Real-time super-resolution reconstruction method and system based on historical feature fusion

Abstract

The invention discloses a real-time super-resolution reconstruction method and system based on historical feature fusion. The method comprises the following steps: constructing a network model; the construction of the network model comprises the following steps: carrying out linear feature extraction on a current frame to obtain a linear feature graph of the current frame; performing nonlinear feature extraction and feature fusion on the current frame and the historical frame to obtain a nonlinear feature map after feature fusion; wherein the historical frame is the previous N frames of the current frame, and N is a natural number; the nonlinear feature extraction of the historical frame is carried out based on the image after the motion compensation of the historical frame; and obtaining a super-resolution reconstruction image of the current frame based on the nonlinear feature map after feature fusion and the linear feature map of the current frame. According to the method, a series of problems of poor real-time performance, detail time sequence breakage, false color, poor universality and the like existing in the current super-resolution technology are solved, and the real-time performance and the image quality are both considered.

Description

technical field [0001] The invention belongs to the technical field of image processing, and more specifically relates to a real-time super-resolution reconstruction method and system based on historical feature fusion. Background technique [0002] Super-resolution technology is a technical means of transforming low-resolution images into high-resolution images, and it is gradually applied in video, games and other scenes. Traditional super-resolution techniques include bilinear, bicubic interpolation methods, etc. Although these super-resolution methods represented by interpolation methods do not require high computing power, their essence is to fill the local area with color, and the effect is not very good. ideal. [0003] Since the SRCNN network was proposed, neural networks have been introduced to solve the super-resolution problem. Then, the super-resolution neural network for images and the super-resolution neural network for video have been continuously proposed, ...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the above defects or improvement needs of the prior art, the present invention provides a real-time super-resolution reconstruction method and system based on historical feature fusion, which uses current frame features as the basis and accurately combines historical frame motion conditions to perform feature compensation, solving the problem of The current super-resolution technology has a series of problems such as poor real-time performance, broken detail timing, false color, and poor versatility, taking into account both real-time and image quality

Images