CN109118446A - A kind of underwater image restoration and denoising method - Google Patents
A kind of underwater image restoration and denoising method Download PDFInfo
- Publication number
- CN109118446A CN109118446A CN201810854632.2A CN201810854632A CN109118446A CN 109118446 A CN109118446 A CN 109118446A CN 201810854632 A CN201810854632 A CN 201810854632A CN 109118446 A CN109118446 A CN 109118446A
- Authority
- CN
- China
- Prior art keywords
- image
- transmissivity
- underwater
- channel
- follows
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000001914 filtration Methods 0.000 claims abstract description 30
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 17
- 238000005457 optimization Methods 0.000 claims abstract description 9
- 230000001360 synchronised effect Effects 0.000 claims abstract description 7
- 238000004364 calculation method Methods 0.000 claims description 11
- 239000003595 mist Substances 0.000 claims description 11
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000003384 imaging method Methods 0.000 abstract description 18
- 238000011084 recovery Methods 0.000 abstract description 5
- 239000003086 colorant Substances 0.000 abstract description 4
- 238000007670 refining Methods 0.000 abstract 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 9
- 230000015556 catabolic process Effects 0.000 description 4
- 238000006731 degradation reaction Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000009021 linear effect Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 241000287196 Asthenes Species 0.000 description 1
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000003412 degenerative effect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000031700 light absorption Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 244000005700 microbiome Species 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 239000010981 turquoise Substances 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
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/10—Image enhancement or restoration using non-spatial domain filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of underwater image restoration and denoising methods, propose the single width underwater image restoration algorithm based on non local priori and guiding filtering, using the bias light of dark channel prior algorithm estimation scene, then using the relationship of the wavelength of color of light and scattering coefficient, building meets the non local prior model of underwater picture imaging characteristics and thus estimates the transmissivity of different colours light.Image, and the synchronous characteristic for realizing recovery with denoising are then optimized by guiding filtering.Finally, refining transmissivity using guiding filtering and solving the minimum optimization problem of image restoration denoising, clearly restoration result is obtained.The present invention effectively removes noise on the basis of ensuring operational efficiency, in the engineering practice that can be denoised effective for underwater image restoration.
Description
Technical field
The present invention relates to field of image processings, more particularly to a kind of underwater image restoration and denoising method.
Background technique
In recent years, with the exploitation of marine resources, underwater picture is widely used in marine environment monitoring, and Underwater resources are visited
Rope, the numerous areas such as aquatic organism science.However, medium scatters are existing since water is to light selective absorbing when light is propagated under water
As and water in complex environment have fuzziness high so that underwater picture quality is seriously degenerated, contrast is low, and noise is big to be lacked
Point has seriously affected the accurate acquisition of underwater information.How Fast Restoration is carried out to underwater picture, eliminates fuzzy, removal noise,
Clarity is improved to have great importance.
At present there are a series of underwater image restoration methods based on Applied Physics and mathematics, wherein physics imaging model
Single image restoring method is the research hotspot in the field.The basic principle is that building is underwater according to the degenerative process of underwater picture
The physical model of imaging is to restore clear image.Due to a certain extent, underwater picture and Misty Image imaging have it is similar it
Place, is directed to the reflection and scattering of light, and therefore, many scholars restore underwater picture using dark channel prior defogging algorithm, but
Water is to the selective absorbing of light, so that the dark channel value directly asked using such method is less than normal, the transmissivity of estimation is bigger than normal, restores
Result it is partially dark.The restoration algorithm based on dark channel prior is carried out based on local pixel prior information eventually in the prior art
It restores, blocking artifact as a result easily occurs, and noise when recuperation does not account for Underwater Imaging, while cannot accomplishing to restore also
Remove noise.On the other hand, the image restoration method based on non local color priori was proposed that it is using clearly in 2016 by Berman
In clear image after pixel point degradation similar in color, non local characteristic at line is corresponded in color space to estimate transmissivity,
To effective restored image, but the algorithm is only applicable to atmosphere imaging model, is not suitable for Underwater Imaging model, and algorithm is same
Noise cannot be removed.
