CN106981053A - A kind of underwater picture Enhancement Method based on Weighted Fusion - Google Patents
A kind of underwater picture Enhancement Method based on Weighted Fusion Download PDFInfo
- Publication number
- CN106981053A CN106981053A CN201710121580.3A CN201710121580A CN106981053A CN 106981053 A CN106981053 A CN 106981053A CN 201710121580 A CN201710121580 A CN 201710121580A CN 106981053 A CN106981053 A CN 106981053A
- Authority
- CN
- China
- Prior art keywords
- weight
- underwater picture
- image
- underwater
- picture
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000004927 fusion Effects 0.000 title claims abstract description 27
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000001914 filtration Methods 0.000 claims abstract description 7
- 238000012937 correction Methods 0.000 abstract description 7
- 238000004422 calculation algorithm Methods 0.000 description 25
- 230000000694 effects Effects 0.000 description 13
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 10
- 230000002708 enhancing effect Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 239000007900 aqueous suspension Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004040 coloring Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 230000007850 degeneration Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000004438 eyesight Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 239000003595 mist Substances 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 230000001235 sensitizing effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000005303 weighing Methods 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of underwater picture Enhancement Method based on Weighted Fusion, the underwater picture Enhancement Method comprises the following steps:Gray World and histogram equalization processing are used respectively to the underwater picture degraded, input picture is obtained;By normalized, the definition to weight factor is realized using the method for weighting guiding filtering, weight factor is corrected, obtains revised weight map;Each width input figure is decomposed respectively with laplacian pyramid, and each width weight map is decomposed with gaussian pyramid, the final method with Multiscale Fusion is merged to input picture and weight map, the abundant image of details is obtained.This method need not carry out the computing of deconvoluting of complexity, and carry out rational selection to weight, image is had more rich details on the basis of color correction.
Description
Technical field
Strengthen field, more particularly to a kind of figure under water based on Weighted Fusion the present invention relates to the underwater picture of image co-registration
Image intensifying method.
Background technology
Underwater picture enhancing technology is the important component for obtaining marine information, while being also complete underwater operation one
Individual important technology.Attenuation is had because light is transmitted in water, feux rouges decay is most fast, and bluish-green optical attenuation is most slow, and in water
Suspension can make light that Multiple Scattering effect occur in water, and forward scattering causes image blurring, and back scattering causes image comparison
Degree declines, and therefore, underwater picture can show bluish-green tone and contrast and definition are relatively low, and influence is entered to underwater exploration
Exhibition, and existing underwater picture enhancing technology is still immature, it is necessary to further deeply probe into.
Early in 1979, McGlamery [1] proposed the underwater picture imaging model of classics.He propose, imaging system institute
The light radiation received is made up of three parts:Light, forward scattering and the back scattering directly decayed.On the basis of this theoretical model
On, most widely used is to be based on the defogging method of dark primary priori (Dark Channel Prior, DCP) and be based on
Retinex Enhancement Method.2008, Fattal [2] was using imaging surface shade and atmospheric transfer function local uncorrelated
Hypothesis estimate the transmission of scene.2011, water body scattering effect was equivalent to the change of ambient lighting by Zhang Kai [3] etc.,
Handled by the multi-Scale Retinex Algorithm under coloured image luminance channel under water, water body scattering effect can be reduced, improve image
Contrast, but easily there is noise in the background area of image in the algorithm.2012, Chiang [4] proposed one kind and is based on going
The image intensifying algorithm under water of the wavelength compensation of mist, he considers that the effect of artificial light source obtains depth map, prospect background is split,
Color Channel is compensated by different proportion respectively, but this method computation complexity is higher., Hitam etc. [5] fusions in 2013
The algorithm of histogram equalization enhancing underwater picture of the contrast-limited of rgb space and HSV space, the algorithm computational efficiency is high,
But can equally produce larger noise.2014, Xueyang Fu [6] et al. proposed one kind and are based under variation framework
Underwater picture Enhancement Method theoretical Retinex.
