CN113269763B - Underwater image definition recovery method based on depth map restoration and brightness estimation - Google Patents
Underwater image definition recovery method based on depth map restoration and brightness estimation Download PDFInfo
- Publication number
- CN113269763B CN113269763B CN202110620221.9A CN202110620221A CN113269763B CN 113269763 B CN113269763 B CN 113269763B CN 202110620221 A CN202110620221 A CN 202110620221A CN 113269763 B CN113269763 B CN 113269763B
- Authority
- CN
- China
- Prior art keywords
- image
- depth
- underwater
- value
- brightness
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 75
- 238000011084 recovery Methods 0.000 title claims abstract description 12
- 238000003384 imaging method Methods 0.000 claims abstract description 16
- 238000009499 grossing Methods 0.000 claims abstract description 4
- 238000003709 image segmentation Methods 0.000 claims abstract description 4
- 238000010606 normalization Methods 0.000 claims abstract description 4
- 238000012545 processing Methods 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 abstract 1
- 230000000694 effects Effects 0.000 description 17
- 101100136092 Drosophila melanogaster peng gene Proteins 0.000 description 10
- 241000592718 Ibla Species 0.000 description 8
- 101100014407 Pisum sativum GDCSP gene Proteins 0.000 description 8
- 238000013135 deep learning Methods 0.000 description 6
- 238000006731 degradation reaction Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000015556 catabolic process Effects 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 241000270666 Testudines Species 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000013441 quality evaluation Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000031700 light absorption Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000001303 quality assessment method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- 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
- 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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
- G06T2207/10004—Still image; Photographic 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
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
The invention provides an underwater image definition recovery method based on depth map restoration and brightness estimation. The method of the invention comprises the following steps: firstly, carrying out equalization treatment on an underwater image; secondly, estimating the relative depth of the equalized underwater image by using a monocular depth estimation model, and then dividing a part with incorrect depth estimation by using an image segmentation strategy to re-estimate; then, smoothing the depth re-estimated region using guided filtering; then, converting the relative depth into absolute depth through a depth normalization operation; equally dividing the image pixel point into a plurality of sections according to the depth value, and searching the potential minimum pixel point of the degraded image in each section; using an underwater image imaging model, fitting parameters by a sub-channel, and estimating and removing backscattering; and finally, estimating the brightness parameter by adopting an automatic brightness value estimation method, adjusting the brightness on the image with the back scattering removed by using the optimal brightness parameter, and removing the color cast of the underwater image.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to an underwater image definition recovery method based on depth map restoration and brightness estimation.
Background
The underwater image plays an important role in the fields of marine geological exploration, marine ecological protection, marine resource development and the like. However, underwater images and videos generally have problems of low contrast, low definition, low chromaticity and the like due to the absorption and scattering effects of water and suspended particulate matters on light. The underwater image with serious degradation has no practical application value. In order to effectively improve the quality of an underwater image, an underwater image enhancement method and an underwater image restoration method are two commonly used methods. In recent years, with the rapid development of a deep learning method in the field of image processing, the use of deep learning to restore the sharpness of an underwater image has also become a popular development trend.
The underwater image enhancement method mainly uses methods such as a filter, histogram equalization and the like to recover the color and saturation of the image. Although the method can effectively improve the visual effect of the image, the relation between the degradation degree and the depth of field is ignored, and the true color of the scene cannot be recovered. The underwater image restoration method mainly reverses the degradation process of the underwater image through an underwater imaging model. Such methods typically use a priori knowledge to solve model parameters, but the prior-based underwater image restoration method has the problem of employing a priori and target scene mismatch. Deep learning-based methods are currently still not mature enough and have a number of problems. On the one hand, the deep learning-based method has fixed parameter estimation values after training and lacks sufficient flexibility in processing complex underwater environments. When the new underwater image type is different from the underwater environment type of the training set, the trained model may not output satisfactory results. On the other hand, deep learning has its own limitations such as: a large number of parameters are required to learn the complex mapping function and whether to find a suitable training set, and the potential value of the deep learning method in practical application is limited. The underwater image definition recovery method based on depth map restoration and brightness estimation not only considers the influence of the imaging range on the underwater image degradation, but also uses a more accurate imaging model. Therefore, when the underwater images of different water body types are processed, the method can obtain stable recovery results with better effects. In addition, the color correction method used by the method can obviously improve the brightness, chromaticity and contrast of the underwater image.
