Infrared image convolutional neural network super-resolution method based on visible light image enhancement

Abstract

The invention discloses an infrared image convolutional neural network super-resolution method based on visible light image enhancement. An infrared image and a visible light image of a scene are obtained through shooting of an infrared and visible light dual-resolution camera, an infrared-visible light image pair is formed, and a training set is obtained through processing; and the initialized convolutional neural network model is iteratively trained by using the training set until the number of iterations reaches a preset number of times and the convolutional neural network model is trained,and an infrared image shot by the infrared camera is input into the trained convolutional neural network model to obtain a super-resolution infrared image. According to the method, the information ofthe visible light image is utilized, the problem that the details of the infrared image are not rich in the super-resolution process is solved, the super-resolution infrared image has better detail expression ability, and the robustness of the convolutional neural network model is high.

Description

technical field [0001] The invention belongs to an image super-resolution method in the field of digital image processing, and relates to an image super-resolution processing method of a convolutional neural network model that uses visible light images to enhance image details. Background technique [0002] Infrared images provide a lot of valuable application information in many fields such as thermal analysis, video surveillance, medical diagnosis, remote sensing, etc. The main reasons for poor infrared image quality and resolution are blurring effects due to non-ideal optics and limited detector size. In general, infrared images are of poorer quality and have limited spatial resolution compared to visible light. To achieve high-precision thermal measurements, infrared detectors are housed in individual vacuum packages, a time-consuming and expensive process. For low-resolution infrared images, recovering details by addressing the non-directional ill-conditioned problem ...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the technical problems in the background technology, for infrared imaging systems, it is difficult to use efficient methods to obtain high-quality infrared images during the imaging process, and it is difficult to improve the resolution of infrared images through simple and effective methods. The details of infrared images are significantly improved, and the present invention adopts an image super-resolution processing method of a convolutional neural network model that uses visible light images to enhance image details

[0005] The present invention utilizes the information of the visible light image, solves the problem that the details of the infrared image are not rich in the super-resolution process, the infrared image after the super-resolution has better detail performance ability, and the robustness of the convolutional neural network model is strong

Images