A method for detecting the movement position and posture of the end of the hybrid automobile electrophoretic coating conveying mechanism

Abstract

The invention discloses a method for detecting the movement position and posture of the terminal end of a hybrid automobile electrophoretic coating conveying mechanism. First, the image information of the hybrid automobile electrophoretic coating conveying mechanism is obtained in real time through a binocular camera. Then weighted filtering is performed based on the spatial geometric distance of pixels and the similarity of pixels, and non-maximum suppression and hysteresis thresholding are used to suppress error edges, and the method of cluster analysis is used to extract the terminal connections of complex mechanisms in the parameter space after space mapping The feature points of the rod. Design a moving mask along the main direction of the feature points, describe the feature points in the mask area based on the discrete Gaussian-Hermit moments, and further calculate the similarity criterion between feature vectors based on the Euclidean distance, and filter the feature point pairs to obtain high-precision The characteristic point pairs at the end of the hybrid automobile electrophoretic coating conveying mechanism. Finally, based on the built binocular vision model and the extracted feature point pairs, the high-precision three-dimensional pose parameters of the end of the mechanism are obtained after coordinate transformation.

Description

technical field [0001] The invention relates to a pose detection system based on machine vision, in particular to a binocular vision-based detection method for the end motion pose of a hybrid automobile electrophoretic coating conveying mechanism. Background technique [0002] In the control of the hybrid automobile electrophoretic coating conveying mechanism, the terminal motion pose is an important parameter reflecting the motion state of the mechanism. Accurately measuring the end motion pose of the mechanism can effectively avoid the error caused by the kinematic model solution. And it can further realize the high-performance full-closed-loop motion control of the hybrid automobile electrophoretic coating conveying mechanism based on the terminal pose. Compared with other detection methods, machine vision uses one or more cameras to image target objects from different angles, and the collected image information is richer. At the same time, based on digital image process...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the problems that there are few image feature points of the connecting rod at the end of the mechanism during the operation of the hybrid automobile electrophoretic coating conveying mechanism, and it is easy to be blocked by other components and difficult to detect accurately, the present invention proposes a hybrid automobile electrophoretic coating conveying mechanism end movement position pose detection method

Firstly, in order to solve the problem that the traditional binocular vision algorithm is difficult to accurately extract the feature points of the end of the mechanism, which leads to the low accuracy of the detection of the motion pose of the end of the mechanism, weighted filtering is performed based on the geometric distance of the pixel point and the similarity of the pixel point, and non-maximum suppression is used. and hysteresis thresholding to suppress false edges to reduce the impact of non-edge points on feature extraction

Then, for the discontinuity of regional boundaries caused by light interference, blurred boundaries between mechanism components, and occlusion, a method of cluster analysis in the parameter space after space mapping is proposed to solve the problem of feature points of connecting rods at the end of complex mechanisms in the image space. Difficult-to-extract problems in

Images