CN105989583B - A kind of image defogging method - Google Patents
A kind of image defogging method Download PDFInfo
- Publication number
- CN105989583B CN105989583B CN201610569218.8A CN201610569218A CN105989583B CN 105989583 B CN105989583 B CN 105989583B CN 201610569218 A CN201610569218 A CN 201610569218A CN 105989583 B CN105989583 B CN 105989583B
- Authority
- CN
- China
- Prior art keywords
- image
- value
- transmissivity
- max
- defogging
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 16
- 230000014509 gene expression Effects 0.000 claims description 6
- 230000000717 retained effect Effects 0.000 claims description 3
- 230000008030 elimination Effects 0.000 abstract description 6
- 238000003379 elimination reaction Methods 0.000 abstract description 6
- 239000003595 mist Substances 0.000 abstract description 6
- 230000000694 effects Effects 0.000 abstract description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000004438 eyesight Effects 0.000 description 3
- 239000003086 colorant Substances 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 230000007850 degeneration Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a kind of image defogging methods, this method replaces soft pick figure method using new transmissivity estimation algorithm, transmissivity is acquired by the gain intervention of the primary display channels minimum component of foggy image, it can be under the premise of avoiding halation and fast effect, approximate dark channel image intensity is quickly acquired, to improve the real-time of algorithm, and air light value is estimated using quaternary tree close classification, so that the precision of air light value improves, defogging processing is carried out finally by transmissivity and the more images of air light value.The present invention improves the real-time of defogging and the fidelity of mist elimination image.
Description
Technical field
The invention belongs to Digital Image Processing and technical field of machine vision, more particularly to a kind of image defogging method.
Background technology
With the development of science and technology with the progress of living standards of the people, more and more visions have been used in real life
System, such as：Monitoring system, intelligent transportation system etc., human life quality and demand are gradually increased, these application systems and the mankind
It lives closely related, direct image in human lives.
The reduction of air quality and the reduction of visibility cause prodigious shadow to people’s lives and industrial expansion
It rings.Since light is absorbed and is scattered, the picture shot under bad weather outdoors by turbid media so that the strength reduction of light,
The light intensity that optical sensor receives is caused to generate change, the fidelity for eventually leading to color declines, and there are serious cross-colors
With offset and the reduction of picture contrast, image detail information is lost, and clarity is inadequate, and the identification of pictorial information is significantly
It reduces.In addition, most of automatic system, it is strongly dependent on the definition of input picture, and the image of degeneration can cause automatically
System cisco unity malfunction influences and limits the work such as highway vision monitoring, intelligent navigation, remote sensing monitoring.
Therefore, it has broad application prospects to the processing of the defogging of foggy image, can be applied to underwater photograph technical, takes photo by plane, family
Outer monitoring even medical image etc., the image and video handled by defogging is more valuable, is conducive to many image understandings
With computer vision using (such as aerial image), image classification, image/video retrieval, remote sensing and video analysis and identification, people is given
Life bring many facilities.In image processing field, image defogging starts to walk relatively late.Domestic and foreign scholars carry at present
The method of the image defogging gone out is not also especially perfect, it would be highly desirable to improve, specifically how improve the real-time of defogging processing
Property and fidelity are the key that solve the problems, such as defogging.
Invention content
In order to solve the technical issues of above-mentioned background technology proposes, the present invention is intended to provide a kind of image defogging method, is adopted
With the computational methods of improved transmissivity and air light value, the real-time of defogging and the precision of mist elimination image are improved.
