Infrared image super-resolution reconstruction method and system and electronic equipment

Abstract

The invention provides an infrared image super-resolution reconstruction method and system and electronic equipment, and the method comprises the steps: collecting high-resolution infrared images of aplurality of scenes, and carrying out the preprocessing of the high-resolution infrared images; extracting a feature map of the high-resolution infrared image through a pre-trained ResNet network, constructing a generator network, capturing potential distribution of an infrared image data sample through the generator network, and generating a new high-resolution infrared image sample; inputting the actually acquired high-resolution infrared image and the high-resolution infrared image generated by the generator network into a discriminator network, and calculating and judging the probabilityof actually acquiring the image or generating the image through the discriminator network; and alternately training the generator network and the discriminator network to obtain an optimized and adjusted infrared image super-resolution reconstruction model. By means of the scheme, the problems that an existing super-resolution reconstruction method is low in imaging quality and difficult to applywidely are solved, the quality of reconstructed images can be improved, the requirement for collected images is lowered, and wide application is facilitated.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method, system and electronic equipment for infrared image super-resolution reconstruction. Background technique [0002] Infrared imaging is widely used in the fields of video surveillance, medical detection and industrial detection due to its anti-interference and strong recognition ability. In the current infrared imaging applications, most of them use small-array infrared detectors to collect images, and the infrared images collected by small-area infrared imaging devices have low resolution and cannot meet the growing application requirements. Using a large area array infrared detector can effectively improve the resolution of infrared images, but it is often expensive and difficult to be widely used. [0003] For the processing of low-resolution infrared images, image quality can also be improved through software algorithms. Image-based super-resolution reconstruction com...

AI Technical Summary

Problems solved by technology

[0005] In view of this, an embodiment of the present invention provides a method and system for infrared image super-resolution reconstruction to solve the problems of poor image quality and difficulty in wide application of existing super-resolution image reconstruction

Images