基于绝对相位靶的摄像机标定仿真与实验研究  

Simulation and Experiment Research on Camera Calibration Based on Absolute Phase Target

作　　者：安世勇 朱江平[1,2] 杨红雨 周佩[1,2] 肖雯帆 朱昌会 An Shiyong;Zhu Jiangping;Yang Hongyu;Zhou Pei;Xiao Wenfan;Zhu Changhui(National Key Laboratory of Fundamental Science on Synthetic Vision,Sichuan University,Chengdu,Sichuan 610065,China;College of Computer Science,Sichuan University,Chengdu,Sichuan 610065,China)

机构地区：[1]四川大学视觉合成图形图像技术国家级重点实验室,四川成都610065 [2]四川大学计算机学院,四川成都610065

出　　处：《激光与光电子学进展》2022年第4期262-273,共12页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(61901287);四川省重点研发专项(2021YFG0195,2020YFG0112,2020YFG0306);四川省重大科技专项(2019ZDZX0039,2018GZDZX0029)。

摘　　要：摄像机标定是结构光三维传感技术中联系测量系统内外参数与三维坐标之间的重要环节。基于灰度信息提取特征点的摄像机标定方法易受图像噪声、对比度等因素的影响。提出一种基于绝对相位靶(APT)的摄像机标定方法,采用时间相位展开算法计算绝对相位,提取相位值为4π整数倍的特征点,采用局部窗口最小二乘拟合算法计算特征点的精确亚像素坐标,进而建立特征点的图像坐标与世界坐标的对应关系。通过仿真实验,分析不同高斯噪声和模糊条件下摄像机参数的绝对误差变化,发现相对于传统的棋盘格和圆点标定法,所提APT标定法对图像噪声和模糊具有更好的鲁棒性,且具有更高的标定精度。真实的对比实验显示,APT标定方法的标定精度优于棋盘格和圆点标定法,尤其在“离焦”(标靶处于相机有效工作距离之外)情况下可将重投影误差降低58.68%,证明了APT标定方法的有效性和可行性。Camera calibration is an essential part of 3 D sensing technology based on structured light, which links the intrinsic and extrinsic parameters of the measurement system with the 3 D coordinates. The camera calibration approach based on feature points retrieved from gray information can be easily affected by image noise, contrast, and other factors. Thus, this study proposes an active camera calibration approach based on absolute phase target(APT), in which absolute phase is determined using the temporal phase unwrapping algorithm. The point where phase value is the integer multiples of 4π is selected as the feature point. The local window least-square linear-fitting approach is used to determine the precise subpixel coordinates of every feature point, then the one-to-one correspondence between the image and world coordinates of feature points is established. In simulation experiments,according to the absolute error change of the camera parameters under different degrees of Gaussian noise and blur,we concluded that the proposed APT calibration method is more robust to noise and blur than the traditional checkerboard calibration and dot calibration approach, and calibration accuracy is relatively high. The validity and feasibility of the proposed APT approach are further demonstrated by the real comparison experiment, which reveal that the calibration accuracy of the APT approach is higher and the reprojection error can be reduced by 58. 68%under out-of-focus conditions(the target is outside the working distance of the camera).

关 键 词：测量 摄像机标定 相移条纹 绝对相位 特征点提取 亚像素拟合 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]