Current Issue Cover
一种柔性密封条截面误差自动视觉测量方法(Chinagraph2018-P000153)

廖林,李建华(华东理工大学 信息科学与工程学院 计算机科学与工程系;华东理工大学 信息科学与工程学院 计算机科学与工程系 上海 #$NLjhli@ecusteducn)

摘 要
目的 在柔性密封条误差测量过程中,密封条容易弯曲且形变较大,直接匹配精度较低,测量误差大。针对此问题,本文提出了一种基于视觉的柔性密封条截面误差自动测量方法。方法 该方法通过两步图像轮廓配准来获取测量图段和设计图段之间的匹配关系,然后进行误差度量和质量检验。该方法第一步通过基于多分辨率的轮廓角点提取算法提取出密封条轮廓的角点,然后基于最小化均方误差的思想进行穷举搜索,计算初始配准结果,再使用线性回归进行微调进一步提高初始配准结果;第二步利用形状描述子进行局部轮廓配准,进一步获得两张轮廓图之间的精确局部配准结果;最终进行不同类型的误差定量计算和结果对比,主要测量的误差类型包括点偏移误差、点极限距离误差和角度位置误差等形位误差。结果 本文对密封条进行了逐步轮廓配准和多种误差测量,并在实际生产中进行了测试。实验结果证明,该系统配准结果好,测量精度高。该系统测量精度远高于密封条测量系统精度标准0.2 mm,且系统检测结果与实际人工检测结果完全一致,能有效促进柔性密封条自动化检测的发展。结论 本文提出了一种新的基于视觉的柔性密封条截面误差自动视觉测量方法,该系统具有良好的稳定性和可靠性,能有效进行柔性产品误差测量和质量检验。
关键词
Automatic Vision-Based Deviation Measurement Method for Cross Sections of Flexible Sealing Strips

Liao Lin,Li Jianhua(Department of Information Science and Engineering,East China University of Science and Technology)

Abstract
Objective Sealing strips play an important role in automotive industry. However, it is not easy to obtain accurate results in the measurement of sealing strips due to the large deformation of the complex contour of sealing strips. This paper proposes a novel automatic vision-based deviation measurement method for cross sections of flexible sealing strips. In the method, the matching relationship between the local contour of the captured image and the reference contour of the design drawing is computed by a two-stage image contour registration algorithm, and then the deviation calculation is performed to evaluate the quality of sealing strips. Method There are three steps in the method: the global registration of the contour of the captured image and the contour of the reference drawing, the local registration of the contours of the captured image and the reference drawing, and the calcula-tion of deviations. The global registration includes three substeps: the corner extraction, the initial registration and the fine-tuning. Firstly, the corners of the contours of the sealing strips for computer vision-based measurement are extracted by the mul-ti-resolution-based contour corner extraction algorithm. Secondly, based on the idea of minimizing mean square error, an exhaus-tive search method is performed on the corner sets of the contours of the captured image and the reference drawing to obtain the matched corner pairs and affine transformation matrix. Finally, to improve the accuracy of the initial registration, the corner pairs with larger position deviation than the average position deviation are removed from the matched corner sets and the remaining matched corners are fed into the linear regression equation to fine-tune the affine transformation matrix. On the basis of the global registration, the aim of the local registration of the local contours of the captured image and the reference drawing is to determine the corresponding relationships between the two local contours. The shape descriptors extracted from the two global contours in-clude shape representation and restrictions of the local contours, and the similarity of shape descriptors is used to obtain the op-timal result of local registration. After the global and local registration of the contours of the captured image and the reference drawing, the positional deviations of the sealing strips are measured according to the corresponding predefined instances of posi-tional tolerances. Here, the instances of positional tolerances are defined on the reference drawing and are used in the calculation of corresponding deviations. For all deviations, if the measured value is within the corresponding tolerance, the quality check passes. This paper mainly concentrates on the distance deviation and angular deviation, such as point offsetting deviation, point distance limitation deviation, angular positional deviation, etc. The point offsetting deviation refers to the offsetting distance from the original point defined on the contour of the reference drawing to the corresponding point on the contour of the captured image and the corresponding point is obtained by the similarity between two shape descriptors calculated in the previous local registra-tion. And the point distance limitation deviation refers to the maximum distance from the point on corresponding line segment of the measurement segment to the corresponding datum line on the contour of the captured image while the point distance limitation tolerance refers to the tolerable distance from the original point to the datum line defined in the reference drawing. For angular positional deviation, the intersection of the two perpendicular bisectors of the two tolerance line defined in the standard contour is first computed as the rotation center of the angular positional deviation. In measurement, the angular positional deviation is quantified as the value of the angle between the line segment from the barycenter of the measured local contour of the captured image to the rotation center of the angular positional deviation and the line segment from the barycenter of the standard local contour of the reference drawing to the rotation center of the angular positional deviation. Finally, based on the tolerances and deviations of the sealing strips, the quality of the products can be judged automatically. Result In this paper, the sealing strips are registered by a two-stage registration algorithm and a variety of deviations are measured between the local contour of the captured image and the contour of the reference drawing. The proposed method has been tested in the actual production process. And several types of sealing strips have been tested during the experiments while all captured images of the actual products have been rotated to increase the number of testing images. Finally, the experimental results show that the method achieves good stability and reliability and is invariant to the rotation of the position of the sealing strips. Besides, the experimental results are completely consistent with the manual testing results. Therefore, it shows that the system can effectively promote the development of automated testing for sealing strips. Conclusion This paper proposes a novel vision-based deviation measurement method for flexible sealing strips. The proposed method achieves good stability and reliability in the actual production process, as well as effectively performs deviation measurement and quality inspection of flexible products. The proposed method can accelerate the development of the automated quality inspection because the experiments have proven that the proposed method can measure the deviation of the sealing strips automatically.
Keywords
QQ在线


订阅号|日报