CN114049283A - Self-adaptive gray gradient histogram equalization remote sensing image enhancement method - Google Patents

Self-adaptive gray gradient histogram equalization remote sensing image enhancement method Download PDF

Info

Publication number
CN114049283A
CN114049283A CN202111355703.2A CN202111355703A CN114049283A CN 114049283 A CN114049283 A CN 114049283A CN 202111355703 A CN202111355703 A CN 202111355703A CN 114049283 A CN114049283 A CN 114049283A
Authority
CN
China
Prior art keywords
gray
gradient
image
degrees
histogram
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
Application number
CN202111355703.2A
Other languages
Chinese (zh)
Inventor
于欢
李乃星
王凤姣
焦美敬
林俊贤
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Radio Equipment Research Institute
Original Assignee
Shanghai Radio Equipment Research Institute
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Radio Equipment Research Institute filed Critical Shanghai Radio Equipment Research Institute
Priority to CN202111355703.2A priority Critical patent/CN114049283A/en
Publication of CN114049283A publication Critical patent/CN114049283A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/40—Image enhancement or restoration using histogram techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/90—Dynamic range modification of images or parts thereof
    • G06T5/94—Dynamic range modification of images or parts thereof based on local image properties, e.g. for local contrast enhancement
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10032—Satellite or aerial image; Remote sensing

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

A self-adaptive gray gradient histogram equalization remote sensing image enhancement method comprises the steps of converting an original remote sensing image into a gray image, obtaining an average gray image in an 8-neighborhood range, calculating gradient values of the gray image in the directions of 0 degrees, 90 degrees, 45 degrees and 135 degrees, obtaining a gray gradient combination histogram according to the gray levels and the gradient values, establishing a gray mapping relation, reconstructing the input original remote sensing image through histogram equalization processing, obtaining an enhanced image, calculating variation coefficients of two groups of enhanced images containing gradient information of 0 degrees, 90 degrees, 45 degrees and 135 degrees and the average gray image, marking out pixel points with the largest difference of image data before and after enhancement according to the variation coefficients, and obtaining a final enhanced image according to the gradient variation trend of the pixel points. The enhanced image obtained by reconstruction retains gradient information in four directions of 0 degree, 90 degrees, 45 degrees and 135 degrees, avoids loss of local details, is rich in details, does not need to manually set parameters, and can adaptively complete the whole image reconstruction process.

