Visual inspection method for arc-shaped welding seam and adhesive tape

Abstract

The invention discloses a visual inspection method for an arc-shaped welding seam and adhesive tape. An arc-shaped morphology point cloud of an object to be detected is obtained along a straight line, and the arc-shaped morphology point cloud is converted into a linear morphology point cloud through the following steps of (1) determining a region of interest, moving a selection box, and marking a region with height information most similar to a teaching image as an evaluation region; 2) determining the positions of central framework points in the evaluation region, expanding on two sides of each central framework point at equal step length to obtain height values of corresponding points, and recording the height values as sampling points; 3) for the height value of each sampling point, giving plane coordinate values corresponding to each height value according to the following rules: the abscissa is equal to the offset between each sampling point and the corresponding central framework point; and the longitudinal coordinate is equal to the distance between the central framework point corresponding to each sampling point and the first central framework point. According to the method, the point cloud image of the arc-shaped welding seam / adhesive tape can be processed under the condition of collecting the image along the straight line, and the arc-shaped point cloud image is converted into the shape of the straight line so as to be compatible with a straight line morphology point cloud processing method. Image acquisition is simple, compatibility is good, and implementation is easy.

Description

technical field [0001] The invention relates to the technical field of three-dimensional visual detection, in particular to a visual detection method for arc-shaped welds and rubber strips. Background technique [0002] In the field of industrial manufacturing, the three-dimensional information of objects is crucial to the quality control of the production process. The three-dimensional surface measurement technology based on line structured light vision has the advantages of non-contact and high measurement accuracy, and automatic measurement and scanning can be realized through the cooperation of robots. The three-dimensional point cloud data of the surface of the measured object can be obtained, so as to provide a technical basis for such as glue inspection and welding seam inspection in the automobile production process, and it is more and more applied to the industrial manufacturing process. [0003] Usually, most of the welds and rubber strips on the surface of the wor...

AI Technical Summary

Problems solved by technology

[0004] 1) The robot needs to complete the scanning of the curved object by taking a circular arc trajectory. This method first converts the coordinates of the structured light plane to the coordinate system of the robot end through hand-eye calibration, and then reads the real-time pose of the end of the robot during the scanning process. Finally, according to The conversion relationship between the robot end coordinate system and the base coordinate system unifies the coordinates of the light plane to the base coordinate system, and realizes 3D reconstruction based on the real-time pose of the robot; Multiple coordinate system conversions, because there is a calibration error in the conversion between each coordinate system, this will introduce multiple errors;

[0005] 2) It is necessary to obtain the end pose of the robot in real time, and the underlying development of the robot controller is required, which is difficult to develop

The system is required to have high real-time performance, which increases the complexity of the system, and the communication delay itself will also introduce errors to the obtained real-time pose of the robot;

[0006] 3) When the measured object (rubber strip / weld) has a large degree of bending such as "C" or "S", or the size of the measured object itself is small, it is limited by the size of the sensor and the objects around the measured weld In the case of interference and other situations, the robot cannot adjust the appropriate trajectory, and it cannot guarantee that the outgoing light plane of the structured light sensor is always perpendicular to the extending direction of the adhesive strip / welding seam.

Images