# US 2020/0394767 A1 · Method for rapidly dehazing underground pipeline image based on dark channel prior

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2020/0394767 A1
- Document ID: US20200394767A1
- Status: Published application
- Kind: A1
- Application number: 16/901,093
- Filed: 2020-06-15
- Published: 2020-12-17
- Earliest claimed: 2019-06-17
- Assignees: China University of Mining and Technology, Beijing
- Applicants: China University of Mining & Technology, Beijing
- Inventors: Ce Li; Feng Yang; Tan He
- Web page: https://patentgrep.com/patent/US20200394767A1

## CPC

- G06T 5/73: Deblurring; Sharpening
- G06T 5/20: using local operators
- G06T 5/90: Dynamic range modification of images or parts thereof
- G06T 5/92: based on global image properties
- G06T 2207/10024: Color image
- G06T 2207/30184: Infrastructure
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

The present invention proposes a method for rapidly dehazing an underground pipeline image based on dark channel prior (DCP). The method includes: preprocessing a hazy underground pipeline image to obtain a dark channel image corresponding to the hazy image; average-filtering the obtained dark channel image to estimate an image transmittance; compensating an offset value for an average filtering result to obtain a rough estimate of the transmittance; using a pixel value of the original image and an average-filtered image to estimate a global atmospheric light value; and using a physical restoration model to restore a dehazed image. The method of the present invention realizes the timeliness of the algorithm while ensuring the dehazing effect, and is suitable for scientific fields such as video monitoring of underground pipeline environment and identification of underground pipeline defects.

## Claims

### Claim 1

A method for rapidly dehazing an underground pipeline image based on dark channel prior (DCP), comprising the following steps:
step (1): preprocessing an original hazy underground pipeline image to obtain a dark channel image corresponding to the hazy image, and using the obtained dark channel image to eliminate a factor affecting an atmospheric light value in the hazy image, wherein the corresponding dark channel image is obtained by solving a minimum value of three color channels of the original hazy underground pipeline image:
M

(
x
)
=
min
c
∈
{
r
,
g
,
b
}

(
H
c

(
x
)
)
(
1
)
wherein, H represents the original hazy underground pipeline image; Hc represents a color channel of H; {r,g,b} represents red, green and blue channels; Hc(x) represents a value of a color channel of a single pixel in the original hazy underground pipeline image; M(x) is a dark channel image of the original hazy underground pipeline image H;
step (2): average-filtering the corresponding dark channel image M(x) of the original hazy underground pipeline image to estimate a transmittance by:
average
S
a

(
1
-
M

(
x
)
A
0
)
=
1
-
M
ave

(
x
)
A
0
=
1
-
∑
y
∈
Ω

(
x
)

M

(
y
)
A
0

S
a
2
(
2
)
wherein, A0 is a minimum of the atmospheric light value in the three color channels; averageSa(⋅) represents average filtering performed by using an Sa window; Sa represents the size of the average filtering window; M(x) is the dark channel image of the original hazy underground pipeline image H(x); Mave(x) represents average filtering performed by using an Sa window on the dark channel image M(x) corresponding to the original hazy underground pipeline image; Ω(x) is an Sa×Sa neighborhood of a spatial coordinate x; M(y) is a pixel in the Sa×Sa neighborhood of the spatial coordinate x in the dark channel image corresponding to the original hazy underground pipeline image;
step (3): compensating an offset value for an average filtering result to obtain a rough estimate of the transmittance by:
i

%

(
x
)
=
1
-
δ

M
ave

(
x
)
A
0
(
3
)
δ=ρmav (4)
wherein, t%(ox) is the rough estimate of the transmittance; ρ is an adjustable parameter, 0≤ρ≤1/mav; mav is an average of all pixels in the dark channel image M(x);
in order to prevent a dehazed image from appearing too dark or bright overall, after an offset value is compensated, an upper limit of δ is set to 0.9, and δ is further expressed as:
δ=min(ρmav,0.9) (5)
step (4): expressing the transmittance t(x) according to Formulas (3), (4) and (5) as follows:
t

(
x
)
=
max

(
1
-
min

(
ρ


m
av
,
0.9
)

M
ave

(
x
)
A
0
,
1
-
M

(
x
)
A
0
)
(
6
)
wherein, it is derived from a physical model of hazy image degradation that L(x)=A(1−t(x)), A being the global atmospheric light value, L(x) being an ambient light value, and t(x) being the transmittance; according to Formula (6), the ambient light value L(x) is expressed by:
L(x)=min(min(ρmav,0.9)Mave(x),M(x)) (7)
step (5): using a pixel value of the original hazy underground pipeline image and an average-filtered image to estimate the global atmospheric light value A by:
A
=
ɛ


max
(
max
c
∈
{
r
,
g
,
b
}

(
H
c

(
x
)
)
)
+
(
1
-
ɛ
)


max

(
M
ave

(
x
)
)
(
8
)
wherein, ε is an empirical constant, which is 0.5; and
step (6): using a physical restoration model to restore the dehazed underground pipeline image by:
F

(
x
)
=
H

(
x
)
-
L

(
x
)
1
-
L

(
x
)
A
(
9
)
wherein, F(x) is the dehazed underground pipeline image.
