CN111598791B - Image defogging method based on improved dynamic atmospheric scattering coefficient function - Google Patents
Image defogging method based on improved dynamic atmospheric scattering coefficient function Download PDFInfo
- Publication number
- CN111598791B CN111598791B CN202010284296.XA CN202010284296A CN111598791B CN 111598791 B CN111598791 B CN 111598791B CN 202010284296 A CN202010284296 A CN 202010284296A CN 111598791 B CN111598791 B CN 111598791B
- Authority
- CN
- China
- Prior art keywords
- image
- filtering
- scattering coefficient
- depth
- atmospheric scattering
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000001914 filtration Methods 0.000 claims abstract description 55
- 238000002834 transmittance Methods 0.000 claims abstract description 13
- 230000011218 segmentation Effects 0.000 claims abstract description 11
- 238000009499 grossing Methods 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000001131 transforming effect Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 12
- 230000000694 effects Effects 0.000 abstract description 8
- 230000006870 function Effects 0.000 description 29
- 230000000875 corresponding effect Effects 0.000 description 8
- 238000011156 evaluation Methods 0.000 description 6
- 238000012937 correction Methods 0.000 description 5
- 238000012795 verification Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 239000000443 aerosol Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000593 degrading effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000003595 mist Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- 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
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
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 image defogging method based on an improved dynamic atmospheric scattering coefficient function, which utilizes R, G, B color channels of an original image to obtain a minimum value channel image, and calculates an atmospheric light value A of a foggy day image by means of a quadtree segmentation method; calculating the depth of field d (x) of the image by using a nonlinear color attenuation priori model, and filtering noise information in the depth of field d by minimum value filtering, smooth filtering and guided filtering to obtain the final depth of field d of the image r (x) The method comprises the steps of carrying out a first treatment on the surface of the Finally, combining the improved dynamic atmospheric scattering coefficient function beta (x) and the image depth of field d obtained by final processing r (x) Calculating the atmospheric transmittance t (x), and recovering a haze-free image through an atmospheric scattering model; the method of the invention not only can solve the problem of inaccurate transmissivity estimation caused by constant atmospheric scattering coefficient, but also can effectively solve the phenomenon of color distortion of the sky area of the image, so that the defogging effect of the image is clearer and more thorough, and the color of a scene is more natural and more true.
Description
Technical Field
The invention belongs to the technical field of image processing, and particularly relates to an image defogging method based on an improved dynamic atmospheric scattering coefficient function.
Background
Haze is a natural phenomenon common on land and on the ocean. In severe weather such as fog and haze, aerosols and solid particles suspended in the atmosphere can absorb and scatter light to some extent, degrading images captured by the photographing device, typically with low contrast and low visibility, which can seriously affect vision systems, particularly the visible vision system. Since the sharpness of the degraded image is seriously reduced, which is a great difficulty and challenge for the subsequent automatic processing of the image, the development of a fast and effective adaptive image defogging method has very important practical significance for the automatic processing of the image and the video.
The model mainly adopted by the image defogging technology is a physical imaging model based on foggy weather conditions, namely an atmospheric scattering model, and the model is used for reversely recovering a foggy image mainly by estimating required physical parameters such as atmospheric light and transmission rate (depth). The atmospheric scattering physical model was proposed by McCartney in 1976, and then the mathematical model was further derived by Narasimhan and Nayar et al, which laid a solid foundation for image defogging research. Over the past few years, many scholars and researchers have achieved significant results in the defogging research area. If He et al propose to replace soft matting with guided filtering, algorithm complexity is reduced, but obvious residual fog still exists in a distant view area; meng et al propose a defogging algorithm based on boundary constraint, the method recovers the defogging image by increasing constraint conditions of parameters in a physical model, and improves recovery effect by sacrificing a small amount of details, so that a clearer image is obtained, but the calculation complexity of post-processing operation is larger; zhu et al found by observing HSV color channels that there was a linear relationship between the difference between brightness and saturation and the image depth of field, and accordingly proposed a priori knowledge of color attenuation, established a mathematical model of depth of field information about image saturation, brightness, and solved depth of field information by means of supervised learning, thereby achieving defogging of images.
