CN115512231B - Remote sensing interpretation method suitable for homeland space ecological restoration - Google Patents
Remote sensing interpretation method suitable for homeland space ecological restoration Download PDFInfo
- Publication number
- CN115512231B CN115512231B CN202211420132.0A CN202211420132A CN115512231B CN 115512231 B CN115512231 B CN 115512231B CN 202211420132 A CN202211420132 A CN 202211420132A CN 115512231 B CN115512231 B CN 115512231B
- Authority
- CN
- China
- Prior art keywords
- gray level
- gray
- interval
- pixel point
- remote sensing
- 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 20
- 230000000694 effects Effects 0.000 claims abstract description 59
- 241001270131 Agaricus moelleri Species 0.000 claims description 4
- 230000002708 enhancing effect Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 abstract description 7
- 230000008859 change Effects 0.000 description 4
- 239000003595 mist Substances 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 239000002689 soil Substances 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/36—Applying a local operator, i.e. means to operate on image points situated in the vicinity of a given point; Non-linear local filtering operations, e.g. median filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Nonlinear Science (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to a remote sensing interpretation method suitable for ecological restoration of a homeland space, which comprises the following steps: acquiring a gray scale interval; obtaining the contrast ratio of the pixel point corresponding to each gray level to the pixel point in the 8 neighborhoods of the pixel point according to the number of the pixel points corresponding to each gray level and the gray value of each pixel point in the 8 neighborhoods of the pixel point corresponding to each gray level; obtaining contrast in a gray scale interval; obtaining an expected enhancement effect of the gray level in the gray level interval; obtaining an optimal division mode according to the expected enhancement effect of the gray level in each divided gray level interval, carrying out histogram equalization on the gray level histogram of the remote sensing image of the ecological restoration area according to the optimal division mode to obtain an optimal enhancement image, and judging the ecological restoration effect of the homeland space according to the optimal enhancement image. The invention improves the efficiency and the capability of natural resource supervision.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a remote sensing interpretation method suitable for ecological restoration of a homeland space.
Background
The existing remote measuring instrument on an artificial earth satellite is used for monitoring the earth surface by induction remote measurement and resource management, so that the monitoring and management of the ecological restoration of the homeland space are realized. However, due to the influence of the atmosphere and cloud and mist, the remote sensing image has the problems of low contrast, poor visual effect and the like, and the efficiency and the capability of natural resource supervision can be directly influenced; therefore, contrast enhancement processing needs to be performed on the acquired remote sensing image, and the gray levels with a small number of pixel points in the remote sensing image can be merged when the image enhancement processing is performed by the traditional histogram equalization algorithm, so that the contrast of the remote sensing image is improved, and meanwhile, the number of the gray levels of the remote sensing image is greatly reduced, so that the entropy of the remote sensing image information is reduced, local details are lost, and the efficiency and the capability of natural resource supervision are influenced.
Disclosure of Invention
The invention provides a remote sensing interpretation method suitable for ecological restoration of a homeland space, which aims to solve the problem that local details of a remote sensing image are lost due to existing histogram equalization.
The remote sensing interpretation method suitable for the ecological restoration of the homeland space adopts the following technical scheme:
acquiring a gray level image and a gray level histogram of a remote sensing image of an ecological restoration area, and dividing the gray level histogram for multiple times according to the number of wave crests of the gray level histogram to obtain multiple gray level intervals after each division;
acquiring the number of pixel points corresponding to each gray level, acquiring the gray value of each pixel point in 8 neighborhoods of the pixel points corresponding to each gray level, and acquiring the contrast ratio of the pixel point corresponding to each gray level to the pixel point in 8 neighborhoods of the pixel points according to the number of the pixel points corresponding to each gray level and the gray value of each pixel point in 8 neighborhoods of the pixel points corresponding to each gray level;
obtaining the contrast ratio in each gray scale interval according to all gray scales in each gray scale interval and the contrast ratio between the pixel point corresponding to each gray scale in the corresponding gray scale interval and the pixel point in the neighborhood of the pixel point 8;
obtaining an expected enhancement effect of the gray level in each gray level interval according to the contrast in each gray level interval, the number of pixel points corresponding to each gray level in each gray level interval and the number of gray levels in each gray level interval;
obtaining an optimal division mode according to the expected enhancement effect of the gray level in each divided gray level interval, dividing the gray level histogram of the remote sensing image of the ecological restoration area according to the optimal division mode to obtain a plurality of target gray level intervals, enhancing each target gray level interval by utilizing histogram equalization to obtain an optimal enhancement image, and judging the ecological restoration effect of the homeland space according to the optimal enhancement image.
