论文部分内容阅读
为提高三坐标测量机零件位姿识别的效率和准确率,提出了一种基于图像质心偏移的立体匹配新方法。将CCD摄像机安装在三坐标测量机的Z轴上,利用三坐标测量机的精确平移特性,构成单摄像机立体视觉系统,在两个不同位置获取被测零件的实时图像,对其进行处理得到图像质心,将图像质心的偏移距离作为约束条件完成立体匹配。该方法避开了极线约束、灰度约束等复杂约束条件,实验表明该方法可以达到较高的匹配精度,实验件的匹配时间为1.818s。
In order to improve the efficiency and accuracy of pose recognition of CMM components, a new stereo matching method based on image centroid migration is proposed. The CCD camera is mounted on the Z-axis of the CMM. Using the precise translational characteristics of the CMM, a single-camera stereoscopic vision system is constructed to acquire real-time images of the tested components at two different positions and process the images Centroid, the image centroid offset distance as a constraint to complete the three-dimensional matching. The method avoids the complex constraints such as polar line constraints and gray level constraints. Experiments show that the method can achieve a high matching accuracy, and the matching time of the experimental pieces is 1.818s.