一种改进的快速SUSAN棋盘格角点检测算法
|
摘要
针对传统SUSAN角点检测算法不能区分棋盘格内角点和边缘点,以及因曝光过度导致的角点分离问题,本文提出改进的SUSAN角点检测算法。改进算法求取2组不相邻特征方向3像素灰度和差值,配合门限阈值和差阈值,提取角点集合;利用角点集合的对称分布特性确定角点集合的质心坐标作为此位置角点的坐标,坐标值可直接达到亚像素精度。实验表明:本文提出的改进的SUSAN角点检测算法可以有效、快速地提取角点,重投影误差在0.3个像素以内,可用于相机标定。
Since the traditional SUSAN corner detection algorithm can not distinguish inner corners and to solve the edge corners of chessboard,and to solve the problem of corner separation caused by excessive exposure,the improved SUSAN corner detection algorithm is proposed.The improved algorithm can obtain the difference of 3 pixels gray sum between two groups of nonadjacent characteristic directions,combining the threshold and difference threshold to extract the corner set.Moreover,using the symmetric distribution of the corner set to determine the centroid coordinates of the corner set as the coordinates of the corner of the position,and the coordinate values can be directly subpixel accuracy.Experiments show that the proposed algorithm can extract corners effectively and quickly,and the reprojection error is within 0.3 pixels.The extraction results can be used for camera calibration.
Since the traditional SUSAN corner detection algorithm can not distinguish inner corners and to solve the edge corners of chessboard,and to solve the problem of corner separation caused by excessive exposure,the improved SUSAN corner detection algorithm is proposed.The improved algorithm can obtain the difference of 3 pixels gray sum between two groups of nonadjacent characteristic directions,combining the threshold and difference threshold to extract the corner set.Moreover,using the symmetric distribution of the corner set to determine the centroid coordinates of the corner set as the coordinates of the corner of the position,and the coordinate values can be directly subpixel accuracy.Experiments show that the proposed algorithm can extract corners effectively and quickly,and the reprojection error is within 0.3 pixels.The extraction results can be used for camera calibration.
引文
[1]HARRIS C,STEPHENS M.A combined corner and edge detector[C]//Proceedings of the 4th Alvey Vision Conference.Manchester,UK:Alvety Vision Club,1988:147-151.
[2]SHEN Xinlan,WANG Zhong,LIU Changjie,et al.A new technique for high precision sub-regional camera calibration based on checkerboard pattern[J].Journal of Measurement Science and Instrumentation,2016,7(4):342-349.DOI:10.3969/j.issn.1674-8042.2016.04.006.
[3]侯建辉,林意.自适应的Harris棋盘格角点检测算法[J].计算机工程与设计,2009,30(20):4741-4743.DOI:10.16208/j.issn1000-7024.2009.20.038.
[4]张裕,方康玲,刘永祥.基于Harris算法的黑白棋盘格角点检测[J].计算机应用与软件,2010,27(8):251-254.
[5]梁志敏,高洪明,王志江,等.摄像机标定中亚像素级角点检测算法[J].焊接学报,2006,27(2):102-104.
[6]陈强.基于实虚靶标融合及无人机摄影的交通事故现场勘测技术研究[D].长春:吉林大学,2017.
[7]ZHANG Yuchi,LI Guolin,XIE Xiang,et al.A new algorithm for accurate and automatic chessboard corner detection[C]//Proceedings of 2017IEEE International Symposium on Circuits and Systems(ISCAS).Piscataway,NJ:IEEE Press,2017:1-4.DOI:10.1109/ISCAS.2017.8050637.
[8]熊显名,任娟娟.黑白棋盘格中的角点提取算法的研究[J].微型机与应用,2014,33(9):66-69.DOI:10.19358/j.issn.1674-7720.2014.09.021.
[9]曹兵,李文博,张云波.基于改进Harris角点算法的摄像机标定技术研究[J].计算机测量与控制,2016,24(5):213-215.DOI:10.16526/j.cnki.11-4762/tp.2016.05.060.
[10]SMITH S M,BRADY M.SUSAN-a new approach to low level image processing[J].International Journal of Computer Vision,1997,23(1):45-78.DOI:10.1023/A:1007963824710.
[11]刘俊杰,谢春利,王娟.棋盘格图像角点坐标亚像素提取方法[J].华中科技大学学报(自然科学版),2015,43(S1):170-172.DOI:10.13245/j.hust.15s1041.
[12]YANGXingfang,HUANG Yumei,GAO Feng.A simple camera calibration method based on sub-pixel corner extraction of the chessboard image[C]//Proceeding of 2010IEEE International Conference on Intelligent Computing and Intelligent Systems.Piscataway,NJ:IEEE Press,2010:688-692.DOI:10.1109/ICICISYS.2010.5658280.
