CN113538276A - Underwater image color correction method based on complex underwater imaging model - Google Patents

Underwater image color correction method based on complex underwater imaging model Download PDF

Info

Publication number
CN113538276A
CN113538276A CN202110802196.6A CN202110802196A CN113538276A CN 113538276 A CN113538276 A CN 113538276A CN 202110802196 A CN202110802196 A CN 202110802196A CN 113538276 A CN113538276 A CN 113538276A
Authority
CN
China
Prior art keywords
image
underwater
imaging model
representing
complex
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
Application number
CN202110802196.6A
Other languages
Chinese (zh)
Inventor
张维石
杨彤雨
周景春
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Dalian Maritime University
Original Assignee
Dalian Maritime University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Dalian Maritime University filed Critical Dalian Maritime University
Priority to CN202110802196.6A priority Critical patent/CN113538276A/en
Publication of CN113538276A publication Critical patent/CN113538276A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/90—Dynamic range modification of images or parts thereof
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/20—Image enhancement or restoration using local operators
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10028—Range image; Depth image; 3D point clouds

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Image Processing (AREA)

Abstract

The invention provides an underwater image color correction method based on a complex underwater imaging model. The method comprises the following five processes: estimating a depth map, removing backscattering, estimating a brightness map, estimating a bandwidth attenuation coefficient and restoring an image; firstly, estimating a depth map of an acquired underwater degraded image; secondly, estimating backscattering by using the depth map and the original underwater image; then, estimating a brightness map of the image from which the backscattering is removed; then, estimating a bandwidth attenuation coefficient by using the brightness map and the depth map; and finally, restoring the underwater image by combining the complex underwater imaging model. The method can effectively realize color correction and contrast enhancement of the underwater image, improves the visual effect of the image, and can be applied to image preprocessing.

