双目立体视觉测量系统的标定

Calibration of binocular vision measurement system

考虑传统的自标定方法虽然无需场景信息即可实现摄像机标定,但是标定精度较低,故本文提出了一种新的大视场双目视觉测量系统自标定方法。该方法无需高精度标定板或者标定物,仅需利用空间中常见的平行线和垂直线建立摄像机参数与特征线间的约束方程,即可实现摄像机的内参数与旋转矩阵标定;同时利用空间中距离已知的3个空间点即可线性标定两摄像机间的平移向量。通过标定实验对本文提出的方法进行了验证。结果表明:该方法标定精度能够达到0.51%,可以较高精度地标定双目测量系统。由于避免了大视场测量系统标定中大型标定物制造困难,以及摄像机自标定过程中算法冗杂,标定精度不高等问题,该方法操作简便,精度较好,适用于大视场双目测量系统的在线标定。

When traditional self-calibration methods are used to calibrate the cameras without scene in formation, it usually shows lower calibration accuracy. In order to solve this problem, an improved self-calibration method for a binocular vision measurement system was proposed. Without high-accuracy calibration pattern, the proposed method could calibrate intrinsic parameters and rotation matri- xes only by using parallel and perpendicular lines to establishing the constraint equation between the camera parameter and the characteristic line. Meanwhile, the translation vector was calibrated by fea ture points with the known distances between them. The calibration experiment was conducted to verify the proposed method. It shows that the proposed method calibrates the binocular vision measurement system in high accuracy, the accuracy reaches to 0.51%. As the proposed method avoids the dif ficulties from the high-accuracy calibration pattern needed in the calibration of measuring system, and the complex algorithm and low calibration accuracy in camera self-calibration, it has advantages of easy operating and high accuracy.