In order to make full use of the non local prior information of degraded image, and meet recovery synchronous the needs of denoising, the present invention
Propose the underwater image restoration algorithm of non local color priori and guiding filtering.Main contributions are: 1. moving back from underwater picture
The angle of change is set out, and underwater fuzzy and noise image degradation model is derived.2. wavelength and scattering using each Color Channel light
The correlation of coefficient, the non local prior model of building underwater picture and the transmissivity for estimating each channel.3. in analysis degraded image
When the solution strategies of optimization and Denoising Problems, show that filtering operation can not only optimize image, moreover it is possible to synchronous to realize image restoration
With the conclusion of denoising.As a result, according to the degradation model of derivation, design is restored and the minimum optimization problem of denoising, is filtered using guidance
Wave obtains the clear image restored.
Summary of the invention
The purpose of the present invention is achieved through the following technical solutions:
A kind of underwater image restoration and denoising method, comprising the following steps:
S1. red channel prior image I is calculatedRprior, and the bright background dot searched in image estimates bias light, it is described red
Channel prior image calculation formula is as follows:
In above formula, I is the image observed under Color Channel, under be designated as Color Channel；Y is the neighborhood Ω (x) centered on x
Interior pixel；
S2. preceding 0.1% most bright pixel of search gray value, is set as bias light for the most dark point in channel red in the pixel
Ac；
S3. the thick transmissivity of image is calculated；
S4. the thick transmissivity is optimized based on guiding filtering algorithm, transmissivity t after being optimizedc；
S5. pass through transmissivity t after the optimizationcWith the bias light AcClear image J is calculatedc, calculation formula is such as
Under:
In above formula, I is the image observed under Color Channel, under be designated as Color Channel, t0For transmission lower limit value.
S5. by navigational figure to the clear image JcImplement filtering operation, obtains the clear figure for restoring synchronous denoising
Picture.
The step S3 further comprises:
S31. using k dimension tree clustering algorithm by longitude, the identical pixel of latitude is clustered, and same class pixel is constituted
One mist line of the non local priori of Underwater Imaging；
S32. the thick transmissivity of image is calculated, formula is as follows:
Wherein, tRIt (x) is red channel transmissivity, r (x) is pixel to bias light AcFor the distance of the centre of sphere, JR(x) it is
The red channel value of clear image, ARIt (x) is the red channel value of bias light, subscript G and B are respectively intended to indicate green and blue channel；
λRGAnd λRGCalculation formula it is as follows:
λRG=βR/βG
λRB=βR/βB
Wherein, βRAnd βG、βBRespectively represent the scattering coefficient of the light in red, green, blue channel.
The step S4 further comprises:
Step S41. calculates the transmissivity for meeting and constraining as follows
To transmissivityImplementation navigational figure is IcFiltering operation, the transmissivity t after being optimizedc:
The step S5 further comprises:
Filtering kernel function in the filtering operation are as follows:
In above formula, S (x) is defined as the image of pending filtering, | χ | for the number of pixels in neighborhood Ω (x)；μ and δ2Point
Not Wei in filtering window navigational figure S mean value and variance；ε is adjusting parameter.
The filtering calculation formula are as follows:
Jc(x)=W[m,n](I′c(x))I′c(y)y∈Ω(x)
Wherein, I 'c(x) calculation formula are as follows:
I′c(x)=Jc(x)+n′(x)
N ' (x)=n (x)/tc(x)
In above formula, n (x) is noise parameter, and n ' (x) is the underwater noise being calculated；Y is the neighborhood Ω centered on x
(x) pixel in.
The beneficial effects of the present invention are: propose the single width underwater image restoration based on non local priori and guiding filtering
Algorithm, it estimates field on the basis of deriving the fuzzy underwater picture degradation model of Noise, using dark channel prior algorithm
The bias light of scape, then using the relationship of the wavelength of color of light and scattering coefficient, building meets the non-of underwater picture imaging characteristics
Local prior model and the transmissivity for thus estimating different colours light.Then on the basis of analysis image restoration and Denoising Problems
On, obtaining guiding filtering has optimization image, and the synchronous characteristic for realizing recovery with denoising.Finally, being refined using guiding filtering
Transmissivity and the minimum optimization problem for solving image restoration denoising, obtain clearly restoration result.This paper algorithm is ensuring to run
On the basis of efficiency, noise is effectively removed, recovery accuracy improves 19% compared with the algorithm of the prior art on discrimination, can be effective
In engineering practice for underwater image restoration denoising.
Detailed description of the invention
Fig. 1 is according to the underwater image restoration of one embodiment and the algorithm flow chart of denoising method.
