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

Method for defogging foggy image in real scene based on fog migration and feature aggregation

A technology of real scenes and images, applied in the field of image processing, can solve problems such as poor generalization performance, and achieve a good effect of defogging

Active Publication Date: 2022-03-01
KUNMING UNIV OF SCI & TECH
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a method for defogging foggy images in real scenes based on fog migration and feature aggregation. This method is obtained on foggy images in real scenes. To a certain extent, it overcomes the problem of poor generalization performance on the real foggy image domain after training the defogging model with synthetic public data sets.

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
  • Method for defogging foggy image in real scene based on fog migration and feature aggregation
  • Method for defogging foggy image in real scene based on fog migration and feature aggregation
  • Method for defogging foggy image in real scene based on fog migration and feature aggregation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] Embodiment 1: as figure 1 As shown, a foggy image defogging method based on fog migration and feature aggregation in a real scene, the specific steps of the method include:

[0049] Step1 pre-trains the transmission map estimation network: pre-trains the transmission map estimation network through the indoor foggy image and the corresponding transmission map. In the pre-training process of the transmission map estimation network, we select the indoor synthetic foggy image and its corresponding transmission map in the public dataset RESIDE dataset as the data set pre-training network, so that the network has the ability to estimate the transmission map from the foggy image. ability, and then save the training model parameters. When the training set in Step 1 is indoor synthesis of foggy images and corresponding transmission maps in the RESIDE dataset, the transmission maps are used as labels to train the transmission map estimation network so that it has the ability to ...

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 defogging method for a foggy image in a real scene based on fog migration and feature aggregation, and belongs to the field of image processing. The invention designs a method for realizing image defogging by migrating fog in a foggy image in a real scene to a clear image to generate a data set and then utilizing a defogging network based on feature aggregation. In a fog migration process, a multi-level feature block identification method is designed to migrate fog in a real scene to a clear image to generate a foggy image training data set, and the image in the data set has a style similar to that of a foggy image in the real foggy scene and distribution characteristics of fog in the foggy image. In addition, extraction features are supplemented in a fine-grained detail information and semantic information aggregation mode so as to realize image defogging. According to the method, a good defogging effect is achieved on the foggy image in a real scene, and the problem that a defogging model trained by a synthetic data set is poor in generalization performance on the real foggy image is greatly solved.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a fog image defogging method in a real scene based on fog migration and feature aggregation. Background technique [0002] Image defogging is an image processing technique used to improve image quality. High-quality image quality can play a good auxiliary role in high-level computer vision tasks such as image recognition and classification, semantic segmentation, and object detection. In image defogging, researchers consider the imaging principle of fog—the main reason for image quality degradation is that the light reflected by the target object is absorbed and scattered by the suspended particles in the atmosphere, which attenuates the light reflected by the object. Ambient light such as sunlight is scattered by the scattering medium in the atmosphere to form background light, and the intensity of this part of background light is greater than the light reflected by the target ob...

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): G06T5/00G06T7/00G06V10/80G06V10/776G06V10/82G06V10/774G06K9/62
CPCG06T7/0002G06T2207/20081G06T2207/20084G06T2207/30168G06F18/217G06F18/253G06F18/214G06T5/73
Inventor 张亚飞高继蕊李华锋谢明鸿
Owner KUNMING UNIV OF SCI & TECH
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