A method, device, and storage medium for absolute detection of rotation and translation of surface shapes of irregularly shaped optical elements based on deep learning

Abstract

The present invention relates to a method, device and storage medium for absolute detection of rotation and translation of the surface shape of an irregularly shaped optical element based on deep learning, including: (1) extracting the amount of rotation and translation of the irregularly shaped optical element based on a convolutional neural network : First use the interferometer to detect the relative detection of three positions on the surface shape of the irregular optical element, and then obtain the rotation and translation of the irregular optical element through the convolutional neural network; (2) the rotation and translation The absolute surface shape of the irregular shape optical element is obtained by substituting the wave surface recovery algorithm of the irregular shape optical element. For the first time, the invention combines the absolute detection method of the rotation and translation of the surface shape of the irregular shape optical element with the deep learning algorithm. By binarizing the image, it is possible to accurately predict the pose of the components in the image, that is, the prediction of the amount of rotation and translation.

Description

technical field [0001] The invention belongs to the fields of precision measurement technology and deep learning technology, and in particular relates to a method for absolute detection of rotation and translation of surface shapes of high-precision irregular-shaped optical elements based on deep learning. Background technique [0002] With the development of optical technology, irregular shaped optical elements have been widely used in various optical systems due to their high flexibility and freedom. Modern optical systems have higher and higher requirements for the processing precision of irregular-shaped optical components. The processing precision of optical components largely depends on the surface shape detection technology, so the requirements for detection precision are also getting higher and higher. [0003] The method of measuring the surface shape of the interferometer belongs to relative detection, and the accuracy of the measurement results is subject to the s...

AI Technical Summary

Problems solved by technology

[0008] In order to solve the problems of high cost, long adjustment time, complicated process, and low efficiency of the precision translation and rotation stage used in the detection of optical components by the rotation-translation absolute detection method, the present invention provides a deep learning-based method that does not require strict and precise adjustment. Absolute Detection Method for Rotation and Translation of Irregular Optical Components

Images