Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Road scene defogging method based on conditional generative adversarial network

A condition generation and road technology, applied in the field of image processing, can solve the problems of rare, missing data, etc., achieve good robustness, good defogging effect, and reduce image processing time

Inactive Publication Date: 2019-07-09
SHANGHAI UNIV OF ENG SCI
View PDF3 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the lack of data, such deep learning-based methods are rare

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
  • Road scene defogging method based on conditional generative adversarial network
  • Road scene defogging method based on conditional generative adversarial network
  • Road scene defogging method based on conditional generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0029] Below in conjunction with accompanying drawing, further describe the present invention by example, but do not limit the scope of the present invention in any way.

[0030] The present invention takes the RESIDE data set as an example, and the specific operations are as follows:

[0031] Step 1: Use the RESIDE dataset, which contains training sets and test sets;

[0032] Step 2: Send the foggy image x in the training set as input to the generator G to generate G(x), that is, the fog-free image

[0033] Step 3: Convert the generated fog-free image to Send it to the discriminator D to judge whether the picture is true or false;

[0034] Step 4: After 200 iterations, the optimal generation model is obtained;

[0035] Step 5: Apply the obtained optimal generation model to real foggy images for dehazing processing.

[0036] In this implementation, the generator is composed of three parts: encoder, converter and decoder; the encoder is composed of 3 layers of convolutio...

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 relates to a road scene defogging method based on a conditional generative adversarial network. The road scene defogging method comprises the following steps: 1) constructing a trainingset and a test set by adopting a RESIDE data set; 2) taking the foggy picture x in the training set as the input of a generator G and generating G (x), namely a fogless picture; 3) sending the generated fogless picture to a discriminator D to judge whether the picture is true or false; 4) obtaining an optimal generation model after iteration setting for rounds, and 5) applying the obtained optimalgeneration model to a real foggy image for defogging. Compared with the prior art, the method has the advantages of good robustness, short processing time and the like.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a road scene defogging method based on a conditional generation confrontation network. Background technique [0002] With the development of computer vision and its application in the field of traffic and security monitoring, image defogging has become an important research field of computer vision. Under severe weather conditions with low visibility caused by fog and haze, the pictures collected by the camera are affected by suspended particles in the atmosphere (such as fog, haze, etc.), resulting in poor picture quality, and it is difficult to distinguish the characteristics of objects in the picture, and even Affects image quality in applications such as outdoor surveillance, object recognition, and traffic navigation. Therefore, the definition of foggy image features has important research significance. [0003] At present, there are two main categories of image 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): G06T7/90G06T5/00G06N3/04G06K9/62
CPCG06T7/90G06N3/045G06F18/214G06T5/00
Inventor 张娟李智高永彬方志军
Owner SHANGHAI UNIV OF ENG SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com