期刊文献+

立体图像对的极线校正 被引量:6

Epipolar line rectification for stereo pairs
下载PDF
导出
摘要 将Seitz方法和Francesco方法结合起来,给出了一种改进的极线校正方法。该方法利用改进的八点算法算出基本矩阵,根据基本矩阵采用Seitz方法计算投影变换矩阵,最后以算出的投影变换矩阵为初值采用Francesco方法对其进行最优化,从而有效地避免了最优化时陷入局部最优的可能,同时又不过分依赖基本矩阵的精度。通过对Francesco方法、Mallon方法和该方法进行对比实验,可以发现该方法具有更高的校正精度,图像的扭曲也比较小。 Combining Seitz method with Francesco method, a improved method to rectify epipolar lines for stereo pairs is introduced. In this method, the fundamental matrix is calculated using the improved eight-point algorithm and then as an input for Seitz method to get the projective transformation matrices. Finally, these matrices are used to initialize the Francesco method for optimization, avoiding in this way local minima as well as the dependence on the precision of the fundamental matrix. Experimental results show that the presented method works more accurately with low image distortion in contrast to Francesco method and Mallon method.
出处 《计算机工程与设计》 CSCD 北大核心 2009年第17期4027-4030,共4页 Computer Engineering and Design
基金 国家自然科学基金项目(60773082/F0205) 国家863高技术研究发展计划基金项目(2006AA10Z233) 重庆大学研究生科技创新基金项目(200701Y1A0080194)
关键词 极线几何 极线校正 立体图像对 图像校正 投影校正 epipolar geometry epipolar line rectification stereo pairs image rectification projective rectification
  • 相关文献

参考文献10

二级参考文献42

  • 1刘正东,杨静宇.自适应窗口的时间规整立体匹配算法[J].计算机辅助设计与图形学学报,2005,17(2):291-294. 被引量:12
  • 2刘庆华,唐伯良,董戎萍.双目立体匹配图像对的预处理研究[J].计算机工程与设计,2005,26(3):793-795. 被引量:7
  • 3Ayache N. Artificial Vision for Mobile Robots: Stereo Vision and Multisensory Perception. Cambridge: MIT Press, 1991.
  • 4Pollefeys M, Koch R, van Gool L. A simple and efficient rectification method for general motion. In: Werner B, ed. Proc. of the Int'l Conf. on Computer Vision. Los Alamitos: IEEE Press, 1999. 496-501.
  • 5Loop C, Zhang Z. Computing rectifying homographies for stereo vision. In: Baldwin T, Sipple RS, eds. Proc. of the Int'l Conf. on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Press, 1999. 125-131.
  • 6Hartley R. Theory and practice of projective rectification. Int'l Journal of Computer Vision, 1999,35(2):115-127.
  • 7Gluckman J, Nayar S. Rectifying transformations that minimize resampling effects. In: Jacobs A, Baldwin T, eds. Proc. of the Int'l Conf. on Computer Vision and Pattern Recognition, Vol I. Los Alamitos: IEEE Press, 2001. 111~117.
  • 8Hartley R, Zisserman A. Multiple View Geometry in Computer Vision. Cambridge: Cambridge University Press, 2000.
  • 9Fischler M, Bolles R. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Graphics and Image Processing, 1981,26(4):381-395.
  • 10Zhang H, Sara R. A linear method for trinocular rectification. Research Report, CTU-CMP-2002-09, Prague: Center for Machine Perception, Czech Technical University, 2002.

共引文献23

同被引文献44

引证文献6

二级引证文献10

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