CN116681606A - Underwater uneven illumination image enhancement method, system, equipment and medium - Google Patents
Underwater uneven illumination image enhancement method, system, equipment and medium Download PDFInfo
- Publication number
- CN116681606A CN116681606A CN202310590991.2A CN202310590991A CN116681606A CN 116681606 A CN116681606 A CN 116681606A CN 202310590991 A CN202310590991 A CN 202310590991A CN 116681606 A CN116681606 A CN 116681606A
- Authority
- CN
- China
- Prior art keywords
- image
- channel
- brightness
- pixel
- illumination
- 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
- 238000005286 illumination Methods 0.000 title claims abstract description 134
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000012937 correction Methods 0.000 claims abstract description 38
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 15
- 238000010586 diagram Methods 0.000 claims abstract description 9
- 238000012545 processing Methods 0.000 claims description 18
- 230000003044 adaptive effect Effects 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000002708 enhancing effect Effects 0.000 claims description 13
- 230000009466 transformation Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 238000003702 image correction Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000000926 separation method Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 7
- 230000002194 synthesizing effect Effects 0.000 abstract 1
- 230000008569 process Effects 0.000 description 9
- 239000011159 matrix material Substances 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 230000000007 visual effect Effects 0.000 description 5
- 238000007781 pre-processing Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012634 optical imaging Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004091 panning Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Classifications
-
- 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]
-
- 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
- Image Processing (AREA)
- Processing Of Color Television Signals (AREA)
Abstract
The application relates to the technical field of computer vision, in particular to an underwater uneven illumination image enhancement method, an underwater uneven illumination image enhancement system, an underwater uneven illumination image enhancement device and an underwater uneven illumination image enhancement medium, wherein the method comprises the following steps: correcting the acquired standard image of the brightness channel by using a self-adaptive gamma correction algorithm and an illumination distribution diagram to obtain a brightness correction image; synthesizing a color image according to the brightness correction image, and obtaining UV channel values of the color image at each pixel point in a YUV color space; determining the Y-channel white point position in a YUV color space according to the UV channel values at all the pixel points and a preset UV bright point threshold value; performing white balance adjustment on each channel of the color image at the white point position of the Y channel to obtain an enhanced image; and carrying out wavelet denoising treatment on the enhanced image to obtain a denoised image. The method provided by the application effectively improves the quality of the underwater illumination uneven image, can be suitable for various complex underwater scenes, and improves the reliability and stability of the enhancement effect.
Description
Technical Field
The application relates to the technical field of computer vision, in particular to an underwater uneven illumination image enhancement method, an underwater uneven illumination image enhancement system, an underwater uneven illumination image enhancement device and an underwater uneven illumination image enhancement medium.
Background
In underwater shallow water environments, light can generate intensity and color changes due to different depth changes, so that the phenomenon of uneven illumination of objects in an image occurs, particularly under the depth of tens of meters from the water surface, the ambient illumination is almost absent due to rapid attenuation of the underwater light, which means that most of optical imaging in deep sea is completed through artificial illumination, and therefore, the optical imaging in deep sea is also usually accompanied by uneven illumination, which can cause great difficulty in identifying and detecting target objects, and thus, enhancement treatment is required.
The traditional underwater uneven illumination image enhancement method mainly adopts image preprocessing and image enhancement algorithms, and in the aspect of image preprocessing, the common preprocessing method comprises white balance correction, color correction, mean value filtering and the like; in terms of image enhancement algorithms, common methods include histogram equalization, limited contrast adaptive histogram equalization (CLAHE), wavelet transformation and the like, and although the methods can effectively reduce noise and ambiguity in an underwater image, enhance contrast and definition of a target object and improve the visibility and quality of the image, the complexity of the underwater environment causes that the distribution of underwater illumination is difficult to predict, the current underwater uneven illumination image enhancement method is difficult to process different types of underwater environments, resulting in poor reliability and stability of an enhancement effect, and certain limitation in the aspect of nature of the enhancement effect.
Disclosure of Invention
The application provides an underwater uneven illumination image enhancement method, an underwater uneven illumination image enhancement system, an underwater uneven illumination image enhancement device and an underwater uneven illumination image enhancement medium, which solve the technical problems that the reliability and the stability of an enhancement effect are poor and certain limitation exists in the aspect of enhancing the nature of the effect when the traditional underwater uneven illumination image enhancement method is used for processing a complex underwater environment.
In order to solve the technical problems, the application provides an underwater uneven illumination image enhancement method, an underwater uneven illumination image enhancement system, an underwater uneven illumination image enhancement device and an underwater uneven illumination image enhancement medium.
