Monitoring scene-oriented image super-resolution method and device and storage medium

Abstract

The invention relates to a monitoring scene-oriented image super-resolution method and device, and a storage medium, and belongs to the technical field of image processing. The method comprises the steps of inputting a target low-resolution image into a pre-trained feature mapping network to obtain high-dimensional features located in a target feature space; inputting the target low-resolution image and the high-dimensional features into a pre-trained image reconstruction network to obtain a high-resolution image; the problems that a low-resolution image synthesized through an existing image super-resolution method based on deep learning is different from a real low-resolution image, and generalization is poor can be solved. The feature mapping network learns a feature mapping relationshipin advance; and the image reconstruction network is trained by combining the output result obtained after the feature mapping network, so that the domain difference between the synthesized low-resolution image and the real low-resolution image is further reduced, and the image reconstruction effect is improved.

Description

technical field [0001] The present application relates to a monitoring scene-oriented image super-resolution method, device and storage medium, belonging to the technical field of image processing. Background technique [0002] Image Super Resolution (Image Super Resolution) technology refers to the technology of restoring low-resolution images to high-resolution images. [0003] With the development of Convolutional Neural Network (CNN) and Generative Adversarial Network (GAN) in the field of pixel-level image processing, learning-based image super-resolution methods emerge in an endless stream. For example: the method of image super-resolution using Super Resolution Convolutional Network (Super Resolution Convolutional Network, SRCNN); or, the method of image super-resolution using Super Resolution Generative Adversarial Network (Super Resolution Generative Adversarial Network, SRGAN); or , using the (Enhanced Deep Residual Networks for Single Image Super-Resolution, EDSR...

AI Technical Summary

Problems solved by technology

[0006] This application provides an image super-resolution method, device and storage medium for monitoring scenes, which can solve the difference between the low-resolution image synthesized by the existing deep learning-based image super-resolution method and the real low-resolution image , the problem of poor generalization

Images