CN113822829A - Underwater polarization image fusion enhancement method - Google Patents
Underwater polarization image fusion enhancement method Download PDFInfo
- Publication number
- CN113822829A CN113822829A CN202110993183.1A CN202110993183A CN113822829A CN 113822829 A CN113822829 A CN 113822829A CN 202110993183 A CN202110993183 A CN 202110993183A CN 113822829 A CN113822829 A CN 113822829A
- Authority
- CN
- China
- Prior art keywords
- image
- polarization
- underwater
- channel
- fusion
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000010287 polarization Effects 0.000 title claims abstract description 111
- 230000004927 fusion Effects 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000010586 diagram Methods 0.000 claims abstract description 42
- 230000000694 effects Effects 0.000 claims abstract description 16
- 238000005286 illumination Methods 0.000 claims abstract description 11
- 230000000007 visual effect Effects 0.000 claims abstract description 6
- 238000012937 correction Methods 0.000 claims description 18
- 230000003044 adaptive effect Effects 0.000 claims description 12
- 238000000354 decomposition reaction Methods 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 9
- 238000004364 calculation method Methods 0.000 abstract description 4
- 230000002708 enhancing effect Effects 0.000 abstract description 4
- 238000003384 imaging method Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 238000005290 field theory Methods 0.000 description 3
- 238000007500 overflow downdraw method Methods 0.000 description 3
- 238000010521 absorption reaction Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000012634 optical imaging Methods 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000000149 argon plasma sintering Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20064—Wavelet transform [DWT]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an underwater polarization image fusion enhancing method, which relates to the technical field of underwater images and comprises the following steps: the method comprises the steps of constructing a beam concentration light source in advance as underwater illumination to establish a non-uniform light field, collecting polarization diagrams at different angles from a target scene at the same position away from the target scene, forming a polarization diagram group by the obtained polarization diagrams, respectively restoring the polarization diagrams at different angles in the polarization diagram group to obtain polarization restoration image sets at different angles, and performing feature fusion on the underwater polarization images based on human eye visual characteristics. The underwater polarization image acquisition method achieves the purpose of obtaining the underwater polarization image with clear details and high contrast, not only achieves a more precise enhancement effect on the obtained underwater polarization image, but also meets the adaptability to different fuzzy degrees, solves the problem of color distortion of the traditional fusion enhancement, has low data calculation degree, and provides clear and reliable image data for realizing underwater target detection.
Description
Technical Field
The invention relates to the technical field of underwater images, in particular to an underwater polarization image fusion enhancement method.
Background
In recent years, with the increase of the demand for sensing underwater environment, the underwater optical imaging technology is widely applied to the fields of underwater target detection, hydraulic engineering, marine geographic engineering investigation, marine military and the like. However, the quality of the underwater image is significantly reduced due to the nonlinear influence of the water body on the scattering and absorption effects of light in the underwater imaging process, the image details are blurred, the noise is strong, the contrast is low, and great difficulty is brought to the manual interpretation and the automatic interpretation of the image. Therefore, how to effectively suppress the backscattering is a key for improving the performance of the underwater imaging system, and the method is widely concerned by researchers, and a non-uniform illumination light field theory and a polarization imaging technology are representative solutions of the non-uniform illumination light field theory and the polarization imaging technology. The non-uniform illumination light field theory reduces the influence of back scattering noise from the light source and light field analysis perspective: in the close range of the image receiving system, the low-energy density illumination is used, so that the influence of scattering noise is reduced as much as possible; for distant targets, illumination with high energy density is used, the intensity of target signals is improved, blind-zone-free reception is realized, and the definition of images is improved. Because the polarization characteristic change of light is stable and predictable, the polarization imaging has unique advantages in the aspects of avoiding light scattering, absorption and the like, and is a new development direction of underwater optical imaging. How to fully utilize the complementarity of a plurality of polarization image information to research an information fusion processing method of an underwater polarization image, and improve the quality of the image, so that the method is beneficial to subsequent target detection and analysis and is an important research direction for current underwater polarization image processing. In an underwater optical environment, the change of the polarization characteristic of light is stable and predictable, and the polarization degree of the backward scattering light of the target object is greater than that of the backward scattering light of the suspended particles, so that the influence of the backward scattering light of the suspended particles can be reduced by placing a linear polarizer or a circular polarizer in front of a detector, and the definition of underwater imaging is improved. The polarization detection technology is used for underwater target detection, and a brand new technical approach is provided for target detection in a complex underwater environment.