Disclosure of Invention
The invention aims to provide an image defogging method based on an improved dynamic atmospheric scattering coefficient function, which can effectively solve the problem of insufficient color attenuation priori algorithm in the prior art.
The first technical scheme adopted by the invention is that an image defogging method based on an improved dynamic atmospheric scattering coefficient function is implemented according to the following steps:
step 1, acquiring a minimum value channel image I of red, green and blue channel values of an input foggy day image I (x) dark (x) Calculating an atmospheric light value A of a foggy day image I (x) by a quadtree segmentation method;
step 2, carrying out color space domain transformation on an original foggy day image I (x), namely transforming from RGB color space to HSV color space, and extracting a brightness component v (x) and a saturation component s (x) of the foggy day image I (x);
step 3, utilizing nonlinear colorThe depth of field d (x) of the foggy-day image I (x) is calculated by the color attenuation priori model, noise information in the foggy-day image I (x) is filtered through minimum value filtering, smooth filtering and guided filtering, and the final image depth of field d is obtained r (x)；
Step 4, combining the improved dynamic atmospheric scattering coefficient function beta (x) and the image depth of field d r (x) Calculating the atmospheric transmittance t (x);
and 5, substituting the atmospheric light value A and the atmospheric transmissivity t (x) into an atmospheric scattering model formula of the foggy day image, denoising through a foggy image restoration formula, and calculating a foggy image J (x).
The invention is also characterized in that:
step 1 minimum channel image I dark (x) The expression is:
where y represents one of the R, G, B color channels.
The specific process of the step 1 is as follows:
step 1.1, according to the initial threshold T 0 For 30×30, a gray image I is obtained for the input foggy day image I (x) gray ；
Step 1.2, for gray scale image I gray Obtaining a filtered image I using median filtering median ；
Step 1.3, image I median Dividing into four rectangular areas averagely by a quadtree segmentation method;
step 1.4, calculating an average pixel value of each rectangular region, subtracting the standard deviation of the region from the average pixel value to obtain a score, and selecting a maximum score and a region block corresponding to the maximum score;
step 1.5, comparing the region corresponding to the maximum score with an initial threshold T 0 Is of a size of (2); if the region corresponding to the maximum score is greater than the initial threshold T 0 Returning to the step 1.2; otherwise, the region corresponding to the maximum score is a target region;
and 1.6, obtaining an average value of the gray value of the target area, wherein the average value is the atmospheric light value A.
The nonlinear color attenuation prior model expression in the step 3 is as follows:
in the formula (2), v (x) represents the luminance component of the foggy day image I (x), s (x) represents the saturation component of the foggy day image I (x), and the parameter α=4.99, θ 0 ＝-0.29，θ 1 ＝0.83，θ 2 ＝-0.16。
In the step 3, the specific process of filtering noise information in the noise information through minimum value filtering, smooth filtering and guided filtering is as follows:
step a, denoising the problem that the white object is mistaken for a distant view by adopting minimum value filtering;
wherein d min (x) Representing the minimum filtered image depth of field, d (y) representing the image depth of field to be filtered, Ω (x) representing the filtering region centered on pixel x, the filtered structural element taking a square matrix of 15 x 15.
Step b, depth of field d of the image after minimum value filtering min (x) Smoothing and guided filtering to obtain final image depth d r (x)：
d r (x)＝guidedfilter(I gray ,d erode (x),r,esp) (5)
Wherein I is gray Gray scale image representing original foggy day image I (x), d erode (x) The depth of field of the image after smooth filtering is represented, r is the radius of a filtering window, the value is 30, esp is a regularization parameter, and the value is 0.01.
The expression of the dynamic atmospheric scattering coefficient function beta (x) is improved in the step 4:
and (4) calculating the atmospheric transmittance t (x) as follows:
t(x)＝exp[-βd r (x)] (15)
the atmospheric scattering model formula is:
I(x)＝J(x)t(x)+A[1-t(x)] (16)
the process of calculating the haze-free image J (x) is as follows:
in the formula (9), t 0 The lower threshold value set for the transmittance t (x) takes a value of 0.1.