In order to achieve the above technical purposes, the technical scheme is that：
A kind of image defogging method, includes the following steps：
(1) transmissivity of foggy image is calculated：
T (x, y)=(1-Im(x,y))+gρ (1)
In formula (1), t (x, y) is transmissivity, and (x, y) indicates pixel coordinate, and ρ is calibration factor, and g is gain constant：
In formula (2), | Im| and | d | it is I respectivelymWith the sum of all pixels of d, corresponding ImAnd d：
D (x, y)=Im(x,y)-Id(x,y) (4)
In formula (3), IcIndicate the Color Channel of mist elimination image；
In formula (4),Ω (x, y) indicates rectangular centered on (x, y)
Region, min expressions are minimized；
(2) air light value for using quaternary tree close classification estimation foggy image, is as follows：
(a) foggy image is divided into several equal-sized rectangular sub blocks；
(b) average pixel value for calculating each rectangular sub blocks, retains the maximum rectangular sub blocks of average pixel value, and by the square
The average pixel value of shape sub-block is denoted as max pixel value Amax；
If (c) max pixel value AmaxIt is smaller than preset pixel threshold a, and max pixel value AmaxCorresponding rectangular sub blocks
Size is more than or equal to preset minimum window size, then return to step (a), further divides rectangular sub blocks, otherwise enter step
(d)；
(d) image is transformed into YCbCr space from rgb space, and corresponding to the rectangular sub blocks finally retained, selects the square
The maximum value of shape sub-block luminance component is as air light value Ac；
(3) air light value that the transmissivity and step (2) obtained according to step (1) obtains carries out defogging processing to image：
In formula (5), J indicates defogging treated image, and I is foggy image, t0For transmissivity threshold value, max expressions take most
Big value.
Further, in step (1), the value range of calibration factor ρ is [0.8,1].
Further, the value of calibration factor ρ is 0.9.
Further, in step (3), transmissivity threshold value t0Value range be [0.05,0.15].
Further, transmissivity threshold value t0Value be 0.1.
The advantageous effect brought using above-mentioned technical proposal：
The present invention replaces soft pick figure method using new transmissivity estimation algorithm, passes through compared in original dark algorithm
The gain intervention of the primary display channels minimum component of foggy image acquires transmissivity, can be before avoiding halation and fast effect
It puts, quickly acquires approximate dark channel image intensity, to improve the real-time of algorithm, and estimated greatly using quaternary tree close classification
Gas light value so that the precision of air light value improves, to achieve the effect that real-time is good and fidelity is high image defogging.
Description of the drawings
Fig. 1 is the basic flow chart of the present invention.
Fig. 2 is the flow chart that air light value is calculated in the present invention.
Specific implementation mode
Below with reference to attached drawing, technical scheme of the present invention is described in detail.
As shown in Figure 1, a kind of image defogging method, includes the following steps：
Step 1, the transmissivity for calculating foggy image：
T (x, y)=(1-Im(x,y))+gρ (1)
In formula (1), t (x, y) is transmissivity, and (x, y) indicates pixel coordinate, and ρ is calibration factor, and the value of ρ usually exists
In [0.8,1], it is gain constant that the present embodiment, which can enable ρ=0.9, g,：
In formula (2), | Im| and | d | it is I respectivelymWith the sum of all pixels of d, corresponding ImAnd d：
D (x, y)=Im(x,y)-Id(x,y) (4)
In formula (3), IcIndicate the Color Channel of mist elimination image；
In formula (4),Ω (x, y) indicates rectangular centered on (x, y)
Region, min expressions are minimized.
Step 2, the air light value that foggy image is estimated using quaternary tree close classification, specific steps are as shown in Figure 2：
(a) foggy image is divided into several equal-sized rectangular sub blocks；
(b) average pixel value for calculating each rectangular sub blocks, retains the maximum rectangular sub blocks of average pixel value, and by the square
The average pixel value of shape sub-block is denoted as max pixel value Amax；
If (c) max pixel value AmaxIt is smaller than preset pixel threshold a, and max pixel value AmaxCorresponding rectangular sub blocks
Size is more than or equal to preset minimum window size, then return to step (a), further divides rectangular sub blocks, otherwise enter step
(d)；
(d) image is transformed into YCbCr space from rgb space, and corresponding to the rectangular sub blocks finally retained, selects the square
The maximum value of shape sub-block luminance component is as air light value Ac。
The air light value that step 3, the transmissivity obtained according to step 1 and step 2 obtain carries out defogging processing to image：
In formula (5), J indicates that defogging treated image, I are foggy image, and max expressions are maximized, t0For transmissivity
Threshold value, t0Value range be [0.05,0.15], the present embodiment can enable t0=0.1, for limiting transmissivity t (x, y), due to
As t (x, y) → 0, J (x, y) t (x, y) can also level off to 0 so that mist elimination image includes noise, to avoid the hair of such case
It is raw, t is set0To improve the quality of mist elimination image.
