Unlock instant, AI-driven research and patent intelligence for your innovation.

Image defogging method and generator network

A generator, image technology, applied in biological neural network model, image enhancement, image data processing and other directions, can solve the problems of increasing image visibility, blurred images, etc., to achieve good dehazing effect, good visual effect, design effect of science

Pending Publication Date: 2021-06-11
SHANGHAI MARITIME UNIVERSITY
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to address the deficiencies in the prior art, and propose a dark channel attention optimization cycle generation confrontation network image defogging method and generator network, the method can remove the haze in the image, increase the image visibility, effectively Solve the problem of blurry images in foggy conditions

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image defogging method and generator network
  • Image defogging method and generator network
  • Image defogging method and generator network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0085]The technical solution of the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments, and the described specific embodiments are only for explaining the present invention, and are not intended to limit the present invention.

[0086] The concrete steps of a kind of image defogging method proposed by the present invention are as follows:

[0087] First establish the dark channel attention subnetwork, generators G1, G2, and discriminator D X Global, D Y Global, D X Partial, D Y local office figure 1 shown.

[0088] where the generator G network model such as figure 2 As shown, including dark channel attention subnetwork, encoder structure, intermediate conversion layer structure and decoder structure;

[0089] The dark channel attention subnetwork contains twenty-four convolutional layers, each layer contains a set of 64 3×3×1 convolution kernels, the stride is 2, the padding is 1, a BatchNo...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an image defogging method of a dark channel attention optimization cyclic generative adversarial network. The method comprises the following steps: establishing a dark channel attention sub-network, establishing generators G1 and G2, and establishing discriminators DX global, DX local, DY global and DY local; calculating a dark channel of a foggy image, inputting the foggy image into the generator G1, inputting the dark channel into a dark channel attention sub-network to obtain an attention map, weighting the middle output of the generator, and finally obtaining a defogged image; adopting a global discriminator to discriminate the defogged image, cutting the defogged image into four small blocks randomly, and adopting a local discriminator to discriminate the defogged image. Haze in the image can be removed, the visual performance of the image is improved, and the problem that the image is blurred under the foggy weather condition is effectively solved.

Description

technical field [0001] The invention relates to the technical field of single image defogging, specifically, an image defogging method and a generator network are designed. Background technique [0002] In the information age, image processing technology is widely used in face recognition, gait tracking, road monitoring, automatic driving, target detection, drone aerial photography, and space exploration. However, the performance of image information processing systems is extremely vulnerable to climate change. influences. The existence of smog is due to the presence of a large amount of dust, water vapor, and large-diameter suspended particles in the air. The scattering effect of these suspended particles reduces the contrast, color distortion, and blurred details of the image captured by the camera equipment. A lot of noise is made to outdoor images, which significantly degrades outdoor images. These degradation phenomena directly affect subsequent tasks such as target d...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T5/50G06T5/00G06N3/04G06N3/08
CPCG06T5/50G06N3/08G06N3/048G06N3/045G06T5/73Y02A90/10
Inventor 李朝锋莫耀宗杨勇生
Owner SHANGHAI MARITIME UNIVERSITY