Structured light profilometry (SLP) is now widely utilized in noncontact three-dimensional (3D) reconstruction due to its convenience in dynamic measurements. Compared with classic fringe projection profilometries, multiple deep neural networks are proposed to demodulate or unwrap the fringe phase, and these networks utilize convolution layers to extract local features while omitting global characteristics. In this paper, we propose SwinConvUNet, a deep neural network for single-shot SLP that can extract local and global features simultaneously. In the network structure design, convolution layers are applied in shallow layers to extract local features, whereas transformer layers extract global features in deep layers, and an improved loss function by combining gradient-based structural similarity is employed to improve reconstruction details. The experimental results demonstrate that SwinConvUNet is more effective than the U-net model at decreasing learnable parameters while maintaining 3D reconstruction accuracy.
This paper proposed a method of detection to the grinding wheel layer thickness based on computer vision. A camera is used to capture images of grinding wheel layer on the whole circle. Forward lighting and back lighting are used to enables a clear image to be acquired. Image processing is then executed on the images captured, which consists of image preprocessing, binarization and subpixel subdivision. The aim of binarization is to help the location of a chord and the corresponding ring width. After subpixel subdivision, the thickness of the grinding layer can be calculated finally. Compared with methods usually used to detect grinding wheel wear, method in this paper can directly and quickly get the information of thickness. Also, the eccentric error and the error of pixel equivalent are discussed in this paper.
In the center measuring device consisting of a plurality of laser triangular displacement sensors (LDS) for coaxiality measurement of shaft, it fits the center coordinate of the shaft by obtaining the coordinates of the outer contour, this poses a higher requirement for the relative position calibration accuracy of the multi-LDS. Aiming at the positional relationship between multi-LDS, the CMM is leaded into the calibration of the center measuring device. Randomly moves a standard column and reading the length values of multi-LDS, combined with the known center coordinates of the column from CMM, to establish the over-determined nonlinear equations, the angle and starting position of the laser beam of each LDS in the measuring device are calculated. The experiment result indicates that measuring uncertainty of the system is 30 μm, this proved the validity and feasibility of the multi-LDS center measuring device in the use of coaxiality measurement of shaft. As a result, it is found that the proposed calibration method is accuracy to the multi-LDS center measuring device and can be implemented easily.
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.