摘要： 在分析现有重构方法局限性的基础上,提出了一种基于神经网络的点云数据重构三维网格形状的新算法。首先对点云数据平滑处理;然后进行特征线提取,并以特征线为基础对曲面进行分割。该方法能直接从神经网络的权值矩阵得到曲线的控制顶点/曲面的控制网格,通过神经网络的权值约束实现曲线段/曲面片之间的光滑拼接。能显著提高逼近网格的品质,从而实现了点云数据的精确曲面重构,实际的算例结果表明该方法实用可靠。

关键词: 神经网络, 反向工程, 曲面建模, 点云

Abstract: This paper presents a new approach to three mesh surface reconstruction using Radical basis function neural networks(RBFNN).It includes three steps: First,the cloud data are preprocessed for smoothing;second,feature lines are extracted and the cloud data are segmented;At last,NURBS surface patches are created over rectangular mesh and trimmed to form an entire surface using RBFNN.A specific application of this technique to the geometric mesh reconstruction is then outlined,which aims on boundary reconstructing surface model with inherent continuity.Thus the precise reconstruction of data cloud is realized.The experiment result testifies that the approach is feasible.

中图分类号: 

• TP391.72