基于散乱数据表面法矢的二次曲面拟合  

Quadric Surface Direct Fitting Based on Normal Vectors of Random Data

作　　者：曲学军[1] 杨亚文[1] 韩志仁[1] 

机构地区：[1]沈阳航空工业学院航空宇航工程学院,辽宁沈阳110136

出　　处：《航空学报》2007年第4期1018-1024,共7页Acta Aeronautica et Astronautica Sinica

基　　金：航空科学基金(2006ZE154)

摘　　要：为了解决二次曲面拟合算法中因几何参数初值计算方法不精确而导致的求解效率低,甚至失败的问题,提出了基于表面法矢的二次曲面直接拟合算法。采用不同的模型对该方法与已有二次曲面拟合技术进行了性能对比测试与分析。在此基础上建立了二次曲面提取的方案,给出了散乱数据二次曲面提取的实例。实验与理论分析表明,文中方法可以精确求解二次曲面的几何参数的初值,从而提高了曲面拟合算法的性能,为逆向工程中的数据分割与特征提取提供了新的技术手段。A new method named quadric surface direct fitting based on normal vectors of measured data is proposed to overcome the current quadric surface fitting method＇s shortcomings. In the current method, the calculations of the initial geometric parameters are imprecise, and the using of it in surface fitting can cause poor efficiency and stability. Then, the performance contrasts of this method with existing methods are presented based on various test models. Finally, the strategy of quadric surface extraction is established based on the proposed surface fitting method, and the extraction of quadric surface from random data is also provided. Both the experiment data and theoretic analysis prove that the proposed method can give initial geometric parameters precisely, thus enhance the capability of surface fitting method and provide new technique of feature extraction and data segmentation in reverse engineering.

关 键 词：计算几何 二次曲面 逆向工程 曲面拟合 特征提取 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]