期刊文献+

基于变分原理的亚像素级立体匹配方法 被引量:2

Sub-pixel stereo matching method based on variational principle
下载PDF
导出
摘要 针对小基高比立体匹配当中的亚像素级视差精度和匹配效率较低问题,提出一种基于变分原理的亚像素级立体匹配方法。该方法以规范互相关函数作为能量函数的数据项,并将图像驱动的平滑项和视差驱动的平滑项相结合作为能量函数的平滑项,然后通过变分原理获得能量函数的欧拉方程,最后通过连续过松弛法进行迭代求解获得亚像素级视差。实验结果表明,提出的亚像素级匹配方法不但可以获得较高精度的亚像素级视差,得到更为精确的高程信息,而且还具有较快的匹配速度。 This paper presented a sub-pixe| stereo matching method based on variational principle to improve the accuracy of sub-pixel disparity and the matching efficiency in small baseline stereo matching. First of all, it used the cross-correlation function as the data term of energy function and used the combination of image-driven smoothness term and disparity-driven smoothness term as the smoothness term of energy function. Then, it derived the Euler equation of energy function according to variational principle. Finally, it solved the Euler equation of the energy function to obtain sub-pixel disparities with successive over-relaxation iteration method. The experimental results show that the proposed method not only obtains highly accurate sub- Dixel disparities and DEM, but also has a faster matching speed.
出处 《计算机应用研究》 CSCD 北大核心 2014年第9期2846-2849,共4页 Application Research of Computers
基金 中央高校基本科研业务费专项资金资助项目(DL13BBX02) 国家自然科学基金资助项目(71001023) 林业行业公益性专项资金资助项目(201104037) 牡丹江师范学院基金资助项目(QZ2012)
关键词 小基高比 立体匹配 亚像素匹配 变分原理 small baseline stereo matching sub-pixel matching variational principle
  • 相关文献

参考文献3

二级参考文献30

  • 1TISSAtNAYAGAM P,SUTER D. Assessing the performance of corner detectors for point feature tracking applications [ J ]. Image and Vision Computing,2004,22(8) :663-679.
  • 2GONZALEZ R, WOODS R. Digital image processing [ M ]. 2nd ed. Englewood Cliffs, NJ : Prentice Hall, 2002.
  • 3PHAM D L, XU Chan-yang, PRINCE J L. A survey of current methods in medical image segmentation [ J]. Annual Review Biomedical En- gineeing ,2000,2(8 ) :315-337.
  • 4HAN J H, PARK J S. Contour matching using epipolar geometry [ J ]. IEEE Trans on Analysis and Machine Intelligence,2000,22 (4) : 358-3?0.
  • 5ZHANG Zheng-you, DERICHE R, FAUGERAS O, et al. A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry [ J]. Artificial Intelligence, 1995, 78:87-119.
  • 6XU Gang, TERAI J, SHUM H Y. A linear algorithm for camera self- calibration, motion and structure recovery for multi-planar scenes from two perspective Images [ C]//Proc of Computer Vision and Pattern Recognition. South Carolina: [ s. n. ] ,2000:474-479.
  • 7LU Yu-zhu, SMITH S. A comprehensive tool for recovering 3D models from 2D photos with wide baselines[ J]. Journal of Computing and Information Science in Enginoering,2006,6:372-380.
  • 8JULIE D,BERNARD R.Small Baseline Stereovision[J].Journal of Mathematical Imaging and Vision,2007,28(3):209-223.
  • 9SABATER N,BLANCHET G,MOISAN L,et al.Review ofLow-Baseline Stereo Algorithms and Benchmarks[J].IJCV,2004,60(2):91-110.
  • 10SABATER N,MOREL J M,ALMANSA A H.Sub-Pixel StereoMatching[J].Computer Vision,Graphics and Image Process-ing,1986,35(2):220-233.

共引文献30

同被引文献17

引证文献2

二级引证文献1

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