The image fusion is to perform registration and synthesis on a plurality of images of the same target, fully utilize the information complementarity among the plurality of images to overcome the limitation of a single image, increase the information content of the images and make the target image more complete, thereby improving the reliability and the definition of the images and achieving the purpose of enhancing the image quality. Since the polarization image processing essentially needs to utilize the complementarity of image information with different polarization angles, the polarization image processing technology based on the image fusion method has attracted extensive attention of researchers. In a complex underwater environment, the method for processing the polarization image information fusion is researched, the definition and the contrast of the polarization image are improved, and the method is important for improving the quality of the polarization image and realizing accurate and reliable underwater target detection. At present, most of polarization image fusion methods are applied to ground and remote sensing polarization imaging. The fusion method mainly adopts two modes, one mode is image fusion based on pseudo color mapping, and the other mode is image fusion based on multi-scale transformation. But, the polarization parameter images are directly fused, so that the calculation complexity is higher; only the polarization intensity image is selected for fusion with the polarization degree, which causes partial polarization information loss to influence the fusion result.
An effective solution to the problems in the related art has not been proposed yet.
Disclosure of Invention
Aiming at the problems in the related art, the invention provides an underwater polarization image fusion enhancement method to overcome the technical problems in the prior related art.
The technical scheme of the invention is realized as follows:
an underwater polarization image fusion enhancing method comprises the following steps:
step S1, pre-building a beam concentration light source as underwater illumination to establish a non-uniform light field, collecting polarization diagrams of different angles from a target scene at the same position away from the target scene, and forming a polarization diagram group by the obtained polarization diagrams;
step S2, respectively restoring the polarization diagrams of different angles in the polarization diagram group to obtain polarization restoration image sets of different angles;
step S3, based on human visual characteristics, carrying out feature fusion of underwater polarization images, and obtaining a polarization fusion result image with rich detail information and high contrast, comprising the following steps:
step S301, converting the obtained polarized image into an LAB color space;
step S302, and based on the result L of the adaptive Gamma correction on the L channelGAnd the L channel after color correction is used as two inputs to execute wavelet decomposition, and the result after the wavelet decomposition is subjected to self-adaptive fusion;
and step S303, combining the L channel with the color channels A and B to obtain an LAB image, converting the image from an LAB space to an RGB space, and outputting to obtain a polarization image for fusion optimization.
Further, the collecting of polarization diagrams at different angles for the target scene at the same position from the target scene includes the following steps:
step S101, a line polaroid is pre-assembled in front of the underwater camera, and the angle of the polaroid is adjusted to collect a plurality of polarization diagrams for the target scene at a calibration position away from the target scene.
Further, the respectively restoring the polarization diagrams at different angles in the polarization diagram group includes the following steps:
step S201, based on the total light intensity image of the image scene at the current position and the intensity difference image in the horizontal direction and the vertical direction, determining the polarization degree of the image scene at the current position;
step S202, acquiring a dark channel image of the total light intensity image according to the total light intensity image of the image scene at the current position;
step S203, determining a region of the dark channel image only containing the scattering effect, determining the position of the brightest pixel point in the region only containing the scattering effect, and acquiring the region only containing the scattering effect;
and step S204, acquiring the polarization degree and the polarization angle of the region only containing the scattering effect based on the current position, and restoring the image scene at the current position.