2012, Ancuti etc. [7] proposed a kind of underwater picture enhancing algorithm based on fusion.The algorithm is mainly pair
The selection of input picture and weight map and the purpose that enhancing underwater picture is reached by multi-resolution Fusion.What underwater picture was protruded
Feature is that cross-color and contrast decline, and for this feature, Ancuti proposes respectively to handle each feature progress
Figure and weight map are inputted to two width, then recovers underwater picture by multi-resolution Fusion.First, the light of different wave length is being transmitted across
Cheng Zhonghui causes the color displacement of image by different degrees of absorption, and color constancy algorithm is the correction to offseting color
Method, for the These characteristics of underwater picture, Ancuti is using traditional Gray-World [8] methods to the image procossing that degrades
Obtain input picture I1, wherein, illuminance is adjusted:
μI=0.5+ λ μref (1)
Wherein, μrefIt is average brightness, μIIt is illumination estimate value (value obtained in Gray-World).Light attenuation
Afterwards, the global contrast of image substantially weakens, and in order to obtain clearly image, Ancuti is using traditional histogram equalization
Method improves global contrast, obtains input picture I2。
After the two width input figures that color correction and global contrast are improved are obtained, it is contemplated that the image of degeneration is notable
Property, also have many shortcomings in terms of part and global contrast and exposure, therefore, the weight of input picture will be weighed by following four
Repeated factor is determined:
(1) Laplce's contrast weight is by each luminance channel application La Pula wave filter, and to calculate it
Thoroughly deserve the weight map of global contrast.
(2) local contrast weight is obtained by each pixel and its neighborhood territory pixel:
WLC(x, y)=| | Ik-Ik whc|| (2)
Wherein, IkIt is the luminance channel of input picture, Ik whcIt is the passage after low pass filter is handled.
(3) main information of image is only concentrated in the key areas of minority, and people are of interest is also generally focused on
The region of image outline curvature maximum or contour direction suddenly change, these information are embodied by notable figure, conspicuousness weight map
Obtained by Achanta [9].
(4) exposure weight is used for weighing the depth of exposure of pixel, and it is obtained by a Gauss model:
Wherein, Ik(x, y) represents the brightness value at (x, y) place;σ is 0.25.
In order to obtain good effect, four width weight maps are normalized this method obtains two width weight maps, following institute
Show:
Wherein, n_WLI, n_WLCI, n_WSI and n_WEI (i=1,2) is normalized Laplce's weight respectively, local right
Than degree weight, conspicuousness weight and exposure weight.Finally, by two width input figures and two width weight map laplacian pyramids
The method processing of multi-resolution Fusion, obtains enhanced image:
Wherein, L { I } is the laplacian pyramid of input picture,It is the gaussian pyramid of weight.
Bibliography
[1]McGlamery B L.A computer model for underwater camera systeiiis
[C]//Ocean Optics VI.International Society for Optics and Photonics,1980:221-
231.
[2]R.Fattal,“Single Image Dehazing,”J.ACM Siggraph 08,1-9(2008).
[3] Zhang Kai, Qiu Su, multiple dimensioned Retinex enhancings algorithm [J] of luminance channel of Wang Xia coloured images under water is infrared
Technology, 2012,33 (11):630-634.
[4]Chiang J Y and Chen Ying-Ching.Underwater image enhancement by
wavelength compensation and dehazing[J].IEEE Transactions on Image
Processing,2012,21(4):1756-1769.
[5]Hitam M S,Yussof W,Awalludin E A.Mixture contrast limited adaptive
histogram equalization for underwater enhancement[C]//International
Conference on Computer Applications Technology,Sousse,Tunisia:IEEE Press,
2013:1-5.
[6]X.Y.Fu and P.X.Zhuang,“A Retinex-based Enhancing Approach for
Single Underwater Image,”IEEE Inter.Conf.Image Process.,Paris,France,October
2014,pp.27-30.
[7]C.Ancuti,C.O.Ancuti,T.Haber and P.Bekaert,“Enhancing underwater
images and videos by fusion,”in proc.IEEE Conf.Comput.Vis.Patt.Recogn.(CVPR),
Providence,RI,Jun.2012,pp.81-88.
[8]B.Gershon,“A spatial processor model for object colour
perception,”J.Frank.Inst.,vol.310,no.1,pp.1-26,1980.
[9]R.Achantay,S.Hemamiz,F.Estraday,and S.Susstrunky.Frequency-tuned
salient region detection.IEEE CVPR,2009.
