Segmentation of a wrap-around model using an active contour
Segmentation of a wrap-around model using an active contour
复制标题
DOI：
10.1016/s0010-4485(96)00058-9
复制
发表时间：
1997-04-01
影响因子：
4.3
通讯作者：
Vickers, GW
中科院分区：
文献类型：
--
作者：
Milroy, MJ;Bradley, C;Vickers, GW
分割在过去已被应用到单一的范围地图，这是能够建模的对象，从相机的观点是可见的部分。在反求工程领域中，对完整环绕物体模型的分割有着很大的需求。本文提出了一种新的分割方法，用于分割由多幅范围图插值合并而成的环绕式线框模型。一个半自动的基于边缘的方法用于分割。在模型中的每个点估计表面微分特性，并将曲率极值确定为可能的边缘点。一个能量最小化的活动轮廓被交互地用来连接边缘点。设计者在要分割的区域内定义小的闭合轮廓，并且轮廓被“膨胀”直到被边缘点处的电势捕获。(C)1997 Elsevier Science Ltd.
Segmentation in the past has been applied to single range maps, which are capable of modelling only the part of an object that is visible from the camera viewpoint. In the field of reverse engineering, there is a great need for the segmentation of complete wrap-around object models. In this paper, a new method is presented for segmenting a wrap-around wireframe model, which is created by interpolating and merging multiple range maps. A semi-automatic edge-based approach is used for the segmentation. Surface differential properties are estimated at each point in the model, and curvature extrema are identified as possible edge points. An energy-minimizing active contour is used interactively to link the edge points. The designer defines small closed contours within the regions to be segmented, and the contour is 'inflated' until it is trapped by the potentials at the edge points. (C) 1997 Elsevier Science Ltd.