The invention belongs to the technical field of
deep learning, and particularly discloses an ultra-precision full-field displacement measurement method and
system based on a convolutional variational auto-
encoder. Comprising the following steps: acquiring a video when a to-be-detected structure is subjected to vibration deformation, and selecting a picture of a deformation position to construct a
data set; training a
deep learning model of the convolutional variational auto-
encoder based on the
data set; reconstructing the gray value of the original image by using the trained
deep learning model to obtain a gray value containing infinitesimal displacement information; and carrying out displacement calculation on the reconstructed image by utilizing an
optical flow method, and realizing ultra-precision displacement calculation on the to-be-measured structure according to gray value conversion. According to the method, the problem that the infinitesimal displacement smaller than the
sensitivity limit is difficult to measure is solved, the problem that the to-be-measured structure is blocked and cannot be measured is solved by utilizing the characteristics of the generative deep learning model, and the basic data precision of displacement measurement is remarkably improved.