The content of the invention
It is of the invention by weight factor and La Pu the invention provides a kind of underwater picture Enhancement Method based on Weighted Fusion
Lars pyramid fusion is combined, described below:
A kind of underwater picture Enhancement Method based on Weighted Fusion, the underwater picture Enhancement Method comprises the following steps:
Gray-World and histogram equalization processing are used respectively to the underwater picture degraded, input picture is obtained;
By normalized, the definition to weight factor is realized using the method for weighting guiding filtering, amendment weight because
Son, obtains revised weight map;
Each width input figure is decomposed respectively with laplacian pyramid, and to each width weight map Gauss gold
Word tower is decomposed, and the final method with Multiscale Fusion is merged to input picture and weight map, obtains the abundant image of details.
It is described to be specially the step of obtain revised weight map:
m_W1=a_1*n_WLC1+b_1*n_WS1+c_1*n_WE1
m_W2=a_2*n_WLC2+b_2*n_WS2+c_2*n_WE2
Wherein, a_i, b_i and c_i are the scale factor of each weight, n_W respectivelyLCI, n_WSI and n_WEOn i is respectively
The normalized weight result of local contrast weight, conspicuousness weight and the exposure weight stated;I=1,2.
The step of method using weighting guiding filtering is realized to the definition of weight factor be specially:
Wherein, ε is the positive number of a very little, and it is zero to prevent denominator;n_WLCK, n_WSK and n_WEK is respectively local contrast
Spend the normalized weight of weight, conspicuousness weight and exposure weight;K is 2;N is sum of all pixels.
The beneficial effect for the technical scheme that the present invention is provided is:See overall quick from subjective using technical scheme
Sense effect is preferable, and brightness uniformity, and color more enriches, and this algorithm is recovering underwater picture color, increasing definition and right
Than having good effect in terms of degree.Image average, average gradient, comentropy and standard deviation four is respectively adopted in objective aspects
Image quality measurement index is measured to experimental result.Fig. 3~Fig. 6 shows the result of Fig. 2 objective indicator, thus comes
See, inventive algorithm result is above other three kinds of methods.This explanation inventive algorithm is in extraction and processing of detailed information etc.
Aspect is yielded good result.
Brief description of the drawings
Fig. 1 is a kind of flow chart of the underwater picture Enhancement Method based on Weighted Fusion;
Fig. 2 is the contrast effect figure of algorithms of different result;
Fig. 3 be underwater picture average ratio compared with schematic diagram;
Fig. 4 is the schematic diagram that underwater picture average gradient compares;
Fig. 5 is the schematic diagram that underwater picture comentropy compares;
Fig. 6 is the schematic diagram that underwater picture standard deviation compares.
Embodiment
To make the object, technical solutions and advantages of the present invention clearer, further is made to embodiment of the present invention below
It is described in detail on ground.
Due to the decay and scattering in light under water transmitting procedure, underwater picture can seriously degenerate, and cause loss in detail, right
Decline than degree and cross-color.Although existing underwater picture Enhancement Method achieves progress to a certain extent, figure
As treatment effect is still not fully up to expectations, related algorithm complexity is high in addition, or is proposed based on a certain specified conditions, application by
Limit.
Embodiment 1
In order to improve the definition of underwater picture, the embodiment of the present invention proposes a kind of underwater picture based on Weighted Fusion
Strengthen algorithm (Enhancing Underwater Images based on Weighted Fusion, EUIWF), the algorithm with
Other existing enhancing algorithms are compared, and are simple pixel operations, concise, it is not necessary to carry out complicated computing of deconvoluting, and
And rational selection has been carried out to weight, make image that there is more rich details on the basis of color correction.
101:Gray-World (gray world) and histogram equalization processing are used respectively to the underwater picture degraded, obtained
Input picture;
102:By normalized, the definition to weight factor, amendment power are realized using the method for weighting guiding filtering
Repeated factor, obtains revised weight map;
103:Each width input figure is decomposed respectively with laplacian pyramid, and it is high to each width weight map
This pyramid decomposition, the final method with Multiscale Fusion is merged to input picture and weight map, obtains the abundant image of details.
In summary, the embodiment of the present invention by above-mentioned steps 101- steps 103 by the golden word of weight factor and Laplce
Tower fusion is combined, it is not necessary to is carried out complicated computing of deconvoluting, and has been carried out rational selection to weight, makes image in face
There is more rich details on the basis of color correction.