Specific embodiment
For a clearer understanding of the technical characteristics, objects and effects of the present invention, this hair of Detailed description of the invention is now compareed
Bright specific embodiment.
When Underwater Imaging, water is maximum to longer wavelengths of red light absorption rate, and as the depth of field increases, most fast, blue light of decaying
It is relatively short with green wavelength, decay weaker.Based on the above principles, Galdran et al. proposed red channel prior in 2015
The bias light estimation technique[11], it indicates the image after red channel reversionIts non-background area meets red channel
Priori, i.e.,In non-background area local neighborhood in the minimum value of all pixels triple channel level off to zero, such as formula (4).Due to
Background area is unsatisfactory for this priori, we can calculate red channel prior image IRprior, and search for background dot brighter in image
Estimate bias light.
In formula: y is the neighborhood territory pixel point centered on x.I is obtained by formulaRpriorAfterwards, before search gray value is most bright
0.1% pixel, they are located at the background area of farthest, and the depth of field of pixel is bigger, and the value in red channel is got in original image
It is low, therefore the most dark point in red channel in these pixels is searched further for, and its value is set as bias light Ac。
Non local priori applied to the estimation of Misty Image transmissivity shows that clear fogless outdoor image at most can be by several
Hundred kinds of different colours indicate, and the pixel of same color is polymerized to cluster in rgb space, however by the shadow of fog scattering process
It rings, corresponds to the pixel of cluster in clear image originally, form a mist line, the picture on line in the rgb space of degraded image
Vegetarian refreshments has not to be limited by regional area, is distributed in the characteristic of image different location.Mist can be estimated using this non local priori
The transmissivity of pixel on line.But the priori is to propose that transmissivity is consistent in each Color Channel value, and water for atmosphere imaging
The scattering coefficient β of the light of different colours in water when lower imagingcIt is not identical, the transmissivity t of each Color ChannelcIt need to individually estimate.
For this purpose, the invention proposes the non local priori transmissivity estimation methods for being suitable for Underwater Imaging.
The computation model in each channel is as follows:
β is done in formula 2,3 formula both sidesR/βG, βR/βBPower operation, enables λRG=βR/βGAnd λRB=βR/βB:
(IR(x)-AR(x))=tR(x)(JR(x)-AR(x))
In formula: sign () is stet operation, it is λ in order to preventRGAnd λRBPower operation change Ic-AcIt is original
Symbol and implement.The imaging model in each channel can be by tR(x) it indicates.If by IR(x)-AR(x) it is defined as It is defined as It is defined asThen the source point of rgb space is transformed into bias light Ac
Place, with bias light AcFor under the spherical coordinate system of the centre of sphereIs defined as:
In formula: θ (x) andRespectively longitude and latitude, r (x) are distance of the pixel to the centre of sphere:
In Jc, Ac, λRGAnd λRBIn the case where determination, the scene point of different depthOnly with tR(x) variation is related, and
In θ (x) andIn the case where constant, tR(x) variation is again only related to r (x), therefore, longitude and latitude θ (x) withIt is identical
Pixel should have similar rgb value in clear image, tie up tree clustering algorithm for longitude using k, the identical pixel of latitude clicks through
Row cluster, same class pixel are a mist line for meeting the non local priori of Underwater Imaging.
For any bar mist line, the t put on mist line can be estimatedR(x) value:
In view of tR(x) value range is [0,1], works as tR(x) be 1 when, corresponding maximum distance rmax(x):
And r on mist linemax(x) corresponding point is nearest apart from video camera on the line, and the degree that degrades is the smallest approximate clear
Point, it is assumed that every mist line all has such point, then transmissivity tR(x) calculation formula is as follows:
In formula: rmaxIt (x) is the maximum value of all pixels r (x) on this mist line.Thus it can get the transmission of whole image
Rate tR, then by known λRGAnd λRBIt can be obtained the transmissivity t in turquoise channelGAnd tB。
When the pixel of mist line is less or the depth of field of pixel is larger, the value of r (x) is smaller, transmissivity tR(x) by noise jamming
Seriously, estimated result is distorted.In view of transmissivity is the function of the depth of field, therefore the depth of field changes smooth region in observed image I,
Transmissivity tcAlso respective smoothed, and in I when the mutation of the edge depth of field, tcAlso transition should be generated therewith.It therefore need to be to above-mentioned rough estimate
Transmissivity further implement to optimize, while keeping its smooth, keep the marginal information of transition.