The beneficial effects of the invention are as follows:
the image defogging method based on the improved dynamic atmospheric scattering coefficient function utilizes the improved dynamic atmospheric scattering coefficient function model, so that the problem of insufficient defogging degree of a local area caused by constant atmospheric scattering coefficient in the conventional color attenuation priori image defogging algorithm is solved, and the problem of color distortion of an image sky area is also solved.
Drawings
FIG. 1 is a flow chart of an image defogging method based on an improved dynamic atmospheric scattering coefficient function in the present invention;
FIG. 2 is a graph of experimental results of different values of a and b;
FIG. 3 is a foggy day image;
FIG. 4 is an image before correction;
FIG. 5 is a corrected image;
FIG. 6 is an original foggy day image;
FIG. 7 is a He algorithm processing result;
FIG. 8 is a graph showing the results of the Meng algorithm;
FIG. 9 is a graph showing the results of the Zhu algorithm;
FIG. 10 shows the result of the treatment according to the method of the present invention.
Detailed Description
The invention will be described in detail below with reference to the drawings and the detailed description.
The origin of the color decay a priori theory is: a new defogging solution proposed by Zhu et al in 2015, zhu et al found after a lot of experiments on outdoor foggy images: there is a linear relationship between the depth of field of the image and the difference between the luminance and saturation, and a color decay prior model (color attenuation prior, CAP) is proposed accordingly, namely
d(x)＝θ 0 +θ 1 v(x)+θ 2 s(x)+ε(x) (10)
Where d (x) is the depth of field at pixel point x, v (x) and s (x) are the luminance component and saturation component at x, respectively, θ 1 And theta 2 For unknown linear coefficients, ε (x) is the random error of the model, assuming that its obeying mean is 0, and variance is σ 2 Normal distribution of (a), i.e. epsilon (x) to N (0, sigma) 2 ) From the nature of normal distribution
d(x)～N(θ 0 +θ 1 v(x)+θ 2 s(x)，σ 2 ) (11)
Finally, training a linear model by adopting 500 training samples and 1.2 hundred million pixel points, and obtaining an optimal coefficient theta through 517 generations 0 ＝0.121779，θ 1 ＝0.959710，θ 2 = -0.780245, σ= 0.041337. As can be seen from the formula (10), the depth of field of the image can be calculated after obtaining the brightness and saturation information of the foggy image.
The invention discloses an image defogging method based on an improved dynamic atmospheric scattering coefficient function, which is implemented according to the following steps as shown in figure 1:
step 1, acquiring a minimum value channel image I of red, green and blue channel values of an input foggy day image I (x) dark (x) Calculating an atmospheric light value A of a foggy day image I (x) by a quadtree segmentation method;
minimum value channel image I dark (x) The expression is:
where y represents one of the R, G, B color channels.
The specific process of the step 1 is as follows:
step 1.1, according to the initial threshold T 0 For 30×30, a gray image I is obtained for the input foggy day image I (x) gray ；
Step 1.2, for gray scale image I gray Obtaining a filtered image I using median filtering median ；
Step 1.3, image I median Dividing into four rectangular areas averagely by a quadtree segmentation method;
step 1.4, calculating an average pixel value of each rectangular region, subtracting the standard deviation of the region from the average pixel value to obtain a score, and selecting the maximum score and the region corresponding to the maximum score;
step 1.5, comparing the region corresponding to the maximum score with an initial threshold T 0 Is of a size of (2);
if the region corresponding to the maximum score is greater than the initial threshold T 0 Returning to the step 1.2;
otherwise, the region corresponding to the maximum score is a target region;
and 1.6, obtaining an average value of the gray value of the target area, wherein the average value is the atmospheric light value A.