Description

Self-adaptive gray gradient histogram equalization remote sensing image enhancement method
Technical Field
The invention relates to the field of image enhancement, in particular to a method for enhancing a remote sensing image through gray gradient histogram equalization processing.
Background
The image enhancement is to improve the contrast and image definition of the target and the background in the image through various mathematical methods and transformation algorithms so as to highlight the interested part of people or other receiving systems, while the remote sensing image enhancement is to improve the contrast and definition of a certain gray scale area so as to improve the information content of image display and enable the image to be more beneficial to the resolution of human eyes.
Image enhancement methods are mainly divided into two main categories: a spatial domain method and a frequency domain method. The spatial domain method is mainly to directly process the gray scale coefficients of an image in a spatial domain, and the frequency domain method is to perform some correction on the transform coefficient values of the image in some transform domain of the image and then obtain an enhanced image through inverse transformation. The histogram equalization method belongs to a single-point enhanced histogram correction method in a spatial domain.
Document "infrared image adaptive inverse histogram enhancement technology" proposes that the contrast and brightness of a high gray level region are effectively improved through inverse statistics, adaptive threshold selection and segmented mapping enhancement of an image, but the contrast and brightness of a low and medium gray level region are not improved. Document "an image detail enhancement method of histogram equalization interpolation" proposes that a certain gray level is inserted into a position where an interval value between adjacent gray levels of a histogram of the traditional histogram equalization is from large to small to form a new histogram, so that image details are retained, but the contrast is not improved well.
Patent document CN109345491A, "a method for enhancing remote sensing image by fusing gradient and gray scale information", proposes to implement adaptive enhancement of remote sensing image by combining histogram transformation and gradient detail compensation through gradient and gray scale, but only considering gradient information in horizontal and vertical directions, has certain limitations. Patent document CN111311525A, "a histogram probability correction based image gradient field dual-interval equalization algorithm", proposes to divide a gradient histogram into an edge part and a non-edge part of an image, and equalize the two parts separately, which may result in erroneous division of the edge part and the non-edge part of the gradient histogram. Patent document CN110827229A, an infrared image enhancement method based on texture weighted histogram equalization, proposes to perform nonlinear transformation on the histogram of the statistical region where the pixel points whose local extreme value difference is greater than or equal to a preset difference threshold are located, and perform equalization processing on the transformed histogram, which is not suitable for remote sensing images.
Disclosure of Invention
According to the self-adaptive gray gradient histogram equalization remote sensing image enhancement method provided by the invention, gradient information of the remote sensing image in different directions is considered, loss of local details is avoided, details of the enhanced image are rich, parameters do not need to be set manually, and the whole image reconstruction process can be completed in a self-adaptive manner.
In order to achieve the above object, the present invention provides a method for enhancing a self-adaptive gray-scale gradient histogram balanced remote sensing image, comprising the following steps:
s1, converting the input remote sensing image into a gray image G;
s2, calculating the average gray image G in the 8-neighborhood rangeaver：
Figure BDA0003356997990000021
Wherein G isaver(x, y) represents the average gray value of the pixel point (x, y) in the range of 8 neighborhoods;
s3, calculating the gradients of the pixel points G (x, y) in the directions of 0 degree and 90 degrees
Figure BDA0003356997990000022
Gradients in the 45 ° and 135 ° directions
Figure BDA0003356997990000023
Figure BDA0003356997990000024
Figure BDA0003356997990000025
Wherein G isx(x, y) represents a gradient value of the pixel point (x, y) in the 0 DEG direction, Gy(x, y) represents the gradient value of the pixel point (x, y) in the direction of 90 DEG, Gu(x, y) represents the gradient value of the pixel point (x, y) in the 45 DEG direction, Gv(x, y) represents a gradient value of the pixel point (x, y) in the 135 ° direction;
s4, according to the gray scale of the gray image G and the gray scale gradient in the 0 degree and 90 degree directions
Figure BDA0003356997990000026
Establishing a histogram Hxy：
Figure BDA0003356997990000027
Figure BDA0003356997990000028
Wherein, the gray scale number of the gray image G is L, phi (m, n) is equal when the gray scale value G (x, y) is the same and the gray gradient is
Figure BDA0003356997990000031
The same is 1, and the other cases are 0, and the function is a binary function;