Assuming that noise-containing observed image S=Q+n, Q and n are respectively clear image and additive noise, and clear image Q
Solution can construct the minimum optimization problem f (Q) such as following formula to solve:
In formula: λ is weight coefficient.Dm,nIt is transfer ratio, expression both horizontally and vertically moves image Q respectively
Dynamic m pixel and n pixel；L is neighborhood window size；W[m,n]It (S) is the weight square for reducing pixel smoothing effect on the edge S
Gust, element value is 0 on matrix off-diagonal, and the element value and edge strength on diagonal line are at anti-.
Assuming that initial value Q0=S, calculates the main diagonalizable matrix M (S)/2 of Hessian matrix first, then carries out primary
Jacobi iteration obtains the preliminary solution of f (Q) are as follows:
Essence from solution strategies known to above formula is by filter operator W[m,n](S) it is multiplied to complete with image S, i.e., to figure
As S implements filtering operation.Therefore by W[m,n](S) it is very crucial to be designed as reasonable filter kernel function.It is proposed by the present invention fast
Fast wave filter is input picture differ the smallest local linear with output image under the guidance of given image to filter
Device, it not only overcomes the gradient reversal development of two-sided filter, also smoothly special with the filtering at reservation edge with local linear
Property.By W[m,n](S) it is set as the filtering kernel function that navigational figure is S are as follows:
In formula: y is pixel in the neighborhood Ω (x) centered on x, | χ | for the number of pixels in neighborhood Ω (x)；μ and δ2Point
Not Wei in filtering window navigational figure S mean value and variance；ε is adjusting parameter.
Due toWithTherefore known tR,λRGAnd λRBThe transmissivity t of image can be acquiredc.Such as preceding 3.2 section
It is described, transmissivity tcVariation with observation chart I should be consistent.To tcImplement the guiding filtering that navigational figure is I, obtains fine
Transmissivity.
Transmissivity t is determined firstcBounds, because of Jc>=0, red channel t can be obtainedRBoundary, recycle tRWith tB, tG
Relationship, obtain and meet the transmissivity that constrains as follows
To transmissivityImplementation navigational figure is IcFiltering operation, the transmissivity t after being optimizedc:
By calculating fine transmissivity tcWith bias light AcClear image can be obtained:
In formula: t0It is transmission lower limit value, however by the error of imaging system itself, medium, microorganism and water in water
The influence of liquid flowability, there are a large amount of noises for Underwater Imaging, restore clear image merely with above formula, not can be removed noise.
From above-mentioned analysis it is not difficult to find that noise-containing Underwater Imaging model can be solved by constructing minimum optimization problem.For this purpose, by
Counted AcWith tcThe objective function of synchronous denoising is restored in building, implements filtering operation using navigational figure, it is same to can be obtained recovery
Walk the clear image of denoising.
Jc(x)=W[m,n](I′c(x))I′c(y)y∈Ω(x)
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in some embodiment
Part, reference can be made to the related descriptions of other embodiments.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the program can be stored in computer-readable storage medium
In, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the storage medium can be magnetic
Dish, CD, ROM, RAM etc..
The above disclosure is only the preferred embodiments of the present invention, cannot limit the right model of the present invention with this certainly
It encloses, therefore equivalent changes made in accordance with the claims of the present invention, is still within the scope of the present invention.
Claims (5)
1. a kind of underwater image restoration and denoising method, it is characterised in that: the described method comprises the following steps:
S1. red channel prior image I is calculatedRprior, and the bright background dot searched in image estimates bias light, the red channel
Prior image calculation formula is as follows:
In above formula, I is the image observed under Color Channel, under be designated as Color Channel；Y is picture in the neighborhood Ω (x) centered on x
Element；
S2. preceding 0.1% most bright pixel of search gray value, is set as bias light A for the most dark point in channel red in the pixelc；
S3. the thick transmissivity of image is calculated；
S4. the thick transmissivity is optimized based on guiding filtering algorithm, transmissivity t after being optimizedc；
S5. pass through transmissivity t after the optimizationcWith the bias light AcClear image J is calculatedc, calculation formula is as follows:
In above formula ,/for the image observed under Color Channel, under be designated as Color Channel, t0For transmission lower limit value.
