首页 > 论文 > 光学学报 > 38卷 > 12期(pp:1215007--1)

基于椭圆外切矩形性质的圆形标志点检测

Circular Control Points Detection Based on Circumscribed Rectangle of an Ellipse

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

圆形标志点检测通常被视为椭圆检测。由于光线、角度等原因,采集到的标志点会出现残缺,另外,当背景或物体较复杂时,非标志点边缘为标志点的提取带来干扰。为此,提出了一种基于椭圆外切矩形性质的圆形标志点检测方法。通过拟合椭圆的准圆来检测椭圆的中心,利用椭圆外切矩形的几何性质来确定椭圆的长短轴位置及旋转角度。为了去除非标志点的干扰边缘影响,进一步构造验证参数,并结合聚类算法,最终提取有效的标志点类。仿真与实物实验表明,该算法拟合精度高,检测性能优良,对具有部分残缺的椭圆有良好的识别效果,且对于复杂情况下的标志点识别仍具有较高的精度和稳健性。

Abstract

Circular control points detection is usually considered as the detection of ellipses. Due to the illumination, measuring angle and other reasons, the edges of control points may be incomplete. Furthermore, the noise edge of complex background or object will interfere with the extraction of control points. For those reasons, we propose a method of circular control point detection based on the circumscribed rectangle of an ellipse. Firstly, the center position of an ellipse is obtained by fitting director circle. Then the orientation and two semi-axis of an ellipse are determined by using the geometric properties of the external rectangle. The detected ellipses will be verified in order to reduce the detection errors. Finally, a clustering algorithm based method is proposed to extract the efficient control points. The simulation and real experimental results show that the proposed algorithm has high accuracy and excellent detection performance even for incomplete ellipses or cases in complex situation.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP301.6

DOI:10.3788/aos201838.1215007

所属栏目:机器视觉

基金项目:国家自然科学基金(61405034,51475092,51175081)

收稿日期:2018-06-11

修改稿日期:2018-07-13

网络出版日期:2018-08-07

作者单位    点击查看

杨忞:东南大学自动化学院,复杂工程系统测量与控制教育部重点实验室, 江苏 南京 210096
达飞鹏:东南大学自动化学院,复杂工程系统测量与控制教育部重点实验室, 江苏 南京 210096

联系人作者:达飞鹏(dafp@seu.edu.cn)

【1】Zhang H Y, Yu Z J. Initial displacement estimation method for speckle image based on marker matching[J]. Acta Optica Sinica, 2017, 37(3): 0303001.
张红颖, 于之靖. 基于标志点匹配的散斑图像变形初值估计法[J]. 光学学报, 2017, 37(3): 0303001.

【2】Yu J, Da F P. Bi-tangent line based approach for multi-camera calibration using spheres[J]. Journal of the Optical Society of America A, 2018, 35(2): 000221.

【3】Fitzgibbon A, Pilu M, Fisher R B. Direct least square fitting of ellipses[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999, 21(5): 476-480.

【4】Jia Q, Fan X, Luo Z X, et al. A fast ellipse detector using projective invariant pruning[J]. IEEE Transactions on Image Processing, 2017, 26(8): 3665-3679.

【5】Wu Y F, Wang W, Lu K Q, et al. Fast ellipse detection based on edge grouping[J]. Journal of Zhejiang University (Engineering Science), 2016, 50(3): 405-411.
吴尧锋, 王文, 卢科青, 等. 边界聚类椭圆快速检测方法[J]. 浙江大学学报(工学版), 2016, 50(3): 405-411.

【6】Kwon B K, Teng Z, Roh T J, et al. Fast ellipse detection based on three point algorithm with edge angle information[J]. International Journal of Control, Automation and Systems, 2016, 14(3): 804-813.

【7】Prasad D K, Leung M K H, Cho S Y. Edge curvature and convexity based ellipse detection method[J]. Pattern Recognition, 2012, 45(9): 3204-3221.

