基于视觉图像的二次曲线特征参数精密测量方法

Accurate measurement method of quadratic curve parameters based on vision image

为了满足视觉检测中对二次曲线参数(圆或椭圆)高精度测量要求,提出了一种基于视觉图像的二次曲线特征参数精密测量方法。该方法利用变结构元广义形态学边缘检测算法对图像中的二次曲线进行初始边缘定位,充分提取图像边缘细节信息的同时抑制图像噪声的影响。在亚像素图像处理中,基于Zernike矩边缘检测算法计算出的边缘参数,提出了对二次曲线特征进行亚像素边缘定位的边缘检测算法,建立了曲线边缘点与边缘参数之间的映射关系。利用检测出的二次曲线亚像素边缘点数据,通过定义的数据点分布优化的参数拟合算法,可以计算出二次曲线的特征参数。实验结果表明:该方法稳定性好且实时性强,定位不确定度优于0.03像素,可实现二次曲线特征参数的精密测量。

In order to satisfy the stringent requirements of high accurate measurement of quadratic curve parameters in vision detection,a novel measurement method based on vision image is proposed in this paper,which can be used to carry out precise parameter estimation of quadratic curve.The edge of quadratic curve is fully extracted using multiple structuring element-based generalized morphological edge detection algorithm;meanwhile the influences of noises on image are diminished.In subpixel image processing,according to the edge parameters computed based on the principle of Zernike moment edge detection,an edge detection algorithm is proposed to locate the subpixel edge of quadratic curve,and circular edge location is accomplished through establishing the mapping between the edge point and the parameters of the circle where the edge points lie in images.Then,the estimation of quadratic curve parameters based on a set of subpixel edge-point data is realized through defining and minimizing an error function that is used to optimize the distribution of data points.Experimental results show that the algorithm is very accurate and stable,and the uncertainty is better than 0.03 pixel.The proposed method is very effective in detecting quadratic curves for vision measurements.