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

Single image dehazing method and device based on depth information to separate sky regions

A technology of sky area and depth information, which is applied in image enhancement, image analysis, image data processing, etc., can solve problems such as sky distortion and obvious halo at the junction of the sky, so as to reduce running time, reduce the number of clusters, good recovery effect

Active Publication Date: 2018-04-03
BEIHANG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a single image defogging method and device for separating sky regions based on depth information, with the purpose of solving the problems of sky distortion and obvious halo at the junction of the sky that cannot be completely solved in the existing defogging methods

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 and device based on depth information to separate sky regions
  • Single image dehazing method and device based on depth information to separate sky regions
  • Single image dehazing method and device based on depth information to separate sky regions

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] Refer to attached figure 1 , a kind of image defogging method based on sky separation provided by the present invention mainly comprises the following steps:

[0032] Step S1, superpixel image segmentation: using the superpixel segmentation method of SLIC to perform over-segmentation preprocessing on the original foggy image I to obtain an over-segmented image;

[0033] Step S2, sky separation: extract the depth information of each region from the over-segmented image obtained in step S1, merge the adjacent regions with the closest depth information, detect the sky region by color and texture conditions, and realize the separation of sky and non-sky regions ;

[0034] Step S3. Estimate the atmospheric light value and transmittance distribution map: Estimate the atmospheric light value A with the average value of the sky area, use the dark channel prior theory to estimate the transmittance of the sky and non-sky areas respectively, and form the transmittance distributio...

Embodiment 2

[0062] Refer to attached Figure 4 , an image defogging device provided by the present invention mainly includes: an image over-segmentation module 41 , a sky separation module 42 , a parameter calculation module 43 , and a restoration module 44 . The specific functions of the above modules are:

[0063] Image over-segmentation module 41 is used for utilizing SLIC superpixel segmentation method to carry out over-segmentation preprocessing to foggy image, obtains over-segmentation image;

[0064]The sky separation module 42 is used to extract the depth information of each region for the obtained over-segmented image, merge the adjacent regions closest to the depth information, and detect the sky region by the color and texture conditions, so as to realize the separation of sky and non-sky;

[0065] The parameter calculation module 43 is used to estimate the atmospheric light value with the average value of the sky area, and utilize the dark channel prior theory to estimate the...

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 present invention provides a single image defogging method and device for separating the sky region based on depth information, which mainly includes the following steps: (1) using the SLIC superpixel segmentation method to perform over-segmentation preprocessing on the foggy image containing the sky to obtain the over-segmented image Segment the image; (2) extract the depth information of the region, merge the regions of the over-segmented image, and separate the sky and non-sky; (3) estimate the atmospheric light value with the average value of the sky region, and then calculate the transmission of the sky and non-sky region respectively Ratio, forming the transmittance distribution map of the entire image; (4) Restore the fog-free image from the atmospheric light value and transmittance distribution map. Combining superpixel segmentation and region merging technology, the present invention can accurately extract the boundary line between the sky and the scene, obtain an accurate and complete sky region, not only obtain reliable atmospheric light values, but also avoid sky distortion and reduce the depth of field at the sky boundary. The halo phenomenon caused by sudden changes can realize image defogging.

Description

technical field [0001] The invention belongs to the field of computer vision and digital image processing, and relates to a single image defogging method and device for separating sky regions based on depth information. Background technique [0002] With the development of computer vision, outdoor vision systems are being widely used in various fields, such as road monitoring, security monitoring, etc. However, in severe weather such as fog and haze, the imaging quality of the outdoor vision system is seriously degraded, which affects the identification of effective information in the image, and causes the vision system to fail to operate normally. Therefore, it is very necessary to perform defogging processing on the foggy images collected in hazy weather so that the outdoor vision system can adapt to various weather conditions. At present, image defogging techniques are mainly divided into two categories: non-model-based image enhancement and model-based image defogging. ...

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): G06T5/00G06T7/11G06T7/194
Inventor 王睿李蕊
Owner BEIHANG UNIV