In a first aspect, the present application provides a method for enhancing an underwater non-uniform illumination image, the method comprising the steps of:
acquiring an illumination distribution map and a brightness channel standard image according to the acquired original illumination image;
correcting the brightness channel standard image by using an adaptive gamma correction algorithm and the illumination distribution map to obtain a brightness correction image;
acquiring a color image according to the brightness correction image, converting the color image into a YUV color space, and acquiring UV channel values at each pixel point in the YUV color space;
determining the Y-channel white point position in a YUV color space according to the UV channel values at all the pixel points and a preset UV bright point threshold value;
performing white balance adjustment on each channel of the color image at the white point position of the Y channel to obtain an enhanced image;
and carrying out wavelet denoising treatment on the enhanced image to obtain a denoised image.
In a further embodiment, the step of acquiring the illumination distribution map and the brightness channel standard image according to the acquired original illumination image includes:
acquiring an original illumination image;
guiding and filtering the original illumination image to obtain an illumination distribution map;
performing color space conversion and channel separation on an original illumination image to obtain a single-channel image; the single-channel image comprises a tone single-channel image, a saturation single-channel image and a brightness single-channel image;
and carrying out standardization processing on the brightness single-channel image to obtain a brightness channel standard image.
In a further embodiment, the adaptive gamma correction algorithm is calculated as:
I out (x,y)＝I(x,y) Y(x,y) ×255
wherein ,
in the formula ,Iout (x, y) represents a brightness correction image; i (x, y) represents a luminance channel standard image; y (x, Y) represents an adaptive gamma parameter; j (x, y) represents an illumination profile; beta (x, y) represents a luminance image dark area threshold; alpha (x, y) represents a luminance channel standard image; v (x, y) represents the luminance value of the luminance channel standard image at (x, y); s (x, y) represents the saturation value of the luminance channel standard image at (x, y);an average value representing the standard image brightness of the brightness channel; />Representing luminance channel standard image saturationAverage value of (2); θ (x, y) represents the gray value of the luminance channel standard image at (x, y); delta represents the median of the standard image gray values of the luminance channels.
In a further embodiment, the step of determining the Y-channel white point position in YUV color space according to the UV channel values at all pixels and the preset UV bright point threshold value comprises:
determining a UV bright spot threshold according to UV channel values at all pixel points, wherein the UV bright spot threshold comprises a U-channel bright spot threshold and a V-channel bright spot threshold;
screening out bright pixel points according to the UV channel values at each pixel point and the UV bright point threshold value;
counting a histogram of the bright pixel points in a Y channel, and determining a bright point average value according to pixel values of the bright pixel points with preset duty ratios in the histogram;
and determining the white point position of the Y channel in the YUV color space according to the bright point average value.
In a further embodiment, the step of screening out bright pixels based on the UV channel values at each pixel and the UV bright point threshold value comprises:
traversing all pixel points in the YUV color space, and dividing the current pixel point into bright pixel points if the difference value between the U channel value of the current pixel point and the U channel bright point threshold value is not smaller than a first preset threshold value or the difference value between the V channel value of the current pixel point and the V channel bright point threshold value is not smaller than a second preset threshold value;
the U-channel bright spot threshold is determined according to a U-channel mean value and a preset U-channel dynamic threshold, and the V-channel bright spot threshold is determined according to the V-channel mean value and the preset V-channel dynamic threshold.
In a further embodiment, the white balance adjustment is performed on each channel of the color image at the white point position of the Y channel, so as to obtain a calculation formula of the enhanced image, where the calculation formula is as follows:
wherein R (x, y) represents the R channel pixel value of the enhanced image; g (x, y) represents G channel pixel values of the enhanced image; b (x, y) represents B-channel pixel values of the enhanced image; r (x, y) represents the R channel pixel value of the original illumination image; r is (r) aver An R channel pixel average value representing an original illumination image; g (x, y) represents the G channel pixel value of the original illumination image; g aver A G channel pixel average representing the original illumination image; b (x, y) represents the B-channel pixel values of the original illumination image; b aver A B-channel pixel average value representing an original illumination image; y is max Representing the Y-channel pixel maximum in YUV color space.
In a further embodiment, the step of performing wavelet denoising processing on the enhanced image to obtain a denoised image includes:
performing YCrCb color space conversion on the enhanced image to obtain a Y brightness channel image;
performing wavelet transformation on the Y brightness channel image to obtain wavelet coefficients;
setting a wavelet threshold, and performing wavelet inverse transformation on the Y brightness channel image by utilizing the wavelet threshold and a wavelet coefficient to obtain a denoised Y brightness channel image;
combining the denoised Y brightness channel image with the hue channel and the saturation channel of the enhanced image to obtain a combined image;
and converting the combined image from the YCrCb color space to an RGB space to obtain a denoising image.
