CN115908179B - Underwater image contrast enhancement method based on double priori optimization - Google Patents
Underwater image contrast enhancement method based on double priori optimization Download PDFInfo
- Publication number
- CN115908179B CN115908179B CN202211449049.6A CN202211449049A CN115908179B CN 115908179 B CN115908179 B CN 115908179B CN 202211449049 A CN202211449049 A CN 202211449049A CN 115908179 B CN115908179 B CN 115908179B
- Authority
- CN
- China
- Prior art keywords
- base layer
- layer
- priori
- detail
- local
- 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 56
- 238000005457 optimization Methods 0.000 title claims abstract description 13
- 239000003086 colorant Substances 0.000 claims abstract description 10
- 238000012937 correction Methods 0.000 claims description 10
- 239000013598 vector Substances 0.000 claims description 9
- 230000002708 enhancing effect Effects 0.000 claims description 6
- 230000014509 gene expression Effects 0.000 claims description 5
- 230000009977 dual effect Effects 0.000 claims description 4
- 230000003190 augmentative effect Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 206010007559 Cardiac failure congestive Diseases 0.000 description 3
- 101100014407 Pisum sativum GDCSP gene Proteins 0.000 description 3
- 230000015556 catabolic process Effects 0.000 description 3
- 238000006731 degradation reaction Methods 0.000 description 3
- 238000010521 absorption reaction Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 102100031786 Adiponectin Human genes 0.000 description 1
- -1 DTVR Proteins 0.000 description 1
- 101000775469 Homo sapiens Adiponectin Proteins 0.000 description 1
- 241000196171 Hydrodictyon reticulatum Species 0.000 description 1
- 241000592718 Ibla Species 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000000889 atomisation Methods 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention provides a double priori optimized underwater image contrast enhancement method, which is characterized in that an underwater image with corrected colors is obtained, the underwater image with corrected colors is converted into an HSV color model from an RGB color model, and a base layer and a detail layer are decomposed aiming at a V channel, wherein the method is represented as follows: for the V channel, decomposing the V channel into a base layer and a detail layer by adopting a space priori and a texture priori, realizing local contrast enhancement of the base layer by utilizing an integral strategy to count local mean and variance for the base layer, and realizing enhancement of texture details by utilizing a nonlinear stretching function for the detail layer. The underwater image contrast enhancement method with double priori optimization enhances the contrast of the image, highlights texture details, and can well solve the problem of texture detail loss caused by scattering.
Description
Technical Field
The invention relates to a processing method of an underwater image, in particular to a contrast enhancement method of an underwater image with double priori optimization.
Background
In the field of underwater robot vision, clear underwater images are important carriers and presentation forms for acquiring valuable information. However, underwater images often suffer from various quality degradation problems due to the complex physical environment of the water and absorption and scattering of light. The scattering effect is easy to cause the atomization blurring and detail loss of the underwater image; absorption tends to cause color distortion, contrast and brightness degradation in the underwater image.
Among them, color distortion is a quality degradation problem that is mainly faced by underwater images. Currently, a statistical-based method, a linear stretching-based method, a compensation-based method, and a color transmission-based method are gradually applied to color distortion correction of an underwater image, and effectiveness is achieved.
Statistical-based methods rely on a priori information, but the prior information is difficult to solve. Both the linear stretching-based and compensation-based methods are prone to reddish distortion and overcorrection problems. Color transmission based methods rely on reference images, so that the effectiveness and robustness of the algorithm is challenging. In general, although these methods have been effective in underwater color correction, these methods have some limitations.
The application number is as follows: CN202210556777.0, invention name: the invention patent of a local self-adaptive underwater image contrast enhancement method provides that an underwater image with corrected colors is obtained, the underwater image with corrected colors is converted from an RGB color model to a CIELAB color model, and different strategies are respectively executed aiming at a brightness channel L, a color channel a and a color channel b: for the brightness channel L, taking a local image block as an object, counting the mean value and the variance of the local image block by utilizing an integral graph and a square integral graph, and adaptively enhancing the contrast of the brightness channel L by utilizing the mean value and the variance of the local image block; introducing guided filtering to reduce noise in the process of enhancing the contrast of the brightness channel L; and balancing the chromatic aberration between the color channel a and the color channel b by adopting a color balancing strategy aiming at the color channel a and the color channel b. The method has moderate contrast of the enhanced image and low time complexity, can inhibit noise and enables the contrast and color of the enhanced image to be close to those of the land image. But the method ignores texture details and does not have wide applicability.
