结合多阶段优化的圆检测算法

ISSN1004‐9037,CODEN SCYCE4

Journal of Data Acquisition and Processing Vol.33,No.1,Jan.2018,pp.144-150DOI:10.16337/j.1004‐9037.2018.01.016

ⓒ2018by Journal of Data Acquisition and Processing

http://sjcj.nuaa.edu.cn E‐mail:sjcj@nuaa.edu.cn Tel/Fax:+86‐025‐84892742

结合多阶段优化的圆检测算法

蒋联源1,2王智文2李春贵2孔凡福3邓向姣2

(1.南京航空航天大学自动化学院,南京,210016;2.广西科技大学计算机科学与通信工程学院,柳州,545006;3.柳州市广播电视台,柳州,545006)

摘要:在常规圆检测算法中,Hough变换、随机Hough变换以及随机圆检测算法的检测效率低,导致难以适用于复杂场景或者对检测速度有较高要求的情况。为了提高圆检测的效率,本文从采样点的选取、候选圆的确定以及真圆的确认3个阶段进行分析,结合这3个阶段的优化方法,提出一种结合多阶段优化的圆检测算法。人工图像和实际图像的实验结果表明:该算法较其他算法有效地提高了圆检测的速度,并且具有较好的检测鲁棒性和检测精度。

关键词:圆检测;多阶段优化;采样点;候选圆

中图分类号:T P391文献标志码:A

Multi‐stage Optimized Algorithm for Circle Detection

Jiang Lianyuan1,2,Wang Zhiwen2,Li Chungui2,Kong Fanfu3,Deng Xiangjiao2

(1.College of Automation Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing,210016,China;2.College of Computer Science and Communication Engineering,Guangxi University of Science and Technology,Liuzhou,545006,China;3.Li‐uzhou Radio and Television Station,Liuzhou,545006,China)

Abstract:A s a basic and fundamental issue in computer vision area,many algorithm s have been pro‐p osed to address the issue of circle detection,such as Hough transform,randomized Hough trans‐form,randomized circle detection and so on.How ever,the low efficiency of these methods makes them hard to be used in complicated situations or conditions that require m uch higher circle detection speed.T o improve the efficiency of circle detection,this paper analyzes three stages,including the se‐lection of sampling points,the determination of candidate circle and the confirmation of true circle.Com bined with the optimization of these three stages,a circle detection algorithm w ith m ulti‐stage optimization is proposed.Experimental results of synthetic images and real images indicate that the p roposed algorithm has faster detection speed compared w ith other methods,and has a high detection accuracy and strong robustness.

Key words:circle detection;multi‐stage optimization;sampling point;candidate circle

基金项目:国家自然科学基金(61751213;61462008)资助项目;广西省自然科学基金(2016GXNSFBA380081)资助项目;广西教育厅科研基金(K Y2016YB256,KY2016LX172)资助项目;广西高校工业过程智能控制技术重点实验室主任基金(IPICT‐2016‐03)资助项目;柳州市科学研究与技术开发计划(2016C050205)资助项目。

收稿日期:2016‐04‐04;修订日期:2016‐04‐11

万方数据

相关推荐
相关主题
热门推荐