Embodiment 2
The scheme in embodiment 1 is further introduced with reference to specific calculation formula, accompanying drawing, it is as detailed below
Description:
Fusion method of the embodiment of the present invention based on Ancuti is merged to input picture and weight map.Melt in basic
In conjunction method, weight plays important role, and its definition, conspicuousness and its contrast to image etc. has decisive work
With therefore, simple normalize and be directly added obtained result four width weight maps can not weigh the pixel in four features
Above which is more occupied an leading position, it is impossible to the characteristic information of rational distribution image, so that missing image part details.To be terrible
The image enriched to details, the embodiment of the present invention is as follows to weight map amendment:
m_W1=a_1*n_WLC1+b_1*n_WS1+c_1*n_WE1 (7)
m_W2=a_2*n_WLC2+b_2*n_WS2+c_2*n_WE2 (8)
Wherein, a_i, b_i and c_i are the scale factor of each weight, n_W respectivelyLCI, n_WSI and n_WEOn i is respectively
The normalized weight result of local contrast weight, conspicuousness weight and the exposure weight stated.
(n_WLCI=WLCi/(WLC1+WLC2), similarly two other weight map n_WSI and n_WEI, i=1,2) weight because
The meaning of son is that when in border affecting parameters are more than 1, and the weight is in leading position, easily convex when now merging
Aobvious border, improves definition, strengthens edge.
201:Gray-World and histogram equalization processing are used respectively to the underwater picture degraded, input picture I is obtained1
And I2;
202:Its local contrast weight, conspicuousness weight and exposure weight are calculated respectively to each width input picture,
By normalized, and its weight factor is corrected, obtain revised weight map;
In order to strengthen edge and remove the interference of noise, the embodiment of the present invention is realized using the method for weighting guiding filtering
Definition to weight factor, i.e.,:
Wherein, ε is the positive number of a very little, and it is zero to prevent denominator.
203:Each width input figure is decomposed respectively with laplacian pyramid, and it is high to each width weight map
This pyramid decomposition, the final method with Multiscale Fusion is merged to input picture and weight map, obtains the abundant image of details.
In summary, the embodiment of the present invention by above-mentioned steps 201- steps 203 by the golden word of weight factor and Laplce
Tower fusion is combined, it is not necessary to is carried out complicated computing of deconvoluting, and has been carried out rational selection to weight, makes image in face
There is more rich details on the basis of color correction.
Embodiment 3
Feasibility checking is carried out to the scheme in Examples 1 and 2 with reference to specific example, it is described below:
For the effect of verification algorithm, enhanced image is obtained to underwater picture processing using algorithm as described above.Water
Hypograph is coloured image, therefore tri- passages of R, G, B are respectively calculated in fusion.Calculated to compare Weighted Fusion
The picture quality of method, the embodiment of the present invention will be compared with existing algorithm, for example, the enhancing under water based on defogging processing
Algorithm [2], the Enhancement Method [6] based on Retinex and basic blending algorithm [7].
Objective experiment is respectively adopted image average, average gradient, four image quality measurements of comentropy and standard deviation and referred to
Mark is measured to experimental result.Image average reflects the average bright-dark degree of image;Average gradient is the definition of image,
Reflect ability to express of the image to Detail contrast;Comentropy reflects the size that image includes information content, is to weigh image information
One important indicator of abundant degree;Standard deviation reflects the dispersion degree of gray average.
Figure it is seen that Fattal et al. algorithms have preferable effect in terms of defogging, but in color correction side
Face effect is not so good, because its method needs enough colouring informations, underwater picture G, channel B information content are larger, therefore lose
To the color compensating of R passages.Xueyang Fu et al. algorithm is overall partially dark, lacks detailed information.Equally, Ancuti et al.
Algorithm distribute weight due to being not drawn to, therefore subregion is partially dark, and details is not obvious.
Overall sensitizing effect is seen preferably from subjective using technical scheme, and in terms of objective indicator, Fig. 3
Show this method to knot of the five width images in terms of image average, average gradient, comentropy and standard deviation in Fig. 2 to Fig. 6
Really, from the results of view, the result of this method is above other three kinds of methods.This extraction and place of explanation this method in detailed information
Other two kinds of algorithms are superior in terms of reason.
In actual applications, in order to obtain optimal enhancing result, the parameter being related in this method is set as follows:
ε=10 in σ=0.25 in formula (3), formula (9), (10) and (11)-4.Using the underwater picture that degrades as experimental subjects, using this
The step of described in method, set by above-mentioned parameter value, the preferable fused images of visual effect can be obtained.Experimental result table
Bright, this method has preferable effect in terms of subjective vision and objective quantitative index.