Description

Underwater image color correction method based on complex underwater imaging model
Technical Field
The invention relates to the technical field of image processing, in particular to an underwater image color correction method based on a complex underwater imaging model.
Background
The underwater image plays an important role in the aspects of marine environment protection, marine engineering development, marine archaeology and the like, and provides a visual basis for the underwater robot to finish main tasks such as pipeline detection, deep sea detection and the like. However, unlike land imaging, underwater imaging is affected by light, weather, season, and suspended matter in water, resulting in problems such as blue-green color cast and contrast degradation in underwater images. These problems greatly reduce the quality of underwater images, affecting the application of underwater images to advanced vision tasks.
Image restoration is an important means of restoring degraded images. Restoration methods typically model the imaging environment and invert the degradation process based on the resulting physical model and estimated parameters to restore the image. With the development of underwater optical imaging systems, underwater image restoration methods have become an important branch of underwater image sharpening methods. Past underwater image restoration methods are typically based on simple underwater imaging models, restoring the underwater image by estimating transmittance and background light. However, the simple underwater imaging model is improved from the foggy day imaging model, and the influence of selective absorption of light by water is not considered. The method based on the model has no robustness, and the effect is to be improved. On the contrary, the recovery method based on the complex underwater imaging model considers the dominant factors of underwater imaging and can more accurately represent the underwater imaging process. The restoration method based on the complex underwater imaging model can effectively improve the color and contrast of the underwater image, so that the processed underwater image is more in line with the visual perception of human beings.
Disclosure of Invention
The invention provides an underwater image color correction method based on a complex underwater imaging model. The method adopts a contrast stretching method to the collected underwater degraded image to obtain a depth estimation input image; secondly, estimating a depth map by using an auto-supervised monocular depth estimation method, and enhancing depth details by using guide filtering; then, converting the relative depth map into an absolute depth map by using a normalization operation; then, the depth map is divided into eight same-size intervals, and the first 1% point with the minimum sum of three channels of red, green and blue is searched in each interval. Fitting by using a complex underwater imaging model according to the found points and the corresponding depth values of the points to obtain backscattering values, and removing on the original image to obtain an underwater image without backscattering; secondly, Gaussian filtering is carried out on the underwater image without the backward scattering to obtain a brightness image, and a bandwidth attenuation coefficient is estimated according to the brightness image and the depth image; and finally, restoring the image based on the complex underwater imaging model according to the bandwidth attenuation coefficient, the non-scattering underwater image and the depth map.
The technical scheme adopted by the invention is as follows:
an underwater image color correction method based on a complex underwater imaging model comprises the following steps:
step S01: carrying out contrast stretching treatment on the input original underwater image;
step S02: acquiring a relative depth map of the underwater image after contrast stretching, and enhancing depth details by using guide filtering;
step S03: converting the relative depth map into an absolute depth map by using a normalization operation;
step S04: the equally divided absolute depth map is eight intervals with the same size, and the first 1% of points in the points with the red, green and blue three-channel values in the sequence from small to large are searched in each interval;
step S05: fitting by using a complex underwater imaging model according to the found points and the corresponding depth values of the points to obtain backscattering values, and removing on the original image to obtain an underwater image without backscattering;
step S06: using Gaussian filtering on the underwater image without backward scattering to obtain a brightness map;
step S07: estimating a bandwidth attenuation coefficient according to the brightness map and the depth map;
step S08: and performing image restoration based on a complex underwater imaging model according to the bandwidth attenuation coefficient, the non-scattering underwater image and the depth map.
Further, the contrast stretching process in step S01 employs the following equation:
Figure BDA0003165080730000021
wherein x isminAnd xmaxRespectively representing the minimum value and the maximum value of pixel points of each channel in the original underwater image, wherein x represents each pixel point of the image, and y represents the image after contrast stretching.
Further, the guiding filtering method adopted by step S02 is expressed as:
Figure BDA0003165080730000022
where q (x, y) represents the filtered output image, TL,i(x, y) denotes a guide image, i and k each denote a pixel index, a and b each denote a coefficient of the linear function when the window center is located at k, wkRepresenting the window size in k-center.
Further, the complex underwater imaging model employed in step S05 is represented as:
Ic＝Dc+Bc
wherein, IcRepresenting the original underwater image taken, DcRepresenting a direct reflected signal; b iscRepresents backscattering; dc，BcCan be represented by the following formula:
Figure BDA0003165080730000031
wherein, JcRepresenting an undegraded underwater image;
