采用环形模板的棋盘格角点检测

储珺; 郭卢安政; 赵贵花

doi:10.3788/OPE.20132101.0189

您当前的位置：

首页 >

文章列表页 >

采用环形模板的棋盘格角点检测

信息科学 | 更新时间：2020-08-12

- 采用环形模板的棋盘格角点检测
- Chessboard corner detection based on circular template
- 光学精密工程 2013年21卷第1期页码：189-196
- 作者机构：
  
  南昌航空大学计算机视觉研究所
- 作者简介：
- 基金信息：
  
  中国国家自然科学基金();中国国家基础研究项目();中国航空科学基金()
- DOI：10.3788/OPE.20132101.0189
  中图分类号：
- 收稿日期：2012-07-26，
  
  修回日期：2012-09-11，
  
  网络出版日期：2013-01-24，
  
  纸质出版日期：2013-01-15
- 稿件说明：
移动端阅览
储珺郭卢安政赵贵花. 采用环形模板的棋盘格角点检测[J]. 光学精密工程, 2013,21(1): 189-196

CHU Jun GUOLU An-zheng ZHAO Gui-hua. Chessboard corner detection based on circular template[J]. Editorial Office of Optics and Precision Engineering, 2013,21(1): 189-196
储珺郭卢安政赵贵花. 采用环形模板的棋盘格角点检测[J]. 光学精密工程, 2013,21(1): 189-196 DOI： 10.3788/OPE.20132101.0189.

CHU Jun GUOLU An-zheng ZHAO Gui-hua. Chessboard corner detection based on circular template[J]. Editorial Office of Optics and Precision Engineering, 2013,21(1): 189-196 DOI： 10.3788/OPE.20132101.0189.

摘要

曝光过度和镜头畸变将分别导致棋盘格角点分离和角点局部区域不对称现象。现有的角点检测算法通常难以准确提取棋盘格角点。此外，在复杂背景下，现有角点检测算法也极易出现错误。针对上述问题，本文提出了一种图像坐标系下的基于环形模板的棋盘格角点检测算法。首先，通过分析得出棋盘格角点附近的灰度分布应满足一定的对称性和灰度交替性等性质，进而得出环形模板卷积后的图像应满足的性质。而后，利用该性质来定义并提取棋盘格角点，使提取的角点直接达到亚像素精度。实验结果表明：本文提出的棋盘格角点检测算法在曝光过度，镜头畸变和复杂背景情况下，均能取得较好的棋盘格角点检测效果。将该算法应用于实际摄像机标定，实验结果显示重投影误差在0.3个像素以内。

Abstract

Over exposure and Camera lens distortion often result in chessboard corner separation and chessboard corner local area asymmetry. The existing chessboard corner detection algorithms can not extract corners in such conditions accurately. Besides

the existing chessboard corner detection algorithms will go wrong easily under complex background. To solve these problems

this paper proposes an algorithm based on circular template under image coordinate. We first analyze the gray distribution of the local area of chessboard corner to achieve the properties of convoluted image and define the chessboard corner with those properties. Finally we extract the chessboard corners coordinates through those properties and our detected chessboard corners can reach sub-pixel level in merely one step by employing the image coordinate. Experiment results show that our algorithm can achieve better results in both simple backgrounds and complex scenes. Applying our detector to camera calibration

we obtain smaller re-projection error

which is less than 0.3 pixels.

关键词

Keywords

references

万孝军. 基于逆向工程鞋楦参数化建模及其修改技术研究[D]. 合肥：合肥工业大学，2009.WAN X J. Research on parametric modeling of shoe-last and its modification based on reverse engineering [D]. Hefei: Hefei University of Technology, 2009. (in Chinese)[2]孙毅，丘理. 鞋楦设计教程[M]. 北京：中国轻工业出版社，2011.SUN Y, QIU L. The Course of Last Design [M]. Beijing：China Light Industry Press，2011. (in Chinese)[3]ROUT N, KHANDUAL A, ZHANG Y F, et al.. 3D foot scan to custom shoe last [J]. Special Issue of IJCCT, 2010, 1(2/3/4): 14-18.[4]XIONG SH P, ZHAO J H, JIANG Z H, et al.. A computer aided design system for foot-feature-based shoe last customization [J]. The International Journal of Advanced Manufacturing Technology, 2010, 46(1-4): 11-19.[5]徐从富，刘勇，蒋云良. 个性化鞋楦CAD系统的设计与实现[J]. 计算机辅助设计与图形学学报，2004，16(10)： 1437-1441.XU C F, LIU Y, JIANG Y L. Design and realization of customized shoe last CAD system [J]. Journal of Computer Aided Design & Computer Graphics, 2004, 16(10): 1437-1441. (in Chinese)[6]陆国栋，顾铭秋，王剑，等. 基于脚部三维扫描的鞋楦建模方法研究[J]. 设计与研究，2005，32（4）：13-15.LU G D, GU M Q, WANG J, et al.. Research of shoe-last modeling algorithm based on feet range scans [J]. Design and Research, 2005, 32(4): 13-15. (in Chinese)[7]贾倩倩，王伯雄，罗秀芝. 光切法形貌测量中光条中心的亚像素提取 [D]. 光学精密工程，2010，18（2）：390-396.JIA Q Q, WANG B X, LUO X Z. Extraction of central positions of light stripe in sub-pixel in 3D surface measurement based on light sectioning method [D]. Opt. Precision Eng., 2010, 18(2): 390-396. (in Chinese)[8]PIEGL L, TILLER W. The NURBS Book [M]. Berlin: Springer, 1995.[9]沈洪垚. 自适应NURBS曲线插补关键技术及实现研究[D]. 杭州：浙江大学，2010.SHEN H Y. Research on adaptive NURBS interpolation and implementation [D]. Hangzhou: Zhejiang University, 2010. (in Chinese)[10]POURAZADY M, XU X. Direct manipulations of B-spline and NURBS curve [J]. Advances in Engineering Software, 2000, 31(2): 107-118.[11]史辉，王伯雄，贾倩倩，等. 定制鞋楦的分段自适应修改[J]. 光学精密工程，2009，17（4）：880-885.SHI H, WANG B X, JIA Q Q, et al.. Segment-based adaptive modification for customized shoe last [J]. Opt. Precision Eng., 2009, 17(4): 880-885. (in Chinese)[12]柳晓艳. NURBS曲线曲面形状修改[D]. 西安：西北工业大学，2006.LIU X Y. On Shape modification of NURBS curves and surfaces [D]. Xian: Northwest University, 2006. (in Chinese)[13]AU C K, YUEN M F. Unified approach to NURBS curve shape modification [J]. Computer Aided Design, 1995, 27:85-93.[14]LEE R S, LIANG S P. A strain energy minimization method for generating continuous NURBS-based motion curves in free-form surface machining [J]. The International Journal of Advanced Manufacturing Technology, 2006, 28(11-12): 1136-1145.

浏览量

140

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

野外大视场单相机空间坐标测量系统的快速标定

构建虚拟立体靶标的大视场高精度视觉标定

双目立体视觉测量系统的标定

航空变焦距斜视成像几何畸变的自动校正

共面点的摄像机非线性畸变校正