Super-resolution reestablishment method for microwave remote sensing image based on SRCNN (Super-Resolution Convolutional Neural Network)

Abstract

The invention discloses a super-resolution reestablishment method for a microwave remote sensing image based on an SRCNN (Super-Resolution Convolutional Neural Network) and belongs to the technology of microwave remote sensing and detection. The method comprises the steps of firstly simulating a microwave remote sensing flow, and forwardly producing a high-resolution microwave remote sensing imageTB and a low-resolution microwave remote sensing image TA to form a data set; then preprocessing the data set to generate an SRCNN training set; constructing a five-layer depth convolutional neural network based on the SRCNN training set; and finally inputting the to-be-processed low-resolution microwave remote sensing image to the constructed five-layer depth convolutional neural network, wherein the output of a fourth-layer of the depth convolutional neural network is the reestablished high-resolution microwave remote sensing image. With the super-resolution reestablishment method for the microwave remote sensing image based on the SRCNN, the calculation complexity in reestablishment can be effectively reduced, an accurate antenna pattern is not needed, the method is a novel microwave remote sensing image reestablishment method, and a brightness temperature image of an original scene can be efficiently reestablished in real time.

Description

technical field [0001] The invention belongs to the technical field of microwave remote sensing and detection, and more specifically relates to a method for super-resolution reconstruction of microwave remote sensing images based on SRCNN. Background technique [0002] Microwave remote sensing is an extremely important remote sensing technology, which has the characteristics of all-day and all-weather. Compared with visible light and infrared remote sensing, it has a deeper penetration ability. Satellite microwave remote sensing has many unique advantages such as wide coverage of time and space, large amount of detection information, and high detection frequency. With the in-depth research on the application of spaceborne radiometers in China in recent years, the role of spaceborne microwave radiometers in satellite microwave remote sensing is becoming more and more important. Spaceborne microwave radiometers can be used to detect various elements of the atmospheric environ...

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 method for super-resolution reconstruction of microwave remote sensing images based on SRCNN. The current method is complex and needs to know the technical problems of the specific antenna pattern

Images