Further, the multiple gray scale intervals after each division are determined as follows:
obtaining the ratio of the numerator and the denominator by taking 255 as the numerator and the number of wave crests of the gray level histogram as the denominator;
multiplying the ratio of the numerator and the denominator by the dividing times to obtain the interval length of the division, dividing the gray level histogram according to the interval length of the division to obtain a plurality of divided gray level intervals, wherein the dividing times of the gray level histogram are
，
The number of peak points in the gray level histogram is represented, and the number of gray level intervals obtained by each division is different.
Further, a specific expression of the contrast between the pixel point corresponding to each gray level and the pixel point in the 8 neighborhoods of the pixel point is as follows:
in the formula:
representing grey levels
The contrast of the corresponding pixel point to the pixel points in the neighborhood of this pixel point 8,
represents the g-th gray level of
The gray value of the pixel point of (a),
represents the g-th gray level of
The gray value of the h neighborhood pixel point in 8 neighborhoods of the pixel point,
represents the g-th gray level of
The number of the pixel points of (a),
representing 8 neighborhoods, g representing gray levels of
The g-th pixel point.
Further, the contrast in the gray scale interval is determined as follows:
accumulating the contrast between the pixel point corresponding to each gray level in each gray level interval and the pixel point in the neighborhood of the pixel point 8, calculating the average value, and taking the average value as a first average value;
acquiring a difference value of adjacent gray levels in each gray level interval, accumulating all the difference values obtained in each gray level interval, calculating an average value, and taking the average value as a second average value;
and subtracting the second average value from the first average value in each gray scale interval to obtain the contrast in the gray scale interval.
Further, the expected enhancement effect of the gray levels in the gray scale interval is determined as follows:
acquiring the variance of the number of pixel points corresponding to each gray level in a gray level interval;
acquiring the quantity difference of the quantity of pixel points corresponding to the adjacent gray levels in the gray level interval, accumulating all the quantity differences obtained in the gray level interval to obtain an accumulated sum, calculating an average value, and taking the average value as a third average value;
and taking the contrast in the gray scale interval as a numerator, and taking the product of the third mean value in the gray scale interval and the variance of the number of the pixels corresponding to each gray scale as a denominator to obtain the expected enhancement effect of the gray scale in the gray scale interval.
Further, an average value of expected enhancement effects of the gray levels in all the divided gray level intervals is obtained, and the division mode corresponding to the maximum average value is used as the optimal division mode.
Further, judging the ecological restoration effect of the homeland space according to the optimal enhanced image further comprises:
acquiring remote sensing images of the same ecological restoration area acquired at the same period year by year;
acquiring an optimal enhanced image of the remote sensing image of the same ecological restoration area acquired at the same period year by using the remote sensing image of the same ecological restoration area acquired at the same period year by year;
and obtaining the ecological restoration effect of the homeland space according to the number of pixel points in the forest region in the optimal enhanced image of the remote sensing image of the same ecological restoration region in the same period year by year.
The invention has the beneficial effects that: according to the method, the initial length of the gray level interval of the gray level histogram is obtained according to the number of peak points of the gray level histogram of the remote sensing image, the divided gray level interval range is too small, the merging and widening effect of the gray level is poor, and the contrast enhancement effect of the remote sensing image is insufficient, so that on the basis of the primary division by using the peak points, the highest peak points in the primary interval are counted, the interval is divided again according to the adjacent highest peak points, the division is performed to avoid the problem that the divided gray level interval range is too small to a certain extent, however, in order to enable the final enhancement effect of the remote sensing image to be optimal, the overall expected enhancement effect of the gray level interval after each division is calculated, the step realizes the self-adaption of the division of the gray level interval, ensures that the final equalized effect of each remote sensing image is optimal, the optimal interval self-adaption division is performed on the gray level histogram of the gray level image, and then the equalization enhancement is performed on each interval, the number of the gray level interval is reduced during the equalization, the ecological detail part of the image is protected, the ecological detail enhancement effect of the remote sensing image is ensured, and the final repair effect of the remote sensing image is more accurate according to the remote sensing image is judged;
meanwhile, due to the fact that the optimal image is obtained, when the restoration effect of the soil space ecology is judged according to the optimal image, the judgment efficiency can be improved, and finally the efficiency and the capability of natural resource supervision are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flowchart of an embodiment of the remote sensing interpretation method applicable to the ecological restoration of the homeland space.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the remote sensing interpretation method applicable to the ecological restoration of the homeland space, as shown in figure 1, comprises the following steps:
s1, obtaining a gray level image and a gray level histogram of a remote sensing image of an ecological restoration area, and dividing the gray level histogram for multiple times according to the number of wave crests of the gray level histogram to obtain multiple gray level intervals after each division.