Step 2, carrying out color space domain transformation on an original foggy day image I (x), namely transforming from RGB color space to HSV color space, and extracting a brightness component v (x) and a saturation component s (x) of the foggy day image I (x);
step 3, calculating the depth of field d (x) of the foggy-day image I (x) by using a nonlinear color attenuation priori model, filtering noise information in the foggy-day image I (x) by minimum value filtering, smooth filtering and guided filtering to obtain the final depth of field d of the image r (x)；
The nonlinear color decay prior model expression is:
in the formula (2), v (x) represents the luminance component of the foggy day image I (x), s (x) represents the saturation component of the foggy day image I (x), and the parameter α=4.99, θ 0 ＝-0.29，θ 1 ＝0.83，θ 2 ＝-0.16。
The specific process of filtering noise information in the filter by the minimum value filtering, the smoothing filtering and the guiding filtering is as follows:
step a, denoising the problem that the white object is mistaken for a distant view by adopting minimum value filtering;
wherein d min (x) Representing the minimum filtered image depth of field, d (y) representing the image depth of field to be filtered, Ω (x) representing the filtering region centered on pixel x, the filtered structural element taking a square matrix of 15 x 15.
Step b, depth of field d of the image after minimum value filtering min (x) Smoothing and guided filtering to solve the occurrence of block effect and obtain final image depth d r (x)：
d r (x)＝guidedfilter(I gray ,d erode (x),r,esp) (5)
Wherein I is gray Gray scale image representing original foggy day image I (x), d erode (x) The depth of field of the image after smooth filtering is represented, r is the radius of a filtering window, the value is 30, esp is a regularization parameter, and the value is 0.01.
Step 4, improving the evidence seeking process of the dynamic atmospheric scattering coefficient function:
according to the characteristic that the depth of field of an image is positively correlated with the fog concentration, the invention improves the function of the dynamic atmospheric scattering coefficient only by using mist, and the function form of defining the improved dynamic atmospheric scattering coefficient is as follows
Wherein a and b are unknown coefficients, and the value range d epsilon (0.1, 1) of the depth of field of the image and the value range beta epsilon (0.1,2.5) of the atmospheric scattering coefficient are combined to obtain the following steps: a epsilon (0, 1.5) and b epsilon (0, 0.5).
To further determine the unknown parameters a, b in the improved dynamic atmospheric scattering coefficient function, 100 non-uniform fog images were first randomly selected over the network and then used with the average gradient I grad Sum information entropy I entropy The two objective evaluation indexes determine the optimal values of the parameters a and b by evaluating the definition of the image and the degree of detail richness. The method comprises the following specific steps:
1) Taking 0.1 as a value interval for a and b, and taking 0.1 as a value interval in intervals (0, 1.5) and (0, 0.5) respectively to obtain 75 groups of atmospheric scattering coefficients;
2) Processing 100 non-uniform fog images by adopting the 75 groups of atmospheric scattering coefficients respectively, and obtaining 75 groups of defogging images by utilizing a formula (9);
3) Calculating the average gradient I of each group of defogging images grad Sum information entropy I entropy And carrying out normalization and average weighting treatment on the obtained product to obtain comprehensive evaluation parameters of
cep＝0.5*normal(I grad )+0.5*normal(I entropy ) (7)
4) Accumulating the comprehensive evaluation parameters of each group to obtain a final 75-group comprehensive evaluation parameter cep;
5) And (3) drawing a two-dimensional graph of a, b and cep by combining 75 groups of comprehensive evaluation parameters cep, wherein the experimental result graph is shown in fig. 2.
The expression for improving the dynamic atmospheric scattering coefficient function is determined by the experiment
Although a specific expression for improving the dynamic atmospheric scattering coefficient function is successfully obtained, the atmospheric scattering coefficient function is found to have the problem of sky area color distortion through practical verification. Therefore, in order to obtain an improved dynamic atmospheric scattering coefficient function with better effect, the adaptive atmospheric scattering coefficient function suitable for the sky area of the image is obtained by reversely deducing the dynamic atmospheric scattering coefficient function according to a sky area transmissivity correction algorithm based on color attenuation priori. The specific deduction process is as follows:
the following two characteristics are satisfied for the image sky region:
1) The difference between the brightness and saturation of the image pixels is greatest between |v (x) -s (x);
2) The transmittance t (x) is minimum.
