期刊文献+

单应约束与核线约束对于影像匹配精度的对比

Comparison of Homography Constraint with Epipolar Geometry Constraint on Image Matching Accuracy
下载PDF
导出
摘要 数字影像匹配是摄影测量作业的关键环节,其精度影响后续前方交会、生成DSM的质量。单应约束和核线约束作为两种基于先验同名点的约束准则,在提高匹配精度的同时也能提高匹配效率。本文首先对重叠的、有严重几何变形的两张影像进行特征匹配,得到可靠的高精度同名点;然后进行单应约束与核线约束实验,对比两种约束方法的精度。结果表明,在同等条件下,核线矩阵约束比单应矩阵约束精度高;同时,本文也为匹配约束中像素偏移阈值的选择提供了参考依据。 Digital image matching is critical in photogrammetry, whose accuracy directly influences the process of forward intersection and quality of DSM. As for homography constraint and epipolar line constraint are the constraint criteria based on the known matching pairs, they can improve matching accuracy as well as efficiency. First, this paper obtains reliable and precise matching pairs by establishing the feature matching on the two overlapping images with serious geometric distortion. Then it conducts homography constraint and epipolar line constraint experiments to compare the accuracy of the two constraints. The results show that epipolar geometry constraint can achieve higher accuracy compared with homography constraint under the equivalent conditions. Besides this paper also provides references for choose of pixel offset threshold in the image matching constraints.
出处 《测绘科学与工程》 2015年第2期42-45,62,共5页 Geomatics Science and Engineering
关键词 单应约束 核线约束 单应矩阵 基础矩阵 影像匹配 homography constraint epipolar line constraint homography fundamental matrix image matching
  • 相关文献

参考文献7

  • 1R. Hartley, A. Zisserman. Multiple view geometry in computer vision [ M ]. Cambridge University Press, 2003.
  • 2G.Bradski,A.Kaehler.学习OpenCV(中文版)[M].北京:清华大学出版社,2009.
  • 3杨化超,张磊,姚国标,王永波.局部单应约束的高精度图像自动配准方法[J].测绘学报,2012,41(3):401-408. 被引量:19
  • 4M. Fisehler, R. Bolles. Random sample consensus: aparadigm for model fitting with applications to image anal- ysis and automated cartography [ J ]. Communications of the ACM, 1981,24(6) : 381 -395.
  • 5牛津大学计算机视觉实验室:Graffiti模拟影像序列[EB/OL].[2014-11-26].http://www.robots.OX.ac.uk/一vgg/data/data-aff.html.
  • 6上海航遥信息技术有限公司.AMC580[EB/OL] .(2013-09-05)[2013-09-26] .http:∥www.shhangyao.com/company/a1.
  • 7H. Bay,T. Tuyte|aars, L. V. Gool. SURF: Speeded up robust features [ C ]. European Conference on Computer Vision, 2006.

二级参考文献19

  • 1韦燕凤,赵忠明,闫冬梅,曾庆业.基于特征的遥感图像自动配准算法[J].电子学报,2005,33(1):161-165. 被引量:27
  • 2李晓明,郑链,胡占义.基于SIFT特征的遥感影像自动配准[J].遥感学报,2006,10(6):885-892. 被引量:154
  • 3BROWN L. A Survey of Image Registration Techniques [J]. ACM Computing Surveys, 1992, 24(4): 325-376.
  • 4ZITOVA B, FLUSSER J. Image Registration Methods: a Survey[J]. Image and Vision Computing, 2003, 21 ( 11 ), 977-1000.
  • 5HONG G, ZHANG Y. Wavelet-based Image Registration Technique {or High resolution Remote Sensing Images[J]. Computer & Geosciences, 2008, 34: 1708-1720.
  • 6YU L, ZHANG D R, HOLDEN E J. A Fast and Fully Automatic Registration Approach Based on Point Features for Multi-source Remote-sensing Images[J]. Computer Geosciences, 2008, 34: 838-848.
  • 7KIM Y S, LEE J H, RA J B. Multi-sensor Image Registration Based on Intensity and Edge Orientation Information[J].Pattern Recognition, 2008, 41: 3356-3365.
  • 8LI H, MANJUNATH B S, MITRA S K. A Contour- based Approach to Multisensor Image Registration [J]. IEEE Transactions on Image Processing, 1995, 4 (3): 320- 334.
  • 9LOWE D. Distinctive Image Features from Scale invariant Keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.
  • 10MIKOLAJCZYK K, TUYTELAARS T, SCHMID C. A Comparison of Affine Region Detectors[J]. International Journal of Computer Vision, 2005, 65 (1) : 43-72.

共引文献19

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部