s5, according to the gray scale of the gray image G and the gray scale gradients in the 45 degree and 135 degree directions
Figure BDA0003356997990000032
Establishing a histogram Huv：
Figure BDA0003356997990000033
Figure BDA0003356997990000034
Wherein, the gray scale number of the gray image G is L, phi (m, n) is equal when the gray scale value G (x, y) is the same and the gray gradient is
Figure BDA0003356997990000035
The same is 1, and the other cases are 0, and the function is a binary function;
s6, histogram H of gray gradientxy、HuvNormalization:
Figure BDA0003356997990000036
Figure BDA0003356997990000037
where S is the size of the image, Hxy(m, n) is a gradient in gradation value G (x, y) in the 0 ° and 90 ° directions at the same time as m
Figure BDA0003356997990000038
Frequency of occurrence of time, Huv(m, n) is a gradient in which the gradation value G (x, y) is m while the gradient is 45 ° or 135 °
Figure BDA0003356997990000039
The frequency of the occurrence of the time;
and S7, carrying out equalization processing on the normalized gray gradient histogram:
Figure BDA00033569979900000310
Figure BDA00033569979900000311
wherein, Pxy(m, n) and Puv(m, n) are respectively a gray gradient histogram Hxy、HuvNormalized function of (1), G1Is an enhanced image obtained by histogram equalization processing containing gray scale information and gradient information of 0 degree and 90 degrees, G2The image is an enhanced image obtained after histogram equalization processing according to the information containing gray level and gradient information of 45 degrees and 135 degrees;
s8, contrast enhanced image G1、G2And Gaver：
λ(x,y)＝G1(x,y)-G2(x,y)
λ1(x,y)＝G1(x,y)-Gaver(x,y)
λ2(x,y)＝G2(x,y)-Gaver(x,y)
Wherein λ (x, y), λ1(x,y)、λ2(x, y) each represents G1And G2、G1And Gaver、G2And GaverThe data difference of (a);
s9, calculating lambda (x, y) and lambda1(x,y)、λ2Coefficient of variation of (x, y):
Figure BDA0003356997990000041
Figure BDA0003356997990000042
Figure BDA0003356997990000043
wherein mu (x, y), mu1(x,y)、μ2(x, y) represents λ (x, y), λ1(x,y)、λ2(x, y) mean, σ (x, y), σ in the 8 neighborhood1(x,y)、σ2(x,y) denotes λ (x, y), λ1(x,y)、λ2(x, y) standard deviation within 8 neighborhoods;
s10, labeling two groups of enhanced images G according to the coefficient of variation c.v (x, y)1And G2Pixel position where data difference is large:
Figure BDA0003356997990000044
wherein, when c.v (x, y) is less than or equal to 15 percent, G1And G2The data are close and have little change;
s11, coefficient of variation c.v1(x,y)、c.v2(x, y), labeling two sets of enhanced images G1And G2Relative average gray image GaverPixel position with maximum data difference:
Figure BDA0003356997990000045
when Z (x, y) is 1, the gradient difference of the pixel point (x, y) in the directions of 0 ° and 90 ° is greater than the gradient difference in the directions of 45 ° and 135 °, and vice versa;
s12, obtaining the final enhanced image:
Figure BDA0003356997990000051
and judging the variation trend of the gradient of each pixel point in different directions to obtain the finally enhanced image.
Compared with the prior art, the invention has the following advantages:
on the basis of enhancing the global contrast of the remote sensing image, the invention combines the gray level and the gradient information in four directions of 0 degree, 90 degrees, 45 degrees and 135 degrees to ensure that the local details are not lost, so that the local details of the remote sensing image are rich and the enhancement effect is obvious. Meanwhile, parameters related in the implementation process of the method are calculated according to the characteristics of the image, the parameters do not need to be set manually, and the whole image reconstruction process can be completed in a self-adaptive mode.
Drawings
FIG. 1 is a flow chart of a method for enhancing a self-adaptive gray scale gradient histogram equalization remote sensing image according to the present invention;
FIG. 2 is a grayscale image of an original remote sensing image;
FIG. 3 is a histogram of gray scale gradients in the 0 and 90 directions;
FIG. 4 is a histogram of gray scale gradients in the 45 and 135 directions;
fig. 5 is an enhanced remote sensing image.
Detailed Description
Referring to fig. 1 to 5, a preferred embodiment of the present invention is specifically described.
As shown in fig. 1, the present invention provides a method for enhancing a self-adaptive gray-scale gradient histogram equalization remote sensing image, comprising:
step S1, converting the input remote sensing image into a gray image G, as shown in fig. 2;
step S2, calculating average gray image G in 8-neighborhood rangeaverAs shown in the following formula:
Figure BDA0003356997990000061
where i ═ 1,0,1 and j ═ 1,0,1 denote 8 pixels in the neighborhood of the selected pixel (x, y), and G represents the number of pixels in the neighborhood of the selected pixel (x, y)aver(x, y) represents the average gray value of the pixel point (x, y) in the range of 8 neighborhoods;
step S3, calculating the gradients of the pixel points G (x, y) in the directions of 0 degree and 90 degrees
Figure BDA0003356997990000062
Gradients in the 45 ° and 135 ° directions
Figure BDA0003356997990000063
Figure BDA0003356997990000064
Figure BDA0003356997990000065
