基于圆点阵列靶标的特征点坐标自动提取方法  

A Method of Automatic Extracting Feature Point Coordinates Based on Circle Array Target

作　　者：夏瑞雪[1] 卢荣胜[1] 刘宁[1] 董敬涛[1] 

机构地区：[1]合肥工业大学,合肥230009

出　　处：《中国机械工程》2010年第16期1906-1910,共5页China Mechanical Engineering

基　　金：国家863高技术研究发展计划资助项目(2009AA04Z114)

摘　　要：以用于摄像机标定的2D平面圆点阵列靶标为研究对象,提出一种在复杂背景环境下,无需人工干预,自动提取靶标标定特征点图像坐标的方法。对摄像机标定图像进行自适应阈值分割,将其转换为由多个连通区域组成的黑白二值图像,根据靶标图案的形态特征,首先对图像上的连通区域进行面积判断,初步剔除非目标区域;然后对其进行特征识别,提取出靶标图案区域;再对靶标图案区域进行轮廓提取,使用最小二乘椭圆拟合的方法,计算得到靶标各圆点中心的图像坐标;最后对各标定特征点进行定位操作,确定其所对应的圆点在7×7圆点矩阵中的位置。This paper proposed a method of automatic extracting feature point coordinates for 2D circle array target in complex background environment,which was used for camera calibration.The grey-scale image was converted into a binary image,which was composed by a multitude of connection areas,using adaptive thresholding algorithm.Firstly,the connection areas were judged by area to eliminate non-target regions.Secondly,the target region was identified by its morphological characteristics,and then its contour was extracted.Thirdly,the ellipse fitting method based on least-square principle was applied to calculate the central coordinates of every circle in the calibration image.Finally,every calibration feature point was located in order to determine the position of the corresponding dot in the 7×7rectangular array of dots.

关 键 词：摄像机标定 圆点阵列靶标 连通区域 椭圆拟合 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]