Further, the obtaining of the polarization image is converted into an LAB color space, comprising the steps of:
the removal of color shift in the image is performed as:
wherein, C represents three channels of RGB,
the maximum value in each channel is represented,
represents the minimum value in each channel;
and then carrying out adaptive color compensation based on blue and green channels on a red channel of the image after color correction, wherein the adaptive color compensation is represented as follows:
wherein, muR、μGAnd muBThe coefficients corresponding to the RGB three channels for compensating the red channel are respectively;
obtaining a color corrected image ICC。
Further, the adaptive Gamma correction based on the L channel includes the following steps:
calibrating the value range of an L channel to be [0,100 ];
based on gamma correction, expressed as:
wherein L is ICCLuminance channel of, LGFor the luminance channel after Gamma correction, indexγ(x,y)Is the gamma value.
Further, the wavelet decomposition, including based on a two-dimensional discrete wavelet transform, is represented as:
where H denotes a low-pass filter operation, G denotes a high-pass filter operation, r and C denote rows and columns of an input two-dimensional image, respectively, and CjRepresents the low-pass component of the j-th stage, Cj+1Is CjLow frequency information of DH j+1Is CjHigh frequency vertical direction information of DV j+1Is CjHigh frequency horizontal direction information of DD j+1Is CjInformation on the high frequency diagonal of (1).
Further, the obtaining of the polarization image fusion comprises the low-frequency band C of the two input imagesLAnd CLGA weighted average operation is performed, which fuses the low frequency bands of each image, as:
CL′＝λ1CL+λ2CLG；
wherein λ is1+λ2＝1。
The invention has the beneficial effects that:
the underwater polarized image fusion enhancement method establishes a non-uniform light field by pre-establishing a beam concentrating light source as underwater illumination, acquires polarization diagrams with different angles at the same position away from a target scene, forms the acquired polarization diagrams into a polarization diagram group, respectively restores the polarization diagrams with different angles in the polarization diagram group to obtain polarization restoration image sets with different angles, performs characteristic fusion of the underwater polarized images based on human eye visual characteristics, acquires a polarization fusion result image with rich detail information and high contrast, realizes acquisition of the underwater polarized images with clear detail and high contrast, obtains a more precise enhancement effect on the acquired underwater polarized images, also meets the adaptability of different fuzzy degrees, solves the problem of color distortion of the traditional fusion enhancement, and has low data calculation degree, clear and reliable image data are provided for realizing underwater target detection.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a schematic flow chart of an underwater polarization image fusion enhancement method according to an embodiment of the present invention.
Detailed Description
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 that can be derived by one of ordinary skill in the art from the embodiments given herein are intended to be within the scope of the present invention.
According to the embodiment of the invention, an underwater polarization image fusion enhancement method is provided.
As shown in fig. 1, the underwater polarized image fusion enhancing method according to the embodiment of the present invention includes the following steps:
step S1, a beam concentration light source is set up in advance to serve as underwater illumination to establish a non-uniform light field, polarization diagrams of different angles are collected from a target scene at the same position away from the target scene, and the obtained polarization diagrams form a polarization diagram group;
step S2, respectively restoring the polarization diagrams of different angles in the polarization diagram group to obtain polarization restoration image sets of different angles;
step S3, based on human visual characteristics, carrying out feature fusion of underwater polarization images, and obtaining a polarization fusion result image with rich detail information and high contrast, comprising the following steps:
step S301, converting the obtained polarized image into an LAB color space;
step S302, andself-adaptive Gamma correction result L based on L channelGAnd the L channel after color correction is used as two inputs to execute wavelet decomposition, and the result after the wavelet decomposition is subjected to self-adaptive fusion;
and step S303, combining the L channel with the color channels A and B to obtain an LAB image, converting the image from an LAB space to an RGB space, and outputting to obtain a polarization image for fusion optimization.
The method comprises the following steps of acquiring polarization diagrams at different angles from the same position of a target scene, wherein the polarization diagrams are acquired at different angles from the target scene, and the method comprises the following steps:
and S101, assembling a line polarizer in front of the underwater camera in advance, and adjusting the angle of the polarizer to collect a plurality of polarization diagrams for a target scene at a position which is calibrated at a distance from the target scene.