From this, the transmittance of the image sky region is defined as follows (taking t=0.5):
t'(x)＝max{1-[v(x)-s(x)]*t(x),t(x)}，|t(x)/[v(x)-s(x)]|＜T (9)
let t' (x) =e -β'd(x) t(x)＝e -βd(x) Substituting the above into formula (15) to obtain
e -β'd(x) ＝max{1-[v(x)-s(x)]*e -βd(x) ,e -βd(x) } (10)
Taking logarithm of two sides of the pair (16) at the same time, and deforming to obtain
Because the segmentation threshold value is required to be set manually, the automatic segmentation effect cannot be achieved, the automatic segmentation of the sky region is achieved by adopting a sky region feature recognition method, namely two large sky region discrimination conditions:
max|I c -I c' |＜10,c,c'∈{R,G,B} (12)
wherein I is c And I c' Is any of the same pixel pointsTwo of the R, G, B channels are intended, with R, G, B values being similar for sky areas. Based on this, the text will (|i) c -I c' |<10)&(|A c -I c |<30 Defined as the area of sky color distortion, will (|i) c -I c' |≥10)&(|A c -I c I.gtoreq.30) is defined as a non-sky region where the transmittance does not need to be adjusted. Thus, the final modified dynamic atmospheric scattering coefficient function is:
through a large number of experimental verification, the corrected improved dynamic atmospheric scattering coefficient function can well solve the problem of sky area color distortion, and fig. 4 and 5 are comparison graphs of effects before and after correction.
Combining the improved dynamic atmospheric scattering coefficient function beta (x) and the image depth dr (x), the atmospheric transmittance t (x) is calculated as:
t(x)＝exp[-βd r (x)] (15)
and 5, substituting the atmospheric light value A and the atmospheric transmissivity t (x) into an atmospheric scattering model formula of the foggy day image, denoising through a foggy image restoration formula, and calculating a foggy image J (x).
The atmospheric scattering model formula is:
I(x)＝J(x)t(x)+A[1-t(x)] (16)
the process of calculating the haze-free image J (x) is as follows:
in the formula (17), t 0 The lower threshold value set for the transmittance t (x) takes a value of 0.1 to avoid introducing noise.
The following are specific examples of the process of the invention:
the invention obtains the depth of field information d (x) of an image through a color attenuation priori algorithm proposed by Zhu et al, and reversely derives the transmissivity t (x) of the image by utilizing an improved dynamic atmospheric scattering coefficient function beta (x) and a formula t (x) =exp < -beta d (x), and finally restores an unobscured image by means of an atmospheric scattering model I (x) =J (x) t (x) +A [1-t (x) ]. The following verification is performed for the method of the present invention:
1) Color distortion phenomenon for sky area
Selecting a foggy day image as shown in fig. 3; FIG. 4 is a graph showing the result of the processing before function correction; fig. 5 is a processing result after the function correction.
As can be seen from a comparison of fig. 4 and fig. 5, the sky area distortion of the corrected image is significantly reduced, so that the defogging result is more natural and real. The experimental result of fig. 5 shows that the method based on the improved dynamic atmospheric scattering coefficient function provided by the invention can effectively eliminate the sky color distortion phenomenon.
2) Comparison of results
Selecting an original foggy day image as shown in FIG. 6; FIG. 7 is a graph of the He algorithm processing results, with significant residual haze still present in the vision area; FIG. 8 is a graph showing the results of the Meng algorithm; FIG. 9 is a graph showing the results of the Zhu algorithm; FIG. 10 shows the result of the treatment of the method of the present invention; compared with other algorithm processing, the image restored by the method is true and natural, and brightness is more in line with the observation of human eyes.