In general, conventional linear stretching methods are prone to overcorrection problems, and such methods cannot effectively correct underwater images with color distortion diversity.
In order to solve the above problems, an ideal technical solution is always sought.
Disclosure of Invention
The invention aims at overcoming the defects of the prior art, thereby providing a double priori optimized underwater image contrast enhancement method which can enhance the contrast of an image, highlight texture details and well solve the problem of texture detail loss caused by scattering.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows: the method for enhancing the contrast of the underwater image with double priori optimization comprises the steps of firstly obtaining an underwater image with corrected colors, converting the underwater image with corrected colors from an RGB color model to an HSV color model, and decomposing a base layer and a detail layer aiming at a V channel, wherein the method is represented as follows:
aiming at the V channel, decomposing the V channel into a base layer and a detail layer by adopting a space priori and a texture priori, realizing local contrast enhancement of the base layer by utilizing an integral strategy to count local mean and variance aiming at the base layer, and realizing enhancement of texture details by utilizing a nonlinear stretching function aiming at the detail layer;
wherein an optimization model that decomposes the base layer and the detail layer of the V-channel using spatial and texture priors is defined as follows:
wherein I is V 、I B And I V -I B Representing an input image, a base layer and a detail layer, respectively;and->Respectively represent I V And I B Is a concatenation vector of (a); />Representing an integrated vector; />Representing expressions of the gradient operation matrix in different directions; n represents the total number of pixels of the input image;
the first itemForcing the base layer as close as possible to the input image; then introduce the second item->Is a base layer space priori; while texture a priori of the third detail layer +.>Performing element-wise non-zero operations generates binary vectors.
Based on the above, redefined using the augmented lagrangian model as:
wherein two auxiliary variables are introducedAnd->Replace->And->j 1 And j 2 Two variables of the Lagrangian function are used, and eta is a parameter for iterative updating of the objective function;
iterative optimization of the objective function by minimizing several sub-problems and maximizing both problems using the Alternate Direction Method of Multipliers (ADMM), when λ 1 =0.25 and λ 2 When=0.025, the alternate direction method of the multiplier effectively decomposes I near the bottom of the input image in at least 20 iterations B After the base layer is solved, the detail layer passes through I D ＝I V -I B Solving is performed, and then different enhancement operations are performed on the base layer and the detail layer.
Based on the above, the dominant attribute of the local image block is used to enhance the base layer, the average value of the local block K is approximated to be a low-frequency component, and the information obtained by subtracting K from the input image block is approximated to be a high-frequency component; the key to improving the detail layer is how to effectively improve the high frequency components; in the local image block K, the intra-block local mean is solved using the integral map and used to refine the base layer, the enhancement process is defined as:
wherein,delta is the enhancement control parameter of the high frequency component, which is the mean value of the local image block, ++>To strengthen the base layer;
avoiding artifacts or local darkness during local block enhancement, using Gamma correction strategies has better stretching performance for low pixel values, redefining it as:
wherein θ is a correction factor parameter, θ is set to 0.65, and the bottom layer is traversed by using the local block to obtain a final enhanced bottom layer
Based on the above, the detail layer is further stretched using a nonlinear stretching function, which has the expression:
where σ is a stretch control reference, set to 0.88.Is an enhanced detail layer;
enhanced V-channels using enhanced detail layers and enhanced base layers are defined as:
wherein,is an enhanced V-channel.
Compared with the prior art, the method has outstanding substantive characteristics and remarkable progress, and specifically, the method firstly utilizes an algorithm to obtain a foundation layer and a detail layer of the underwater image, and utilizes a double priori optimized underwater image contrast enhancement strategy: i.e. in the base layer, the dominant properties of the local image blocks are used to enhance the base layer. In consideration of the texture structure of the sharpened image in the detail layer, the nonlinear stretching function is used for further stretching the detail layer, and the method is used for solving the problem that the traditional linear stretching method is easy to cause overcorrection.
In addition, the present invention utilizes spatial and texture policies: the base layer and the detail layer are further corrected, so that the enhanced image is as close to a land image as possible in contrast and color, and the enhanced image can be widely popularized and applied in the underwater image processing field.
