梯度矢量流Snake模型临界点剖析
作者:
基金项目:

Supported by the National Natural Science Foundation of China under Grant No.60543007 (国家自然科学基金)


Analysis of the Critical Point of the Gradient Vector Flow Snake Model
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [17]
  • |
  • 相似文献 [20]
  • |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    作为经典Snake模型的一个变体,梯度矢量流(gradient vector flow,简称GVF)Snake在扩大Snake轮廓的捕捉范围和深度凹陷区域的收敛上具有卓越的性能.但GVF Snake在初始化时存在一个临界点问题:在目标内部的临界点必须在初始Snake轮廓的内部;在目标外部的临界点必须在Snake轮廓的外部.否则,Snake轮廓将不能收敛到正确的结果.对GVF Snake的临界点问题进行探讨,详细分析了临界点的影响因素,指出GVF场只有在合适的条件下才是有效的;证明了相关文献中从粘性流体力学

    Abstract:

    Gradient vector flow (GVF) snake shows high performance at capture-range enlarging and boundary concavity convergence, however, the initial contours encounter a so-called critical point problem (CPP). The initial contour must contain the critical points inside the object and exclude those outside the object, otherwise, the final result would be far from the expected. This paper investigates the CPP of the GVF snake and points out that, serving as an external force field for snake models, gradient vector flow could be effective only under some restrictions. Also, it is proved that the theoretical foundation, the Navier-Stokes equation for viscous fluid flow, for the solution to this CPP in literatures is incorrect. Finally, an empirical solution to the CPP is presented and its performance is validated by experiments.

    参考文献
    [1]Kass M,Witkin A,Terzopoulos D.Snake:Active contour models.Int'l J.Computer Vision,1988,1(4):321-331.
    [2]Siddiqui K,Lauriere YB,Tannenbaum A,Zucker,SW.Area and length minimizing flows for shape segmentation.IEEE Trans.on Image Processing,1998,7(3):433-443.
    [3]Wang YQ,Tang M,Heng PA,Xia DS,Wang PA.A new two-step-deformation snake with application to LV epicardium segmentation of cardiac MR images.Pattern Recognition and Artificial Intelligence,2004,17(1):46-51 (in Chinese with English abstract).
    [4]Li J,Zhou JL,Yu SS,Chen JZ,He XC.Sequential image segmentation using block-motion weighted snakes model.Journal of Computer Research and Development,2003,40(2):277-282 (in Chinese with English abstract).
    [5]Park HW,Schoepflin T,Kim Y.Active contour model with gradient directional information:Directional snake.IEEE Trans.on Circuits and Systems for Video Technology,2001,11(2):252-256.
    [6]Xu C,Prince JL.Snakes,shapes and gradient vector flow.IEEE Trans.on Image Processing,1998,7(3):359-369.
    [7]Xu C,Prince JL.Generalized gradient vector flow external forces for active contours.Signal Processing,1998,71(2):131-139.
    [8]Zhou SJ,Liang B,Chen WF.A new approach to the motion estimation of cardiac image sequences:Active contours motion tracking based on the generalized fuzzy gradient vector glow.Chinese Journal of Computers,2003,26(11):1470-1478 (in Chinese with English abstract).
    [9]Tang JH,Acton ST.Vessel boundary tracking for intravital microscopy via multiscale gradient vector flow snakes.IEEE Trans.on Biomedical Engineering,2004,51(2):316-324.
    [10]Paragios N,Mellina-Gottardo O,Ramesh V.Gradient vector flow fast geometric active contours.IEEE Trans.on PAMI,2004,26(3):402-407.
    [11]Ray N,Acton ST,Altes T,de Lange EE,Brookeman JR.Merging parametric active contours within homogeneous image regions for MRI-based lung segmentation.IEEE Trans.on Medical Imaging,2003,22(2):189-199.
    [12]Wang YQ.Numerical simulation of fluid flow using adaptive triangular mesh[MS.Thesis].Nanjing:Nanjing University of Science and Technology,1998 (in Chinese with English abstract).
    [13]White FM.Fluid Mechanics.5th ed.Beijing:Tsinghua University Press,2004.
    [3]王元全,王平安,夏德深,王平安.基于预测-校正改进Snake的心脏MR图像左心室外轮廓分割.模式识别与人工智能,2004,17(1):46-51.
    [4]李军,周敬利,余胜生,陈加忠,何小诚.基于块运动矢量加权的Snakes模型及在序列图像分割中的应用.计算机研究与发展,2003,40(2):277-282.
    [8]周寿军,梁斌,陈武凡.心脏序列图像运动估计新方法:基于广义模糊梯度矢量流的形变曲线运动估计与跟踪.计算机学报,2003,26(11):1470-1478.
    [12]王元全.应用三角形自适应网格的流场数值模拟[硕士学位论文].南京:南京理工大学,1998.
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

王元全,贾云得.梯度矢量流Snake模型临界点剖析.软件学报,2006,17(9):1915-1921

复制
分享
文章指标
  • 点击次数:4666
  • 下载次数: 6272
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2005-03-07
  • 最后修改日期:2005-08-25
文章二维码
您是第19754468位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京市海淀区中关村南四街4号,邮政编码:100190
电话:010-62562563 传真:010-62562533 Email:jos@iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号