In a second aspect, the present application provides an underwater non-uniform illumination image enhancement system, the system comprising:
the image acquisition module is used for acquiring an illumination distribution map and a brightness channel standard image according to the acquired original illumination image;
the image correction module is used for correcting the brightness channel standard image by utilizing an adaptive gamma correction algorithm and the illumination distribution diagram to obtain a brightness correction image;
the space conversion module is used for acquiring a color image according to the brightness correction image, converting the color image into a YUV color space, acquiring UV channel values at all pixel points in the YUV color space, and determining the Y-channel white point position in the YUV color space according to the UV channel values at all pixel points and a preset UV bright point threshold;
the image enhancement module is used for carrying out white balance adjustment on each channel of the color image at the white point position of the Y channel to obtain an enhanced image;
and the image denoising module is used for carrying out wavelet denoising processing on the enhanced image to obtain a denoised image.
In a third aspect, the present application also provides a computer device, including a processor and a memory, where the processor is connected to the memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the computer device performs steps for implementing the method.
In a fourth aspect, the present application also provides a computer readable storage medium having stored therein a computer program which when executed by a processor performs the steps of the above method.
The application provides a method, a system, equipment and a medium for enhancing an underwater uneven illumination image, wherein the method corrects a brightness channel standard image through a self-adaptive gamma correction algorithm and an illumination distribution map, obtains UV channel values of brightness correction images at all pixel points in a YUV color space, determines a Y channel white point position in the YUV color space according to the UV channel values of all pixel points and a preset UV bright point threshold value, and carries out white balance adjustment on all channels of the color image at the Y channel white point position to obtain an enhanced image; and carrying out wavelet denoising treatment on the enhanced image to obtain a denoised image. Compared with the traditional method, the method provided by the application effectively solves the problem of color deviation of the underwater image, realizes the removal of noise of the underwater image, improves the definition of the low-quality underwater photographed image, and achieves better visual effect.
Drawings
FIG. 1 is a schematic flow chart of an underwater uneven illumination image enhancement method provided by an embodiment of the application;
FIG. 2 is a schematic diagram of an underwater non-uniform illumination image enhancement process provided by an embodiment of the present application;
FIG. 3 is a schematic illustration of an original illumination image provided by an embodiment of the present application;
FIG. 4 is a schematic diagram of a denoised image provided by an embodiment of the present application;
FIG. 5 is a block diagram of an underwater non-uniform illumination image enhancement system provided by an embodiment of the present application;
fig. 6 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
The following examples are given for the purpose of illustration only and are not to be construed as limiting the application, including the drawings for reference and description only, and are not to be construed as limiting the scope of the application as many variations thereof are possible without departing from the spirit and scope of the application.
Referring to fig. 1, an embodiment of the present application provides a method for enhancing an underwater non-uniform illumination image, as shown in fig. 1, the method includes the following steps:
s1, acquiring an illumination distribution map and a brightness channel standard image according to an acquired original illumination image.
In this embodiment, the step of acquiring the illumination distribution map and the brightness channel standard image according to the acquired original illumination image includes:
acquiring an original illumination image;
guiding and filtering the original illumination image to obtain an illumination distribution map;
performing color space conversion and channel separation on an original illumination image to obtain a single-channel image; the single-channel image comprises a tone single-channel image, a saturation single-channel image and a brightness single-channel image;
and carrying out standardization processing on the brightness single-channel image to obtain a brightness channel standard image.
Specifically, in this embodiment, after an original illumination image is acquired, guiding filtering is performed on the acquired original illumination image to obtain an illumination distribution map, gaussian filtering is performed on a gray scale image of the illumination distribution map as a guiding image to obtain a blurred guiding image, and a mean vector of the blurred guiding image and the original image is calculated, in this embodiment, the filtering radius is preferentially set to 15, and a formula for calculating the mean vector of the blurred guiding image and the original image is as follows:
in the formula ,μA A mean vector representing the original illumination image; ω represents the domain of convolution kernels; p represents a pixel point in an original illumination image; a (p) represents an original illumination image; mu (mu) G A mean vector representing the blur guide image; g (p) denotes a blur guide image.
After calculating the mean vector of the fuzzy guide image and the original illumination image, calculating a covariance matrix of the fuzzy guide image and the original illumination image in the corresponding adjacent area of each pixel point, wherein the specific calculation formula is as follows:
in the formula ,CAG A covariance matrix representing the blur-oriented image and the original illumination image.
After the covariance matrix of the fuzzy guide image and the original illumination image is obtained by calculation, the covariance matrix of the fuzzy guide image in the corresponding adjacent area of each pixel point is calculated, and the specific calculation formula is as follows:
in the formula ,CG Representing the covariance matrix of the blur-oriented image.
And then calculating the mean value coefficient of a guide filter according to the covariance matrix of the fuzzy guide image and the original illumination image and the covariance matrix of the fuzzy guide image, taking the fuzzy guide image as the guide image, filtering the original illumination image by using the mean value coefficient of the guide filter to obtain a filtered image, namely an illumination distribution map, and filtering the original illumination image by using the mean value coefficient of the guide filter according to the calculation formula:
wherein ,
b＝μ A -a×μ G
wherein a represents the mean coefficient of the pilot filter; b represents the bias coefficient of the pilot filter; epsilon represents a very small positive number; j (p) represents an illumination profile.