Drawings
FIG. 1 is a flow chart of the underwater image contrast enhancement method of the double prior optimization of the present invention in an embodiment of the present invention.
FIG. 2 is a view showing the result of underwater image enhancement in the embodiment of the present invention and other methods.
Detailed Description
The technical scheme of the invention is further described in detail through the following specific embodiments.
In order to verify the effectiveness of the color correction, the underwater images with different color distortion types are selected as a test set, and the IBLA, HMUC, GDCP, DTVR, BRU, ACDC, UNTV, waterNet, FUnlEGAN and UIESNet methods are subjected to subjective and objective comparison.
As shown in fig. 1, a dual prior optimized underwater image contrast enhancement method firstly acquires an underwater image with corrected colors, converts the underwater image with corrected colors from an RGB color model to an HSV color model, and implements base layer and detail layer decomposition for a V channel, which is represented as follows:
for the V channel, decomposing the V channel into a base layer and a detail layer by adopting a space priori and a texture priori, realizing local contrast enhancement of the base layer by utilizing an integral strategy to count local mean and variance for the base layer, and realizing enhancement of texture details by utilizing a nonlinear stretching function for the detail layer.
Wherein an optimization model that decomposes the base layer and the detail layer of the V-channel using spatial and texture priors is defined as follows:
wherein I is V 、I B And I V -I B Representing an input image, a base layer and a detail layer, respectively;and->Respectively represent I V And I B Is a concatenation vector of (a); />Representing an integrated vector; />Representing expressions of the gradient operation matrix in different directions; n represents the total number of pixels of the input image;
the first itemForcing the base layer as close as possible to the input image; then introduce the second item->Is a base layer space priori; while texture a priori of the third detail layer +.>Performing element-wise non-zero operations generates binary vectors.
Redefined using the augmented lagrangian model as:
the formula is mainly used for obtaining each sub-term in the formula so as to obtain a base layer and a detail layer. Wherein two auxiliary variables are introducedAnd->Replace->And->j 1 And j 2 Two variables of the Lagrangian function are used, and eta is a parameter for iterative updating of the objective function;
iterative optimization of the objective function by minimizing several sub-problems and maximizing both problems using the Alternate Direction Method of Multipliers (ADMM), when λ 1 =0.25 and λ 2 When=0.025, the alternate direction method of the multiplier effectively decomposes I near the bottom of the input image in at least 20 iterations B After the base layer is solved, the detail layer passes through I D ＝I V -I B Solving is performed, and then different enhancement operations are performed on the base layer and the detail layer.
Enhancing the base layer by using the dominant attribute of the local image block, approximating the mean value of the local block K to be a low-frequency component, and approximating the information obtained by subtracting K from the input image block to be a high-frequency component; the key to improving the detail layer is how to effectively improve the high frequency components; in the local image block K, the intra-block local mean is solved using the integral map and used to refine the base layer, the enhancement process is defined as:
wherein,delta is the enhancement control parameter of the high frequency component, which is the mean value of the local image block, ++>To strengthen the base layer;
to avoid artifacts or local darkness during local block enhancement, the Gamma correction strategy is used to have better stretching performance for low pixel values, redefined as:
wherein θ is a correction factor parameter, θ is set to 0.65, and the bottom layer is traversed by using the local block to obtain a final enhanced bottom layer
The detail layer is further stretched using a nonlinear stretching function, the expression of which is:
wherein σ is a stretch control reference, set to 0.88;is an enhanced detail layer;
enhanced V-channels using enhanced detail layers and enhanced base layers are defined as:
wherein,is an enhanced V-channel.
As shown in fig. 2, the present invention demonstrates the enhancement results of testing underwater images at color distortion with other methods. As can be seen from fig. 2, the GDCP and funlggan methods are inferior in contrast enhancement and detail highlighting, and other methods are superior to the GDCP and funlggan methods, but they are inferior to the present invention in detail highlighting. The subjective results of the enhanced image of the present invention are more widely distributed and more uniform than other methods.
This example compares the different methods from the UIQM and CCF, and from the data in tables 1 and 2, it is clear that the present invention has the highest UIQM and secondary CCF values, which illustrate that the present invention also has better enhancement performance in terms of objective evaluation index. Thus, the present approach is superior to the comparative approach in both subjective and objective assessment.
