Vision-based adaptive stereo measurement of pins on multi-type electrical connectors

Abstract

As a non-contact inspection approach, vision technology usually undertakes the task of positioning, measuring and defect identification in the field of industrial automation. However, traditional visual programs at a high price are often designed for only a single category of products. Furthermore, the quantitative measurement tasks in the industry usually require a rigorous visual environment as well as hardware equipment, which implies a lack of generalization. Hence, it is imperative to establish a robust approach to break the barriers of multi-type product inspection, while reducing both system complexity and costs. This paper proposed an adaptive approach that performs inspections of the pins’ position for multi-type connectors. A joint strategy of deep neural network and pattern matching based on prior knowledge registration is constructed to achieve rapid positioning of sub-elements arranged in the target. Then, a hierarchical extraction method is designed to analyze features with various appearances and improve the anti-interference of vision-based system. The 3D version of the registration algorithm is embedded into the framework to determine abnormal positions of spatial data without reference. The proposed algorithm demonstrates a successful inspection of a total of 33 types of connectors, significant measurement robustness and adaptivity to the target pose, imaging status and feature diversity.

An AR-Assisted Deep Learning-Based Approach for Automatic Inspection of Aviation Connectors

“…Meanwhile, compared to other existing industrial camera-based inspection > REPLACE THIS LINE WITH YOUR PAPER IDENTIFICATION NUMBER (DOUBLE-CLICK HERE TO EDIT) < 9 systems (Refs. [14][15][16] or robotic systems (Refs. 12-13), the deployed system has prominent advantages in terms of competitive price and powerful computation efficiency, as shown in Table IV.…”

“…To verify the position of pins both in height and in the 2D plane where they lie, a stereo vision system [15] was designed to measure the position of pins that are present in various shapes. Then, deep neural network and pattern matching based on prior knowledge registration were introduced to a 3D vision measurement platform, which can detect abnormal positions of pins for a total of 33 types of connectors [16].…”

Research on the examination technology of connector pin skewing according to Blob analysis*

“…The results are shown in table 12. In order to validate the superiority of the algorithm proposed in this paper in terms of accuracy and detection precision, we compared it with existing literature [18,19,27] to evaluate its performance. From table 12, it can be observed that compared to the first dataset (Group x), the accuracy of the algorithm proposed in this paper has improved by 1.58%.…”

A Review and Analysis of Automatic Optical Inspection and Quality Monitoring Methods in Electronics Industry

“…This method of acquiring image can reduce the time for the feature extraction process such as simple segmentation and thresholding approaches are enough to determine the features of the component. Zhao et al in [312] proposed a similar stereo vision system using two cameras to inspect the pins on multi-type electrical connectors of the components. Because each film capacitor has six surfaces to be detected, Yang et al in [299] used four image acquisition systems that are adjusted to detect the surface defects of capacitors.…”