Disclosure of Invention
According to the technical problem, an underwater image definition recovery method based on depth map restoration and brightness estimation is provided. According to the invention, the thinned depth map and the minimum pixel point are used, the backscattering is estimated and removed according to the underwater imaging physical model, the information entropy is used for automatically selecting the optimal brightness parameter, and the integral brightness of the image is adjusted to obtain the colorful underwater image.
The invention adopts the following technical means:
an underwater image definition recovery method based on depth map restoration and brightness estimation comprises the following steps:
step S01: stretching the contrast of the original RGB image, ensuring that the minimum value and the maximum value of pixels of the original image are 0 and 255 respectively, and estimating the relative depth map of the image after stretching the contrast by using a monocular depth estimation model;
step S02: dividing a background region error estimation part of the image subjected to contrast stretching by using a dividing method, re-estimating the depth of the part, and smoothing the re-estimation region by using a guide filter;
step S03: selecting upper and lower depth limits according to the actual depth of the scene to perform depth normalization processing so as to obtain an absolute depth map of the original RGB image;
step S04: dividing each pixel point of an original RGB image into 10 groups from small to large according to the depth value, sequencing each group according to the sum of the RGB values of the pixel points from small to large, and taking 200 pixel points which are sequenced to the front;
step S05: according to the underwater image imaging model, the minimum pixel point and the depth value thereof are respectively fittedWherein A is a value of c Represents atmospheric light; />Representing the backscattering coefficient; j (J) c Representing an undegraded underwater image; beta c D Representing the bandwidth coefficient;
step S06: imaging models and parameters through the underwater imageValue, estimate and remove the back scatter;
step S07: on the image from which the back scattering is removed, sorting the pixel values of the three channels respectively, and taking the pixel values of the pixel points between 0.5% and 2% as brightness parameters according to the interval value of 0.15;
step S08: each brightness parameter corresponds to an image enhanced by the brightness parameter, and the image with the highest information entropy is selected as a final enhancement result.
Further, the image contrast stretching formula in step S01 is:
wherein x is min And x max Respectively representing the minimum value and the maximum value of pixel points in the original image, wherein x represents each pixel point of the image, and y represents the image with stretched contrast.
Further, the image segmentation method in step S02 adopts mahalanobis distance to measure the similarity between points in RGB space; the mahalanobis distance D (z, m) between any point z and average color m in RGB space is given by:
where C represents the covariance matrix of the selected samples.
Further, in step S03, for each relative depth value x in the original depth map, the relative depth value x is converted into an absolute depth value y by using a linear conversion manner, and a specific conversion formula is as follows:
wherein,,representing the maximum value and the minimum value of the depth values in the original depth map; /> Representing the minimum and maximum values of the depth values that need to be converted.
Further, the underwater image imaging model in step S05 is:
wherein A is c Represents atmospheric light;representing the backscattering coefficient; j (J) c Representing an undegraded underwater image; />Representing the bandwidth factor.
Further, the manner of automatically obtaining the optimal enhanced image in step S08 is as follows:
wherein H (D) ri ) Represents the maximum entropy of the information,after the pixel values of the three channels are sequenced, the pixel values of the pixel points between 0.5% and 2% of each channel are selected according to 0.15 as the interval; dc is the image after scattering removal, W 0 ＝0.1；/>The optimal enhanced image is obtained, wherein the information entropy is calculated as follows:
wherein i represents the gray level of the pixel, p i Representing the occupancy of a pixel having a gray level i in an entire imageRatio.
Compared with the prior art, the invention has the following advantages:
1. for the problems of color distortion of an image enhancement method and large transmissivity estimation deviation of a traditional DCP-based method, the invention uses a novel underwater physical imaging model to estimate back scattering in consideration of an underwater image degradation mechanism, the scattering removal effect is obvious, and the restoration result is close to a real undegraded underwater scene.
2. The invention only needs to obtain the depth map of the image, and does not need to estimate the transmissivity and the background light of the image, and compared with the traditional restoration method, the invention has lower complexity.
3. The invention has better practicability and robustness, and can process various underwater images without the problems of over-enhancement, artifact and the like.
For the reasons, the method can be widely popularized in the fields of image processing and the like.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to the drawings without inventive effort to a person skilled in the art.
Fig. 1 is a schematic flow chart of the underwater image definition recovery method according to the present invention.
FIG. 2 is a graph of the effect of the present invention compared to other methods of underwater image restoration in an offshore scenario; wherein, FIG. 2-1 is an image artwork (marine organism) acquired underwater; FIG. 2-2 is a diagram showing the processing effect of the Li et al UWCNN method; FIGS. 2-3 are graphs showing the effects of the Peng et al GDCP method; FIGS. 2-4 are graphs showing the effect of the Peng et al IBLA method; FIGS. 2-5 are graphs showing the effect of the method according to the present invention.