TABLE 1 UIQM contrast of corrected images for the method of the present invention and other methods
TABLE 2 CCF contrast of corrected images for the methods of the present invention and other methods
Finally, it should be noted that the above-mentioned embodiments are only for illustrating the technical scheme of the present invention and are not limiting; while the invention has been described in detail with reference to the preferred embodiments, those skilled in the art will appreciate that: modifications may be made to the specific embodiments of the present invention or equivalents may be substituted for part of the technical features thereof; without departing from the spirit of the invention, it is intended to cover the scope of the invention as claimed.
Claims (4)
1. The method for enhancing the contrast ratio of the underwater image with double priori optimization is characterized by comprising the following steps of: firstly, acquiring an underwater image with corrected colors, converting the underwater image with corrected colors from an RGB color model to an HSV color model, and decomposing a base layer and a detail layer aiming at a V channel, wherein the method is represented as follows:
aiming at the V channel, decomposing the V channel into a base layer and a detail layer by adopting a space priori and a texture priori, realizing local contrast enhancement of the base layer by utilizing an integral strategy to count local mean and variance aiming at the base layer, and realizing enhancement of texture details by utilizing a nonlinear stretching function aiming at the detail layer;
wherein an optimization model that decomposes the base layer and the detail layer of the V-channel using spatial and texture priors is defined as follows:
wherein I is V 、I B And I V -I B Representing an input image, a base layer and a detail layer, respectively;and->Respectively represent I V And I B Is a concatenation vector of (a); />Representing an integrated vector; />Representing expressions of the gradient operation matrix in different directions; n represents the total number of pixels of the input image;
the first itemForcing the base layer as close as possible to the input image; then introduce the second item->Is a base layer space priori; while texture a priori of the third detail layer +.>Performing element-wise non-zero operations generates binary vectors.
2. The dual a priori optimized underwater image contrast enhancement method of claim 1 wherein: redefined using the augmented lagrangian model as:
wherein two auxiliary variables are introducedAnd->Replace->And->j 1 And j 2 Two variables of the Lagrangian function are used, and eta is a parameter for iterative updating of the objective function;
iterative optimization of an objective function using the alternate direction method of multipliers when λ 1 =0.25 and λ 2 When=0.025, the alternate direction method of the multiplier effectively decomposes I near the bottom of the input image in at least 20 iterations B After the base layer is solved, the detail layer passes through I D ＝I V -I B Solving is performed, and then different enhancement operations are performed on the base layer and the detail layer.
3. The dual a priori optimized underwater image contrast enhancement method of claim 2 wherein: enhancing the base layer by using the local image block, approximating the mean value of the local block K to be a low-frequency component, and approximating the information obtained by subtracting K from the input image block to be a high-frequency component; in the local image block K, the intra-block local mean is solved using the integral map and used to refine the base layer, the enhancement process is defined as:
wherein,delta is the enhancement control parameter of the high frequency component, which is the mean value of the local image block, ++>To strengthen the base layer;
correction was performed using a Gamma correction strategy, redefined as:
wherein θ is a correction factor parameter, θ is set to 0.65, and the bottom layer is traversed by using the local block to obtain a final enhanced bottom layer
4. A dual a priori optimized underwater image contrast enhancement method as claimed in claim 3, wherein: further stretching the detail layer using a nonlinear stretching function, expressed as:
wherein σ is a stretch control reference, set to 0.88;is an enhanced detail layer;
enhanced V-channels using enhanced detail layers and enhanced base layers are defined as:
wherein,is an enhanced V-channel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211449049.6A CN115908179B (en) | 2022-11-18 | 2022-11-18 | Underwater image contrast enhancement method based on double priori optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211449049.6A CN115908179B (en) | 2022-11-18 | 2022-11-18 | Underwater image contrast enhancement method based on double priori optimization |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115908179A CN115908179A (en) | 2023-04-04 |