The method for respectively restoring the polarization diagrams at different angles in the polarization diagram group comprises the following steps of:
step S201, based on the total light intensity image of the image scene at the current position and the intensity difference image in the horizontal direction and the vertical direction, determining the polarization degree of the image scene at the current position;
step S202, acquiring a dark channel image of the total light intensity image according to the total light intensity image of the image scene at the current position;
step S203, determining a region of the dark channel image only containing the scattering effect, determining the position of the brightest pixel point in the region only containing the scattering effect, and acquiring the region only containing the scattering effect;
and step S204, acquiring the polarization degree and the polarization angle of the region only containing the scattering effect based on the current position, and restoring the image scene at the current position.
Wherein the obtained polarization image is converted into an LAB color space, comprising the steps of:
the removal of color shift in the image is performed as:
wherein, C represents three channels of RGB,
the maximum value in each channel is represented,
represents the minimum value in each channel;
and then carrying out adaptive color compensation based on blue and green channels on a red channel of the image after color correction, wherein the adaptive color compensation is represented as follows:
wherein, muR、μGAnd muBThe coefficients corresponding to the RGB three channels for compensating the red channel are respectively;
obtaining a color corrected image ICC。
It should be particularly noted that, in the present technical solution, when the average pixel value of the luminance map is set to be greater than 50, the luminance map is regarded as a bright image, and the image should be corrected by an exponential parameter greater than 1; conversely, when the average gray-scale value is less than 50, the luminance map is regarded as a darker image, and such an image should be corrected using an exponential parameter less than 1.
Specifically, the adaptive adjustment of the correction index parameter is realized according to the light and shade characteristics of the image, and the set index parameter is expressed as:
wherein L isman(x, y) is the luminance channel average pixel value.
In addition, based on the adaptive Gamma correction on the L channel, the method comprises the following steps:
calibrating the value range of an L channel to be [0,100 ];
based on gamma correction, expressed as:
wherein L is ICCLuminance channel of, LGFor the luminance channel after Gamma correction, indexγ(x,y)Is the gamma value.
Wherein, the wavelet decomposition, including based on two-dimensional discrete wavelet transform, is expressed as:
where H denotes a low-pass filter operation, G denotes a high-pass filter operation, r and C denote rows and columns of an input two-dimensional image, respectively, and CjRepresents the low-pass component of the j-th stage, Cj+1Is CjLow frequency information of DH j+1Is CjHigh frequency vertical direction information of DV j+1Is CjHigh frequency horizontal direction information of DD j+1Is CjInformation on the high frequency diagonal of (1).
Further, obtaining a polarization image fusion, including a low frequency band C for two input imagesLAnd CLGA weighted average operation is performed, which fuses the low frequency bands of each image, as:
CL′＝λ1CL+λ2CLG；
wherein λ is1+λ2＝1。
In summary, with the aid of the technical solutions of the present invention, through
A beam concentration light source is pre-established as underwater illumination to establish a non-uniform light field, polarization diagrams of different angles are acquired at the same position away from a target scene, and the obtained polarization diagrams form a polarization diagram group, and the polarization diagrams at different angles in the polarization diagram group are respectively restored to obtain polarization restoration image sets at different angles, and the characteristic fusion of the underwater polarization image is carried out based on the visual characteristics of human eyes, the polarization fusion result image with rich detail information and high contrast is obtained, the underwater polarization image with clear detail and high contrast is obtained, not only the finer enhancement effect is obtained on the obtained underwater polarization image, and also satisfies the adaptability at different fuzzy degrees, solves the color distortion problem of the traditional fusion enhancement, and the data calculation degree is low, and clear and reliable image data are provided for realizing underwater target detection.
