一种基于曲线跟踪的快速椭圆检测算法  

Fast Ellipse Detection Algorithm Based on Curve Tracking

作　　者：李振坤 闫志华[1] 王占云[1] LI Zhen-kun;YAN Zhi-hua;WANG Zhan-yun(School of Mechanical Engineering,Zhengzhou University,Henan Zhengzhou 450001,China)

机构地区：[1]郑州大学机械工程学院,河南郑州450001

出　　处：《机械设计与制造》2018年第10期245-248,共4页Machinery Design & Manufacture

摘　　要：为了实现对具有椭圆特征的目标进行在线检测,需要一种快速、高效的椭圆检测算法。目前研究最广泛的椭圆检测算法是基于Hough变换及其改进的算法,通过在参数空间中对图像中每一个前景点进行投票累加,得到的局部最大值所处位置即为检测出的椭圆参数。但该算法检测精度不高、占用空间大、运行时间长,后期的改进算法也只是通过各种方法间接减小参数空间,没有从根本上减少计算量,不适用于在线检测。对此,提出了一种基于曲线跟踪的椭圆检测算法,通过检测轮廓线得到参数,判断是否为椭圆。经过验证,新算法检测精度高、识别率高、速度快,满足在线检测要求。In order to realize the on-line detection of the target with elliptic feature,a fast and efficient algorithm for ellipse detection is required.At present,the most widely studied ellipse detection algorithm is based on the Hough transform and its improved algorithm.By voting in each point of the image in the parameter space,the location value of the local maximum is detected as the ellipse parameters.But the algorithm has low detection accuracy,large space occupation and long running time.The improved algorithm can only indirectly reduce the parameter space through a variety of methods,instead of reducing the amount of computation,and therefore not suitable for on-line detection.So,an ellipse detection algorithm based on curve tracing is proposed,which determine whether it is an ellipse by obtaining parameters by detecting contour lines.After verification,the new algorithm is of high accuracy,high recognition rate and fast speed,which is to meet the requirements of online detection.

关 键 词：椭圆特征 在线检测 HOUGH变换 曲线跟踪 

分 类 号：TH16[机械工程—机械制造及自动化] TP391[自动化与计算机技术—计算机应用技术]