It will be appreciated by those skilled in the art that accompanying drawing is the schematic diagram of a preferred embodiment, the embodiments of the present invention
Sequence number is for illustration only, and the quality of embodiment is not represented.
The foregoing is only presently preferred embodiments of the present invention, be not intended to limit the invention, it is all the present invention spirit and
Within principle, any modification, equivalent substitution and improvements made etc. should be included in the scope of the protection.
Claims (3)
1. a kind of underwater picture Enhancement Method based on Weighted Fusion, it is characterised in that the underwater picture Enhancement Method includes
Following steps:
Gray-World and histogram equalization processing are used respectively to the underwater picture degraded, input picture is obtained;
By normalized, the definition to weight factor is realized using the method for weighting guiding filtering, weight factor is corrected, obtains
To revised weight map;
Each width input figure is decomposed respectively with laplacian pyramid, and to each width weight map gaussian pyramid
Decompose, the final method with Multiscale Fusion is merged to input picture and weight map, obtain the abundant image of details.
2. a kind of underwater picture Enhancement Method based on Weighted Fusion according to claim 1, it is characterised in that described
The step of to revised weight map is specially:
m_W1=a_1*n_WLC1+b_1*n_WS1+c_1*n_WE1
m_W2=a_2*n_WLC2+b_2*n_WS2+c_2*n_WE2
Wherein, a_i, b_i and c_i are the scale factor of each weight, n_W respectivelyLCI, n_WSI and n_WEI is respectively above-mentioned office
The normalized weight result of portion's contrast weight, conspicuousness weight and exposure weight;I=1,2.
3. a kind of underwater picture Enhancement Method based on Weighted Fusion according to claim 1, it is characterised in that described to adopt
The step of being realized with the method for weighting guiding filtering to the definition of weight factor be specially:
Wherein, ε is the positive number of a very little, and it is zero to prevent denominator;n_WLCK, n_WSK and n_WEK is respectively local contrast power
The normalized weight of weight, conspicuousness weight and exposure weight;K is 2;N is sum of all pixels.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710121580.3A CN106981053A (en) | 2017-03-02 | 2017-03-02 | A kind of underwater picture Enhancement Method based on Weighted Fusion |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710121580.3A CN106981053A (en) | 2017-03-02 | 2017-03-02 | A kind of underwater picture Enhancement Method based on Weighted Fusion |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106981053A true CN106981053A (en) | 2017-07-25 |
Family
ID=59338706
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710121580.3A Pending CN106981053A (en) | 2017-03-02 | 2017-03-02 | A kind of underwater picture Enhancement Method based on Weighted Fusion |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106981053A (en) |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107909617A (en) * | 2017-11-13 | 2018-04-13 | 四川大学 | A kind of light source colour method of estimation based on non-linear contrast's weighting |
CN108288259A (en) * | 2018-01-06 | 2018-07-17 | 昆明物理研究所 | A kind of gray scale fusion Enhancement Method based on color space conversion |
CN109002750A (en) * | 2017-12-11 | 2018-12-14 | 罗普特(厦门)科技集团有限公司 | A kind of correlation filtering tracking based on conspicuousness detection and image segmentation |
CN109325919A (en) * | 2018-07-27 | 2019-02-12 | 浙江省计量科学研究院 | A kind of underwater picture enhancing system and shooting image recovery method based on the fusion of double light sources |
CN110148097A (en) * | 2019-05-27 | 2019-08-20 | 电子科技大学 | The color calibration method of cataract image |
CN110175964A (en) * | 2019-05-30 | 2019-08-27 | 大连海事大学 | A kind of Retinex image enchancing method based on laplacian pyramid |
CN110232668A (en) * | 2019-06-17 | 2019-09-13 | 首都师范大学 | A kind of multi-scale image Enhancement Method |
CN110648288A (en) * | 2019-08-27 | 2020-01-03 | 上海理工大学 | Choledochoscope image enhancement method based on residual transposition deconvolution neural network |