Above example is merely illustrative of the invention's technical idea, and protection scope of the present invention cannot be limited with this, every
According to technological thought proposed by the present invention, any change done on the basis of technical solution each falls within the scope of the present invention
Within.
Claims (5)
1. a kind of image defogging method, which is characterized in that include the following steps：
(1) transmissivity of foggy image is calculated：
T (x, y)=(1-Im(x,y))+gρ (1)
In formula (1), t (x, y) is transmissivity, and (x, y) indicates pixel coordinate, and ρ is calibration factor, and g is gain constant：
In formula (2), | Im| and | d | it is I respectivelymWith the sum of all pixels of d, corresponding ImAnd d：
D (x, y)=Im(x,y)-Id(x,y) (4)
In formula (3), IcIndicate the Color Channel of input picture；
In formula (4),Ω (x, y) indicates the square region centered on (x, y),
Min expressions are minimized；
(2) air light value for using quaternary tree close classification estimation foggy image, is as follows：
(a) foggy image is divided into several equal-sized rectangular sub blocks；
(b) average pixel value for calculating each rectangular sub blocks retains the maximum rectangular sub blocks of average pixel value, and the rectangle is sub
The average pixel value of block is denoted as max pixel value Amax；
If (c) max pixel value AmaxIt is smaller than preset pixel threshold a, and max pixel value AmaxThe size of corresponding rectangular sub blocks
More than or equal to preset minimum window size, then return to step (a), further divides rectangular sub blocks, otherwise enters step (d)；
(d) image is transformed into YCbCr space from rgb space, and corresponding to the rectangular sub blocks finally retained, selects the rectangle
The maximum value of Block Brightness component is as air light value Ac；
(3) air light value that the transmissivity and step (2) obtained according to step (1) obtains carries out defogging processing to image：
In formula (5), J indicates defogging treated image, and I is foggy image, t0For transmissivity threshold value, max expressions are maximized.
2. a kind of image defogging method according to claim 1, it is characterised in that：In step (1), calibration factor ρ's takes
Value range is [0.8,1].
3. a kind of image defogging method according to claim 2, it is characterised in that：The value of calibration factor ρ is 0.9.
4. a kind of image defogging method according to claim 1, it is characterised in that：In step (3), transmissivity threshold value t0's
Value range is [0.05,0.15].