Wherein G isx(x, y) represents a gradient value of the pixel point (x, y) in the 0 DEG direction, Gy(x, y) represents the gradient value of the pixel point (x, y) in the direction of 90 DEG, Gu(x, y) represents the gradient value of the pixel point (x, y) in the 45 DEG direction, Gv(x, y) represents a gradient value of the pixel point (x, y) in the 135 ° direction;
step S4, according to the gray scale of the gray image G and the gray gradient in the 0 degree and 90 degree directions
Figure BDA0003356997990000066
Establishing a histogram HxyAs shown in fig. 3:
Figure BDA0003356997990000067
Figure BDA0003356997990000068
wherein, the gray scale number of the gray image G is L, phi (m, n) is a binary function, when the gray scale values G (x, y) are the same and the gray scale gradient is the same
Figure BDA0003356997990000069
When the same phi (m, n) is 1, the other phi (m, n) is 0;
according to the gray scale of the gray image G and the gray gradient in the 45 DEG and 135 DEG directions
Figure BDA00033569979900000610
Establishing a histogram HuvAs shown in fig. 4:
Figure BDA00033569979900000611
Figure BDA0003356997990000071
wherein, the gray scale number of the gray image G is L, phi (m, n) is a binary function, when the gray scale values G (x, y) are the same and the gray scale gradient is the same
Figure BDA0003356997990000072
When the same phi (m, n) is 1, the other phi (m, n) is 0;
step S5, histogram of gradation gradients Hxy、HuvNormalized as shown in the following formula:
Figure BDA0003356997990000073
Figure BDA0003356997990000074
where S is the size of the image, Hxy(m, n) is a gradient in gradation value G (x, y) in the 0 ° and 90 ° directions at the same time as m
Figure BDA0003356997990000075
Frequency of occurrence of time, Huv(m, n) is a gradient in which the gradation value G (x, y) is m while the gradient is 45 ° or 135 °
Figure BDA0003356997990000076
The frequency of the occurrence of the time;
step S6, performing equalization processing on the normalized grayscale gradient histogram:
Figure BDA0003356997990000077
Figure BDA0003356997990000078
wherein, Pxy(m, n) and Puv(m, n) are respectively a gray gradient histogram Hxy、HuvNormalized function of (1), G1Is an enhanced image obtained by histogram equalization processing containing gray scale information and gradient information of 0 degree and 90 degrees, G2The image is an enhanced image obtained after histogram equalization processing according to the information containing gray level and gradient information of 45 degrees and 135 degrees;
step S7, contrast enhanced image G1、G2And Gaver：
λ(x,y)＝G1(x,y)-G2(x,y)
λ1(x,y)＝G1(x,y)-Gaver(x,y)
λ2(x,y)＝G2(x,y)-Gaver(x,y)
Wherein λ (x, y), λ1(x,y)、λ2(x, y) each represents G1And G2、G1And Gaver、G2And GaverThe data difference of (a);
step S8, calculating lambda (x, y), lambda1(x,y)、λ2Coefficient of variation of (x, y):
Figure BDA0003356997990000081
Figure BDA0003356997990000082
Figure BDA0003356997990000083
wherein mu (x, y), mu1(x,y)、μ2(x, y) represents λ (x, y), λ1(x,y)、λ2(x, y) mean, σ (x, y), σ in the 8 neighborhood1(x,y)、σ2(x, y) represents λ (x, y), λ1(x,y)、λ2(x, y) standard deviation within 8 neighborhoods;
in step S9, according to the coefficient of variation c.v (x, y), the pixel positions of the two groups of enhanced images G1 and G2 are marked with large difference:
Figure BDA0003356997990000084
wherein when c.v (x, y) is less than or equal to 15%, the data of G1 is close to that of G2, and the change is not large;
step S10, according to the coefficient of variation c.v1(x,y)、c.v2(x, y) labeling two sets of enhanced images G1 and G2Relative average gray image GaverPixel position with maximum data difference:
Figure BDA0003356997990000085
when Z (x, y) is 1, the gradient difference of the pixel point (x, y) in the directions of 0 ° and 90 ° is greater than the gradient difference in the directions of 45 ° and 135 °, and vice versa;
step S11, obtaining the final enhanced image, as shown in fig. 5:
Figure BDA0003356997990000086
and judging the variation trend of the gradient of each pixel point in different directions to obtain the finally enhanced image.
In summary, aiming at the characteristics of low contrast and unclear detail texture of the remote sensing image, on the basis of improving the contrast of the whole remote sensing image, the gray level and gradient information in four directions of 0 degree, 90 degrees, 45 degrees and 135 degrees are combined to construct a gray gradient histogram, and the image enhancement is completed by utilizing a histogram equalization method; and further judging the direction with larger detail change by comparing the average gray level image, the 0-degree and 90-degree gray level gradient histogram enhanced image and the 45-degree and 135-degree gray level gradient histogram enhanced image to obtain a final enhanced image. The final enhanced image simultaneously retains gradient information in four directions of 0 degrees, 90 degrees, 45 degrees and 135 degrees, and avoids over-enhancement and under-enhancement of information in a certain direction.
While the present invention has been described in detail with reference to the preferred embodiments, it should be understood that the above description should not be taken as limiting the invention. Various modifications and alterations to this invention will become apparent to those skilled in the art upon reading the foregoing description. Accordingly, the scope of the invention should be determined from the following claims.

