期刊文献+

一种高精度的TV-L^1光流算法 被引量:8

An Efficient TV-L^1 Optical Flow Method
原文传递
导出
摘要 介绍了一种求解光流方程的新型数值方法。针对变分光流法无法有效检测由于间断、遮挡等造成的错误光流分量的缺陷,引入了光流有效性检测技术,同时提出了邻域修正法来修正错误分量。并采用结构纹理分解、加权中值滤波、金字塔等高效的光流技术,进一步增强了光流算法的精确性与实用性。 A new type of numerical method to solve variational optical flow equations is illus- trated. Introduce an efficient flow vector availability strategy to detect the wrong compo- nents which are caused by discontinuities, occlusions, etc, and then, a neighboring correc tion approach is proposed the correct them. Some advanced techniques are employed into the compute procedure, which further strengthen the accuracy and applicability of the variational optical flow algorithms.
出处 《武汉大学学报(信息科学版)》 EI CSCD 北大核心 2012年第4期496-499,共4页 Geomatics and Information Science of Wuhan University
基金 湖北省自然科学基金重点资助项目(2009CDA141 2011CDB452) 国家科技支撑计划资助项目(2011BAK08B02) 中央高校基本科研业务费专项资金资助项目(111078) 国家自然科学基金资助项目(61070079)
关键词 变分光流法 间断 光流有效性检测技术 variational optical flow melhod discontinuity flow vector availabilily strategy
  • 相关文献

参考文献2

二级参考文献12

共引文献35

同被引文献117

  • 1邓非,张祖勋,张剑清.基于序列影像的城市三维建模[J].计算机工程,2007,33(8):208-209. 被引量:12
  • 2Horn B K,Schunck B G.Determining optical flow[J].Artificial Intelligence,1981,17:185-203.
  • 3Lauze F,Kornprobst P,Mémin (E).A course to fine multiscale approach for linear least squares optical flow estimation[C]//Proceedings of the Annual British Machine Vision Conference.London:Kingston University,2004:1-10.
  • 4Kim Y H,Martínez A M,Kak A C.Robust motion estimation under varying illumination[J].Image and Vision Computing,2005,23(4):365-375.
  • 5Bruhn A,Weickert J,Schn(o)rr C.Lucas/Kanade meets Horn/Schunck:combining local and global optic flow methods[J].International Journal of Computer Vision,2005,61 (3):211-231.
  • 6Li Y,Osher S.A new median formula with applications to PDE based denoising[J].Communications in Mathematical Sciences,2009,7(3):741-753.
  • 7Aujol J F,Gilboa G,Chan T,et al.Structure-texture image decomposition-modeling,algorithms,and parameter selection[J].International Journal of Computer Vision,2006,67 (1):111-136.
  • 8Lucas B D,Kanade T.An iterative image registration technique with an application to stereo vision[C]//Proceedings of the International Joint Conference on Artificial Intelligence.Vancouver,San Francisico,CA,USA:Morgan kaufman Publishers Inc.,1981,81:674-679.
  • 9Wedel A,Pock T,Zach C,et al.Animproved algorithm for TV-L1 optical flow[M]//Statistical and Geometrical Approaches to Visual Motion Analysis.Berlin Heidelberg:Springer 2009:23-45.
  • 10Black M J,Anandan P.The robust estimation of multiple motions:parametric and piecewise-smooth flow fields[J].Computer vision and image understanding,1996,63(1):75-104.

引证文献8

二级引证文献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