Figure BDA0003165080730000032
representing the bandwidth attenuation coefficient, z representing the depth map;
Figure BDA0003165080730000033
wherein A iscRepresenting underwater ambient light;
Figure BDA0003165080730000034
representing the scattering attenuation coefficient, z representing depthFigure (a). The process of obtaining the backscattering value is to combine Jc，
Figure BDA0003165080730000035
Ac，
Figure BDA0003165080730000036
And taking the four unknowns as four unknowns, fitting the four unknowns based on the complex underwater imaging model by using the minimum sum of the red, green and blue channels and the depth map, and substituting the four unknowns into the complex underwater imaging model, so as to solve the back scattering of the whole image according to the model and the depth map.
Further, the gaussian filter expression employed in step S06 is as follows:
Figure BDA0003165080730000037
wherein, (x, y) represents the coordinates of the pixel points, G (x, y) is a gaussian convolution function, and σ represents the size of a gaussian convolution kernel.
Further, the process of estimating the bandwidth attenuation coefficient in step S07 is as follows:
Figure BDA0003165080730000038
wherein,
Figure BDA0003165080730000039
represents the bandwidth attenuation coefficient, EcRepresenting a luminance map and z a depth map.
Further, the process of performing image restoration according to the complex underwater imaging model in step S08 is as follows:
Figure BDA00031650807300000310
wherein, JcRepresenting an undegraded underwater image, DcWhich represents the direct reflected signal, is,
Figure BDA00031650807300000311
representing the bandwidth attenuation coefficient and z representing the depth map.
Compared with the prior art, the invention has the following advantages:
1. the underwater image color correction method is based on a more accurate physical imaging model, can effectively recover the color and contrast of the underwater image compared with the method based on a simple underwater imaging model in the prior art, can be applied to various types of underwater images, and has more stable recovery result.
2. Compared with the enhancement method in the prior art, the method for correcting the color of the underwater image can recover the real color of the underwater image, and the reconstructed color is closer to the original color of an object on the basis of an accurate physical model.
3. The underwater image color correction method does not need to use external hardware equipment, and is different from a mode of obtaining parameters by expensive hardware equipment.
Based on the reason, the method can be popularized and applied in the fields of image preprocessing and the like.
Drawings
In order to clarify the invention or the technical solution, the drawings to be used for the description of the embodiments or the prior art will be briefly summarized below.
FIG. 1 is a schematic flow diagram of the principles of the present invention;
FIG. 2 is an effect diagram of the present invention and other underwater image methods, and FIG. 2-1 is an original image (statue) of an underwater collected image; FIG. 2-2 is a graph showing the effect of treatment by He et al.DCP method; FIG. 2-3 is a graph showing the effect of the treatment by the Peng et al GDCP method; FIGS. 2-4 are graphs of treatment effects using the Peng et al IBLA method;
FIGS. 2-5 are graphs showing the effect of the treatment by the method of the present invention.
FIG. 3 is an effect diagram of the present invention and other underwater image methods, and FIG. 3-1 is an underwater collected image original (coral); FIG. 3-2 is a graph showing the effect of treatment by the He et al. DCP method; FIG. 3-3 is a graph showing the effect of the treatment by the Peng et al GDCP method; FIGS. 3-4 are graphs of treatment effects using the Peng et al IBLA method;
FIGS. 3-5 are graphs showing the effect of the treatment by the method of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
As shown in fig. 1, the present invention provides an underwater image color correction method based on a complex underwater imaging model, comprising the following steps:
step S01: carrying out contrast stretching treatment on the input original underwater image;
the contrast stretching process uses the following formula:
Figure BDA0003165080730000051
wherein x isminAnd xmaxRespectively representing the minimum value and the maximum value of pixel points of each channel in the original underwater image, wherein x represents each pixel point of the image, and y represents the image after contrast stretching;
step S02: acquiring a relative depth map of the underwater image after contrast stretching, and enhancing depth details by using guide filtering;
the acquired depth map may be obtained using a monocular depth estimation method based on self-supervision (c.godard, o.mac Aodha, m.fire, and g.brostow, "scaling in self-superimposed monitor estimation," in proc.ieee/CVF int.con.on Computer Vision (ICCV), (2019), pp.3827-3837) or using a stereo camera;
the guiding filtering method adopted by step S02 is expressed as:
Figure BDA0003165080730000052
where q (x, y) represents the filtered output image, TL,i(x, y) denotes a guide image, i and k each denote a pixel index, a and b each denote a coefficient of the linear function when the window center is located at k, wkRepresents the window size in k-center;
step S03: converting the relative depth map into an absolute depth map by using a normalization operation;
step S04: the equally divided absolute depth map is eight intervals with the same size, and the first 1% of points in the points with the red, green and blue three-channel values in the sequence from small to large are searched in each interval;
step S05: fitting by using a complex underwater imaging model according to the found points and the corresponding depth values of the points to obtain backscattering values, and removing on the original image to obtain an underwater image without backscattering;
the complex underwater imaging model is represented as:
Ic＝Dc+Bc
