Non-uniform fog removal method for remote sensing image
The invention discloses a non-uniform fog removal method for a remote sensing image. The method comprises the following steps: constructing a fog removal network of a remote sensing image, and carrying out supervised learning; obtaining and synthesizing a foggy remote sensing image data set and a fo...
Saved in:
Main Authors | , , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
17.05.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention discloses a non-uniform fog removal method for a remote sensing image. The method comprises the following steps: constructing a fog removal network of a remote sensing image, and carrying out supervised learning; obtaining and synthesizing a foggy remote sensing image data set and a fog-free label image; inputting the synthesized foggy remote sensing image data set into a remote sensing image fog removal network for processing, and outputting a synthesized defogged remote sensing image data set; calculating a loss value between the synthesized defogged remote sensing image data set and the fog-free label image; reversely transmitting the loss value to a remote sensing image fog removal network for optimization to obtain an optimized remote sensing image fog removal network; and obtaining a real foggy remote sensing image and inputting the real foggy remote sensing image into the optimized remote sensing image fog removal network for processing to obtain a real defogged remote sensing image. Acco |
---|---|
Bibliography: | Application Number: CN202210137039 |