ZHANG Chunsen

Expand

1. State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China;
2. College of Geomatics, Xi'an University of Science and Technology, Xi'an 710054, China

Received date: 2014-01-21

Revised date: 2014-12-11

Online published: 2015-04-27

Supported by

The National Basic Research Program of China(973 Program)(No. 2012CB719905);The National Natural Science Foundation of China (No. 61172174);The Open Foundation of State Key Laboratory of Information Engineering in Surveying,mapping and Remote Sensing(No.(13) Key Project)

Fold

摘要

提出了一种较为快速且具有仿射不变性的倾斜影像匹配方法.通过估算影像的相机轴定向参数计算出初始仿射矩阵,通过逆仿射变换得到纠正影像,对纠正影像进行SIFT匹配.首先利用比值提纯法(NNDR)、归一化互相关(NCC)测度约束和左右一致性检验得到粗匹配点对,由粗匹配点对利用RANSAC方法计算出基本矩阵F和单应矩阵H.匹配时,匹配策略采用最邻近匹配,并利用极线约束、单应矩阵约束、NCC测度约束和主方向差值一致性约束剔除误匹配.通过对三组典型的倾斜影像数据进行试验,试验表明该方法匹配准确率高,匹配点对较为密集、均匀,且效率较高.

关键词： 倾斜影像匹配; 仿射不变特征(AIF); ASIFT; 逆仿射变换; 匹配约束

本文引用格式

肖雄武 , 郭丙轩 , 李德仁 , 赵霞 , 江万寿 , 胡翰 , 张春森 . 一种具有仿射不变性的倾斜影像快速匹配方法[J]. 测绘学报, 2015 , 44(4) : 414 -421 . DOI: 10.11947/j.AGCS.2015.20140048

Abstract

This paper proposed a quick, affine invariance matching method for oblique images. It calculated the initial affine matrix by making full use of the two estimated camera axis orientation parameters of an oblique image, then recovered the oblique image to a rectified image by doing the inverse affine transform, and left over by the SIFT method. We used the nearest neighbor distance ratio(NNDR), normalized cross correlation(NCC) measure constraints and consistency check to get the coarse matches, then used RANSAC method to calculate the fundamental matrix and the homography matrix. And we got the matches that they were interior points when calculating the homography matrix, then calculated the average value of the matches' principal direction differences. During the matching process, we got the initial matching features by the nearest neighbor(NN) matching strategy, then used the epipolar constrains, homography constrains, NCC measure constrains and consistency check of the initial matches' principal direction differences with the calculated average value of the interior matches' principal direction differences to eliminate false matches. Experiments conducted on three pairs of typical oblique images demonstrate that our method takes about the same time as SIFT to match a pair of oblique images with a plenty of corresponding points distributed evenly and an extremely low mismatching rate.

Key words： oblique images matching; affine invariant feature(AIF); ASIFT; inverse affine transform; matching constrains