Meanwhile, in this embodiment, the original illumination image is subjected to color segmentation and channel separation in the HSV color space, three single-channel images, namely, a hue single-channel image, a saturation single-channel image and a brightness single-channel image, are extracted, and the brightness single-channel image is subjected to standardization processing to obtain a brightness channel standard image, wherein the calculation formula of the standardization processing is as follows:
wherein I (x, y) represents a luminance channel standard image; i in Representing a luminance single channel image; i min Representing a minimum value of pixel values in the luminance single-channel image; i max Representing the maximum value of the pixel values in the luminance single channel image.
According to the embodiment, the illumination distribution map obtained by adopting the guide filtering method can well keep the image illumination details, and a more accurate calculation model is provided for the adjustment of the subsequent uneven illumination image.
S2, correcting the brightness channel standard image by using an adaptive gamma correction algorithm and the illumination distribution map to obtain a brightness correction image, wherein in the embodiment, the calculation formula of the adaptive gamma correction algorithm is as follows:
I out (x,y)＝I(x,y) Y(x,y) ×255
wherein ,
in the formula ,Iout (x, y) represents a brightness correction image; i (x, y) represents a luminance channel standard image; y (x, Y) represents an adaptive gamma parameter for controlling an increase or decrease in brightness when Y (x, Y)>1, the brightness of the standard image of the brightness channel increases, when Y (x, Y)<1, the brightness of the standard image of the brightness channel is reduced; j (x, y) represents an illumination profile; beta (x, y) represents the brightness image dark area threshold, considering that the image is in a darker area when both the brightness and saturation of the image are at lower values, and therefore, in this embodimentThe brightness image dark area threshold value of (1) is determined by the brightness and saturation of the image; alpha (x, y) represents a luminance channel standard image; v (x, y) represents the luminance value of the luminance channel standard image at (x, y); s (x, y) represents the saturation value of the luminance channel standard image at (x, y);an average value representing the standard image brightness of the brightness channel; />An average value representing the saturation of the standard image of the brightness channel; θ (x, y) represents the gray value of the luminance channel standard image at (x, y); delta represents the median of the standard image gray values of the luminance channels.
The image gamma correction is an image processing technology for adjusting the brightness and contrast of an image, and the principle is that the brightness and the contrast of the image are adjusted by carrying out nonlinear transformation on the image, so that the aim of enhancing the image is fulfilled.
S3, acquiring a color image according to the brightness correction image, converting the color image into a YUV color space, and acquiring UV channel values at all pixel points in the YUV color space.
S4, determining the Y-channel white point position in the YUV color space according to the UV channel values at all the pixel points and a preset UV bright point threshold value.
Because the adaptive gamma correction algorithm can only improve the problem of uneven illumination of an image and cannot effectively solve the problem of color cast of an underwater image, the embodiment adopts a dynamic threshold white balance method to adjust the color temperature and the color balance of the image and solve the problem of color cast of the underwater image, so that the color of the image is richer, and the specific process comprises the following steps:
in this embodiment, the brightness correction image, the hue single-channel image and the saturation single-channel image extracted in the step S1 are recombined into a color image, the synthesized color image is converted into a YUV color space, and then a UV bright point threshold is determined according to UV channel values at all pixel points, wherein the UV bright point threshold includes a U channel bright point threshold and a V channel bright point threshold, in this embodiment, the U channel bright point threshold is determined according to a U channel mean value and a preset U channel dynamic threshold, the V channel bright point threshold is determined according to a V channel mean value and a preset V channel dynamic threshold, and a specific acquisition process of the U channel bright point threshold and the V channel bright point threshold is as follows:
according to the obtained U channel value and V channel value of each pixel point in the YUV color space, calculating a U channel mean value and a V channel mean value;
taking the sum of the U-channel mean value and a preset U-channel dynamic threshold value as a U-channel bright point threshold value;
and taking the sum of the V-channel mean value and a preset V-channel dynamic threshold value as a V-channel bright spot threshold value.
The calculation formulas of the U channel dynamic threshold and the V channel dynamic threshold are as follows:
in the formula ,representing a U channel dynamic threshold; delta u (x, y) represents the U-channel value of the U-channel at (x, y) for the color image in YCbCr color space; m is M u Representing the U channel mean value of the color image in the YCbCr color space; n represents the total number of pixels of the color image; />Representing a V-channel dynamic threshold; delta v (x, y) represents the V-channel value of the V-channel at (x, y) in the YCbCr color space of the color image; m is M v Representing the V-channel mean of the color image in YCbCr color space.