In order to further verify the actual recovery effect of the method, the defogging results are objectively evaluated by adopting various indexes such as average gradient, contrast, information entropy, mean square error, peak signal to noise ratio, processing time and the like, and the defogging results are combined with fig. 6 and are shown in table 1.
TABLE 1
The experimental data show that the method has certain advantages in the aspects of image restoration fidelity, detail preservation and definition compared with other classical defogging algorithms.
Through the mode, the image defogging method based on the improved dynamic atmospheric scattering coefficient function not only can solve the problem of inaccurate transmissivity estimation caused by constant atmospheric scattering coefficientThe problem is solved, the phenomenon of color distortion of the sky area of the image can be effectively solved, the defogging effect of the image is clearer and more thorough, and the color of a scene is more natural and more true. The method comprises the following specific implementation steps: firstly, obtaining a minimum value channel image by utilizing R, G, B color channels of an original image, and calculating an atmospheric light value A of a foggy day image by means of a quadtree segmentation method; then, calculating the depth of field d (x) of the image by using a nonlinear color attenuation priori model, and filtering noise information in the depth of field d of the image by minimum value filtering, smooth filtering and guided filtering to obtain the final depth of field d of the image r (x) The method comprises the steps of carrying out a first treatment on the surface of the Finally, combining the improved dynamic atmospheric scattering coefficient function beta (x) and the image depth of field d obtained by final processing r (x) The atmospheric transmittance t (x) is calculated and the haze-free image is restored by the atmospheric scattering model. The feasibility and the effectiveness of the method are proved by experimental results and subjective and objective evaluation.
Claims (8)
1. An image defogging method based on an improved dynamic atmospheric scattering coefficient function is characterized by comprising the following steps:
step 1, acquiring a minimum value channel image I of red, green and blue channel values of an input foggy day image I (x) dark (x) Calculating an atmospheric light value A of a foggy day image I (x) by a quadtree segmentation method;
step 2, carrying out color space domain transformation on an original foggy day image I (x), namely transforming from RGB color space to HSV color space, and extracting a brightness component v (x) and a saturation component s (x) of the foggy day image I (x);
step 3, calculating the depth of field d (x) of the foggy-day image I (x) by using a nonlinear color attenuation priori model, filtering noise information in the foggy-day image I (x) by minimum value filtering, smooth filtering and guided filtering to obtain the final depth of field d of the image r (x)；
The nonlinear color attenuation prior model expression is:
in the formula (2), v (x) represents the luminance component of the foggy day image I (x), s (x) represents the saturation component of the foggy day image I (x), and the parameter α=4.99, θ 0 ＝-0.29，θ 1 ＝0.83，θ 2 ＝-0.16；
Step 4, combining the improved dynamic atmospheric scattering coefficient function beta (x) and the image depth dr (x), and calculating the atmospheric transmittance t (x);
and 5, substituting the atmospheric light value A and the atmospheric transmissivity t (x) into an atmospheric scattering model formula of the foggy day image, denoising through a foggy image restoration formula, and calculating a foggy image J (x).
2. The image defogging method based on the improved dynamic atmospheric scattering coefficient function according to claim 1, wherein the minimum value channel image I of step 1 dark (x) The expression is:
where y represents one of the R, G, B color channels.
3. The image defogging method based on an improved dynamic atmospheric scattering coefficient function according to claim 1, wherein the specific process of step 1 is as follows:
step 1.1, according to the initial threshold T 0 For 30×30, a gray image I is obtained for the input foggy day image I (x) gray ；
Step 1.2, for gray scale image I gray Obtaining a filtered image I using median filtering median ；
Step 1.3, image I median Dividing into four rectangular areas averagely by a quadtree segmentation method;
step 1.4, calculating an average pixel value of each rectangular region, subtracting the standard deviation of the region from the average pixel value to obtain a score, and selecting the maximum score and the region corresponding to the maximum score;
step 1.5, comparing the region corresponding to the maximum score with an initial threshold T 0 Is of a size of (2); if the region corresponding to the maximum score is greater than the initial threshold T 0 Returning to the step 1.2; otherwise, the region corresponding to the maximum score is a target region;
and 1.6, obtaining an average value of the gray value of the target area, wherein the average value is the atmospheric light value A.
