基于图像分割的三维重构  

3D Reconstruction Based on Image Segmentation

作　　者：强伟哲[1,2] 宋广华[1,2] 郑耀[1,2] 

机构地区：[1]浙江大学工程与科学计算研究中心,杭州310027 [2]浙江大学计算机科学与技术学院,杭州310027

出　　处：《计算机工程与应用》2005年第36期76-78,82,共4页Computer Engineering and Applications

摘　　要：三维重构方法是医学图像可视化系统、治疗计划系统的重要技术。基于图像分割的三维重构方法结合了图像分割、等值面抽取、网格简化三种技术,是不同于传统Marching Cubes算法的一种三维重构方法。它首先将医学图像分割为二值图,然后利用Marching Cubes方法进行等值面抽取,最后对得到的网格模型进行简化。实验结果表明,基于图像分割的三维重构方法加快了Marching Cubes的运算速度,改善了重构的效果,有利于实现对基于三维重构的大型几何模型的实时绘制和交互。3D reconstruction is important for medical image visualization and treatment plan system,This paper presents a method of 3D reconstruction based on image segmentation,which is different from traditional Marching Cubes algorithm.The method consists of image segmentation,isosurface extraction and mesh simplification.Firstly,the images are segmented to binary images,then the isosurface is extracted by means of Marching Cubes,lastly the mesh representation is simplified.Experimental results are given to show that the present method improves the performance of Marching Cubes,enhances the result of reconstruction and realizes the real-time rendering and interaction of large geometry models.

关 键 词：三维重构 图像分割 MARCHING CUBES 网格简化 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]