After the U-channel bright spot threshold and the V-channel bright spot threshold are obtained, the bright pixel points are screened out according to the UV channel values at the pixel points and the UV bright spot threshold, and the specific process is as follows:
traversing all pixel points in YUV color space, if the difference value between the U channel value and the U channel bright point threshold value of the current pixel point is not smaller than a first preset threshold value, or the difference value between the V channel value and the V channel bright point threshold value of the current pixel point is not smaller than a second preset threshold value, dividing the current pixel point into bright pixel points, wherein in the embodiment, the first preset threshold value is set as the first preset threshold value preferentiallyThe second preset threshold is set to be +.>
After the bright pixel points belonging to the near-white area are screened out according to the rule, counting the histogram of the bright pixel points in the Y channel, determining a bright point average value according to the pixel value of the bright pixel points with preset duty ratio in the histogram, and determining the Y channel white point position in YUV color space according to the bright point average value, wherein the embodiment preferably determines the Y channel white point position according to the average value of the bright points of the first 1% in the histogram.
S5, performing white balance adjustment on each channel of the color image at the white point position of the Y channel to obtain an enhanced image.
In this embodiment, white balance adjustment is performed on B, G, R channels of the color image at the white point position of the Y channel, and the RGB channels are scaled to make the white point become the maximum brightness value, and then the RGB three channels are combined to obtain an enhanced image after dynamic threshold white balance processing, where a calculation formula for obtaining the enhanced image through white balance adjustment is as follows:
wherein R (x, y) represents the R channel pixel value of the enhanced image; g (x, y) represents G channel pixel values of the enhanced image; b (x, y) represents B-channel pixel values of the enhanced image; r (x, y) represents the R channel pixel value of the original illumination image; r is (r) aver An R channel pixel average value representing an original illumination image; g (x, y) represents the G channel pixel value of the original illumination image; g aver A G channel pixel average representing the original illumination image; b (x, y) represents the B-channel pixel values of the original illumination image; b aver A B-channel pixel average value representing an original illumination image; y is max Representing the Y-channel pixel maximum in YUV color space.
S6, carrying out wavelet denoising treatment on the enhanced image to obtain a denoised image.
In this embodiment, the step of performing wavelet denoising processing on the enhanced image to obtain a denoised image includes:
performing YCrCb color space conversion on the enhanced image to obtain a Y brightness channel image;
performing wavelet transformation on the Y brightness channel image to obtain wavelet coefficients;
setting a wavelet threshold, and performing wavelet inverse transformation on the Y brightness channel image by utilizing the wavelet threshold and a wavelet coefficient to obtain a denoised Y brightness channel image;
combining the denoised Y brightness channel image with the hue channel and the saturation channel of the enhanced image to obtain a combined image;
and converting the combined image from the YCrCb color space to an RGB space to obtain a denoising image.
Although the problems of uneven illumination and color cast of the image are well improved through the steps S1 to S5, noise is commonly existed in the underwater image due to the influence of factors such as underwater water quality and turbidity, which has adverse effect on the quality and definition of the underwater image, so that the embodiment adopts wavelet to carry out denoising treatment, and the noise in the underwater image can be effectively removed, and the specific process is as follows:
converting the enhanced image into a YCrCb color space to obtain a Y brightness channel image, and performing wavelet transformation and threshold processing on the Y brightness channel image only, namely performing wavelet transformation on the Y brightness channel image to obtain wavelet coefficients, wherein the wavelet transformation formula is as follows:
wherein W (e, λ) represents a wavelet coefficient; f (t) represents a Y luminance channel image; psi e,λ (t) represents a wavelet function; e represents the scale of the wavelet transform; λ represents a panning parameter of the wavelet transform.
The wavelet coefficient is subjected to threshold processing, the high-frequency component lower than a certain threshold value is set to be zero, and the wavelet threshold value is calculated according to the following formula:
in the formula ,Tthresh Represents the wavelet threshold, σ represents the standard deviation of the noise, and n is the number of wavelet coefficients.
And carrying out wavelet inverse transformation on the wavelet coefficient subjected to the threshold processing to obtain a denoised Y-luminance channel image, combining the denoised Y-luminance channel image with a chromaticity channel of the enhanced image, and converting the combined image into an RGB space to obtain a final denoised image.
The embodiment of the application provides a method, a system, equipment and a medium for enhancing an underwater uneven illumination image, wherein the method utilizes guided filtering to obtain an illumination distribution map, and simultaneously performs standardization treatment on an extracted brightness single-channel image, and then performs illumination adjustment on the brightness single-channel image by utilizing a self-adaptive gamma correction algorithm and the illumination distribution map, so that more detailed information of a dark area is highlighted, and a better visual effect is achieved; and meanwhile, the method carries out dynamic threshold white balance and wavelet function denoising on the obtained image so as to solve the color cast problem of the underwater image and realize the removal of the noise of the underwater image. Compared with the prior art, the method and the device can carry out self-adaptive correction according to the image, carry out targeted enhancement and denoising on the image, enable detail information of the enhanced and denoised underwater image to be clearer and more complete, and improve visual quality of the underwater uneven image.