S6. by navigational figure to the clear image JcImplement filtering operation, obtains the clear image for restoring synchronous denoising.
2. underwater image restoration according to claim 1 and denoising method, the step S3 further comprises:
S31. using k dimension tree clustering algorithm by longitude, the identical pixel of latitude is clustered, and same class pixel constitutes underwater
A mist line of non local priori is imaged；
S32. the thick transmissivity of image is calculated, formula is as follows:
Wherein, tRIt (x) is red channel transmissivity, r (x) is pixel to bias light AcFor the distance of the centre of sphere, JRIt (x) is clear
The red channel value of image, ARIt (x) is the red channel value of bias light, subscript G and B are respectively intended to indicate green and blue channel；
λRGAnd λRGCalculation formula it is as follows:
λRG=βR/βG
λRB=βR/βB
Wherein, βRAnd βG、βBRespectively represent the scattering coefficient of the light in red, green, blue channel.
3. underwater image restoration according to claim 1 and denoising method, the step S4 further comprises:
Step S41. calculates the transmissivity for meeting and constraining as follows
To transmissivityImplementation navigational figure is IcFiltering operation, the transmissivity t after being optimizedc:
4. underwater image restoration according to claim 1 and denoising method, the step S5 further comprises:
Filtering kernel function in the filtering operation are as follows:
In above formula, S (x) is defined as the image of pending filtering, | χ | for the number of pixels in neighborhood Ω (x)；μ and δ2Respectively filter
The mean value and variance of navigational figure S in wave device window；ε is adjusting parameter.
5. underwater image restoration according to claim 4 and denoising method, comprising:
The filtering calculation formula are as follows:
Jc(x)=W[m, n](I′c(x))I′c(y) y∈Ω(x)
Wherein, I 'c(x) calculation formula are as follows:
I′c(x)=Jc(x)+n′(x)
N ' (x)=n (x)/tc(x)
In above formula, n (x) is noise parameter, and n ' (x) is the underwater noise being calculated；Y is in the neighborhood Ω (x) centered on x
Pixel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810854632.2A CN109118446B (en) | 2018-07-30 | 2018-07-30 | Underwater image restoration and denoising method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810854632.2A CN109118446B (en) | 2018-07-30 | 2018-07-30 | Underwater image restoration and denoising method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109118446A true CN109118446A (en) | 2019-01-01 |
| CN109118446B CN109118446B (en) | 2021-08-24 |
Family
ID=64863821
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810854632.2A Active CN109118446B (en) | 2018-07-30 | 2018-07-30 | Underwater image restoration and denoising method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109118446B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110009586A (en) * | 2019-04-04 | 2019-07-12 | 湖北师范大学 | A kind of underwater laser image recovery method and system |
| CN110335210A (en) * | 2019-06-11 | 2019-10-15 | 长江勘测规划设计研究有限责任公司 | Underwater image restoration method |
| CN110689490A (en) * | 2019-09-09 | 2020-01-14 | 天津大学 | Underwater image restoration method based on texture color features and optimized transmittance |
| CN110689504A (en) * | 2019-10-11 | 2020-01-14 | 大连海事大学 | Underwater image restoration method based on secondary guide transmission diagram |
| CN110717869A (en) * | 2019-09-11 | 2020-01-21 | 哈尔滨工程大学 | Underwater turbid image sharpening method |
| CN112581461A (en) * | 2020-12-24 | 2021-03-30 | 深圳大学 | No-reference image quality evaluation method and device based on generation network |
| CN113658110A (en) * | 2021-07-22 | 2021-11-16 | 西南财经大学 | Medical image identification method based on dynamic field adaptive learning |
| CN113989164A (en) * | 2021-11-24 | 2022-01-28 | 河海大学常州校区 | Underwater color image restoration method, system and storage medium |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013182838A (en) * | 2012-03-02 | 2013-09-12 | Stanley Electric Co Ltd | Luminaire |
| CN105761227A (en) * | 2016-03-04 | 2016-07-13 | 天津大学 | Underwater image enhancement method based on dark channel prior algorithm and white balance |
