基于双目立体视觉的标定技术及应用

为提升双目立体视觉装置的准确度和精度，提出基于双目立体视觉的标定技术。针对双目立体视觉中两个相机的特点，采用圆形标志阵列标定板为图像源，通过对图像预处理，以径向误差做约束条件，根据圆的几何关系和最小二乘法综合提取特征点的算法获取图像标识点坐标并求取单应性矩阵，最后推导得到理想的外参和内参，从而获得双目立体视觉装置准确的参数。实验结果为该装置对待测数据的获取提供了精确的数据基础和可靠的矫正条件，进而提升了双目立体视觉装置的准确度和精度。

Calibration Technology and Application Based on Binocular Stereo Vision

In order to improve the accuracy and precision of binocular stereo vision device，a calibrationtechnology based on binocular stereo vision is proposed． According to the characteristics of two cameras inbinocular stereo vision，using the calibration plate of circular symbol array as the image source，through thepreprocessing of the image，under the constraint of radial error，the method of extracting feature points by usinggeometric relation of circle and least square data processing is used to obtain coordinate of identification point andhomography matrix of image． The ideal external and internal parameters are inferred． The accurate parameters ofbinocular stereo vision device are obtained． This test provides accurate data basis and reliable correctionconditions for the device to acquire measured data．