Feature point elimination method based on correlation

Abstract

The invention discloses a correlation-based feature point elimination method. The method is used for visually guiding an assembling/grabbing process and pre-acquiring standard coordinates and theoretical coordinates; acquiring measurement coordinates, and utilizing a first projection error; judging whether wrong feature points need to be removed or not, wherein the method for searching the wrong feature points comprises the following steps: sorting the plurality of feature points; removing the ith feature point in sequence according to the sequence, calculating a standard reprojection error array corresponding to the ith feature point, and measuring the reprojection error array; calculating a correlation coefficient between the standard reprojection error array corresponding to the ith feature point and the measurement reprojection error array; finding an abnormal point from a plurality of correlation coefficients, and then finding an error feature point from the abnormal point; The method is advantaged in that two arrays obtained through the method are high in relevancy, and amplitudes of all elements in the set are close; therefore, accuracy of the remaining feature points is guaranteed, and assembly/grabbing accuracy is improved.

Description

technical field [0001] The invention relates to the field of visual guidance, in particular to a feature point elimination method based on correlation. Background technique [0002] Vision guidance usually uses visual sensors to collect workpiece images and compares them with the previously taught standard workpiece images to analyze the deviation between the coordinates of the two measuring points, compensate for the trajectory of the grasping / assembly robot, and then realize the intelligent assembly process; in this process In this case, since the position of the workpiece to be assembled / grabbed cannot be completely coincident with that of the standard workpiece when it is placed at the detection position, and there are also processing errors between different workpieces, if the workpiece to be assembled / grabbed is placed at the detection position The deviation on the surface is large or the deformation at a certain measuring point position is large during the processing ...

AI Technical Summary

Problems solved by technology

[0002]Vision guidance usually uses vision sensors to collect workpiece images and compares them with the previously taught standard workpiece images to analyze the deviation between the coordinates of the two measuring points and compensate for the gripping parts / Assembly robot trajectory, and then realize the intelligent assembly process; in this process, because the placement position of the workpiece to be assembled / grabbed cannot be completely overlapped with the standard workpiece when it is placed at the detection position, and there are also processing errors between different workpieces , at this time, if the deviation of the workpiece to be assembled / grabbed at the detection position is large or the deformation at a certain measuring point position during the processing itself is large, when obtaining the measured coordinates of the feature points of the workpiece to be assembled / grabbed There may be errors in the calculation of the measured coordinates of individual feature points, and the mismatching of feature points, which will affect the subsequent deviation calculation and cause the failure of the robot to grasp / assemble

Images