wherein, IcRepresenting the original underwater image taken, DcRepresenting a direct reflected signal; b iscRepresents backscattering; dc，BcCan be represented by the following formula:
Figure BDA0003165080730000061
wherein, JcRepresenting an undegraded underwater image;
Figure BDA0003165080730000062
representing the bandwidth attenuation coefficient, z representing the depth map;
Figure BDA0003165080730000063
wherein A iscRepresenting underwater ambient light;
Figure BDA0003165080730000064
representing the scattering attenuation coefficient and z representing the depth map. The process of obtaining the backscattering value is to combine Jc，
Figure BDA0003165080730000065
Ac，
Figure BDA0003165080730000066
The four unknown quantities are fitted based on a complex underwater imaging model by using the minimum sum of red, green and blue channels and a depth map as four unknown quantities, and then the four unknown quantities are brought into the complex underwater imaging model, so that the backscattering of the whole image is solved according to the model and the depth map;
step S06: using Gaussian filtering on the underwater image without backward scattering to obtain a brightness map;
the gaussian filter expression used is as follows:
Figure BDA0003165080730000067
wherein, (x, y) represents the coordinates of the pixel points, G (x, y) is a Gaussian convolution function, and sigma represents the size of a Gaussian convolution kernel;
step S07: estimating a bandwidth attenuation coefficient according to the brightness map and the depth map;
the process of estimating the bandwidth attenuation coefficient is as follows:
Figure BDA0003165080730000068
wherein,
Figure BDA0003165080730000071
represents the bandwidth attenuation coefficient, EcRepresents a luminance map, and z represents a depth map;
step S08: performing image restoration based on a complex underwater imaging model according to the bandwidth attenuation coefficient, the non-scattering underwater image and the depth map;
the process of image restoration according to the complex underwater imaging model is as follows:
Figure BDA0003165080730000072
wherein, JcRepresenting an undegraded underwater image, DcWhich represents the direct reflected signal, is,
Figure BDA0003165080730000073
representing the bandwidth attenuation coefficient and z representing the depth map.
To verify the effectiveness of the Image enhancement of the present invention, different scene images were selected as test datasets and compared with the results of the He et al.DCP (K.He, J.Sun and X.Tang, "Single Image Haze Removal Using Dark Channel Printer," in IEEE Transactions on Pattern Analysis and Machine Analysis, vol.33, No.12, pp.2341-2353, Dec.2011, dot: 10.1109/TPAMI.2010.168.), Peng et al.GDCP (Y.Peng, K.Cao, and P.C.Coan, "Generation of Dark Channel Printer for Single storage," IEEE transaction Image Process.27(6),2856 (2868) GDCP, Y.LA.blend and Image catalog, "IEEE transaction Image catalog Image Analysis, and" IEEE reflection Image library 19 "12. upright. 12. C.12. 12, and P.12. C.7. 12. for the same, respectively, for the Image storage, respectively, for the first, respectively, and for the first, respectively, and for the first, and for the first, the second, and the second, respectively, the first, and the second, respectively, and the second, respectively, and the first, respectively, and the second, respectively, and the second, respectively, and the first, respectively, and the second Image, respectively, and the first, and the second, respectively, and the second of the second Image, respectively, and the first, respectively, and the second of the second, respectively, and the first, respectively, and the second of the second Image, respectively, and the second of the first, respectively, and the second Image, respectively, and the second of the first, respectively, and the second of the second, respectively, and the second embodiment, respectively.
As shown in fig. 2, the present invention provides an experimental effect graph after restoring an underwater scene (statue) by other methods. It can be seen from the comparison that the method of the present invention not only does not excessively enhance the underwater scene, but also the color recovery effect and the contrast enhancement effect are both significantly better than those of other methods (He et al. Therefore, the method can effectively improve the quality and visual effect of the underwater image.
As shown in FIG. 3, the invention provides an experimental effect graph after the rehabilitation of an underwater scene (coral) by other methods. Through the comparative analysis with the (He et al DCP, Peng et al GDCP, Peng et al IBLA) method, the coral edge details after the treatment are obviously better than other methods, and the image definition is higher. Therefore, the method can effectively improve the definition of the underwater image.
In order to further verify the robustness of the method provided by the invention, the non-reference image quality evaluation indexes (UIQM and UCIQE) for the underwater image are adopted for comparative analysis, and specific data are shown in table 1 and table 2. The larger the no-reference image quality evaluation index is, the better the restoration effect of the restoration result of the method on image chroma, saturation and contrast is. As shown in tables 1 and 2, the images processed by the method of the present invention have significantly higher values than the results of the other methods without reference indicators, i.e., UIQM and UCIQE. The method disclosed by the invention is proved to be capable of effectively improving the chroma, saturation and contrast of the underwater degraded image.
TABLE 1 No-reference image quality evaluation index (UIQM) of the results of the inventive and other methods
Raw image DCP GDCP IBLA Our
1.3867 1.5246 1.7041 1.6207 1.7849
1.1217 1.4983 1.4964 1.4435 1.6214
TABLE 2 No-reference image quality evaluation index (UCIQE) of results processed by the present invention and other methods
Raw image DCP GDCP IBLA Our
0.4360 0.4843 0.4883 0.5534 0.5996
0.4328 0.5617 0.5594 0.5431 0.6449
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.