FIG. 3 is a graph showing the effect of the invention compared with other underwater imaging methods in a turbid water body, wherein FIG. 3-1 is an original image (turtle) acquired underwater; FIG. 3-2 is a diagram showing the processing effect of the Li et al UWCNN method; FIG. 3-3 is a graph of the processing effect of the Peng et al GDCP method; FIGS. 3-4 are graphs showing the effect of the Peng et al IBLA method; FIGS. 3-5 are graphs showing the processing effects of the method of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise 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 invention provides an underwater image definition recovery method based on depth map restoration and brightness estimation, which comprises the following steps:
step S01: stretching the contrast of the original RGB image, ensuring that the minimum value and the maximum value of pixels of the original image are 0 and 255 respectively, and estimating the relative depth map of the image after stretching the contrast by using a monocular depth estimation model; the image contrast stretching formula is:
wherein x is min And x max Respectively representing the minimum value and the maximum value of pixel points in an original image, wherein x represents each pixel point of the image, and y represents the image with stretched contrast;
step S02: dividing a background region error estimation part of the image subjected to contrast stretching by using a dividing method, re-estimating the depth of the part, and smoothing the re-estimation region by using a guide filter; the image segmentation method adopts a mahalanobis distance to measure the similarity between each point in an RGB space; the mahalanobis distance D (z, m) between any point z and average color m in RGB space is given by:
wherein C represents the covariance matrix of the selected samples; because the background area of the image is the area farthest from the camera in the whole image, the depth value of the sample point of the result area is estimated to be the 1% depth value of the original depth map after being sequenced from small to large;
step S03: selecting proper approximate depth upper and lower limits (in the range of 0-20 meters) according to the actual depth of a scene to perform depth normalization processing so as to acquire an absolute depth map of the original RGB image; for each relative depth value x in the original depth map, the relative depth value x is converted into an absolute depth value y by using a linear conversion mode, and a specific conversion formula is as follows:
wherein,,representing the maximum value and the minimum value of the depth values in the original depth map; /> Minimum and maximum values representing depth values to be converted, here +.>A depth estimation range (in meters) representing the reality of the image;
step S04: dividing each pixel point of an original RGB image into 10 groups from small to large according to the depth value, sequencing each group according to the sum of the RGB values of the pixel points from small to large, and taking 200 pixel points which are sequenced to the front;
step S05: according to the underwater image imaging model, the minimum pixel point and the depth value thereof are respectively fittedWherein A is a value of c Represents atmospheric light; />Representing the backscattering coefficient; j (J) c Representing an undegraded underwater image; beta c D Representing the bandwidth coefficient; the underwater image imaging model is as follows:
step S06: imaging models and parameters through the underwater imageValue, estimate and remove the back scatter;
step S07: on the image from which the back scattering is removed, sorting the pixel values of the three channels respectively, and taking the pixel values of the pixel points between 0.5% and 2% as brightness parameters according to the interval value of 0.15;
step S08: each brightness parameter corresponds to an image enhanced by the brightness parameter, and an image with highest information entropy is selected as a final enhancement result; the mode of automatically obtaining the optimal enhanced image is as follows:
wherein H (D) ri ) Represents the maximum entropy of the information,after the pixel values of the three channels are sequenced, the pixel values of the pixel points between 0.5% and 2% of each channel are selected according to 0.15 as the interval; d (D) c Is an image after scattering removal, W 0 ＝0.1；/>The optimal enhanced image is obtained. The information entropy is calculated as follows:
wherein i represents the gray level of the pixel, p i The duty cycle of a pixel point of gray level i in the entire image is represented.
In order to verify the effectiveness of the scattering removal of the invention, underwater images of different scenes are selected as a test set, and the experimental results of the methods of Li et al UWCNN (C.Li, S.Anwar, and F.Porikli, "Underwater scene prior inspired deep underwater image and video enhancement," Pattern Recognit.98,1-11 (2020). UWCNN), peng et al GDCP (Y.Peng, K.Cao, and P.C. Cosman, "Generalization of the Dark Channel Prior for Single Image Restoration," IEEE Trans.image Process.27 (6), 2856-2868 (2018). GDCP), peng et al IBLA (Y.Peng and P.C. Cosman, "Underwater Image Restoration Based on Image Blurriness and Light Absorption," IEEE Trans.image Process.26 (4), 1579-1594 (2017). IBLA) are compared and analyzed qualitatively and quantitatively.