While the foregoing is directed to the preferred embodiment of the present invention, other and further embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (7)
1. An underwater polarization image fusion enhancement method is characterized by comprising the following steps:
a beam concentration light source is built in advance to serve as underwater illumination to establish a non-uniform light field, polarization diagrams at different angles are collected from a target scene at the same position away from the target scene, and the obtained polarization diagrams form a polarization diagram group;
respectively restoring the polarization diagrams at different angles in the polarization diagram group to obtain polarization restoration image sets at different angles;
the method for carrying out feature fusion on the underwater polarization image based on the visual characteristics of human eyes and obtaining the polarization fusion result image with rich detail information and high contrast comprises the following steps:
converting the acquired polarization image into an LAB color space;
and based on the result L of the adaptive Gamma correction on the L channelGAnd the L channel after color correction is used as two inputs to execute wavelet decomposition, and the result after the wavelet decomposition is subjected to self-adaptive fusion;
and combining the L channel with the color channels A and B to obtain an LAB image, converting the image from an LAB space to an RGB space for output, and acquiring polarization image fusion optimization.
2. The underwater polarized image fusion enhancement method according to claim 1, wherein the acquisition of the polarized image of the target scene at different angles from the same position of the target scene comprises the following steps:
a line polaroid is assembled in front of an underwater camera in advance, and the angle of the polaroid is adjusted to collect a plurality of polarization diagrams for a target scene at a calibration position away from the target scene.
3. The underwater polarized image fusion enhancement method according to claim 2, wherein the respectively restoring the polarization diagrams of different angles in the polarization diagram group comprises the following steps:
determining the polarization degree of the image scene at the current position based on the total light intensity image of the image scene at the current position and the intensity difference images in the horizontal direction and the vertical direction;
acquiring a dark channel image of the total light intensity image according to the total light intensity image of the image scene at the current position;
determining a region of the dark channel image only containing a scattering effect, determining the position of a brightest pixel point in the region only containing the scattering effect, and acquiring the region only containing the scattering effect;
and acquiring the polarization degree and the polarization angle of the region only containing the scattering effect based on the current position, and restoring the image scene at the current position.
4. The underwater polarized image fusion enhancement method according to claim 3, wherein the obtained polarized image is converted into an LAB color space, comprising the steps of:
the removal of color shift in the image is performed as:
wherein, C represents three channels of RGB,
the maximum value in each channel is represented,
represents the minimum value in each channel;
and then carrying out adaptive color compensation based on blue and green channels on a red channel of the image after color correction, wherein the adaptive color compensation is represented as follows:
wherein, muR、μGAnd muBThe coefficients corresponding to the RGB three channels for compensating the red channel are respectively;
obtaining a color corrected image ICC。
5. The underwater polarized image fusion enhancement method according to claim 4, wherein the adaptive Gamma correction based on the L channel comprises the following steps:
calibrating the value range of an L channel to be [0,100 ];
based on gamma correction, expressed as:
wherein L is ICCLuminance channel of, LGFor the Gamma corrected luminance channelThe exponent γ (x, y) is a gamma value.
6. The underwater polarized image fusion enhancement method of claim 5, wherein the wavelet decomposition, including based on a two-dimensional discrete wavelet transform, is represented as:
where H denotes a low-pass filter operation, G denotes a high-pass filter operation, r and C denote rows and columns of an input two-dimensional image, respectively, and CjRepresents the low-pass component of the j-th stage, Cj+1Is CjLow frequency information of DH j+1Is CjHigh frequency vertical direction information of DV j+1Is CjHigh frequency horizontal direction information of DD j+1Is CjInformation on the high frequency diagonal of (1).