参考文献

[1] MATAS J, CHUM O, URBAN M, et al. Robust Wide-baseline Stereo from Maximally Stable Extremal Regions[J]. Image and Vision Computing, 2004, 22(10): 761-767.
[2] MIKOLAJCZYK K, SCHMID C. An Affine Invariant Interest Point Detector[C]//Proceedings of the 7th European Conference on Computer Vision (ECCV). Copenhagen: Springer, 2002: 128-142.
[3] MIKOLAJCZYK K, SCHMID C. Scale & Affine Invariant Interest Point Detectors[J]. International Journal of Computer Vision, 2004, 60(1): 63-86.
[4] MIKOLAJCZYK K, TUYTELAARS T, SCHMID C, et al. A Comparison of Affine Region Detectors[J]. International Journal of Computer Vision, 2005, 65(1-2): 43-72.
[5] MOREL J M, YU G S. ASIFT: A New Framework for Fully Affine Invariant Image Comparison[J]. SIAM Journal on Imaging Sciences, 2009, 2(2): 438-469.
[6] LOWE D G. Distinctive Image Features from Scale-invariant Key Points[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.
[7] RICHARD H, ANDREW Z. Multiple View Geometry in Computer Vision[M]. 2nd ed. United Kingdom: Cambridge University Press, 2003: 117-123.
[8] YANG H C, ZHANG S B, WANG Y B. Robust and Precise Registration of Oblique Images Based on Scale-invariant Feature Transformation Algorithm[J]. IEEE Geoscience and Remote Sensing Letters, 2012, 9(4): 783-787.
[9] WANG C Y, ZHANG Y, WU Y, et al. Highly Accurate Geometric Correction for Serious Oblique Aero Remote Sensing Image Based on the Piecewise Polynomial Model[J]. Journal of Computational Information Systems, 2011, 7(2): 342-349.
[10] YU Y N, HUANG K Q, CHEN W, et al. A Novel Algorithm for View and Illumination Invariant Image Matching[J]. IEEE Transaction on Image Processing, 2012, 21(1): 229-240.
[11] YU G, MOREL J M. ASIFT: An Algorithm for Fully Affine Invariant Comparison[J/OL]. Image Processing On Line, 2011. [2013-11-29]. http://dx.doi.org/10.5201/ipol.2011.my-asift.
[12] YU G, MOREL J M. A Fully Affine Invariant Image Comparison Method[C]//Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing. Taipei: IEEE, 2009: 1597-1600.
[13] OJI R. An Automatic Algorithm for Object Recognition and Detection Based on ASIFT Key Points[J]. Signal & Image Processing: An International Journal, 2012, 3(5): 29-39.
[14] ISHII J, SAKAI S, ITO K, et al. Wide-baseline Stereo Matching Using ASIFT and POC[C]//Proceedings of 19th IEEE 2012 International Conference on Image Processing. Orlando, Florida: IEEE, 2012: 2977-2980.
[15] ANCUKIEWICZ D, SIDERIS K, RICKETT A. 3D Reconstruction from RGB and Depth Video[EB/OL]. [2014-01-10]. http://cs.ucla.edu/~costas/kinect_reconstruction.html.
[16] OHTA M, IWAMOTO K, SATO Y, et al. Perspective Robust Object Identification Using Depth and Color Image Sensor for Real-world Annotation[C/OL]//The 5th International Conference on 3D Systems and Applications, 2013. http://www.3dsa.kr/3DSA2013/contents/program.html.
[17] ZHANG Li, GRUEN A. Multi-image Matching for DSM Generation from IKONOS Imagery[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2006, 60(3): 195-211.
[18] ZHANG Li, ZHANG Jixian. Multi-image Matching for DEM Generation from Satellite Imagery[J]. Science of Surveying and Mapping, 2008, 33(Suppl): 35-39. (张力, 张继贤. 基于多基线影像匹配的高分辨率遥感影像DEM自动生成[J]. 测绘科学, 2008, 33(专刊): 35-39.)
[19] BON A D. Initial Approximations for the Three-dimensional Conformal Coordinate Transform[J]. Photogrammetric Engineering & Remote Sensing, 1996, 62(1): 79-83.
[20] KLIPPENSTEIN J, ZHANG H. Quantitative Evaluation of Feature Extractors for Visual SLAM[C]//Proceedings of the 4th Canadian Conference on Computer and Robot Vision. Quebec: IEEE, 2007: 157-164.
[21] LEŠKOVSKÝ P, ALEKSEYCHUK A, STANSKI A, et al. Point-based Registration of High-resolution Histological Slices for Navigation Purposes in Virtual Microscopy[J]. Annals of the BMVA, 2012, 2012(10): 1-18.
[22] MIKOLAJCZYK K, SCHMID C. A Performance Evaluation of Local Descriptors[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1615-1630.
[23] LEI Lin, CHEN Tao, LI Zhiyong, et al. A New Approach to Image Invariant Extraction under Global Affine Transformation[J]. Journal of National University of Defense Technology, 2008, 30(4): 64-70. (雷琳, 陈涛, 李智勇, 等. 全局仿射变换条件下图像不变量提取新方法[J]. 国防科技大学学报, 2008, 30(4): 64-70.)
[24] YAO Guobiao, DENG Kazhong, ZHANG Li, et al. An Automated Registration Method with High Accuracy for Oblique Stereo Images Based on Complementary Affine Invariant Features[J]. Acta Geodaetica et Cartographica Sinica, 2013, 42(6): 869-876, 883. (姚国标, 邓喀中, 张力, 等. 融合互补仿射不变特征的倾斜立体影像高精度自动配准方法[J]. 测绘学报, 2013, 42(6): 869-876, 883.)

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献