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

Single Image Dehazing Method Based on Sky Region Segmentation

A sky area, segmentation processing technology, applied in the field of image processing, can solve problems such as poor halo effect improvement, color distortion, etc., and achieve excellent defogging ability, soft color, and noise reduction effects

Active Publication Date: 2018-12-11
XIDIAN UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a method of defogging suitable for haze images containing sky areas, which can overcome the color distortion problem caused by the existing dark channel algorithm in the sky area, and the poor improvement of the halo effect by the existing optimization algorithms The problem

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
  • Single Image Dehazing Method Based on Sky Region Segmentation
  • Single Image Dehazing Method Based on Sky Region Segmentation
  • Single Image Dehazing Method Based on Sky Region Segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] The basic idea of ​​the method of the present invention is: obtain the preliminary estimated transmittance image according to the dark channel prior theory; respectively use the median filter and the guide filter to optimize the preliminary estimate transmittance image; To determine whether the corresponding point is located in the halo area, for a point located in the halo area, replace the transmittance optimized by the guided filter with the transmittance optimized by the median filter; use Canny edge calculation The edge information of the original image is sub-extracted, and the binary template of the sky area is obtained through closed operation and misjudgment area correction; the transmittance of the sky area that has been guided and filtered is extracted by using the template, and the transmittance of the sky area is analyzed. Linear expansion processing, and then combine the transmittance of the sky area processed by non-linear expansion with the transmittance ...

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 single image defogging method based on sky region segmentation processing, comprising the steps of: calculating the preliminary estimation transmittance of an input image according to a dark channel prior theory, optimizing the preliminary estimation transmittance respectively through median filtering and guide filtering, combining two results, and replacing the transmittance optimized by halo region guide filtering with the transmittance optimized by median filtering; employing a Canny boundary operator to calculate the boundary images of original images, correcting miscalculated regions, dividing the images into sky and ground regions to be used as binary template to extract the sky region transmittance after guide filtering optimization, and performing non-linear expansion processing on the extracted sky region transmittance; combining the transmittance respectively obtained through the two steps, and performing guide filtering smooth processing; and utilizing obtained optimization transmittance to perform filtering processing. The single image defogging method can better improve halo effects and sky region color distortion, and greatly improve defogging effects of fog-degraded images.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method for defogging haze images, and is especially suitable for haze images including sky areas. Background technique [0002] In modern society, a large number of systems rely on imaging equipment to obtain relevant information of targets, such as traffic, surveillance, and remote sensing imaging. In recent years, large-scale smog weather has occurred frequently in northern my country, and the quality of images acquired by outdoor imaging equipment has deteriorated in smog weather, causing related systems to fail to work normally. The impact of haze on imaging equipment is mainly caused by the scattering effect of haze particles, and the light reflected from objects deviates from the transmission path during the propagation process and does not participate in imaging. On the other hand, other light in the environment will also be scattered by the haze pa...

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 Patents(China)
IPC IPC(8): G06T5/00G06T5/20G06T5/30G06T5/50G06T7/13G06T7/10
CPCG06T5/002G06T5/003G06T5/20G06T5/30G06T5/50G06T2207/20032G06T2207/20221
Inventor 李良超张向东曹运华弓树宏莫荣华
Owner XIDIAN UNIV
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