Snakes, shapes, and gradient vector flow
Snakes, shapes, and gradient vector flow
复制标题
DOI：
10.1109/83.661186
复制
发表时间：
1998-03-01
影响因子：
10.6
通讯作者：
Prince, JL
中科院分区：
文献类型：
--
作者：
Xu, CY;Prince, JL
Snake（主动轮廓线）在计算机视觉和图像处理中有着广泛的应用，尤其是在目标边界的定位方面，但由于初始化和收敛性差等问题，限制了其应用.本文提出了一种新的主动轮廓外力，在很大程度上解决了这两个问题.这个外部的优势，我们称之为梯度矢量流（GVF），是作为一个扩散的梯度矢量的灰度或二进制边缘图来自图像。它从根本上不同于传统的蛇外力，因为它不能写为负梯度的势函数，相应的蛇是直接从力平衡条件，而不是变分制定制定。使用几个二维（2-D）的例子和一个三维（3-D）的例子，我们表明，GVF有一个大的捕获范围，并能够移动到边界凹蛇。
Snakes, or active contours, are used extensively in computer vision and image processing applications, particularly to locate object boundaries, problems associated with initialization and poor convergence to boundary concavities, however, have limited their utility, This paper presents a new external force for active contours, largely solving both problems. This external forte, which we call gradient vector flow (GVF), is computed as a diffusion of the gradient vectors of a gray-level or binary edge map derived from the image. It differs fundamentally from traditional snake external forces in that it cannot be written as the negative gradient of a potential function, and the corresponding snake is formulated directly from a force balance condition rather than a variational formulation. Using several two-dimensional (2-D) examples and one three-dimensional (3-D) example, we show that GVF has a large capture range and is able to move snakes into boundary concavities.