CN110853070A (en) * | 2019-11-11 | 2020-02-28 | 山东科技大学 | Underwater sea cucumber image segmentation method based on significance and Grabcut |
CN111080537A (en) * | 2019-11-25 | 2020-04-28 | 厦门大学 | Intelligent control method, medium, equipment and system for underwater robot |
CN111462022A (en) * | 2020-04-29 | 2020-07-28 | 青岛大学 | Underwater image sharpness enhancement method |
CN111948215A (en) * | 2020-08-11 | 2020-11-17 | 水利部交通运输部国家能源局南京水利科学研究院 | Underwater structure flaw detection method based on optical imaging |
CN112561804A (en) * | 2020-10-09 | 2021-03-26 | 天津大学 | Low-illumination underwater image enhancement method based on multi-scale detail enhancement |
CN113269681A (en) * | 2021-04-20 | 2021-08-17 | 飞马滨(青岛)智能科技有限公司 | Underwater real-time image enhancement method based on multi-algorithm fusion |
CN113763367A (en) * | 2021-09-13 | 2021-12-07 | 中国空气动力研究与发展中心超高速空气动力研究所 | Comprehensive interpretation method for infrared detection characteristics of large-size test piece |
CN113763368A (en) * | 2021-09-13 | 2021-12-07 | 中国空气动力研究与发展中心超高速空气动力研究所 | Large-size test piece multi-type damage detection characteristic analysis method |
CN113793318A (en) * | 2021-09-13 | 2021-12-14 | 中国空气动力研究与发展中心超高速空气动力研究所 | Multi-region complex damage defect characteristic comprehensive analysis method |
CN114494089A (en) * | 2021-12-17 | 2022-05-13 | 湖南国天电子科技有限公司 | Multi-scale fusion-based seabed image processing method |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104616273A (en) * | 2015-01-26 | 2015-05-13 | 电子科技大学 | Multi-exposure image fusion method based on Laplacian pyramid decomposition |
-
2017
- 2017-03-02 CN CN201710121580.3A patent/CN106981053A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104616273A (en) * | 2015-01-26 | 2015-05-13 | 电子科技大学 | Multi-exposure image fusion method based on Laplacian pyramid decomposition |
Non-Patent Citations (1)
Title |
---|
郭剑桥: "基于改进的引导滤波算法的多曝光图像融合", 《微 电 子 学 与 计 算 机》 * |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107909617B (en) * | 2017-11-13 | 2020-03-17 | 四川大学 | Light source color estimation method based on nonlinear contrast weighting |
CN107909617A (en) * | 2017-11-13 | 2018-04-13 | 四川大学 | A kind of light source colour method of estimation based on non-linear contrast's weighting |
CN109002750A (en) * | 2017-12-11 | 2018-12-14 | 罗普特(厦门)科技集团有限公司 | A kind of correlation filtering tracking based on conspicuousness detection and image segmentation |
CN108288259A (en) * | 2018-01-06 | 2018-07-17 | 昆明物理研究所 | A kind of gray scale fusion Enhancement Method based on color space conversion |
CN109325919A (en) * | 2018-07-27 | 2019-02-12 | 浙江省计量科学研究院 | A kind of underwater picture enhancing system and shooting image recovery method based on the fusion of double light sources |
CN110148097A (en) * | 2019-05-27 | 2019-08-20 | 电子科技大学 | The color calibration method of cataract image |
CN110148097B (en) * | 2019-05-27 | 2021-06-29 | 电子科技大学 | Color correction method of cataract image |
CN110175964A (en) * | 2019-05-30 | 2019-08-27 | 大连海事大学 | A kind of Retinex image enchancing method based on laplacian pyramid |
CN110232668A (en) * | 2019-06-17 | 2019-09-13 | 首都师范大学 | A kind of multi-scale image Enhancement Method |
CN110232668B (en) * | 2019-06-17 | 2021-04-09 | 首都师范大学 | Multi-scale image enhancement method |
CN110648288A (en) * | 2019-08-27 | 2020-01-03 | 上海理工大学 | Choledochoscope image enhancement method based on residual transposition deconvolution neural network |
CN110648288B (en) * | 2019-08-27 | 2023-02-03 | 上海理工大学 | Choledochoscope image enhancement method based on residual transposition deconvolution neural network |
CN110853070A (en) * | 2019-11-11 | 2020-02-28 | 山东科技大学 | Underwater sea cucumber image segmentation method based on significance and Grabcut |
CN111080537A (en) * | 2019-11-25 | 2020-04-28 | 厦门大学 | Intelligent control method, medium, equipment and system for underwater robot |
CN111080537B (en) * | 2019-11-25 | 2023-09-12 | 厦门大学 | Intelligent control method, medium, equipment and system for underwater robot |
CN111462022A (en) * | 2020-04-29 | 2020-07-28 | 青岛大学 | Underwater image sharpness enhancement method |