As shown in fig. 2, the present invention provides a contrast effect map in an offshore scene (marine life) with other underwater image restoration methods. As can be seen by comparison, in the effect graph processed by the method, the image contrast is obviously improved and is superior to other methods (Li et al UWCNN, peng et al GDCP, peng et al IBLA). Therefore, the method can correct the color, enhance the contrast of the image and improve the visual effect of the image.
As shown in FIG. 3, the invention provides a graph comparing experimental effects of other methods in turbid water bodies (turtles). By comparing and analyzing with the methods (Li et al UWCNN, peng et al GDCP, peng et al IBLA), the color recovery effect of the processed turtle is obviously better than that of other methods, and the image definition is higher. Therefore, the method can correct the color, enhance the contrast of the image and improve the visual effect of the image.
In order to verify the robustness of the present invention, comparative analysis was performed without reference to the image quality evaluation indexes UIQM and uci qe, and specific data are shown in tables 1 and 2. The larger the non-reference image quality evaluation index is, the better the chromaticity, saturation and contrast of the image generated by the method is, and the better the visual effect can be obtained. The two index data values of the image processed by the method are superior to those of other methods. The method of the invention can effectively improve the color and contrast of the image.
TABLE 1 non-reference image quality assessment index (UIQM) for the results of the inventive and other methods
| Raw image | UWCNN | GDCP | IBLA | Our |
| 1.1217 | 1.2694 | 1.4964 | 1.4435 | 1.6065 |
| 0.6224 | 0.5232 | 0.9900 | 1.0983 | 1.4034 |
TABLE 2 non-reference image quality evaluation index (UCIQE) for processing results of the methods and other methods of the present invention
| Raw image | UWCNN | GDCP | IBLA | Our |
| 0.4328 | 0.4572 | 0.5594 | 0.5431 | 0.6577 |
| 0.3220 | 0.3126 | 0.3730 | 0.4754 | 0.6341 |
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the 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 scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced with equivalents; such modifications and substitutions do not depart from the spirit of the technical solutions according to the embodiments of the present invention.
Claims (5)
1. The underwater image definition recovery method based on depth map restoration and brightness estimation is characterized by comprising the following steps of:
step S01: stretching the contrast of the original RGB image, ensuring that the minimum value and the maximum value of pixels of the original image are 0 and 255 respectively, and estimating the relative depth map of the image after stretching the contrast by using a monocular depth estimation model;
step S02: dividing a background region error estimation part of the image subjected to contrast stretching by using a dividing method, re-estimating the depth of the part, and smoothing the re-estimation region by using a guide filter;
step S03: selecting upper and lower depth limits according to the actual depth of the scene to perform depth normalization processing so as to obtain an absolute depth map of the original RGB image;
step S04: dividing each pixel point of an original RGB image into 10 groups from small to large according to the depth value, sequencing each group according to the sum of the RGB values of the pixel points from small to large, and taking 200 pixel points which are sequenced to the front;
step S05: according to the underwater image imaging model, the minimum pixel point and the depth value thereof are respectively fittedWherein A is a value of c Represents atmospheric light; />Representing the backscattering coefficient; j (J) c Representing an undegraded underwater image; />Representing the bandwidth coefficient;
the underwater image imaging model in step S05 is:
wherein A is c Represents atmospheric light;representing the backscattering coefficient; j (J) c Representing an undegraded underwater image; />Representing the bandwidth coefficient;
step S06: imaging models and parameters through the underwater imageValue, estimate and remove the back scatter;
step S07: on the image from which the back scattering is removed, sorting the pixel values of the three channels respectively, and taking the pixel values of the pixel points between 0.5% and 2% as brightness parameters according to the interval value of 0.15;
step S08: each brightness parameter corresponds to an image enhanced by the brightness parameter, and the image with the highest information entropy is selected as a final enhancement result.
2. The underwater image definition restoration method based on depth map restoration and brightness estimation according to claim 1, wherein the image contrast stretching formula in step S01 is:
wherein x is min And x max Respectively representing the minimum value and the maximum value of pixel points in the original image, wherein x represents each pixel point of the image, and y represents the image with stretched contrast.
3. The underwater image definition restoration method based on depth map restoration and brightness estimation according to claim 1, wherein the image segmentation method in step S02 adopts mahalanobis distance to measure the similarity between points in RGB space; the mahalanobis distance D (z, m) between any point z and average color m in RGB space is given by:
where C represents the covariance matrix of the selected samples.