Claims (7)

1. The underwater image color correction method based on the complex underwater imaging model is characterized by comprising the following steps of:
step S01: carrying out contrast stretching treatment on the input original underwater image;
step S02: acquiring a relative depth map of the underwater image after contrast stretching, and enhancing depth details by using guide filtering;
step S03: converting the relative depth map into an absolute depth map by using a normalization operation;
step S04: the equally divided absolute depth map is eight intervals with the same size, and the first 1% of points in the points with the red, green and blue three-channel values in the sequence from small to large are searched in each interval;
step S05: fitting by using a complex underwater imaging model according to the found points and the corresponding depth values of the points to obtain backscattering values, and removing on the original image to obtain an underwater image without backscattering;
step S06: using Gaussian filtering on the underwater image without backward scattering to obtain a brightness map;
step S07: estimating a bandwidth attenuation coefficient according to the brightness map and the depth map;
step S08: and performing image restoration based on a complex underwater imaging model according to the bandwidth attenuation coefficient, the non-scattering underwater image and the depth map.
2. The underwater image color correction method based on the complex underwater imaging model according to claim 1, characterized in that: the contrast stretching process in step S01 employs the following formula:
Figure FDA0003165080720000011
wherein x isminAnd xmaxRespectively representing the minimum value and the maximum value of pixel points of each channel in the original underwater image, wherein x represents each pixel point of the image, and y represents the image after contrast stretching.
3. The underwater image color correction method based on the complex underwater imaging model according to claim 1, characterized in that: the guiding filtering method adopted by step S02 is expressed as:
Figure FDA0003165080720000012
where q (x, y) represents the filtered output image, TL,i(x, y) denotes a guide image, i and k each denote a pixel index, a and b each denote a coefficient of the linear function when the window center is located at k, wkIs shown ink window size in the center.
4. The underwater image color correction method based on the complex underwater imaging model according to claim 1, characterized in that: the complex underwater imaging model employed in step S05 is represented as:
Ic＝Dc+Bc
wherein, IcRepresenting the original underwater image taken, DcRepresenting a direct reflected signal; b iscRepresents backscattering; dc，BcCan be represented by the following formula:
Figure FDA0003165080720000021
wherein, JcRepresenting an undegraded underwater image;
Figure FDA0003165080720000022
representing the bandwidth attenuation coefficient, z representing the depth map;
Figure FDA0003165080720000023
wherein A iscRepresenting underwater ambient light;
Figure FDA0003165080720000024
representing the scattering attenuation coefficient and z representing the depth map. The process of obtaining the backscattering value is to combine Jc，
Figure FDA0003165080720000025
Ac，
Figure FDA0003165080720000026
The four unknowns are fitted based on a complex underwater imaging model and then taken into the complex underwater imaging model by using the minimum sum of red, green and blue channels and a depth mapA complex underwater imaging model, whereby the backscatter of the entire image is solved from the model and depth map.
5. The method for correcting the color of the underwater image based on the complex underwater imaging model according to claim 1, wherein the gaussian filter expression adopted in the step S06 is as follows:
Figure FDA0003165080720000027
wherein, (x, y) represents the coordinates of the pixel points, G (x, y) is a gaussian convolution function, and σ represents the size of a gaussian convolution kernel.
6. The method for correcting the color of the underwater image based on the complex underwater imaging model according to claim 4, wherein the step S07 comprises the following steps:
Figure FDA0003165080720000028
wherein,
Figure FDA0003165080720000029
represents the bandwidth attenuation coefficient, EcRepresenting a luminance map and z a depth map.
7. The method for correcting the color of the underwater image based on the complex underwater imaging model according to claim 6, wherein the step S08 is to perform image restoration according to the complex underwater imaging model as follows:
Figure FDA00031650807200000210
wherein, JcRepresenting an undegraded underwater image, DcWhich represents the direct reflected signal, is,
Figure FDA00031650807200000211
representing the bandwidth attenuation coefficient and z representing the depth map.
CN202110802196.6A 2021-07-15 2021-07-15 Underwater image color correction method based on complex underwater imaging model Pending CN113538276A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110802196.6A CN113538276A (en) 2021-07-15 2021-07-15 Underwater image color correction method based on complex underwater imaging model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110802196.6A CN113538276A (en) 2021-07-15 2021-07-15 Underwater image color correction method based on complex underwater imaging model