| CN115908179B true CN115908179B (en) | 2023-12-22 |
Family
ID=86479130
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211449049.6A Active CN115908179B (en) | 2022-11-18 | 2022-11-18 | Underwater image contrast enhancement method based on double priori optimization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115908179B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102800059A (en) * | 2012-07-05 | 2012-11-28 | 清华大学 | Image visibility enhancing method with assistance of near-infrared image |
| CN112308793A (en) * | 2020-10-21 | 2021-02-02 | 淮阴工学院 | Novel method for enhancing contrast and detail of non-uniform illumination image |
| CN114757839A (en) * | 2022-03-22 | 2022-07-15 | 浙江万里学院 | Tone mapping method based on macro and micro information enhancement and color correction |
| CN114897735A (en) * | 2022-05-20 | 2022-08-12 | 河南科技学院 | Local self-adaptive underwater image contrast enhancement method |
| EP4050558A1 (en) * | 2019-10-21 | 2022-08-31 | Zhejiang Uniview Technologies Co., Ltd. | Image fusion method and apparatus, storage medium, and electronic device |
-
2022
- 2022-11-18 CN CN202211449049.6A patent/CN115908179B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102800059A (en) * | 2012-07-05 | 2012-11-28 | 清华大学 | Image visibility enhancing method with assistance of near-infrared image |
| EP4050558A1 (en) * | 2019-10-21 | 2022-08-31 | Zhejiang Uniview Technologies Co., Ltd. | Image fusion method and apparatus, storage medium, and electronic device |
| CN112308793A (en) * | 2020-10-21 | 2021-02-02 | 淮阴工学院 | Novel method for enhancing contrast and detail of non-uniform illumination image |
| CN114757839A (en) * | 2022-03-22 | 2022-07-15 | 浙江万里学院 | Tone mapping method based on macro and micro information enhancement and color correction |
| CN114897735A (en) * | 2022-05-20 | 2022-08-12 | 河南科技学院 | Local self-adaptive underwater image contrast enhancement method |
Non-Patent Citations (3)
| Title |
|---|
| LIME: Low-light Image Enhancement via Illumination Map Estimation;Xiaojie Guo et al.;IEEE TRANSACTIONS ON IMAGE PROCESSING;全文 * |
| 基于RTV模型图像分解的去雾算法;王尧;段锦;叶得前;宋宇;朱一峰;;长春理工大学学报(自然科学版)(04);全文 * |
| 最小二乘估计的水下图像恢复算法;王永鑫;刁鸣;韩闯;;计算机辅助设计与图形学学报(11);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115908179A (en) | 2023-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109191390A (en) | A kind of algorithm for image enhancement based on the more algorithm fusions in different colours space | |
| CN106897972A (en) | A kind of self-adapting histogram underwater picture Enhancement Method of white balance and dark primary | |
| CN108062746A (en) | A kind of method of video image processing and device, video coding system | |
| CN105931206B (en) | A kind of color image definition enhancing method of color constancy | |
| CN111210395B (en) | Retinex underwater image enhancement method based on gray value mapping | |
| CN106651817A (en) | Non-sampling contourlet-based image enhancement method | |
| CN111968065A (en) | Self-adaptive enhancement method for image with uneven brightness | |
| CN111476744B (en) | Underwater image enhancement method based on classification and atmospheric imaging model | |
| US8121401B2 (en) | Method for reducing enhancement of artifacts and noise in image color enhancement | |
| CN114897753A (en) | Low-illumination image enhancement method | |
| Xiao et al. | Contrast enhancement of color images based on wavelet transform and human visual system | |
| CN112598607B (en) | Endoscope image blood vessel enhancement algorithm based on improved weighted CLAHE | |
| CN115908179B (en) | Underwater image contrast enhancement method based on double priori optimization | |
| CN114037641A (en) | Low-illumination image enhancement method, device, equipment and medium | |
| CN114897735B (en) | Locally adaptive underwater image contrast enhancement method | |
| CN114820385B (en) | Locally adaptive underwater image color correction method | |
| CN111563866A (en) | Multi-source remote sensing image fusion method | |
| CN116862794A (en) | Underwater image processing method based on double compensation and contrast adjustment | |
| CN111563854A (en) | Particle swarm optimization method for underwater image enhancement processing | |
| Mathur et al. | Dual domain approach for colour enhancement of underwater images | |
| CN116309146A (en) | Retinex-based edge-preserving color low-illumination image enhancement method | |
| CN110706180A (en) | Method, system, equipment and medium for improving visual quality of extremely dark image | |
| Xia et al. | Color image enhancement algorithm based on logarithmic transform coefficient histogram | |
| Hsieh et al. | Hue-preserving image enhancement via complementary enhancing terms | |
| Furukawa et al. | Brightness and saturation enhancement by using color vector on equi-hue plane in RGB color space |
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 |