液晶与显示, 2018, 33 (2): 150, 网络出版: 2018-03-21   

一种基于旋转不变性的角点检测方法研究

Corner detection method based on rotation invariance
作者单位
苏州科技大学 数理学院, 江苏 苏州215009
摘要
针对显微立体视觉标定过程中, 因显微成像产生的畸变和模糊而造成棋盘格标定板角点误检的问题, 提出一种基于旋转不变性的角点检测方法, 研究了棋盘格角点间的几何特征, 对所有特征角点进行排序, 通过实验建立数学模型, 计算筛选的特征角点的置信度, 准确提取出棋盘格角点位置, 并通过一系列实验对这种方法的准确度、噪点数量以及精度进行验证。结果表明, 基于旋转不变性的棋盘格角点检测方法, 准确率达到91.2%, 重投影误差的均方差约为0.1像素, 具有较高的准确性和精度。
Abstract
Aiming at the error detection of the chessboard corners caused by distortion and blur of microscopic imaging during the calibration processing of the micro stereovision, a corner detection method of chessboard based on rotation invariance is proposed, which studies the geometry of chessboard corners and sorts all the characteristic corners. Mathematical model is established through experiments, the confidence level of filtered characteristic corners are calculated, which extracts positions of the chessboard corners and validate the accuracy, the number of noise and the precision through a series of experiments. The results show that the accuracy rate of the corner detection based on rotation invariance reaches 91.2%, and the mean square error of the re-projection error is approximately 0.1 pixels, which has a comparatively high accuracy and high precision.

吴敏杨, 季锋, 蒋明. 一种基于旋转不变性的角点检测方法研究[J]. 液晶与显示, 2018, 33(2): 150. WU Min-yang, JI Feng, JIANG Ming. Corner detection method based on rotation invariance[J]. Chinese Journal of Liquid Crystals and Displays, 2018, 33(2): 150.

本文已被 3 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!