| CN106485681A (en) * | 2016-10-18 | 2017-03-08 | 河海大学常州校区 | Color image restoration method under water based on color correction and red channel prior |
| WO2017048927A1 (en) * | 2015-09-18 | 2017-03-23 | The Regents Of The University Of California | Cameras and depth estimation of images acquired in a distorting medium |
| CN106600547A (en) * | 2016-11-17 | 2017-04-26 | 天津大学 | Underwater image restoration method |
| CN106780368A (en) * | 2016-11-24 | 2017-05-31 | 天津大学 | A kind of underwater picture Enhancement Method based on foreground model |
| CN106971379A (en) * | 2017-03-02 | 2017-07-21 | 天津大学 | A kind of underwater picture Enhancement Method merged based on stratified calculation |
| CN107203977A (en) * | 2017-05-17 | 2017-09-26 | 河海大学 | A kind of underwater image restoration method based on dark primary priori and rarefaction representation |
| CN107316278A (en) * | 2017-05-13 | 2017-11-03 | 天津大学 | A kind of underwater picture clearness processing method |
| CN107403418A (en) * | 2017-07-27 | 2017-11-28 | 北京大学深圳研究生院 | Defogging and the underwater picture Enhancement Method of color correction are carried out based on passage transmissivity |
| CN107798665A (en) * | 2017-11-07 | 2018-03-13 | 天津大学 | Underwater picture Enhancement Method based on structural texture layering |
| CN107909552A (en) * | 2017-10-31 | 2018-04-13 | 天津大学 | Based on underwater prior-constrained image recovery method |
| CN108257101A (en) * | 2018-01-16 | 2018-07-06 | 上海海洋大学 | A kind of underwater picture Enhancement Method based on optimal recovery parameter |
-
2018
- 2018-07-30 CN CN201810854632.2A patent/CN109118446B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013182838A (en) * | 2012-03-02 | 2013-09-12 | Stanley Electric Co Ltd | Luminaire |
| WO2017048927A1 (en) * | 2015-09-18 | 2017-03-23 | The Regents Of The University Of California | Cameras and depth estimation of images acquired in a distorting medium |
| CN105761227A (en) * | 2016-03-04 | 2016-07-13 | 天津大学 | Underwater image enhancement method based on dark channel prior algorithm and white balance |
| CN106485681A (en) * | 2016-10-18 | 2017-03-08 | 河海大学常州校区 | Color image restoration method under water based on color correction and red channel prior |
| CN106600547A (en) * | 2016-11-17 | 2017-04-26 | 天津大学 | Underwater image restoration method |
| CN106780368A (en) * | 2016-11-24 | 2017-05-31 | 天津大学 | A kind of underwater picture Enhancement Method based on foreground model |
| CN106971379A (en) * | 2017-03-02 | 2017-07-21 | 天津大学 | A kind of underwater picture Enhancement Method merged based on stratified calculation |
| CN107316278A (en) * | 2017-05-13 | 2017-11-03 | 天津大学 | A kind of underwater picture clearness processing method |
| CN107203977A (en) * | 2017-05-17 | 2017-09-26 | 河海大学 | A kind of underwater image restoration method based on dark primary priori and rarefaction representation |
| CN107403418A (en) * | 2017-07-27 | 2017-11-28 | 北京大学深圳研究生院 | Defogging and the underwater picture Enhancement Method of color correction are carried out based on passage transmissivity |
| CN107909552A (en) * | 2017-10-31 | 2018-04-13 | 天津大学 | Based on underwater prior-constrained image recovery method |
| CN107798665A (en) * | 2017-11-07 | 2018-03-13 | 天津大学 | Underwater picture Enhancement Method based on structural texture layering |
| CN108257101A (en) * | 2018-01-16 | 2018-07-06 | 上海海洋大学 | A kind of underwater picture Enhancement Method based on optimal recovery parameter |
Non-Patent Citations (5)
| Title |
|---|
| A.CHRISPIN JIJI 等: "Enhancement of underwater deblurred images using gradient guided filter", 《2018 3RD IEEE INTERNATIONAL CONFERENCE ON RECENT TRENDS IN ELECTRONICS, INFORMATION & COMMUNICATION TECHNOLOGY (RTEICT)》 * |
| FELIPE M. CODEVILLA 等: "Underwater Single Image Restoration Using Dark Channel Prior", 《《2014 SYMPOSIUM ON AUTOMATION AND COMPUTATION FOR NAVAL, OFFSHORE AND SUBSEA》》 * |
| 尹芳 等: "一种结合暗通道先验和图像融合的水下图像复原算法", 《小型微型计算机系统》 * |
| 张鑫 等: "雾天降质图像的去雾复原新算法", 《遥感信息》 * |
| 黄松 等: "基于自适应透射率比的水下图像复原算法", 《浙江大学学报（工学版）》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110009586A (en) * | 2019-04-04 | 2019-07-12 | 湖北师范大学 | A kind of underwater laser image recovery method and system |
