基于改进的SUSAN算子的棋盘格亚像素角点检....pdfVIP

SUSAN SUSAN 1, 2 1 1 1 杨幸芳 黄玉美 李 艳 高 峰 1.西安理工大学,西安,710048 2.西安工程大学,西安, 710048 :针对SUSAN 算子在检测棋盘格角点这 一 殊类型角点时出现的不足, 提出了改进的 SUSAN角点检测算子改进的算子在分析原有算子仅考虑USAN 区域的大小而不考虑 USAN 区域 的形状这一局限性的基础上,通过在 SUSAN 圆模板内附加两 个圆环模板来实现对所有棋盘格角点的 有效检测此外,鉴于棋盘格角点图像形状和灰度分布具有对称性以及灰度对比强烈的 点,采用灰度 重心法对角点进行了亚像素定位为了提高算法性能, 具体操作时采用区域分离思想, 将USAN 区域 分成内部像素区域和边缘像素区域两部分,通过对内部像素区域灰度的均值化,达到了抑制内部像素区 域噪声的目的实验结果表明,所提出的算法准确有效,能达到亚像素级的精度 :SUSAN ; ;; ;USAN :TP391 : 1004 132X(2010)21 2541 05 Sub- pixel Corner Detection Algorithm of Chessboard Image Based on Improved SUSAN Operator 1,2 1 1 1 Yang Xingfang Huang Yu ei Li Yan Gao Feng 1.Xi an University of Technology,Xi an, 710048 2.Xi an Polytechnic University,Xi an, 710048 Abstract: An i proved SUSAN corner detection operator was proposed herein ai ing at SUSAN operator s deficiency revealed in detecting chessboard corners. On the basis of the li itation analysis about the SUSAN operator, the authors pointed out that one of the disadvantages of the SUSAN op erator is that it just takes into account USAN s size without considering USAN s shape in detecting feature points andwhich ay result in incorrect detecting results. Therefore, two ring- shaped asks were added within the SUSAN circular ask to overco e this defect. Moreover, in view of chessboard i age has sharp brightness contrast, its shape is sy etric and its brightness distribution is sy et ric, the authors utilized the center of the gravity of brightness to position chessboard corners in order to achieve sub- pixel precision. In practical operation, the USAN was separated into two regions, that is, the internal pixel region