期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

一种改进的从明暗恢复形状的方法 被引量：1

An Improved Algorithm on Shape from Shading
下载PDF
导出
摘要 从明暗恢复形状(SFS)是计算机视觉中三维形状恢复问题的关键技术之一,其任务是利用单幅灰度图像中明暗变化来恢复表面三维形状。快速步进法(FMM)作为求解Eikonal偏微分方程的有效手段,可以用于处理从明暗恢复形状问题。本文提出了一种基于改进的Godunov格式的多模板快速步进法(MSFMM)算法,解决了多源FMM的波动交汇问题,具备了处理多源SFS问题的能力。从实验结果可以看出,本文方法可以得到比MSFMM更高精度的结果,可以有效处理多源SFS。 Shape from shading （SFS） is one of the critical techniques on shape recovery in computer vision, which can obtain 3- D shape of the visible surface of an object from only one image of it using the shading knowledge in the given picture. Fast Marching Method （FMM） is an efficient method for Eikonal Equation and can be adopted in the SFS problem. In this paper, we propose a multi- stencil fast marching method based on the improved Godunov format. In this algorithm the improved Godunov format is used to solve the problem which happens when wave fronts converge. Experiments demonstrate that our algorithm can obtain more accuracy than MSFMM does and yield good performance for multi-source SFS problem.
作者 王学梅 孙即祥
机构地区 国防科技大学电子科学与工程学院
出处 《信号处理》 CSCD 北大核心 2009年第6期905-910,共6页 Journal of Signal Processing
关键词 明暗恢复形状 Eikonal方程 快速步进法 Godunov格式 多模板 多源 shape from shading Eikonal Equation fast marching method Godunov format multi-stencil multi-source
分类号 TP391.4 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献36

  • 1Brooks M J, Horn B K P. Shape and Source from Shading [ A ]. In Proc. Int'l Joint Conf. Artificial Intelligence [ C], Los Angeles,CA,USA, 1985:932-936.
  • 2Horn B K P, Brooks M J. The Variational Approach to Shape from Shading [ J ]. Computer Vision, Graphics, and Image Processing, 1986,33 (2) : 174-208.
  • 3Horn B K P, Brooks M J. Shape from Shading [ M], Cambridge, Mass. : MIT Press,1989.
  • 4Dijkstra E W. A Note on Two Problems in Connection with Graphs [ J ]. Numerische Mathematik, 1959, 1 ( 1 ) : 269- 271.
  • 5Sethian J A. A Fast Marching Level Set Method for Monotonically Advancing Fronts [ J ]. Proceedings of the National Academy of Sciences, 1996,93 (4) : 1591-1595.
  • 6Tsitsiklis J N. Efficient Algorithm for Globally Optimal Trajectories [ J ]. IEEE Transactions on Automatic Control. 1995,40(9) : 1528-1538.
  • 7Kimmel R, Sethian J A. Fast Marching Methods for Computing Distance Maps and Shortest Paths [ R ], Tech. Report 669, CPAM, University of California, Berkeley, 1996.
  • 8Stolarska M, et al.. Modelling Crack Growth by Level Sets in the Extended Finite Element Method [ J ], International Journal for Numerical Methods in Engineering, 2001,51 (8) :943-960.
  • 9Sukumar N, Chopp D L, Moran B. Extended Finite Element Method and Fast Marching Method for Three-Dimensional Fatigue Crack Propagation [ J]. Engineering Fracture Mechanics,2003,70( 1 ) :29-48.
  • 10Sethian J A, Popovici A M. 3-D Travehime Computation Using the Fast Marching Method [ J ] , Geophysics, 1999, 64:516-523.

二级参考文献6

  • 1Bertalmio M,Sapiro G,Caselles V,et al.Image Inpainting[C]//In Proceedings SIGGRAPH 2000,Compmer Graphics Proceedings,Annual Conference Series,edited by Kurt Akeley.Reading,MA:Addison-Wesley,2000:417-424.
  • 2Oliveira M,Bowen B,McKenna R,et al.Fast Digital Image Inpainting[C]//In Proc.VIIP 2001.Marbella,Spain:[s.n.],2001:261-266.
  • 3Chan T,Shen J.Mathematical Models for Local Non-Tex-ture Inpainting[J].SIAM J Appl Math,2001,62(3):1019-1043.
  • 4Chan T,Shen J.Non-Texture Inpainting by Curvature-Driven Diffusions (CDD)[R].CAM 00-35,Image Processing Research Group,UCLA,2000.
  • 5Sethian J A.A Fast Marching Level Set Method for Monotonically Advancing Fronts[J].Proc Nat Acad Sci,1996,93:1591-1595.
  • 6Telea A.An image inpainting technique based on the fast marching method[J].Journal of Graphics Tools,2004,9(1):23-34.

同被引文献30

  • 1Sharer S A. Using color to separate reflection components [ J ]. Color Research & Application, 1985,10(4) : 210-218.
  • 2Mallick S P, Zickler T, Kriegman D J, Belhumeur P N. Specularity Removal in Images and Videos: A PDE Ap- proach [ C ] // Proceeding ECCV' 06. Berlin, German : Springer, 2006,550 -563.
  • 3Tan R T, Ikeuchi K. Separating reflection components of textured surfaces using a single image[ J]. IEEE Trans- actions on Pattern Analysis and Machine Intelligence, 2005, 27(2) : 178-193.
  • 4Yang Q, Wang S, Ahuja N. Real-time Specular Highlight Removal Using Bilateral Filtering[ C]//Computer Vision- ECCV 2010. Berlin, German :Springer,2010:87-100.
  • 5Hyeongwoo K, Jin H, Hadap S, Kweon I. Specular Re- flection Separation Using Dark Channel Prior [ C ]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR2013). Piscataway, NJ: IEEE, 2013 : 1460-1467.
  • 6Zou B, Zhang X, Liao S, Wang L. Specularity removal using dark channel prior[ J]. Journal of Information Sci- ence and Technology, 2013, 29(5) : 835-849.
  • 7Shen H, Zheng Z. Real-time highlight removal using inten- sity ratio[J]. Applied Optics, 2013, 52(19) : 4483-4493.
  • 8He K, Sun J, Tang X. Guided image filtering [ C ] // Computer Vision-ECCV 2010. Berlin,German:Springer, 2010 : 1-14.
  • 9He K, Sun J, Tang X. Guided image filtering[J]. IEEE Transactions on Pattern Analysis and Machine Intelli- gence, 2013, 35(6): 1397-1409.
  • 10Comaniciu D, Meer P. Mean shift: A robust approach to- ward feature space analysis [ J ]. IEEE Transactions on Pat- tern Analysis and Machine Intelligence, 2002, 24 (5): 603-619.

引证文献1

二级引证文献2

信号处理
2009年 第6期

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