Claims (5)

1. A self-adaptive gray gradient histogram equalization remote sensing image enhancement method is characterized by comprising the following steps:
step S1, converting the input remote sensing image into a gray image G;
step S2, calculating average gray image G in 8-neighborhood rangeaver；
Step S3, calculating gradient values of the gray image G in the directions of 0 degree, 90 degrees, 45 degrees and 135 degrees, and obtaining a gray gradient combined histogram H according to the gray level and the gradient valuesxy、Huv；
Step S4, establishing a gray mapping relation, and obtaining an enhanced image G through histogram equalization processing1、G2；
Step S5, calculating an enhanced image G1、G2And average gray image GaverThe final enhanced image G is obtained according to the variation difference of the pixel point gradients。
2. The adaptive gray-scale gradient histogram equalization remote sensing image enhancement method as claimed in claim 1, wherein said step S2 of calculating an average gray-scale image in the 8-neighborhood range further comprises:
Figure FDA0003356997980000011
wherein G isaver(x, y) represents the average gray value of the pixel point (x, y) in the range of 8 neighborhoods.
3. The adaptive gray-scale gradient histogram equalization remote sensing image enhancement method as claimed in claim 1, wherein gradient values of the image in the directions of 0 °, 90 ° and 45 ° and 135 ° are calculated in step S3, and a gray-scale gradient joint histogram H is obtained according to the gray-scale level and the gradient valuesxy、HuvFurther comprising:
step S3.1, calculating gradients of pixel points G (x, y) in 0-degree and 90-degree directions
Figure FDA0003356997980000012
Gradients in the 45 ° and 135 ° directions
Figure FDA0003356997980000013
Figure FDA0003356997980000014
Figure FDA0003356997980000015
Wherein G isx(x, y) represents a gradient value of the pixel point (x, y) in the 0 DEG direction, Gy(x, y) represents the gradient value of the pixel point (x, y) in the direction of 90 DEG, Gu(x, y) represents the gradient value of the pixel point (x, y) in the 45 DEG direction, Gv(x, y) represents a gradient value of the pixel point (x, y) in the 135 ° direction;
step S3.2, according to the gray scale of the gray image G and the gray gradient in the 0 degree and 90 degree directions
Figure FDA0003356997980000021
Establishing a histogram Hxy：
Figure FDA0003356997980000022
Figure FDA0003356997980000023
Wherein, the gray scale number of the gray image G is L, phi (m, n) is equal when the gray scale value G (x, y) is the same and the gray gradient is
Figure FDA0003356997980000024
The same is 1, and the other cases are 0, and the function is a binary function;
step S3.3, based on the gray scale of the gray image G and the gray gradients in the 45 DEG and 135 DEG directions
Figure FDA0003356997980000025
Establishing a histogram Huv：
Figure FDA0003356997980000026
Figure FDA0003356997980000027
Wherein, the gray scale number of the gray image G is L, phi (m, n) is equal when the gray scale value G (x, y) is the same and the gray gradient is
Figure FDA0003356997980000028
The same is 1, and the other case is 0, which is a binary function.
4. The adaptive gray-scale gradient histogram equalization remote sensing image enhancement method as claimed in claim 1, wherein said step S4 is implemented by establishing gray-scale mapping relationship, and reconstructing the inputted original image through histogram equalization processingRemote sensing image, obtaining enhanced image G1、G2Further comprising:
step S4.1, histogram of gradation gradient Hxy、HuvNormalization:
Figure FDA0003356997980000029
Figure FDA00033569979800000210
where S is the size of the image, Hxy(m, n) is a gradient in gradation value G (x, y) in the 0 ° and 90 ° directions at the same time as m
Figure FDA0003356997980000031
Frequency of occurrence of time, Huv(m, n) is a gradient in which the gradation value G (x, y) is m while the gradient is 45 ° or 135 °
Figure FDA0003356997980000032
The frequency of the occurrence of the time;
step S4.2, carrying out equalization treatment on the normalized gray gradient histogram:
Figure FDA0003356997980000033
Figure FDA0003356997980000034
wherein, Pxy(m, n) and Puv(m, n) are respectively a gray gradient histogram Hxy、HuvNormalized function of (1), G1Is an enhanced image obtained by histogram equalization processing containing gray scale information and gradient information of 0 degree and 90 degrees, G2Is based on a linear image containing gray scale information and gradient information of 45 DEG and 135 DEGAnd (4) obtaining an enhanced image after the square equalization processing.
5. The adaptive gray-scale gradient histogram equalization remote sensing image enhancement method as claimed in claim 1, wherein said step S5 of calculating the enhanced image G1、G2And average gray image GaverObtaining a final enhanced image G according to the variation trend of the pixel point gradientsFurther comprising:
step S5.1, contrast enhanced image G1、G2And Gaver：
λ(x,y)＝G1(x,y)-G2(x,y)
λ1(x,y)＝G1(x,y)-Gaver(x,y)
λ2(x,y)＝G2(x,y)-Gaver(x,y)
Wherein λ (x, y), λ1(x,y)、λ2(x, y) each represents G1And G2、G1And Gaver、G2And GaverThe data difference of (a);
step S5.2, calculating lambda (x, y), lambda1(x,y)、λ2Coefficient of variation of (x, y):
Figure FDA0003356997980000035
Figure FDA0003356997980000036
Figure FDA0003356997980000041
wherein mu (x, y), mu1(x,y)、μ2(x, y) represents λ (x, y), λ1(x,y)、λ2(x, y) mean, σ (x, y), σ in the 8 neighborhood1(x,y)、σ2(x, y) represents λ (x, y), λ1(x,y)、λ2(x, y) standard deviation within 8 neighborhoods;
step S5.3, marking two groups of enhanced images G according to the variation coefficients c.v (x, y)1And G2Pixel position where data difference is large:
Figure FDA0003356997980000042
wherein, when c.v (x, y) is less than or equal to 15 percent, G1And G2The data are close and have little change;
step S5.4, according to the variation coefficient c.v1(x,y)、c.v2(x, y), labeling two sets of enhanced images G1And G2Relative average gray image GaverPixel position with maximum data difference:
Figure FDA0003356997980000043
when Z (x, y) is 1, the gradient difference of the pixel point (x, y) in the directions of 0 ° and 90 ° is greater than the gradient difference in the directions of 45 ° and 135 °, and vice versa;
and step S5.5, obtaining a final enhanced image:
Figure FDA0003356997980000044
and judging the variation trend of the gradient of each pixel point in different directions to obtain the finally enhanced image.
CN202111355703.2A 2021-11-16 2021-11-16 Self-adaptive gray gradient histogram equalization remote sensing image enhancement method Pending CN114049283A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111355703.2A CN114049283A (en) 2021-11-16 2021-11-16 Self-adaptive gray gradient histogram equalization remote sensing image enhancement method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111355703.2A CN114049283A (en) 2021-11-16 2021-11-16 Self-adaptive gray gradient histogram equalization remote sensing image enhancement method

