Abstract：In industrial measurement fitting applications, because of the measuring characteristics of instruments, error components of measurement data in different directions are difference, aiming at this problem a fitting algorithm for space line and plane base on error decomposition weighting has been proposed.Spatial attitude of workpiece and relationship between instrument and measuring points are considered.Then, influence quantity of vertical error and horizontal error on space line fitting and plane fitting are analyzed to weight measuring points.Experiment results show that compare with equal-weighted fitting algorithm, this algorithm improved the fitting precision about 16%.
［1］Iske A, Levesley J. Algorithms for Approximation［M］.Berlin:Springer Berlin Heidelberg,2007,259-268.
［2］Zhou Kai, Varadarajan K M, Zillich M, et al. Gaussian-weighted Jensen-Shannon divergence as a robust fitness function for multi-model fitting［J］.Machine Vision and Applications,2013,24(6):1107-1119.
［3］潘国荣,陈晓龙.空间圆形物体数据拟合新方法［J］.大地测量与地球动力学,2008,28(2):92-94.
［4］官云兰,程效军,施贵刚.一种稳健的点云数据平面拟合方法［J］.同济大学学报（自然科学版）,2008,36(7):981-984.
［5］曾齐红, 毛建华, 李先华,等.激光雷达点云平面拟合过滤算法［J］.武汉大学学报·信息科学版, 2008,33(1):25-28.
［6］乔宇, 黄席樾, 柴毅,等.基于自适应直线拟合的角点检测［J］.重庆大学学报,2003,26(2):29-31.
［7］Capello E, Semeraro Q. Harmonic Fitting Approach for Plane Geometry Measurements［J］. The International Journal of Advanced Manufacturing Technology,2000,16(4):250-258.
2015, Vol. 36 
