Generative adversarial network image defogging method fusing feature pyramid

A feature pyramid and feature fusion technology, applied in the field of image processing, can solve problems affecting image effects, loss of image information, and affecting the speed of image defogging, etc., to achieve the effect of reducing training parameters, improving quality and efficiency, and increasing speed

Inactive Publication Date: 2020-10-02
NANJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the deficiencies of the prior art, the object of the present invention is to provide a method for image defogging using generative confrontation network fusion of feature pyramids to solve the problem of information loss in images processed by the image enhancement defogging method in the prior art and the use of image restoration If the image processed by the defogging method is improperly selected, it will affect the effect of the restored image, and the technical problem of using the defogging algorithm based on deep learning will affect the speed of image defogging

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
  • Generative adversarial network image defogging method fusing feature pyramid
  • Generative adversarial network image defogging method fusing feature pyramid
  • Generative adversarial network image defogging method fusing feature pyramid

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.

[0037] The feature pyramid is an efficient feature extraction method. It uses the feature expression of multiple latitudes from low to high inside the Convolutional Neural Networks (CNN) model to generate a multi-dimensional feature expression of the image in a single image view. Compared with the image pyramid, it greatly reduces the calculation and memory requirements of the model, and at the same time can effectively empower the conventional CNN model and generate a feature map with stronger expressive ability. Therefore, the feature extraction ability of the network model can be improved, and the requirements for memory and calculation can be reduced, making the image defogging task more hig...

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 a generative adversarial network image defogging method based on a fusion feature pyramid in the technical field of image processing. The technical problems that in the prior art, information of an image processed through an image enhancement defogging method is lost, if parameters of the image processed through an image restoration defogging method are improperly selected,the effect of the restored image can be influenced, and the image defogging speed is influenced through a defogging algorithm based on deep learning are solved. The method comprises the following steps: inputting a foggy image into a pre-trained generative adversarial network, and obtaining a fogless image corresponding to the foggy image, wherein the generator network of the generative adversarial network is fused with a feature pyramid.

Description

technical field [0001] The invention relates to a generative confrontation network image defogging method based on fusion of feature pyramids, which belongs to the technical field of image processing. Background technique [0002] In foggy weather conditions, there are many suspended particles and water droplets in the air. These particles will absorb and scatter light, resulting in color distortion and a decrease in contrast of the image parameters obtained by the image acquisition system, resulting in loss of details and reducing the image quality on the target. The use value of computer vision applications such as identification, security monitoring, and intelligent transportation. Therefore, it is of great practical significance to study and improve the image defogging technology for the normal work of the computer vision system in the haze environment. [0003] At present, the mainstream image defogging technology can be roughly divided into three categories: one is th...

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): G06T5/00G06T5/50G06N3/04G06N3/08
CPCG06T5/003G06T5/50G06N3/084G06T2207/20081G06T2207/20084G06T2207/20221G06N3/048G06N3/045Y02A90/10
Inventor 张登银曹雪杰董江伟周诗琪赵莎莎
Owner NANJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap