液晶与显示2018，Vol.33Issue(2)：150-155,6.DOI:10.3788/YJYXS20183302.0150
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
摘要
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 chess-board corners and sorts all the characteristic corners.Mathematical model is established through ex-periments,the confidence level of filtered characteristic corners are calculated,which extracts posi-tions 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 9 1.2%,and the mean square error of the re-proj ection error is approxi-mately 0.1 pixels,which has a comparatively high accuracy and high precision.关键词
旋转不变性/角点检测/几何特征/置信度Key words
rotation invariance/corner detection/geometric characteristics/confidence level分类
信息技术与安全科学引用本文复制引用
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):150-155,6.基金项目
国家自然科学基金(No.11172193)Supported by Foundation of National Natural Science(No.11172193) （No.11172193）
