基于语义分析的三维服装曲面生成算法  

Surface generation algorithm of 3-D garment based on semantic analysis

作　　者：杨晓波 YANG Xiaobo(Zhejiang Shuren University,Hangzhou,Zhejiang 310015,China)

机构地区：[1]浙江树人大学,浙江杭州310015

出　　处：《纺织学报》2018年第11期163-167,共5页Journal of Textile Research

基　　金：浙江省自然科学基金资助项目(Y1110023)

摘　　要：为进一步提高三维服装设计效率,提出了一种基于语义分析的三维服装曲面生成算法。首先分析了基于网格模式的几何交互语义,通过服装曲面网格化处理,将草图勾绘映射到三角网格上,确定草绘点与网格点之间的对应关系;然后通过几何语义交互模式建立起草绘图与网格图的映射关系,利用逼近拟合算法完成对草绘线的拟合,并通过光滑、去噪、网格拼接等方法形成完整的三维服装曲面;最后选取几何模型法、约束模型法与语义分析法进行对比实验,将3种算法各自完成100步拟合后分别计算其拟合准确度。结果表明,本文所提算法的运行效率比其他主流算法高出近45%,拟合准确度高出近15%。In order to further improve the efficiency of 3-D garment design,a 3-D garment surface generation algorithm based on semantic analysis was proposed.Firstly,the geometric interaction semantics based on grid mode was analyzed,then the 3-D garment surface generation algorithm and semantic analysis model was studied,and finally the feasibility of the proposed algorithm was verified by comparative experiments.The results indicate that the geometric semantic interaction models can be established to draft drawing and mapping grid map using the approximation fitting algorithm to fit the complete sketch line,and through smoothing,denoising,mesh stitching method to form 3-D garment surface integrity.In addition to the selected geometric model method,constraint model method and semantic analysis method comparative experiments,experimental results show that the proposed algorithm efficiency is nearly 45%higher than other mainstream algorithms,and the fitting accuracy is higher by nearly 15%,more suitable for the reconstruction of 3-D garment surface,which verifies the feasibility of the proposed algorithm.

关 键 词：服装设计 语义分析模型 服装曲面 网格化拟合 重建算法 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]