摘要： 分析椭圆拟合应用中常用算法对噪声过于敏感、抗干扰能力差的缺点，提出一种鲁棒性较强的椭圆拟合算法。采用各点异性回归技术，建立误差与变量有关的(EIV)模型，根据数据矢量观测集合最优地估计线性EIV模型参数和数据矢量真值集合。实验结果表明，该算法精确度高，当初始值与真实值差距较大时，仍然可以快速、稳定地收敛。

关键词: 计算机视觉, 椭圆拟合, 各点异性

Abstract: This paper analyzes the usual algorithms with less anti-jamming ability which are sensitive to the effect of noise in the application of ellipse fitting, and proposes a more robust ellipse fitting algorithm. It utilizes the heteroscedastic regression technique to create the Errors-In-Variables (EIV) model. According to the observation of data vector, the optimal algorithm is found to obtain the optimal estimations of EIV model parameters and the truth-value of the observed data vector. Experimental results show that the algorithm is more accurate and can converge steadily and rapidly, when original data is far from exact value.

Key words: computer vision, ellipse fitting, heteroscedastic

中图分类号: 

• TP301