| CN110335210B (en) * | 2019-06-11 | 2022-05-13 | 长江勘测规划设计研究有限责任公司 | Underwater image restoration method |
| CN110335210A (en) * | 2019-06-11 | 2019-10-15 | 长江勘测规划设计研究有限责任公司 | Underwater image restoration method |
| CN110689490A (en) * | 2019-09-09 | 2020-01-14 | 天津大学 | Underwater image restoration method based on texture color features and optimized transmittance |
| CN110717869B (en) * | 2019-09-11 | 2023-09-19 | 哈尔滨工程大学 | Method for clearing underwater turbid image |
| CN110717869A (en) * | 2019-09-11 | 2020-01-21 | 哈尔滨工程大学 | Underwater turbid image sharpening method |
| CN110689504B (en) * | 2019-10-11 | 2022-09-30 | 大连海事大学 | Underwater image restoration method based on secondary guide transmission diagram |
| CN110689504A (en) * | 2019-10-11 | 2020-01-14 | 大连海事大学 | Underwater image restoration method based on secondary guide transmission diagram |
| CN112581461A (en) * | 2020-12-24 | 2021-03-30 | 深圳大学 | No-reference image quality evaluation method and device based on generation network |
| CN112581461B (en) * | 2020-12-24 | 2023-06-02 | 深圳大学 | No-reference image quality evaluation method and device based on generation network |
| CN113658110A (en) * | 2021-07-22 | 2021-11-16 | 西南财经大学 | Medical image identification method based on dynamic field adaptive learning |
| CN113989164A (en) * | 2021-11-24 | 2022-01-28 | 河海大学常州校区 | Underwater color image restoration method, system and storage medium |
| CN113989164B (en) * | 2021-11-24 | 2024-04-09 | 河海大学常州校区 | Underwater color image restoration method, system and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109118446B (en) | 2021-08-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109118446A (en) | A kind of underwater image restoration and denoising method | |
| Kaur et al. | Color image dehazing using gradient channel prior and guided l0 filter | |
| Wang et al. | Noise detection and image denoising based on fractional calculus | |
| Raikwar et al. | Lower bound on transmission using non-linear bounding function in single image dehazing | |
| Wang et al. | Dehazing for images with large sky region | |
| Yu et al. | Image denoising using trivariate shrinkage filter in the wavelet domain and joint bilateral filter in the spatial domain | |
| Zhong et al. | Robust polarimetric SAR despeckling based on nonlocal means and distributed Lee filter | |
| CN110675340A (en) | Single image defogging method and medium based on improved non-local prior | |
| CN110135434B (en) | Underwater image quality improvement method based on color line model | |
| CN108537756A (en) | Single image to the fog method based on image co-registration | |
| CN105046677A (en) | Enhancement processing method and apparatus for traffic video image | |
| CN111160293A (en) | Small target ship detection method and system based on characteristic pyramid network | |
| CN103871039A (en) | Generation method for difference chart in SAR (Synthetic Aperture Radar) image change detection | |
| CN111968062A (en) | Dark channel prior mirror highlight image enhancement method and device and storage medium | |
| Jovanov et al. | Fuzzy logic-based approach to wavelet denoising of 3D images produced by time-of-flight cameras | |
| Chang | Single underwater image restoration based on adaptive transmission fusion | |
| Wang et al. | An efficient method for image dehazing | |
| Yuan et al. | Image dehazing based on a transmission fusion strategy by automatic image matting | |
| Liu et al. | Haze removal for a single inland waterway image using sky segmentation and dark channel prior | |
| Honnutagi et al. | Fusion-based underwater image enhancement by weight map techniques | |
| Wang et al. | Haze removal algorithm based on single-images with chromatic properties | |
| Fu et al. | An anisotropic Gaussian filtering model for image de-hazing | |
| Zhou et al. | Underwater image enhancement method based on color correction and three-interval histogram stretching | |
| CN110335210A (en) | Underwater image restoration method | |
| Deluxni et al. | A Scrutiny on Image Enhancement and Restoration Techniques for Underwater Optical Imaging Applications |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |