Aerial photography image target sample generation method based on style migration

The invention discloses an aerial photography image target sample generation method based on style migration. The method comprises the following steps: S1, selecting representative images of a plurality of ground object scenes in an aerial photography image, and cutting the representative images; s2, randomly selecting the aerial photography image in S1, and setting the aerial photography image asa background image of a virtual scene; s3, preprocessing the three-dimensional model; s4, importing the three-dimensional model into a virtual scene; s5, outputting a synthesized sample image; s6, outputting a label file; s7, constructing a training data set of a style migration algorithm; s8, constructing a cyclic consistent generative adversarial network; and S9, inferring to obtain a vivid synthetic sample image by using the trained style migration network model, and corresponding the label data obtained in S6 to the vivid synthetic sample image to form a vivid synthetic sample. The invention provides an efficient