机器视觉在物体位姿检测中的应用

Application of the Machine Vision in the Detection of Object Posture

论文旨在对物体位姿检测过程中应用机器视觉的实际效果进行分析。在进行实际验证过程中使用工业相机,从两个方位对目标图片进行全面采集,在相机进行标定的过程中,选择的方法是张正友的以2D平面靶标为基础的标定方法。并且在对目标区域进行测定的过程中,采用了目标图像,减去背景图像并与形态学运算进行结合的方法来实现初步定位。

The purpose of this paper is to analyze the actual effect of applying the machine vision in the process of object pose detection.In the process of carrying out the actual verification,the industrial camera is used,and the target picture is comprehensively collected from two directions,and during the calibration process of the camera,the method is a calibration method based on the 2D plane target of Zhang Zhengyou.And the method of combining the target image,the background image and the morphological operation is adopted to realize the preliminary positioning in the process of measuring the target area.