7. The underwater polarized image fusion enhancement method of claim 6, wherein the obtaining polarized image fusion comprises low-frequency band C of two input mapsLAnd CLGA weighted average operation is performed, which fuses the low frequency bands of each image, as:
CL′＝λ1CL+λ2CLG；
wherein λ is1+λ2＝1。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110993183.1A CN113822829A (en) | 2021-08-26 | 2021-08-26 | Underwater polarization image fusion enhancement method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110993183.1A CN113822829A (en) | 2021-08-26 | 2021-08-26 | Underwater polarization image fusion enhancement method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113822829A true CN113822829A (en) | 2021-12-21 |
Family
ID=78913634
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110993183.1A Pending CN113822829A (en) | 2021-08-26 | 2021-08-26 | Underwater polarization image fusion enhancement method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113822829A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007272536A (en) * | 2006-03-31 | 2007-10-18 | Nikon Corp | Image processing method |
| CN111161170A (en) * | 2019-12-18 | 2020-05-15 | 江苏科技大学 | Underwater image comprehensive enhancement method for target recognition |
| CN111738941A (en) * | 2020-06-05 | 2020-10-02 | 大连海事大学 | Underwater image optimization method fusing light field and polarization information |
-
2021
- 2021-08-26 CN CN202110993183.1A patent/CN113822829A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007272536A (en) * | 2006-03-31 | 2007-10-18 | Nikon Corp | Image processing method |
| CN111161170A (en) * | 2019-12-18 | 2020-05-15 | 江苏科技大学 | Underwater image comprehensive enhancement method for target recognition |
| CN111738941A (en) * | 2020-06-05 | 2020-10-02 | 大连海事大学 | Underwater image optimization method fusing light field and polarization information |
Non-Patent Citations (2)
| Title |
|---|
| 赵轩;郭蔚;刘京;: "RGB-D图像中的分步超像素聚合和多模态融合目标检测", 中国图象图形学报, no. 08, 16 August 2018 (2018-08-16) * |
| 颜阳: "基于图像融合的自适应水下图像增强方法研究", 中国优秀硕士学位论文全文数据库 信息科技辑, no. 2021, 15 January 2021 (2021-01-15), pages 1 - 48 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106504222B (en) | A kind of underwater Polarization Image Fusion system based on bionic visual mechanism | |
| CN104240194B (en) | A kind of enhancement algorithm for low-illumination image based on parabolic function | |
| US10469760B2 (en) | High dynamic range imaging | |
| Namer et al. | Advanced visibility improvement based on polarization filtered images | |
| CN110322410B (en) | Underwater image defogging and color cast correction method based on bright channel transmissivity compensation | |
| CN111064904A (en) | Dark light image enhancement method | |
| Wang et al. | Variational single nighttime image haze removal with a gray haze-line prior | |
| CN113962884B (en) | HDR video acquisition method and device, electronic equipment and storage medium | |
| CN110163807B (en) | Low-illumination image enhancement method based on expected bright channel | |
| CN105122793A (en) | Image processing device, image capture device, and image processing program | |
| CN112104847B (en) | SONY-RGBW array color reconstruction method based on residual error and high-frequency replacement | |
| CN110599418B (en) | Global tone mapping method for transform domain fusion | |
| CN102801993A (en) | Image signal processing device and image signal processing method | |
| CN107527325A (en) | A kind of monocular underweater vision Enhancement Method preferential based on dark | |
| CN109903250A (en) | Underwater picture clearness processing method based on multi-scale gradient domain contrast stretching | |
| CN116228604B (en) | Satellite remote sensing optical image color homogenizing method suitable for polar region | |
| CN109712093B (en) | Image color restoration method and device based on sea-sky background | |
| Gong et al. | Research on the method of color compensation and underwater image restoration based on polarization characteristics | |
| WO2021127972A1 (en) | Image processing method and apparatus, imaging device, and movable carrier | |
| CN113822829A (en) | Underwater polarization image fusion enhancement method | |
| Mi et al. | Multi-scale gradient domain underwater image enhancement | |
| CN111541886A (en) | Vision enhancement system applied to muddy underwater | |
| CN115334294B (en) | Video noise reduction method of local self-adaptive force | |
| CN116664460A (en) | Infrared night vision fusion method | |
| CN103400381B (en) | A kind of Method for Underwater Target Tracking based on optical imagery |
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 |