[13]王瑞,杨润泽,尹晓春,等.一种改进的SUSAN算子棋盘格角点亚像素检测算法[J].计算机与现代化,2012(1):64-66.DOI:10.3969/j.issn.1006-2475.2012.01.017.
[14]BOUGUET JY.Camera calibration toolbox for Matlab[EB/OL].(2015-10-14)[2016-08-26].http://www.vision.caltech.edu/bouguetj/calib_doc/.
[15]MAHMOUDZADEH E,ZEKRI M,MONTAZERI M A,et al.Directional SUSAN image boundary detection of breast thermogram[J].IET Image Processing,2016,10(7):552-560.DOI:10.1049/iet-ipr.2015.0347.
[16]邹凤娇,苏显渝.摄像机标定及相关技术研究[D].成都:四川大学,2005.
[17]徐树奎,李国辉,张军,等.基于多方向对称和匀质约束的SUSAN棋盘格角点检测算法[J].计算机科学,2011,38(9):248-252.
[2]SHEN Xinlan,WANG Zhong,LIU Changjie,et al.A new technique for high precision sub-regional camera calibration based on checkerboard pattern[J].Journal of Measurement Science and Instrumentation,2016,7(4):342-349.DOI:10.3969/j.issn.1674-8042.2016.04.006.
[3]侯建辉,林意.自适应的Harris棋盘格角点检测算法[J].计算机工程与设计,2009,30(20):4741-4743.DOI:10.16208/j.issn1000-7024.2009.20.038.
[4]张裕,方康玲,刘永祥.基于Harris算法的黑白棋盘格角点检测[J].计算机应用与软件,2010,27(8):251-254.
[5]梁志敏,高洪明,王志江,等.摄像机标定中亚像素级角点检测算法[J].焊接学报,2006,27(2):102-104.
[6]陈强.基于实虚靶标融合及无人机摄影的交通事故现场勘测技术研究[D].长春:吉林大学,2017.
[7]ZHANG Yuchi,LI Guolin,XIE Xiang,et al.A new algorithm for accurate and automatic chessboard corner detection[C]//Proceedings of 2017IEEE International Symposium on Circuits and Systems(ISCAS).Piscataway,NJ:IEEE Press,2017:1-4.DOI:10.1109/ISCAS.2017.8050637.
[8]熊显名,任娟娟.黑白棋盘格中的角点提取算法的研究[J].微型机与应用,2014,33(9):66-69.DOI:10.19358/j.issn.1674-7720.2014.09.021.
[9]曹兵,李文博,张云波.基于改进Harris角点算法的摄像机标定技术研究[J].计算机测量与控制,2016,24(5):213-215.DOI:10.16526/j.cnki.11-4762/tp.2016.05.060.
[10]SMITH S M,BRADY M.SUSAN-a new approach to low level image processing[J].International Journal of Computer Vision,1997,23(1):45-78.DOI:10.1023/A:1007963824710.
[11]刘俊杰,谢春利,王娟.棋盘格图像角点坐标亚像素提取方法[J].华中科技大学学报(自然科学版),2015,43(S1):170-172.DOI:10.13245/j.hust.15s1041.
[12]YANGXingfang,HUANG Yumei,GAO Feng.A simple camera calibration method based on sub-pixel corner extraction of the chessboard image[C]//Proceeding of 2010IEEE International Conference on Intelligent Computing and Intelligent Systems.Piscataway,NJ:IEEE Press,2010:688-692.DOI:10.1109/ICICISYS.2010.5658280.
[13]王瑞,杨润泽,尹晓春,等.一种改进的SUSAN算子棋盘格角点亚像素检测算法[J].计算机与现代化,2012(1):64-66.DOI:10.3969/j.issn.1006-2475.2012.01.017.
[14]BOUGUET JY.Camera calibration toolbox for Matlab[EB/OL].(2015-10-14)[2016-08-26].http://www.vision.caltech.edu/bouguetj/calib_doc/.
[15]MAHMOUDZADEH E,ZEKRI M,MONTAZERI M A,et al.Directional SUSAN image boundary detection of breast thermogram[J].IET Image Processing,2016,10(7):552-560.DOI:10.1049/iet-ipr.2015.0347.
[16]邹凤娇,苏显渝.摄像机标定及相关技术研究[D].成都:四川大学,2005.
[17]徐树奎,李国辉,张军,等.基于多方向对称和匀质约束的SUSAN棋盘格角点检测算法[J].计算机科学,2011,38(9):248-252.