Clamping error during automatic welding of axle housing will lead to weld deviation. To that end, a method for axle housing weld seam localization based on monocular vision is proposed in this paper. Firstly, a method of extracting weld seam centerline based on template matching and iterated least squares fitting is proposed according to the grayscale of axle housing image. Then, the end points of weld seam are searched through the gray feature of axle housing on the weld seam centerline. Finally, the mapping relationship between image coordinate system and robot coordinate system is established by calibration. According to the deviation between actual position and standard position of weld under image coordinate system, the actual three-dimensional coordinate of weld in robot coordinate system is found by particle swarm optimization algorithm. The experimental results show that the maximum error of the weld seam endpoints obtained by this method in the x, y axis is less than 0.5mm, and the maximum error in the z axis is less than 0.9mm, which meets the requirements of axle housing automatic welding. This method only uses one monocular camera, and has a low cost while ensuring the positioning accuracy through calibration and optimization algorithms.
A localization method based on monocular vision is proposed to solve the problem of poor flexibility, high cost and unstable accuracy of glue dispensing robot. The method includes the workpiece image feature extraction method based on distribution model and the optimized PNP algorithm based on depth calibration, which can locate the threedimensional coordinates of the workpiece and further generate the gluing track. Firstly, the layout and local coordinates of feature points are determined according to the workpiece model and gluing process, and the feature distribution model and template set are established. Then the image coordinates of feature points are extracted step by step by using workpiece contour features and image gray features, combining multi template and multi angle matching with shape detection, and using acceleration strategies such as image pyramid and angle layer by layer subdivision. Finally, the PNP algorithm is optimized in the Z direction through the depth calibration method to realize the high-precision positioning of the workpiece. The localization experiments of various types of reducer shells under different imaging environments were carried out. The experimental results show that the method has better feature extraction effect for workpieces with complex structure in chaotic environment, and the maximum localization error in one direction is within ± 0.5 mm, which meets the application needs of robot glue positioning. The method can detect the offset of 6 degrees of freedom of the target workpiece at the same time, which has a wider application than the general 2D visual localization method. It can also be used for the localization of parts in other scenes.
To reduce accuracy lost in the calibration process for high-precision optical systems using interferometry, an approach is proposed to detect checkerboard corners based on the level set evolution principle. Compared with existing corner detection methods, no image gradients are required for segmentation of checkerboard patterns. It has the capability of doing corner detection for the images acquired under more complex imaging environments, like underwater, low-contrast, blurred, and heavily distorted images. In addition, no iteration is required in the level set evolution procedure, and a fast speed is achieved. In this implementation, the grids that consist of a checkerboard pattern are first found as level set curves by segmenting the checkerboard pattern image. Then, noting that checkers might be recognized as quadrangles, the four corners of a quadrangle can be located by checking the varying of points of its boundary in slope. Alternatively, they also could be located according to the maximal distance at specific orientations between a point and the center of the closed curve. Finally, several experiment results are presented to validate the proposed approach and to demonstrate its robustness and correctness.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.