Publications (1)

Publication Number Publication Date
CN114049283A true CN114049283A (en) 2022-02-15

Family

ID=80209371

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111355703.2A Pending CN114049283A (en) 2021-11-16 2021-11-16 Self-adaptive gray gradient histogram equalization remote sensing image enhancement method

Country Status (1)

Country Link
CN (1) CN114049283A (en)

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114648530A (en) * 2022-05-20 2022-06-21 潍坊医学院 CT image processing method
CN115035114A (en) * 2022-08-11 2022-09-09 高密德隆汽车配件制造有限公司 Method for monitoring state of hay grinder based on image processing
CN115100304A (en) * 2022-04-24 2022-09-23 南通海隆磁业有限公司 Nuclear magnetic resonance image enhancement method based on image processing
CN115345802A (en) * 2022-10-18 2022-11-15 苏州迈创信息技术有限公司 Remote monitoring method for operation state of electromechanical equipment
CN115512231A (en) * 2022-11-15 2022-12-23 山东省国土空间数据和遥感技术研究院(山东省海域动态监视监测中心) Remote sensing interpretation method suitable for homeland space ecological restoration
CN115546203A (en) * 2022-11-23 2022-12-30 常熟理工学院 Production monitoring and analyzing method based on image data algorithm
CN115797798A (en) * 2023-02-10 2023-03-14 山东省地质矿产勘查开发局八〇一水文地质工程地质大队(山东省地矿工程勘察院) Ecological restoration effect evaluation method based on abandoned mine remote sensing image
CN115830459A (en) * 2023-02-14 2023-03-21 山东省国土空间生态修复中心(山东省地质灾害防治技术指导中心、山东省土地储备中心) Method for detecting damage degree of mountain forest and grass life community based on neural network
CN116012273A (en) * 2023-03-28 2023-04-25 国科天成科技股份有限公司 Image enhancement method and device based on local gray scale fluctuation rate
CN116342588B (en) * 2023-05-22 2023-08-11 徕兄健康科技(威海)有限责任公司 Cerebrovascular image enhancement method
CN117036204A (en) * 2023-10-09 2023-11-10 东莞市华复实业有限公司 Image quality enhancement method for visual interphone
CN117558068A (en) * 2024-01-11 2024-02-13 深圳市阿龙电子有限公司 Intelligent device gesture recognition method based on multi-source data fusion
CN117764893A (en) * 2024-01-08 2024-03-26 惠州市惠阳区兆顺益五金加工有限公司 Numerical control machine tool wear identification method and system
CN117952841A (en) * 2024-03-26 2024-04-30 山东省地质测绘院 Remote sensing image self-adaptive enhancement method based on artificial intelligence

Cited By (25)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115100304A (en) * 2022-04-24 2022-09-23 南通海隆磁业有限公司 Nuclear magnetic resonance image enhancement method based on image processing
CN115100304B (en) * 2022-04-24 2024-04-19 江苏中勤通信科技有限公司 Nuclear magnetic resonance image enhancement method based on image processing
CN114648530B (en) * 2022-05-20 2022-08-16 潍坊医学院 CT image processing method
CN114648530A (en) * 2022-05-20 2022-06-21 潍坊医学院 CT image processing method
CN115035114A (en) * 2022-08-11 2022-09-09 高密德隆汽车配件制造有限公司 Method for monitoring state of hay grinder based on image processing
CN115345802B (en) * 2022-10-18 2023-03-24 苏州迈创信息技术有限公司 Remote monitoring method for operation state of electromechanical equipment
CN115345802A (en) * 2022-10-18 2022-11-15 苏州迈创信息技术有限公司 Remote monitoring method for operation state of electromechanical equipment
CN115512231A (en) * 2022-11-15 2022-12-23 山东省国土空间数据和遥感技术研究院(山东省海域动态监视监测中心) Remote sensing interpretation method suitable for homeland space ecological restoration
CN115512231B (en) * 2022-11-15 2023-02-28 山东省国土空间数据和遥感技术研究院(山东省海域动态监视监测中心) Remote sensing interpretation method suitable for homeland space ecological restoration
CN115546203A (en) * 2022-11-23 2022-12-30 常熟理工学院 Production monitoring and analyzing method based on image data algorithm
CN115546203B (en) * 2022-11-23 2023-03-10 常熟理工学院 Production monitoring and analyzing method based on image data algorithm
CN115797798A (en) * 2023-02-10 2023-03-14 山东省地质矿产勘查开发局八〇一水文地质工程地质大队(山东省地矿工程勘察院) Ecological restoration effect evaluation method based on abandoned mine remote sensing image
CN115830459A (en) * 2023-02-14 2023-03-21 山东省国土空间生态修复中心(山东省地质灾害防治技术指导中心、山东省土地储备中心) Method for detecting damage degree of mountain forest and grass life community based on neural network
CN115830459B (en) * 2023-02-14 2023-05-12 山东省国土空间生态修复中心(山东省地质灾害防治技术指导中心、山东省土地储备中心) Mountain forest grass life community damage degree detection method based on neural network
CN116012273A (en) * 2023-03-28 2023-04-25 国科天成科技股份有限公司 Image enhancement method and device based on local gray scale fluctuation rate
CN116342588B (en) * 2023-05-22 2023-08-11 徕兄健康科技(威海)有限责任公司 Cerebrovascular image enhancement method
CN117036204A (en) * 2023-10-09 2023-11-10 东莞市华复实业有限公司 Image quality enhancement method for visual interphone
CN117036204B (en) * 2023-10-09 2024-02-02 东莞市华复实业有限公司 Image quality enhancement method for visual interphone
CN117764893A (en) * 2024-01-08 2024-03-26 惠州市惠阳区兆顺益五金加工有限公司 Numerical control machine tool wear identification method and system
CN117764893B (en) * 2024-01-08 2024-07-02 惠州市惠阳区兆顺益五金加工有限公司 Numerical control machine tool wear identification method and system
CN117764893B8 (en) * 2024-01-08 2024-07-19 广东上善精机有限公司 Numerical control machine tool wear identification method and system
CN117558068A (en) * 2024-01-11 2024-02-13 深圳市阿龙电子有限公司 Intelligent device gesture recognition method based on multi-source data fusion
CN117558068B (en) * 2024-01-11 2024-03-19 深圳市阿龙电子有限公司 Intelligent device gesture recognition method based on multi-source data fusion
CN117952841A (en) * 2024-03-26 2024-04-30 山东省地质测绘院 Remote sensing image self-adaptive enhancement method based on artificial intelligence
CN117952841B (en) * 2024-03-26 2024-06-04 山东省地质测绘院 Remote sensing image self-adaptive enhancement method based on artificial intelligence

