Method for improving trueness of marine scene simulation picture

Abstract

The invention discloses a method for improving the trueness of a marine scene simulation picture, and the method comprises the steps: carrying out the foreground and background segmentation of a simulation picture, carrying out the style migration through employing a conventional method and a deep learning method CycleGAN, and achieving the conversion from the simulation picture to a real marine picture. The background adopts a Poisson fusion and color conversion method, a real sea surface photo is used as a sub-image, a simulation image is used as a mother image, Poisson fusion is carried out, then Reinhard color migration is carried out to obtain a vivid background, the foreground adopts a CycleGAN algorithm, and each layer of convolution of a generator is subjected to point multiplication with a mask to extract a foreground part; and the splicing with the input layer at the last layer is performed to reserve the background information of the original image so as to generate a complete sea surface image with a real style. Simulation software is used for constructing a marine scene, the style of a real picture is converted after a simulation picture is obtained, the method is usedfor neural network training, and the problem of sample scarcity is solved.

Description

technical field [0001] The invention relates to a method for improving the authenticity of sea scene simulation pictures, and relates to the fields of sample style transfer, deep learning and neural network. Background technique [0002] With the gradual maturity of image simulation technology, it is becoming easier and easier to use computers to simulate some target scenes, and the simulation effect is becoming more and more realistic. Through some common simulation software, such as: 3Dmax, Unity, UE4, Blender, etc. Simulation pictures of various scenes can be obtained easily. In deep learning tasks, samples in some special scenarios are often not easy to obtain. For example, when performing tasks such as sea target recognition, the number of photos that can be obtained through the Internet of Things is limited and the number of samples from various shooting angles is unbalanced. Shooting and constructing data sets will cost a lot of manpower and material resources. There...

AI Technical Summary

Problems solved by technology

[0003]Aiming at the above-mentioned prior art, the technical problem to be solved by the present invention is to provide a method for improving the authenticity of sea scene simulation pictures, which can use simulation software to construct sea scenes, After obtaining the simulated picture, it is converted into the style of the real picture, so as to be used for the training of the neural network and solve the problem of scarce samples

Images