内螺纹螺距视觉测量方法的研究

发布时间：2018-05-29 03:46

本文选题：机器视觉 + 内螺纹　；参考：《长春工业大学》2017年硕士论文

【摘要】：内螺纹是一种常用的机械联接结构,工业生产中为了满足旋合性和联接强度要求,对内螺纹尺寸进行了高度标准化。目前国内内螺纹参数测量主要采用机械检测方法完成,检测速度慢、测量精度低。针对传统内螺纹螺距机械检测方法中存在的问题,本文提出了一种基于机器视觉技术的非接触测量方法。本文建立工业内窥镜摄像机成像模型,采用Tsai两步标定法对所采集的内螺纹图像进行了标定,并对成像过程中的径向畸变进行校正。针对采集到的螺纹表面图像边缘特征弱、纹理复杂、对比度不明显、难以直接提取图像中的牙顶区域信息的问题,采用SIFT模板匹配算法对螺纹图像中的相邻两条牙顶区域图像分别进行了提取,实验结果表明该算法对牙顶图像匹配定位速度快、精度高。针对牙顶图像的中轴线提取问题,利用二值化、中值滤波等方法去除图像噪点,采用数学形态学的膨胀算法填充牙顶图像区域中的孔洞,使用骨架提取算法成功提取了同一图像区域中相邻牙顶图像的中轴线信息。结合摄像机标定结果,实现了内螺纹螺距的视觉测量。实验证明,本文提出的测量方法具有高效、高精度、自动化、无损伤等特点,能够满足实际生产中工业检测的效率、精度要求。
[Abstract]:Internal thread is a kind of commonly used mechanical connection structure. In order to meet the requirements of rotation and connection strength, the dimension of internal thread is highly standardized in industrial production. At present, the measurement of internal thread parameters in China is mainly accomplished by mechanical testing method, which is slow in speed and low in accuracy. Aiming at the problems existing in the traditional mechanical inspection method of internal thread pitch, a non-contact measurement method based on machine vision technology is proposed in this paper. In this paper, the imaging model of industrial endoscope camera is established, and the internal thread image is calibrated by Tsai two-step calibration method, and the radial distortion in the imaging process is corrected. In order to solve the problem that the edge feature of the collected thread surface image is weak, the texture is complex and the contrast is not obvious, it is difficult to directly extract the information of the top of the tooth in the image. The SIFT template matching algorithm is used to extract the two adjacent top images from the thread images. The experimental results show that the algorithm is fast and accurate in matching the top images. Aiming at the problem of extracting the central axis of the tooth top image, the image noise is removed by binary method and median filtering method. The expansion algorithm of mathematical morphology is used to fill the hole in the top tooth image region. The skeleton extraction algorithm is used to extract the information of the central axis of the adjacent top image in the same image region. Combined with the result of camera calibration, the vision measurement of inner thread pitch is realized. The experimental results show that the method proposed in this paper has the characteristics of high efficiency, high precision, automation and no damage, and can meet the requirements of industrial inspection efficiency and precision in actual production.
【学位授予单位】：长春工业大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：TG85;TP391.41

【参考文献】