Because the remote sensing image has the problems of low contrast and poor visual effect, image enhancement processing is required, and the enhancement of the remote sensing image is realized by improving the histogram equalization algorithm.
The method comprises the following specific steps of obtaining a gray level image and a gray level histogram of a remote sensing image of an ecological restoration area: firstly, collecting remote sensing images of the same ecological restoration area in the same period every year, then carrying out graying processing on the collected remote sensing images, then carrying out denoising processing by using self-adaptive median filtering, and then counting a gray level histogram of the remote sensing images to obtain the gray level image and the gray level histogram of the remote sensing images of the ecological restoration area. It should be noted that all the grayscale images and grayscale histograms appearing hereinafter refer to the grayscale images and grayscale histograms of the same year in the same ecological restoration area after the remote sensing image is denoised.
The basic principle of histogram equalization is to widen the gray levels with a large number of pixel points in the gray image and merge the gray levels with a small number of pixel points, so that the image contrast is increased and the image enhancement is achieved.
Firstly, curve fitting is carried out on a gray level histogram, because the environment in a remote sensing image is complex and changeable, a curve fitted by the gray level histogram has a plurality of wave peaks, the abscissa value of each wave peak point is counted, the abscissa value is the gray level of the image, and a gray level set is obtained
Where n represents the number of peak points in the gray-scale histogram.
Because the gray levels in each single local peak in the gray histogram before histogram equalization are adjacent and the number of pixels corresponding to each gray level is relatively similar, the number of the reduced gray levels after the histogram equalization can be effectively reduced by taking the single local peak in the gray histogram as an interval and dividing the gray histogram, but if the range of the gray interval is too small, the merging and widening effect of the gray levels is poor, and the contrast enhancement effect of the image is insufficient, the gray level range between the divided areas is gradually increased from small to large on the basis of the single local peak, various gray histogram gray level interval division modes are obtained, and the gray level interval division method with the optimal histogram equalization enhancement effect is selected.
The specific steps for obtaining the plurality of gray scale intervals after each division are as follows: obtaining the ratio of a numerator and a denominator by taking 255 as a numerator and taking the number of wave crests of the gray level histogram as a denominator; obtaining the interval length of the division according to the multiplication of the ratio of the numerator and the denominator and the division times, and obtaining a plurality of divided gray level intervals by dividing the gray level histogram according to the interval length of the division times, wherein the division times of the gray level histogram are
The number of the gray level intervals obtained by dividing every time is different, and the specific expression of the interval length is as follows:
in the formula:
represents a section length of each gray scale section after the m-th division,
is shown as
The way of sub-division is adopted,
n represents the number of peak points in the gray histogram,
indicating rounding down and 255 indicating the maximum distribution range of the remote sensing image gray levels.
Wherein when
Then, the gray level representing the gray histogram is equally divided into two sections, and the number of divided gray sections is minimized, so that the maximum value of m is
(ii) a Taking m =1 as an example, the section length of the gradation section of the gradation histogram at this time
Then the preliminary interval of gray levels in the gray histogram at this time is divided into 0,
],[
],…,[(n-1)
]sequentially counting the gray levels corresponding to the peak points in each gray interval from left to right, if no peak point exists in the gray interval, not counting, and if a plurality of peak points exist in the gray interval, taking the gray level corresponding to the peak point with the largest vertical coordinate, namely the largest pixel number, to obtain the peak point set when m =1
In which
Indicating the number of peak points selected.
Thus, when m =1 is obtained, the gray scale interval in the gray scale histogram is divided into [0,
],[
],…,[
]wherein
Represents the selected second
Peak point and
the mean value of the sum of the gray levels corresponding to the peak points represents the trough position between the two peak points, so that each gray level interval of the divided gray level histogram contains each local peak point, and the number of the pixel points corresponding to the gray level in each gray level interval is similar.
In the same way, accomplish
And (4) dividing the gray level interval of the gray level histogram.
To this end, finish
Obtaining the division of the gray interval of the secondary gray histogram
And a gray scale interval division mode is adopted.
