检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:黄建 李施阳 章秀华[1] 吴锦梦 HUANG Jian;LI Shiyang;ZHANG Xiuhua;WU Jinmeng(School of Electrical Information,Wuhan Institute of Technology,Wuhan 430205)
出 处:《计算机与数字工程》2022年第4期762-766,共5页Computer & Digital Engineering
基 金:国家自然科学基金面上项目(编号:62171329)资助。
摘 要:基于张氏标定原理的传统双目相机标定方法在单一背景下标定精度高,但在复杂背景下不能精确提取特征点坐标,导致相机标定精度受到影响。文中提出一种基于Halcon标定靶感兴趣区域约束的透视变换方法,可以从复杂背景中精确提取特征点坐标,提高双目相机标定精度。首先通过改进的角点提取方法从背景中提取Halcon标定靶上的感兴趣区域,利用透视变换和最小二乘法提取特征点的精确坐标;然后匹配左、右图像中同名的特征点,利用张氏标定原理计算双目相机的参数。实验表明,利用文中方法标定的相机参数,计算特征点平均重投影精度达0.01像素,相比于传统方法平均重投影精度提高0.02像素,提高了双目相机参数标定的精度。The traditional binocular camera calibration methods based on Zhang's calibration principle have high calibration accuracy under a single background,but it cannot accurately extract feature points coordinates under complex backgrounds,and re⁃sults in poor camera calibration accuracy.This paper proposes a perspective transformation method based on the constraint of the re⁃gion of interest in the Halcon calibration target,which can accurately extract the coordinates of feature points from the complex back⁃ground and improve the calibration accuracy of the binocular camera.The improved corner points extraction method is used to ex⁃tract the region of interest on the Halcon calibration target from the background,and the precise coordinates of the feature points are extracted by perspective transformation and the least square method.Then the feature points of the same name in the left and right images are matched,and Zhang's calibration principle is used to calculate the parameters of the binocular camera.The experiments show that the average reprojection accuracy of the calculated feature points is 0.01 pixels by using the camera parameters calibrated in this paper,which is higher than the average reprojection accuracy of the traditional method by 0.02 pixels,so the accuracy of the binocular camera parameter calibration is improved.
关 键 词:双目视觉 Halcon标定靶 最小二乘法 透视变换 张氏标定原理
分 类 号:TP391[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.63