Research On Vision Measuring Technology Of Shaft Diameters

In the field of precision testing technology,machine vision measurement technology is a new technology,the technology can achieve the size of parts measurement,visual tracking of the target and the movement analysis of mechanical device and other functions.The "human eye" is replaced by the machine vision measurement technology,sees the image and understands the image,extracts the digital image information characteristic acquired by the camera,and finally completes the visual inspection.Shaft parts are the most widely used parts of various types of mechanical devices.With the exploration and progress of technology,the precision and the running speed of mechanical devices are becoming more and more demanding.In the process of machining,it is particularly important to accurately measure the diameter of the shaft parts.In this paper,according to the geometric characteristics of the shaft parts and the optical imaging process,a shaft diameter measurement method is proposed.Firstly,the imaging model of the camera is established according to the principle of small hole imaging,this paper analyzes the camera calibration technology.Based on Zhang Zhengyou's plane calibration method,two radial distortions and two tangential distortions are considered in the distortion model to correct the distortion of the optical lens and improve the calibration accuracy of the internal parameters of the camera and the external parameters.To improve the accuracy of the camera parameters,through the camera calibration experiment to determine the appropriate number of corner detection and back light lighting conditions.Then,in order to improve the detection accuracy of image measurement,it is very important to obtain the sub-pixel edge position of the measured object from the image.In this paper,several common sub-pixel edge detection methods are analyzed theoretically,including gray-scale moment method,spatial moment method,zernike orthogonal moment method,gaussian fitting method,hyperbolic tangent fitting method,gradient interpolation method and three-point interpolation method.Finally,the error of the actual measurement of the dimension is taken as the evaluation criterion of the sub-pixel edge detection accuracy.By means of the measurement experiment,the gradient interpolation method with good stability and high detection precision is determined as the sub-pixel edge detection method of shaft diameter measurement.Next,based on the imaging process of the shaft part under the camera,the mathematical model of the shaft diameter measurement is established,and the error caused by the parallelism of the axis and the image plane is reduced.And then the unknown parameters in the mathematical model of the shaft diameter measurement are calibrated.Finally,based on the practicality and convenience of measuring the shaft diameter,a calibration coefficient method based on the true axis diameter and the pixel diameter ratio of the target axis is proposed.Finally,the accuracy of the shaft diameter measurement method and the practicability of the calibration coefficient method are verified by the shaft diameter measurement experiment.The measurement results of the two shaft diameter measurement methods are compared and the error factors influencing the measurement accuracy are analyzed.Improve the measurement accuracy to determine the direction.For the development of machine vision measurement technology,the research work of this paper has some engineering application significance.