S2, acquiring the number of pixel points corresponding to each gray level, acquiring the gray value of each pixel point in 8 neighborhoods of the pixel points corresponding to each gray level, and acquiring the contrast ratio of the pixel point corresponding to each gray level to the pixel point in 8 neighborhoods of the pixel points according to the number of the pixel points corresponding to each gray level and the gray value of each pixel point in 8 neighborhoods of the pixel points corresponding to each gray level.
Given that the remote sensing image of the ecological restoration area is influenced by atmosphere and cloud and mist, and the remote sensing image has the defect of low contrast, after the gray level interval division is carried out on the gray level histogram in the step S1, if the collected remote sensing image is less influenced by atmosphere and cloud and mist and the contrast in the division interval is higher, the number of pixel points corresponding to the gray level in the interval needing to be divided is gradually changed, so that the contrast is improved after the histogram is equalized, meanwhile, the loss of the gray level is reduced, and the image details are protected.
Therefore, it is necessary to calculate the contrast between the pixel points corresponding to each gray level in the gray level histogram of the remote sensing image before enhancement without histogram equalization and the pixel points in the 8 neighborhoods thereof, count the gray level in the gray level histogram and the number of the pixel points corresponding to each gray level, and obtain a gray level set
Set of number of pixels corresponding to gray level
Where t denotes the number of grey levels within the grey image, the grey level
Correspond toThe number of the pixel points is
。
It is known that the larger the difference between different pixels, the more obvious the contrast ratio, so the gray scale is used
For example, the contrast between the pixel point corresponding to the gray scale and the pixel point in the neighborhood of 8 pixels is calculated
Comprises the following steps:
in the formula:
representing grey levels
The contrast of the corresponding pixel point with the pixel points in the neighborhood of this pixel point 8,
represents the g-th gray level of
The gray value of the pixel point of (a),
represents the g-th gray level of
The gray value of the h neighborhood pixel point in 8 neighborhoods of the pixel point,
represents the g-th gray level of
The number of the pixel points of (a),
representing 8 neighborhoods, g representing gray levels of
The g-th pixel point.
Wherein,
represents the g-th gray level of
The larger the mean value is, the larger the difference between the pixel point and the 8-neighborhood pixel point is, the larger the contrast of the pixel point is, so that the formula
Express a gray level of
And the mean value of the gray differences of all the pixel points and 8 neighborhoods thereof, thereby
The larger the size of the hole is,
the greater the contrast between the pixel point corresponding to the gray level and the pixel point in the neighborhood of the pixel point 8.
Similarly, the contrast between the pixel point corresponding to other gray levels in the gray level set and the pixel point in the neighborhood of the pixel point 8 is calculated, the contrast between the pixel point corresponding to each gray level and the pixel point in the neighborhood of the pixel point 8 is obtained, and thus, the contrast between the pixel point corresponding to each gray level and the pixel point in the neighborhood of the pixel point 8 is obtained.
And S3, obtaining the contrast ratio in each gray scale interval according to all gray scales in each gray scale interval and the contrast ratio between the pixel point corresponding to each gray scale in the corresponding gray scale interval and the pixel point in the neighborhood of the pixel point 8.
The specific steps for obtaining the contrast ratio in the gray scale interval are as follows: taking m =1 as an example, accumulating the contrast of each pixel point corresponding to each gray level in each gray level interval after the first division and the contrast of the pixel points in the neighborhood of 8 of the pixel point, and calculating an average value, and taking the average value as a first average value; acquiring a difference value of adjacent gray levels in each gray level interval, accumulating all the difference values obtained in each gray level interval, calculating an average value, and taking the average value as a second average value; subtracting the first average value and the second average value in each gray scale interval to obtain the contrast in the gray scale interval, wherein the specific expression of the contrast in the gray scale interval is as follows:
in the formula:
showing the contrast in any gray scale interval after the first division,
indicating the number of gray levels in the gray scale interval after the first division,
the contrast between the pixel point corresponding to the q-th gray level in the gray scale interval and the pixel point in the neighborhood of the pixel point 8 is represented,
representing the q +1 th gray level in the gray interval,
representing the q-th gray level within the gray scale interval.
Wherein,
represents the difference of adjacent gray levels in the gray scale interval, therefore
Representing the contrast between the gray levels in the divided gray intervals, wherein the greater the contrast value is, the greater the contrast in the gray intervals is;
the contrast between the pixel point corresponding to the q-th gray level in the gray scale interval and the pixel point in the neighborhood of 8 pixels is expressed, so
Expressing the contrast between the pixel points in the divided gray scale interval and the pixel points in the 8 neighborhoods of the pixel points, wherein the larger the contrast value is, the larger the contrast in the gray scale interval is, thereby
The larger the value of (a), the larger the contrast in this interval.
