The train will inevitably be damaged in the long-term running process, and there is a big security risk, so it is very necessary to inspect the train regularly. The wheel is an important part of the train, and the wear and defects of the wheel tread are directly related to the safety of the train, so the wheel tread testing is the key link of the train testing. In this paper, a three-dimensional profile reconstruction method of wheel tread based on moire profilometry (MP) is proposed. The digital grating patterns generated by computer will be projected onto the surface of the wheel tread, and the moire fringe patterns of the wheel tread can be obtained by frequency domain filtering. By processing moire fringe patterns, the wrapped phase will be acquired. Finally, the reconstruction of wheel tread profile can be realized after phase unwrapping, which provides a new method for wheel tread testing. At the same time, in the frequency domain filtering part of moire profilometry, the effects of different filtering algorithms on the reconstruction results are compared and analyzed in simulations and experiments, which proves the validity and feasibility of the measurement method in this paper.
In this paper, a deep convolution neural network for image registration using homography transformation is proposed to improve the speed and accuracy of image registration. The four-corner homography parameterization is carried out by randomly clipping and perturbing the image block, and then the mapping from one image to another is completed to form the homography image registration dataset. In this network architecture, the homography matrix is obtained by returning the mean square error to the corner variables of the local region. In the preprocessing stage, the image is equalized by the histogram and the feature is magnified. The trained homography matrix is used for the affine transformation of the registered image to verify the effectiveness of the model. We test the dataset of homography image registration and experiment on various noises and various image enhancement effects. We also compare several traditional algorithms. The results prove that the accuracy of the proposed model is state-of-art. The processing speed of a single image is only 0.28 seconds, which has strong noise adaptability and the best performance.
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.