一种新颖的网格综合优化算法  

New Algorithm for Integrated Optimization of Mesh

作　　者：张佑生[1] 王世东[1] 偶春生[1] 谢颖[1] 

机构地区：[1]合肥工业大学计算机与信息学院,安徽合肥230009

出　　处：《系统仿真学报》2007年第3期502-504,共3页Journal of System Simulation

摘　　要：用三角网格逼近三维扫描所得散乱点集,实现曲面重构,是一种得到广泛应用的技术。为了提高网格对物体表面的逼近精度,需要对网格进行优化。提出一种新颖的网格综合优化算法,将基于SOM的网格优化模型和节点分裂算法有机结合,使网格中顶点的分布更符合散乱点数据的空间分布,使网格更好地逼近数据点集,还通过分裂大度数顶点来改善网格的拓扑关系,使其更好地反映原始数据点集的拓扑特征,也使得网格更加平滑。试验结果表明,该算法取得的网格优化效果良好。The method that adopts a triangle mesh to approach the set of scattered points from scanning an object has been widely applied. In order to improve the proximity of mesh to object surface, a process of mesh optimization was required. A new algorithm for integrated mesh optimization was proposed, which combines the SOM-based mesh optimization model and the method of vertexes splitting. By learning 3D scattered data points, the vertices gradually approach the target space and the distribution of vertices coincides the space distribution of scattered points. By splitting those vertices with very high valence, the topological relations of mesh were improved and the shape of the mesh becomes more smooth. Some experiment results show that the new algorithm is ouite effective.

关 键 词：神经网络 自组织特征映射 散乱点 网格优化 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]