Similar Documents

Publication Publication Date Title
CN114049283A (en) Self-adaptive gray gradient histogram equalization remote sensing image enhancement method
Celik Spatial mutual information and PageRank-based contrast enhancement and quality-aware relative contrast measure
CN105931201B (en) A kind of image subjective vision effect reinforcing method based on wavelet transformation
US10198801B2 (en) Image enhancement using self-examples and external examples
CN102982513B (en) A kind of adapting to image defogging method capable based on texture
CN102298774B (en) Non-local mean denoising method based on joint similarity
CN107833189A (en) The Underwater Target Detection image enchancing method of the limited self-adapting histogram equilibrium of contrast
CN109146780A (en) A kind of quality of image optimization method, computer installation and readable storage medium storing program for executing
CN116645569A (en) Infrared image colorization method and system based on generation countermeasure network
CN116012273B (en) Image enhancement method and device based on local gray scale fluctuation rate
CN113222875A (en) Image harmonious synthesis method based on color constancy
CN118134819B (en) Intra-domain-inter-domain self-adaptive underwater image enhancement method and system
CN115809966A (en) Low-illumination image enhancement method and system
CN117252773A (en) Image enhancement method and system based on self-adaptive color correction and guided filtering
Liang et al. Underwater image quality improvement via color, detail, and contrast restoration
Luo et al. Under-display camera image enhancement via cascaded curve estimation
CN111369435B (en) Color image depth up-sampling method and system based on self-adaptive stable model
Hassan et al. A hue preserving uniform illumination image enhancement via triangle similarity criterion in HSI color space
CN116452431A (en) Weak light image enhancement method based on multi-branch progressive depth network
CN114359083B (en) High-dynamic thermal infrared image self-adaptive preprocessing method for interference environment
CN107680068A (en) A kind of digital image enhancement method for considering image naturalness
CN115456912A (en) Tone mapping method based on multi-scale WLS filtering fusion
CN114331925A (en) Multi-scale relative gradient histogram equalization method and device
Subramani et al. Pixel intensity optimization and detail-preserving contextual contrast enhancement for underwater images
CN108038828B (en) Image denoising method based on self-adaptive weighted total variation

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