Publications (1)

Publication Number Publication Date
CN113538276A true CN113538276A (en) 2021-10-22

Family

ID=78128216

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110802196.6A Pending CN113538276A (en) 2021-07-15 2021-07-15 Underwater image color correction method based on complex underwater imaging model

Country Status (1)

Country Link
CN (1) CN113538276A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110689504A (en) * 2019-10-11 2020-01-14 大连海事大学 Underwater image restoration method based on secondary guide transmission diagram
CN111047530A (en) * 2019-11-29 2020-04-21 大连海事大学 Underwater image color correction and contrast enhancement method based on multi-feature fusion
CN112070683A (en) * 2020-07-21 2020-12-11 西北工业大学 Underwater polarization image restoration method based on polarization and wavelength attenuation joint optimization
CN112488948A (en) * 2020-12-03 2021-03-12 大连海事大学 Underwater image restoration method based on black pixel point estimation backscattering

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110689504A (en) * 2019-10-11 2020-01-14 大连海事大学 Underwater image restoration method based on secondary guide transmission diagram
CN111047530A (en) * 2019-11-29 2020-04-21 大连海事大学 Underwater image color correction and contrast enhancement method based on multi-feature fusion
CN112070683A (en) * 2020-07-21 2020-12-11 西北工业大学 Underwater polarization image restoration method based on polarization and wavelength attenuation joint optimization
CN112488948A (en) * 2020-12-03 2021-03-12 大连海事大学 Underwater image restoration method based on black pixel point estimation backscattering

Similar Documents

Publication Publication Date Title
Ancuti et al. Color balance and fusion for underwater image enhancement
Liang et al. Single underwater image enhancement by attenuation map guided color correction and detail preserved dehazing
CN106846263B (en) Based on the image defogging method for merging channel and sky being immunized
Ancuti et al. Enhancing underwater images and videos by fusion
Muniraj et al. Underwater image enhancement by combining color constancy and dehazing based on depth estimation
CN111047530B (en) Underwater image color correction and contrast enhancement method based on multi-feature fusion
Sathya et al. Underwater image enhancement by dark channel prior
CN109118446B (en) Underwater image restoration and denoising method
CN110675340A (en) Single image defogging method and medium based on improved non-local prior
CN112488948B (en) Underwater image restoration method based on black pixel point estimation back scattering
Soni et al. An improved image dehazing technique using CLAHE and guided filter
CN110689504B (en) Underwater image restoration method based on secondary guide transmission diagram
Pan et al. De-scattering and edge-enhancement algorithms for underwater image restoration
CN111861896A (en) UUV-oriented underwater image color compensation and recovery method
CN110827210A (en) Underwater image sharpening method and system based on color curve decomposition
Barros et al. Single-shot underwater image restoration: A visual quality-aware method based on light propagation model
Yu et al. Image and video dehazing using view-based cluster segmentation
CN111210395A (en) Retinex underwater image enhancement method based on gray value mapping
CN114219732A (en) Image defogging method and system based on sky region segmentation and transmissivity refinement
CN113284061A (en) Underwater image enhancement method based on gradient network
CN115393216A (en) Image defogging method and device based on polarization characteristics and atmospheric transmission model
CN110335210B (en) Underwater image restoration method
Tan et al. Image haze removal based on superpixels and Markov random field
CN114119383B (en) Underwater image restoration method based on multi-feature fusion
Wang et al. Single-image dehazing using color attenuation prior based on haze-lines

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