4. The image defogging method based on the improved dynamic atmospheric scattering coefficient function according to claim 1, wherein the specific process of filtering noise information in the image defogging method through minimum value filtering, smoothing filtering and guiding filtering in the step 3 is as follows:
step a, denoising the problem that the white object is mistaken for a distant view by adopting minimum value filtering;
wherein d min (x) Representing the depth of field of the image after minimum value filtering, d (y) representing the depth of field of the image to be filtered, Ω (x) representing a filtering region centered on the pixel x, the filtering structure element taking a square matrix of 15×15;
step b, depth of field d of the image after minimum value filtering min (x) Smoothing and guided filtering to obtain final image depth d r (x)：
d r (x)＝guidedfilter(I gray ,d erode (x),r,esp) (5)
Wherein I is gray Gray scale image representing original foggy day image I (x), d erode (x) The depth of field of the image after smooth filtering is represented, r is the radius of a filtering window, the value is 30, esp is a regularization parameter, and the value is 0.01.
5. The image defogging method based on an improved dynamic atmospheric scattering coefficient function according to claim 1, wherein the expression of the improved dynamic atmospheric scattering coefficient function β (x) in step 4 is:
6. the image defogging method based on an improved dynamic atmospheric scattering coefficient function according to claim 1, wherein the calculated atmospheric transmittance t (x) expression in step 4 is:
t(x)＝exp[-βd r (x)] (15)
7. the image defogging method based on an improved dynamic atmospheric scattering coefficient function according to claim 1, wherein the atmospheric scattering model formula is:
I(x)＝J(x)t(x)+A[1-t(x)] (16)
8. an image defogging method based on an improved dynamic atmospheric scattering coefficient function according to claim 1, wherein the process of calculating a defogging image J (x) is:
in the formula (9), t 0 The lower threshold value set for the transmittance t (x) takes a value of 0.1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010284296.XA CN111598791B (en) | 2020-04-13 | 2020-04-13 | Image defogging method based on improved dynamic atmospheric scattering coefficient function |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010284296.XA CN111598791B (en) | 2020-04-13 | 2020-04-13 | Image defogging method based on improved dynamic atmospheric scattering coefficient function |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111598791A CN111598791A (en) | 2020-08-28 |
| CN111598791B true CN111598791B (en) | 2024-01-23 |
Family
ID=72182041
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010284296.XA Active CN111598791B (en) | 2020-04-13 | 2020-04-13 | Image defogging method based on improved dynamic atmospheric scattering coefficient function |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111598791B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112365467B (en) * | 2020-11-11 | 2022-07-19 | 武汉长江通信智联技术有限公司 | Foggy image visibility estimation method based on single image depth estimation |
| CN112465715B (en) | 2020-11-25 | 2023-08-08 | 清华大学深圳国际研究生院 | Image scattering removal method based on iterative optimization of atmospheric transmission matrix |
| WO2022213372A1 (en) * | 2021-04-09 | 2022-10-13 | 深圳市大疆创新科技有限公司 | Image dehazing method and apparatus, and electronic device and computer-readable medium |
| CN113298729B (en) * | 2021-05-24 | 2022-04-26 | 中国科学院长春光学精密机械与物理研究所 | Rapid single image defogging method based on minimum value channel |
| CN113643323B (en) * | 2021-08-20 | 2023-10-03 | 中国矿业大学 | Target detection system under urban underground comprehensive pipe rack dust fog environment |
| CN117893440B (en) * | 2024-03-15 | 2024-05-14 | 昆明理工大学 | Image defogging method based on diffusion model and depth-of-field guidance generation |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110211067A (en) * | 2019-05-27 | 2019-09-06 | 哈尔滨工程大学 | One kind being used for UUV Layer Near The Sea Surface visible images defogging method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101756173B1 (en) * | 2016-04-29 | 2017-07-10 | 전남대학교산학협력단 | Image dehazing system by modifying the lower-bound of transmission rate and method therefor |