【8】Wu B, Ye D, Guo Y B, et al. Multiple circle recognition and pose estimation for aerospace applications[J]. Acta Optica Sinica, 2017, 37(9): 0915004.
吴斌, 叶东, 郭玉波, 等. 基于航天应用的多圆特征识别和姿态估计[J]. 光学学报, 2017, 37(9): 0915004.

【9】Ptrucean V, Gurdjos P, von Gioi R G. A parameterless line segment and elliptical arc detector with enhanced ellipse fitting[C]∥Proceedings of European Conference on Computer Vision, 2012: 572-585.

【10】Chen S L, Xia R B, Zhao J B, et al. A hybrid method for ellipse detection in industrial images[J]. Pattern Recognition, 2017, 68: 82-98.

【11】Chen Y G, Yang Y. Two improved algorithms for ellipse detection based on Hough transform[J]. Semiconductor Optoelectronics, 2017, 38(5): 745-750.
陈余根, 杨艳. 基于霍夫变换椭圆检测的两种改进算法[J]. 半导体光电, 2017, 38(5): 745-750.

【12】Xie Y H, Ji Q. A new efficient ellipse detection method[C]∥Proceedings of Object Recognition Supported by User Interaction for Service Robots, 2002, 2: 957-960.

【13】Huan H, Huang L X, Zhang Y, et al. Detection of elliptical hole group based on maximum inscribed circle[J]. Journal of Computer Applications, 2015, 35(4): 1101-1105.
宦海, 黄凌霄, 张雨, 等. 基于最大内切圆的椭圆孔组检测[J]. 计算机应用, 2015, 35(4): 1101-1105.

【14】Grbic' R, Grahovac D, Scitovski R. A method for solving the multiple ellipses detection problem[J]. Pattern Recognition, 2016, 60: 824-834.

【15】Cockshott A, Walters F B. Geometric properties of conical curves[M]. Jiang S, Transl. Shanghai: Shanghai Education Press, 2002.
科克肖特, 沃尔特斯. 圆锥曲线的几何性质[M]. 蒋声, 译. 上海: 上海教育出版社, 2002.

【16】Dong H X, Chen I M, Prasad D K. Robust ellipse detection via arc segmentation and classification[C]∥Proceedings of IEEE International Conference on Image Processing, 2017: 66-70.

【17】Fornaciari M, Prati A, Cucchiara R. A fast and effective ellipse detector for embedded vision applications[J]. Pattern Recognition, 2014, 47(11): 3693-3708.

【18】Cheng Y Z. Mean shift, mode seeking, and clustering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17(8): 790-799.

【19】Zhou X, Kong X D, Zeng G H. Method of ellipse detection based on Hough transform[J]. Computer Engineering, 2007, 33(16): 166-167.
周祥, 孔晓东, 曾贵华. 一种新的基于Hough变换的椭圆轮廓检测方法[J]. 计算机工程, 2007, 33(16): 166-167.

【20】Yang Z G, Luan X M. The dynamic searching optimization image reconstruction method on the condition of maximum entropy[J]. Journal of Image and Graphics, 1997, 2(7): 517-519.
杨忠根, 栾晓明. 利用椭圆性质提取椭圆[J]. 中国图象图形学报, 1997, 2(7): 517-519.

【21】Ouellet J N, Hébert P. Precise ellipse estimation without contour point extraction[J]. Machine Vision and Applications, 2009, 21: 59.

【22】Ptrucean V, Gurdjos P, von Gioi R G. Joint a contrario ellipse and line detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4): 788-802.

引用该论文

Yang Min,Da Feipeng. Circular Control Points Detection Based on Circumscribed Rectangle of an Ellipse[J]. Acta Optica Sinica, 2018, 38(12): 1215007

杨忞,达飞鹏. 基于椭圆外切矩形性质的圆形标志点检测[J]. 光学学报, 2018, 38(12): 1215007

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF