机器视觉中的摄像机标定技术研究

Study on Camera Calibration Technology for Machine Vision

机器视觉中在对景物进行定量分析或对物体精确定位时,都需要进行摄像机标定,即准确确定其内部和外部参数。寻找快速有效的摄像机标定计算方法是机器视觉中的重要问题。分析了带有透镜径向的一阶畸变的摄像机模型,利用RAC标定提出一种求解其参数的标定计算方法,标定过程每一步都用线性求解,避免了非线性优化中的不稳定性。试验证明,该标定方法操作简便,标定精度高。

Camera calibration can be used to calculate the internal and external parameters of a camera in viewing. It is one of the basic tasks for analyzing the geometry of a scene and determining the shapes and locations of objects in machine vision. So it is important to find a new high speed method. The camera model with radial distortion is analyzed. A new linear approach which gives the solution through the linear algorithm is introduced, which the camera calibration is done with RAC. The nonlinear iterafive calculation processes is eliminated. The results show that the method is simple and hight accuracy.