摘要
基于曲线提取算法的框架,并利用由椭圆的极点—极弦性质开发的三点组到椭圆参数的收敛映射,开发了一个以鲁棒地直接提取椭圆的随机Hough变换(RHT)为基础的椭圆提取新技术与经二次曲线间接提取椭圆的技术相比,该技术不但能确保RHT的每次收敛映射的结果一定为椭圆参数,而且能高速有效地实时实现用精确仿真的计算机图象和真实图象进行的广泛实验表明,该技术是正确。
Based on the framework of the curve extraction algorithm,and using the convergence-mapping from the triple-point subset to the elliptical parameter set provided by the geometric properties on the pole and polar line of an ellipse,a new method for robust and direct extraction the ellipses of targets is presented.This is a robust RHT-based technique.Compared to the old indirect method,the new method has the attractive advantage of making sure of the results of every mapping to be the valid elliptical parameters.The extensive experiments for the images exactly simulated by PC computer and for the real underwater images have demonstrated that the method is very robust,fast and exact.
出处
《哈尔滨工程大学学报》
EI
CAS
CSCD
1997年第5期70-77,共8页
Journal of Harbin Engineering University
关键词
计算机视觉
椭圆提取
极点-极弦性质
图象识别
computer vision
ellipse extraction
pole and polar line
random Hough transform
robust estimation