It should be noted that, the sequence number of each process does not mean that the execution sequence of each process is determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present application.
In one embodiment, as shown in fig. 5, the system for enhancing an underwater uneven illumination image according to the embodiment of the present application includes:
the image acquisition module 101 is used for acquiring an illumination distribution map and a brightness channel standard image according to the acquired original illumination image;
the image correction module 102 is configured to correct the luminance channel standard image by using an adaptive gamma correction algorithm and the illumination distribution map to obtain a luminance correction image;
the space conversion module 103 is configured to obtain a color image according to the brightness correction image, convert the color image into a YUV color space, obtain UV channel values at each pixel point in the YUV color space, and determine a Y-channel white point position in the YUV color space according to the UV channel values at all the pixel points and a preset UV bright point threshold;
the image enhancement module 104 is configured to perform white balance adjustment on each channel of the color image at the white point position of the Y channel, so as to obtain an enhanced image;
and the image denoising module 105 is used for performing wavelet denoising processing on the enhanced image to obtain a denoised image.
For a specific limitation of the underwater non-uniform illumination image enhancement system, reference may be made to the above limitation of the underwater non-uniform illumination image enhancement method, and the description thereof will not be repeated here. Those of ordinary skill in the art will appreciate that the various modules and steps described in connection with the disclosed embodiments of the application may be implemented in hardware, software, or a combination of both. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The embodiment of the application provides an underwater uneven illumination image enhancement system, which realizes self-adaptive gamma correction on a brightness single-channel image through an image correction module, so that more detail information of a dark area is highlighted and a better visual effect is achieved; the dynamic threshold white balance of the obtained image is realized through the space conversion module and the image enhancement module, so that the color cast problem of the underwater image is solved; meanwhile, the image denoising module is used for removing noise of the underwater image. Compared with the prior art, the application can be suitable for different complex underwater environments, improves the reliability and stability of the enhancement effect, ensures that the enhanced underwater image has more natural overall color, and remarkably improves the visibility of the underwater image.
FIG. 6 is a diagram of a computer device including a memory, a processor, and a transceiver connected by a bus, according to an embodiment of the present application; the memory is used to store a set of computer program instructions and data and the stored data may be transferred to the processor, which may execute the program instructions stored by the memory to perform the steps of the above-described method.
Wherein the memory may comprise volatile memory or nonvolatile memory, or may comprise both volatile and nonvolatile memory; the processor may be a central processing unit, a microprocessor, an application specific integrated circuit, a programmable logic device, or a combination thereof. By way of example and not limitation, the programmable logic device described above may be a complex programmable logic device, a field programmable gate array, general purpose array logic, or any combination thereof.
In addition, the memory may be a physically separate unit or may be integrated with the processor.
It will be appreciated by those of ordinary skill in the art that the structure shown in FIG. 6 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be implemented, and that a particular computer device may include more or fewer components than those shown, or may combine some of the components, or have the same arrangement of components.
In one embodiment, an embodiment of the present application provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the above-described method.
According to the method, the system, the equipment and the medium for enhancing the underwater uneven illumination image, the adaptive gamma correction is utilized to carry out illumination adjustment on the image, the illumination component of the image is fully utilized to adaptively change the parameter of the gamma function, so that the color contrast of a bright-dark junction area of the image is enhanced, more detailed information of a dark area is highlighted, a better visual effect is achieved, white balance adjustment and denoising are carried out on the obtained image, the enhancement and the noise removal of the underwater image are realized, the method is applicable to various complex underwater scenes, and the visibility of the underwater image is remarkably improved.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by a wired (e.g., coaxial cable, fiber optic, digital subscriber line), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., SSD), etc.
Those skilled in the art will appreciate that implementing all or part of the above described embodiment methods may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed, may comprise the steps of embodiments of the methods described above.
The foregoing examples represent only a few preferred embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the application. It should be noted that modifications and substitutions can be made by those skilled in the art without departing from the technical principles of the present application, and such modifications and substitutions should also be considered to be within the scope of the present application. Therefore, the protection scope of the patent of the application is subject to the protection scope of the claims.
Claims (10)
1. An underwater non-uniform illumination image enhancement method is characterized by comprising the following steps:
acquiring an illumination distribution map and a brightness channel standard image according to the acquired original illumination image;
correcting the brightness channel standard image by using an adaptive gamma correction algorithm and the illumination distribution map to obtain a brightness correction image;
acquiring a color image according to the brightness correction image, converting the color image into a YUV color space, and acquiring UV channel values at each pixel point in the YUV color space;
determining the Y-channel white point position in a YUV color space according to the UV channel values at all the pixel points and a preset UV bright point threshold value;
performing white balance adjustment on each channel of the color image at the white point position of the Y channel to obtain an enhanced image;
and carrying out wavelet denoising treatment on the enhanced image to obtain a denoised image.
