摘要
椭圆是视觉测量中重要的基元特征。建立了三级灰度图像边缘模型的空间矩算子,利用LOG算子定位速度快的特点,确定图像像素级边缘,然后在包含边缘点的邻域内利用空间矩进行边缘的亚像素定位,由随机Hough变换提取椭圆边缘像素点,最后采用基于最小二乘原理的椭圆拟合边缘提取方法,得到亚像素级被检测椭圆。对像面椭圆亚像素提取算法的有效性和精度进行了实验研究,实验结果表明提出的基于空间矩亚像素边缘定位算法与像面椭圆亚像素提取算法具有较高的精度和稳定性。
Ellipse is an important element in the computer vision measurement.A spatial moment operator with three gray models is researched in this paper,in which edge at pixel level is confirmed first by applying the rapid positioning of LOG operator.And then the spatial moment is applied to detect subpixel location of the discrete points of edge.Finally elliptic fitting edge extraction based on the least square principle is applied to obtain detected ellipse at subpixel level through the ellipse＇s subpixel edge points which have been detected by Hough transform.The validity and precision of spatial moment subpixel edge detection and the detection of ellipse on image plane is studied through experiments,which results show that spatial moment subpixel edge detection and the detection of ellipse on image plane have acquired high precision stability.
出处
《机械设计与制造》
北大核心
2011年第8期142-144,共3页
Machinery Design & Manufacture