4. The underwater image definition restoration method based on depth map restoration and brightness estimation according to claim 1, wherein in step S03, for each relative depth value x in the original depth map, it is converted into an absolute depth value y by using a linear conversion method, and a specific conversion formula is as follows:
wherein,,representing the maximum value and the minimum value of the depth values in the original depth map; /> Representing the minimum and maximum values of the depth values that need to be converted.
5. The underwater image definition restoration method based on depth map restoration and brightness estimation according to claim 1, wherein the manner of automatically obtaining the optimal enhanced image in step S08 is as follows:
wherein,,representing the maximum entropy of information +.>After the pixel values of the three channels are sequenced, the pixel values of the pixel points between 0.5% and 2% of each channel are selected according to 0.15 as the interval; d (D) c Is an image after scattering removal, W 0 ＝0.1；/>The optimal enhanced image is obtained, wherein the information entropy is calculated as follows:
wherein i represents the gray level of the pixel, p i The duty cycle of a pixel point of gray level i in the entire image is represented.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110620221.9A CN113269763B (en) | 2021-06-03 | 2021-06-03 | Underwater image definition recovery method based on depth map restoration and brightness estimation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110620221.9A CN113269763B (en) | 2021-06-03 | 2021-06-03 | Underwater image definition recovery method based on depth map restoration and brightness estimation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113269763A CN113269763A (en) | 2021-08-17 |
| CN113269763B true CN113269763B (en) | 2023-07-21 |
Family
ID=77234232
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110620221.9A Active CN113269763B (en) | 2021-06-03 | 2021-06-03 | Underwater image definition recovery method based on depth map restoration and brightness estimation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113269763B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115496694B (en) * | 2022-09-30 | 2023-07-25 | 湖南科技大学 | Method for recovering and enhancing underwater image based on improved image forming model |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
-
2021
- 2021-06-03 CN CN202110620221.9A patent/CN113269763B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
Non-Patent Citations (1)
| Title |
|---|
| 基于颜色衰减先验和白平衡的水下图像复原;韩辉;周妍;蔡晨东;;计算机与现代化(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113269763A (en) | 2021-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111047530B (en) | Underwater image color correction and contrast enhancement method based on multi-feature fusion | |
| CN109872285B (en) | Retinex low-illumination color image enhancement method based on variational constraint | |
| CN111489303A (en) | Maritime affairs image enhancement method under low-illumination environment | |
| CN111127359B (en) | Underwater image enhancement method based on selective compensation of colors and three-interval equalization | |
| CN110458792B (en) | Method and device for evaluating quality of face image | |
| CN112488948B (en) | Underwater image restoration method based on black pixel point estimation back scattering | |
| CN110782407B (en) | Single image defogging method based on sky region probability segmentation | |
| CN109816605A (en) | A kind of MSRCR image defogging method based on multichannel convolutive | |
| CN114118144A (en) | Anti-interference accurate aerial remote sensing image shadow detection method | |
| Mostafa et al. | Evaluating the effects of image filters in CT liver CAD system | |
| CN111325688B (en) | Unmanned aerial vehicle image defogging method for optimizing atmosphere light by fusion morphology clustering | |
| CN116823686B (en) | Night infrared and visible light image fusion method based on image enhancement | |
| CN112330613B (en) | Evaluation method and system for cytopathology digital image quality | |
| CN105678245A (en) | Target position identification method based on Haar features | |
| CN115511907B (en) | Scratch detection method for LED screen | |
| CN111476744B (en) | Underwater image enhancement method based on classification and atmospheric imaging model | |
| CN113269763B (en) | Underwater image definition recovery method based on depth map restoration and brightness estimation | |
| CN114119383B (en) | Underwater image restoration method based on multi-feature fusion | |
| CN114693548B (en) | Dark channel defogging method based on bright area detection | |
| CN108596843B (en) | Underwater image color recovery algorithm based on bright channel | |
| CN117197064A (en) | Automatic non-contact eye red degree analysis method | |
| CN115908155A (en) | NSST domain combined GAN and scale correlation coefficient low-illumination image enhancement and denoising method | |
| CN116433525A (en) | Underwater image defogging method based on edge detection function variation model | |
| Dixit et al. | Image contrast optimization using local color correction and fuzzy intensification | |
| CN116797468A (en) | Low-light image enhancement method based on self-calibration depth curve estimation of soft-edge reconstruction |
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 |