CN111462022B (en) * | 2020-04-29 | 2022-11-01 | 青岛大学 | Underwater image sharpness enhancement method |
CN111948215A (en) * | 2020-08-11 | 2020-11-17 | 水利部交通运输部国家能源局南京水利科学研究院 | Underwater structure flaw detection method based on optical imaging |
CN112561804A (en) * | 2020-10-09 | 2021-03-26 | 天津大学 | Low-illumination underwater image enhancement method based on multi-scale detail enhancement |
CN113269681B (en) * | 2021-04-20 | 2022-02-01 | 飞马滨(青岛)智能科技有限公司 | Underwater real-time image enhancement method based on multi-algorithm fusion |
CN113269681A (en) * | 2021-04-20 | 2021-08-17 | 飞马滨(青岛)智能科技有限公司 | Underwater real-time image enhancement method based on multi-algorithm fusion |
CN113763368A (en) * | 2021-09-13 | 2021-12-07 | 中国空气动力研究与发展中心超高速空气动力研究所 | Large-size test piece multi-type damage detection characteristic analysis method |
CN113793318A (en) * | 2021-09-13 | 2021-12-14 | 中国空气动力研究与发展中心超高速空气动力研究所 | Multi-region complex damage defect characteristic comprehensive analysis method |
CN113763367A (en) * | 2021-09-13 | 2021-12-07 | 中国空气动力研究与发展中心超高速空气动力研究所 | Comprehensive interpretation method for infrared detection characteristics of large-size test piece |
CN113793318B (en) * | 2021-09-13 | 2023-04-07 | 中国空气动力研究与发展中心超高速空气动力研究所 | Multi-region complex damage defect characteristic comprehensive analysis method |
CN113763368B (en) * | 2021-09-13 | 2023-06-23 | 中国空气动力研究与发展中心超高速空气动力研究所 | Multi-type damage detection characteristic analysis method for large-size test piece |
CN114494089A (en) * | 2021-12-17 | 2022-05-13 | 湖南国天电子科技有限公司 | Multi-scale fusion-based seabed image processing method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106981053A (en) | A kind of underwater picture Enhancement Method based on Weighted Fusion | |
Song et al. | Enhancement of underwater images with statistical model of background light and optimization of transmission map | |
Wang et al. | An experiment-based review of low-light image enhancement methods | |
CN107507138B (en) | A kind of underwater picture Enhancement Method based on Retinex model | |
Chang et al. | Single underwater image restoration based on depth estimation and transmission compensation | |
CN106485681B (en) | Underwater color image restoration method based on color correction and red channel prior | |
Wang et al. | Variational single nighttime image haze removal with a gray haze-line prior | |
CN106971379A (en) | A kind of underwater picture Enhancement Method merged based on stratified calculation | |
Zhou et al. | Underwater image restoration based on secondary guided transmission map | |
CN108257101B (en) | Underwater image enhancement method based on optimal recovery parameters | |
Bi et al. | Haze removal for a single remote sensing image using low-rank and sparse prior | |
Xu et al. | Image enhancement algorithm based on GAN neural network | |
Yang et al. | Underwater image enhancement using scene depth-based adaptive background light estimation and dark channel prior algorithms | |
Zhou et al. | A multifeature fusion method for the color distortion and low contrast of underwater images | |
Parihar et al. | A comprehensive analysis of fusion-based image enhancement techniques | |
Tang et al. | A local flatness based variational approach to retinex | |
Wang et al. | Multiscale supervision-guided context aggregation network for single image dehazing | |
Zhang et al. | Non-uniform illumination video enhancement based on zone system and fusion | |
Li et al. | Adaptive weighted multiscale retinex for underwater image enhancement | |
Gao et al. | Underwater image enhancement and restoration based on local fusion | |
Gong et al. | Research on the method of color compensation and underwater image restoration based on polarization characteristics | |
Ke et al. | Single underwater image restoration based on descattering and color correction | |
Zhang et al. | Underwater Image Enhancement Based on Red Channel Correction and Improved Multiscale Fusion | |
Raigonda et al. | Haze Removal Of Underwater Images Using Fusion Technique | |
Zhou et al. | Multiscale Fusion Method for the Enhancement of Low‐Light Underwater Images |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170725 |