-
2020
- 2020-04-13 CN CN202010284296.XA patent/CN111598791B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110211067A (en) * | 2019-05-27 | 2019-09-06 | 哈尔滨工程大学 | One kind being used for UUV Layer Near The Sea Surface visible images defogging method |
Non-Patent Citations (2)
| Title |
|---|
| 刘策 ; 杨燕 ; .基于自适应小波融合的单幅图像去雾算法.光电子・激光.2020,(03),全文. * |
| 胡雪薇 ; 李其申 ; .动态大气散射系数的颜色衰减先验图像去雾.电视技术.2017,(Z2),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111598791A (en) | 2020-08-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111598791B (en) | Image defogging method based on improved dynamic atmospheric scattering coefficient function | |
| US11127122B2 (en) | Image enhancement method and system | |
| CN108288258B (en) | Low-quality image enhancement method under severe weather condition | |
| CN108154492B (en) | A kind of image based on non-local mean filtering goes haze method | |
| CN111145105B (en) | Image rapid defogging method and device, terminal and storage medium | |
| CN110675340A (en) | Single image defogging method and medium based on improved non-local prior | |
| CN111861896A (en) | UUV-oriented underwater image color compensation and recovery method | |
| CN108133462B (en) | Single image restoration method based on gradient field region segmentation | |
| Yu et al. | Image and video dehazing using view-based cluster segmentation | |
| CN114219732A (en) | Image defogging method and system based on sky region segmentation and transmissivity refinement | |
| CN109118450B (en) | Low-quality image enhancement method under sand weather condition | |
| CN111598800B (en) | Single image defogging method based on space domain homomorphic filtering and dark channel priori | |
| CN111598814B (en) | Single image defogging method based on extreme scattering channel | |
| CN110349113B (en) | Adaptive image defogging method based on dark primary color priori improvement | |
| CN109949239B (en) | Self-adaptive sharpening method suitable for multi-concentration multi-scene haze image | |
| CN112750089B (en) | Optical remote sensing image defogging method based on local block maximum and minimum pixel prior | |
| CN117495719A (en) | Defogging method based on atmospheric light curtain and fog concentration distribution estimation | |
| CN113379631B (en) | Image defogging method and device | |
| CN115861104A (en) | Remote sensing image defogging method based on transmissivity refinement | |
| CN111260589B (en) | Retinex-based power transmission line monitoring image defogging method | |
| CN115619662A (en) | Image defogging method based on dark channel prior | |
| CN110889805A (en) | Image defogging method based on dark channel compensation and atmospheric light value improvement | |
| CN110647843A (en) | Face image processing method | |
| Naseeba et al. | KP Visibility Restoration of Single Hazy Images Captured in Real-World Weather Conditions | |
| CN117952864B (en) | Image defogging method based on region segmentation, storage medium and terminal equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240129 Address after: 4055C, 4th Floor, No. 82 Taoyu Road, Tianhe District, Guangzhou City, Guangdong Province, 510000 Patentee after: Guangzhou Zhiguo cloud Intellectual Property Operation Co.,Ltd. Country or region after: China Address before: 710000 No. B49, Xinda Zhongchuang space, 26th Street, block C, No. 2 Trading Plaza, South China City, international port district, Xi'an, Shaanxi Province Patentee before: Xi'an Huaqi Zhongxin Technology Development Co.,Ltd. Country or region before: China Effective date of registration: 20240129 Address after: 710000 No. B49, Xinda Zhongchuang space, 26th Street, block C, No. 2 Trading Plaza, South China City, international port district, Xi'an, Shaanxi Province Patentee after: Xi'an Huaqi Zhongxin Technology Development Co.,Ltd. Country or region after: China Address before: 710048 Shaanxi province Xi'an Beilin District Jinhua Road No. 5 Patentee before: XI'AN University OF TECHNOLOGY Country or region before: China |
|
| TR01 | Transfer of patent right |