2. The method for enhancing an underwater non-uniform illumination image according to claim 1, wherein the step of acquiring an illumination distribution map and a luminance channel standard image from the acquired original illumination image comprises:
acquiring an original illumination image;
guiding and filtering the original illumination image to obtain an illumination distribution map;
performing color space conversion and channel separation on an original illumination image to obtain a single-channel image; the single-channel image comprises a tone single-channel image, a saturation single-channel image and a brightness single-channel image;
and carrying out standardization processing on the brightness single-channel image to obtain a brightness channel standard image.
3. The method for enhancing an underwater non-uniform illumination image according to claim 1, wherein the calculation formula of the adaptive gamma correction algorithm is:
I out (x,y)＝I(x,y) Y(x,y) ×255
wherein ,
in the formula ,Iout (x, y) represents a brightness correction image; i (x, y) represents a luminance channel standard image; y (x, Y) represents an adaptive gamma parameter; j (x, y) represents an illumination profile; beta (x, y) represents a luminance image dark area threshold; alpha (x, y) represents a luminance channel standard image; v (x, y) represents the luminance value of the luminance channel standard image at (x, y); s (x, y) represents the saturation value of the luminance channel standard image at (x, y);an average value representing the standard image brightness of the brightness channel; />An average value representing the saturation of the standard image of the brightness channel; θ (x, y) represents the gray value of the luminance channel standard image at (x, y); delta represents the median of the standard image gray values of the luminance channels.
4. The method for enhancing an underwater non-uniform illumination image according to claim 1, wherein the step of determining the Y-channel white point position in YUV color space according to the UV channel values at all pixels and a preset UV bright point threshold value comprises:
determining a UV bright spot threshold according to UV channel values at all pixel points, wherein the UV bright spot threshold comprises a U-channel bright spot threshold and a V-channel bright spot threshold;
screening out bright pixel points according to the UV channel values at each pixel point and the UV bright point threshold value;
counting a histogram of the bright pixel points in a Y channel, and determining a bright point average value according to pixel values of the bright pixel points with preset duty ratios in the histogram;
and determining the white point position of the Y channel in the YUV color space according to the bright point average value.
5. The method of claim 4, wherein the step of screening out bright pixels based on the UV channel values at each pixel and the UV bright point threshold value comprises:
traversing all pixel points in the YUV color space, and dividing the current pixel point into bright pixel points if the difference value between the U channel value of the current pixel point and the U channel bright point threshold value is not smaller than a first preset threshold value or the difference value between the V channel value of the current pixel point and the V channel bright point threshold value is not smaller than a second preset threshold value;
the U-channel bright spot threshold is determined according to a U-channel mean value and a preset U-channel dynamic threshold, and the V-channel bright spot threshold is determined according to the V-channel mean value and the preset V-channel dynamic threshold.
6. The method for enhancing an underwater non-uniform illumination image according to claim 1, wherein the white balance adjustment is performed on each channel of the color image at the white point position of the Y channel, and a calculation formula for obtaining the enhanced image is as follows:
wherein R (x, y) represents the R channel pixel value of the enhanced image; g (x, y) represents G channel pixel values of the enhanced image; b (x, y) represents B-channel pixel values of the enhanced image; r (x, y) represents the R channel pixel value of the original illumination image; r is (r) aver An R channel pixel average value representing an original illumination image; g (x, y) represents the G channel pixel value of the original illumination image; g aver A G channel pixel average representing the original illumination image; b (x, y) represents the B-channel pixel values of the original illumination image; b aver A B-channel pixel average value representing an original illumination image; y is max Representing the Y-channel pixel maximum in YUV color space.
7. The method for enhancing an underwater non-uniform illumination image according to claim 1, wherein the step of performing wavelet denoising processing on the enhanced image to obtain a denoised image comprises:
performing YCrCb color space conversion on the enhanced image to obtain a Y brightness channel image;
performing wavelet transformation on the Y brightness channel image to obtain wavelet coefficients;
setting a wavelet threshold, and performing wavelet inverse transformation on the Y brightness channel image by utilizing the wavelet threshold and a wavelet coefficient to obtain a denoised Y brightness channel image;
combining the denoised Y brightness channel image with the hue channel and the saturation channel of the enhanced image to obtain a combined image;
and converting the combined image from the YCrCb color space to an RGB space to obtain a denoising image.
8. An underwater non-uniform illumination image enhancement system, the system comprising:
the image acquisition module is used for acquiring an illumination distribution map and a brightness channel standard image according to the acquired original illumination image;
the image correction module is used for correcting the brightness channel standard image by utilizing an adaptive gamma correction algorithm and the illumination distribution diagram to obtain a brightness correction image;
the space conversion module is used for acquiring a color image according to the brightness correction image, converting the color image into a YUV color space, acquiring UV channel values at all pixel points in the YUV color space, and determining the Y-channel white point position in the YUV color space according to the UV channel values at all pixel points and a preset UV bright point threshold;
the image enhancement module is used for carrying out white balance adjustment on each channel of the color image at the white point position of the Y channel to obtain an enhanced image;
and the image denoising module is used for carrying out wavelet denoising processing on the enhanced image to obtain a denoised image.
