Method for calculating the pose of a threaded target object based on point cloud data

Abstract

The invention discloses a method for calculating the pose of a threaded target based on point cloud data, and the method comprises the following steps: 1) recording a plane where the threaded target intersects with other objects when the threaded target is fixed as a first plane, and obtaining the point cloud data; Fitting a plane equation of the first plane to obtain a normal vector; 2) carryingout cylinder fitting by utilizing the point cloud data of the thread covering part to obtain an axis Lc of the cylinder; 3) respectively calculating the distance from each point in the point cloud data of the thread covering part to the axis Lc; screening data, and recording the data as a data packet I; 4) performing cylinder fitting by using data in the data packet I to obtain an axis L'of the data packet I, and 5) calculating an included angle between the axis L 'and a specific plane, i.e., the included angle between the threaded target and the specific plane. The method can calculate the pose data of the threaded target after acquiring the point cloud data of the threaded target, and is accurate, real-time and suitable for online detection.

Description

technical field [0001] The invention relates to the fields of industrial manufacturing and construction, in particular to a method for calculating the pose of a threaded object based on point cloud data. Background technique [0002] In the fields of industrial manufacturing and construction, there are many scenarios that require the use of threaded objects for connection, transmission or sealing. The pose of a threaded object has a major impact on the subsequent process. Currently, there are two methods for pose detection of a threaded object: manual detection and line structured light detection. Manual detection is carried out with tools such as break gauges, dial gauges, steel rulers, wedge-shaped feeler gauges, and iron rulers. The measurement accuracy and efficiency are low, and online measurement cannot be realized. For structured light detection, the American Perceptron company has developed a multi-line structured light sensor for stud pose detection. It uses line s...

AI Technical Summary

Problems solved by technology

Manual detection is carried out with tools such as break gauge, dial gauge, steel ruler, wedge-shaped feeler gauge, and iron ruler. The measurement accuracy and efficiency are low, and online measurement cannot be realized.

For structured light detection, the American Perceptron company has developed a multi-line structured light sensor for stud pose detection. It uses line structured light to reconstruct the stud to analyze the stud pose, but the surface of the stud is more complicated. , and has high reflective properties, which will inevitably affect the accuracy of the center extraction of light strips. In addition, it takes a long time to use line lasers, which cannot meet the real-time requirements of online measurement

Images