5. a kind of image defogging method according to claim 4, it is characterised in that：Transmissivity threshold value t0Value be 0.1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610569218.8A CN105989583B (en) | 2016-07-19 | 2016-07-19 | A kind of image defogging method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610569218.8A CN105989583B (en) | 2016-07-19 | 2016-07-19 | A kind of image defogging method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105989583A CN105989583A (en) | 2016-10-05 |
| CN105989583B true CN105989583B (en) | 2018-07-24 |
Family
ID=57044532
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610569218.8A Expired - Fee Related CN105989583B (en) | 2016-07-19 | 2016-07-19 | A kind of image defogging method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105989583B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106846260B (en) * | 2016-12-21 | 2019-06-07 | 常熟理工学院 | Video defogging method in a kind of computer |
| CN107316284B (en) * | 2017-07-19 | 2019-01-08 | 山东财经大学 | Image defogging method and device under intense light source |
| CN108765337B (en) * | 2018-05-28 | 2021-06-15 | 青岛大学 | Single color image defogging processing method based on dark channel prior and non-local MTV model |
| CN112083716B (en) * | 2019-06-13 | 2024-07-12 | 天翼云科技有限公司 | Navigation method, device and system based on machine vision |
| CN112949389A (en) * | 2021-01-28 | 2021-06-11 | 西北工业大学 | Haze image target detection method based on improved target detection network |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104252698A (en) * | 2014-06-25 | 2014-12-31 | 西南科技大学 | Semi-inverse method-based rapid single image dehazing algorithm |
-
2016
- 2016-07-19 CN CN201610569218.8A patent/CN105989583B/en not_active Expired - Fee Related
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104252698A (en) * | 2014-06-25 | 2014-12-31 | 西南科技大学 | Semi-inverse method-based rapid single image dehazing algorithm |
Non-Patent Citations (4)
| Title |
|---|
| A review on dark channel prior based image dehazing algorithms;Sungmin Lee et al;《EURASIP Journal on Image and Video Processing》;20160119;全文 * |
| Single Image Defogging by Multiscale Depth Fusion;Yuan-Kai Wang et al;《IEEE TRANSACTIONS ON IMAGE PROCESSING》;20141130;第23卷(第11期);全文 * |
| Single Image Haze Removal Using Dark Channel Prior;Kaiming He et al;《IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE》;20111231;第33卷(第12期);全文 * |
| Visibility Restoration of Single Hazy Images Captured in Real-World Weather Conditions;Shih-Chia Huang et al;《IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY》;20141031;第24卷(第10期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105989583A (en) | 2016-10-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105989583B (en) | A kind of image defogging method | |
| CN107767354B (en) | Image defogging algorithm based on dark channel prior | |
| CN102750674B (en) | Video image defogging method based on self-adapting allowance | |
| CN104240194B (en) | A kind of enhancement algorithm for low-illumination image based on parabolic function | |
| CN107424198A (en) | Image processing method, device, mobile terminal and computer-readable recording medium | |
| CN106897981A (en) | A kind of enhancement method of low-illumination image based on guiding filtering | |
| CN112837233B (en) | Polarization image defogging method for acquiring transmissivity based on differential polarization | |
| CN103440674B (en) | A kind of rapid generation of digital picture wax crayon specially good effect | |
| CN110428371A (en) | Image defogging method, system, storage medium and electronic equipment based on super-pixel segmentation | |
| CN109389569B (en) | Monitoring video real-time defogging method based on improved DehazeNet | |
| CN106296620B (en) | A kind of color rendition method based on histogram translation | |
| CN110163807B (en) | Low-illumination image enhancement method based on expected bright channel | |
| CN108154492B (en) | A kind of image based on non-local mean filtering goes haze method | |
| CN104766307A (en) | Picture processing method and device | |
| CN108093175B (en) | A kind of adaptive defogging method of real-time high-definition video and device | |
| CN109639994B (en) | Dynamic adjusting method for exposure time of embedded vehicle-mounted camera | |
| CN107277299A (en) | Image processing method, device, mobile terminal and computer-readable recording medium | |
| CN107705263A (en) | A kind of adaptive Penetrating Fog method and terminal based on RGB IR sensors | |
| CN111541886A (en) | Vision enhancement system applied to muddy underwater | |
| CN109451292B (en) | Image color temperature correction method and device | |
| CN107454319A (en) | Image processing method, device, mobile terminal and computer-readable recording medium | |
| CN106709876B (en) | Optical remote sensing image defogging method based on dark image element principle | |
| CN107424134B (en) | Image processing method, image processing device, computer-readable storage medium and computer equipment | |
| CN107277369B (en) | Image processing method, device, computer readable storage medium and computer equipment | |
| CN112465720A (en) | Image defogging method and device based on image sky segmentation and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180724 Termination date: 20210719 |