9. A computer device, characterized by: comprising a processor and a memory, the processor being connected to the memory, the memory being for storing a computer program, the processor being for executing the computer program stored in the memory to cause the computer device to perform the method of any one of claims 1 to 7.
10. A computer-readable storage medium, characterized by: the computer readable storage medium having stored therein a computer program which, when executed, implements the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310590991.2A CN116681606A (en) | 2023-05-23 | 2023-05-23 | Underwater uneven illumination image enhancement method, system, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310590991.2A CN116681606A (en) | 2023-05-23 | 2023-05-23 | Underwater uneven illumination image enhancement method, system, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116681606A true CN116681606A (en) | 2023-09-01 |
Family
ID=87784607
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310590991.2A Pending CN116681606A (en) | 2023-05-23 | 2023-05-23 | Underwater uneven illumination image enhancement method, system, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116681606A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117893457A (en) * | 2024-03-18 | 2024-04-16 | 深圳市塔联科技有限公司 | PCB intelligent detection method, device and computer equipment |
| CN117994160A (en) * | 2024-04-01 | 2024-05-07 | 南昌理工学院 | Image processing method and system |
| CN118154487A (en) * | 2024-05-10 | 2024-06-07 | 南京龟兔赛跑软件研究院有限公司 | Image enhancement method and system based on illumination correction |
-
2023
- 2023-05-23 CN CN202310590991.2A patent/CN116681606A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117893457A (en) * | 2024-03-18 | 2024-04-16 | 深圳市塔联科技有限公司 | PCB intelligent detection method, device and computer equipment |
| CN117893457B (en) * | 2024-03-18 | 2024-05-14 | 深圳市塔联科技有限公司 | PCB intelligent detection method, device and computer equipment |
| CN117994160A (en) * | 2024-04-01 | 2024-05-07 | 南昌理工学院 | Image processing method and system |
| CN117994160B (en) * | 2024-04-01 | 2024-06-04 | 南昌理工学院 | Image processing method and system |
| CN118154487A (en) * | 2024-05-10 | 2024-06-07 | 南京龟兔赛跑软件研究院有限公司 | Image enhancement method and system based on illumination correction |
| CN118154487B (en) * | 2024-05-10 | 2024-08-16 | 南京龟兔赛跑软件研究院有限公司 | Image enhancement method and system based on illumination correction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111047530B (en) | Underwater image color correction and contrast enhancement method based on multi-feature fusion | |
| CN110689587B (en) | Underwater image enhancement method based on color correction and detail enhancement | |
| CN116681606A (en) | Underwater uneven illumination image enhancement method, system, equipment and medium | |
| CN103854259B (en) | Image processing equipment and the method for handling image | |
| RU2400815C2 (en) | Method of enhancing digital image quality | |
| CN111986120A (en) | Low-illumination image enhancement optimization method based on frame accumulation and multi-scale Retinex | |
| Zhou et al. | Multi-scale retinex-based adaptive gray-scale transformation method for underwater image enhancement | |
| CN111210395B (en) | Retinex underwater image enhancement method based on gray value mapping | |
| CN111968062B (en) | Dark channel prior specular highlight image enhancement method and device and storage medium | |
| CN114240789B (en) | Infrared image histogram equalization enhancement method capable of maintaining brightness based on optimization | |
| CN109214996B (en) | Image processing method and device | |
| Hou et al. | Underwater image dehazing and denoising via curvature variation regularization | |
| CN113222866B (en) | Gray scale image enhancement method, computer readable medium and computer system | |
| CN115578297A (en) | Generalized attenuation image enhancement method for self-adaptive color compensation and detail optimization | |
| CN116188339A (en) | Retinex and image fusion-based scotopic vision image enhancement method | |
| CN112822343B (en) | Night video oriented sharpening method and storage medium | |
| CN114037641A (en) | Low-illumination image enhancement method, device, equipment and medium | |
| CN117876233A (en) | Mapping image enhancement method based on unmanned aerial vehicle remote sensing technology | |
| CN110136085B (en) | Image noise reduction method and device | |
| CN113436106B (en) | Underwater image enhancement method and device and computer storage medium | |
| CN115034985A (en) | Underwater image enhancement method | |
| CN113744169A (en) | Image enhancement method and device, electronic equipment and storage medium | |
| Jayanthi et al. | Underwater haze removal using contrast boosted grayscale image | |
| Xu et al. | Multiscale luminance adjustment-guided fusion for the dehazing of underwater images | |
| CN117994160B (en) | Image processing method and system |
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 |