And S4, obtaining an expected enhancement effect of the gray level in each gray level interval according to the contrast in each gray level interval, the number of pixel points corresponding to each gray level in each gray level interval and the number of gray levels in each gray level interval.
The basic principle of histogram equalization is to widen the gray levels with a large number of pixel points in the gray image and merge the gray levels with a small number of pixel points, so that the image contrast is increased and the purpose of image enhancement is achieved. Therefore, the larger the contrast in the selected gray scale interval is, the more the gray scale does not need to be merged in a large quantity, so as to achieve the effect of enhancing the contrast, and therefore when the number of the pixels corresponding to the gray scale changes the smaller the number of the pixels in the gray scale interval is, the fewer the merging conditions of the gray scale with the small number of the pixels in the gray scale interval are, so as to reduce the number of the gray scale with the reduced number after the histogram is equalized, protect the image details, and finally, the better the enhancement effect of the gray scale interval after the histogram equalization is performed is.
Therefore, taking m =1 as an example, according to the contrast in any gray scale interval of the first division and the change of the number of pixels corresponding to the gray scale in the gray scale interval, the expected enhancement effect after histogram equalization enhancement in the gray scale interval is calculated
。
The specific steps for obtaining the expected enhancement effect of the gray level in each gray level interval are as follows: the method comprises the steps of obtaining variance of pixel quantity corresponding to each gray level in a gray level interval, obtaining quantity difference of pixel quantity corresponding to adjacent gray levels in the gray level interval, accumulating all quantity differences obtained in the gray level interval to obtain accumulated sum, solving for average value, taking the average value as a third average value, taking contrast in the gray level interval as numerator, taking the product of the third average value in the gray level interval and the variance of the pixel quantity corresponding to each gray level as denominator to obtain expected enhancement effect of the gray level in the gray level interval, wherein the specific expression of the expected enhancement effect of the gray level in the gray level interval is as follows:
in the formula:
representing the contrast in any one gray scale interval after the first division,
the variance of the number of pixels corresponding to each gray level in the gray level interval is represented,
representing the desired enhancement effect of the grey levels within the grey interval,
indicating a first strokeThe number of gray levels in the divided gray scale interval,
the number of pixels corresponding to the (q + 1) th gray level in the gray scale interval is represented,
and expressing the number of pixel points corresponding to the q-th gray level in the gray scale interval.
Wherein,
expressing the variance of the number of the pixel points corresponding to each gray level in the gray level interval, wherein the variance expresses the uniformity of data, so that the smaller the variance is, the smaller the integral change of the number of the pixel points corresponding to the gray level in the gray level interval is;
representing the number of gray levels in the gray scale interval after the first division,
the difference of the pixel numbers corresponding to two adjacent gray levels in the gray level interval is expressed, so
Expressing the total difference of the number of the pixel points corresponding to the adjacent gray levels in the gray level interval, wherein the smaller the value is, the smaller the change of the number of the pixel points corresponding to the adjacent gray levels in the gray level interval is expressed;
expressing the contrast in the gray scale interval, so that the larger the denominator in the formula, the smaller the numerator, the larger the contrast in the gray scale interval, the smaller the change of the number of the pixels corresponding to the gray scale, and the expected enhancement effect after the gray scale in the gray scale interval is equalized by the histogram
The better.
In the same way, the expected enhancement effect of the gray level in each gray level interval after the histogram in the gray level interval after the first division is equalized is obtained, and a set is obtained
Wherein
When m =1 is represented, the number of peak points selected on the gray level histogram, that is, the number of gray level intervals after the gray level histogram is divided for the first time is represented. In the same way, the expected enhancement effect can be obtained after the gray level in each gray level interval is equalized through the histogram after each division.
And S5, obtaining an optimal division mode according to the expected enhancement effect of the gray level in each divided gray level interval, dividing a gray level histogram of the remote sensing image of the ecological restoration area according to the optimal division mode to obtain a plurality of target gray level intervals, enhancing each target gray level interval by utilizing histogram equalization to obtain an optimal enhancement image, and judging the ecological restoration effect of the homeland space according to the optimal enhancement image.
The specific steps for obtaining the optimal division mode are as follows: taking m =1 as an example, calculating the overall expected enhancement effect of the gray scale interval after the first division, specifically, obtaining the average value of the expected enhancement effects of the gray scales in all the gray scale intervals after the first division, and taking the average value as the overall expected enhancement effect of the gray scale interval after the first division
And in the same way, obtaining the overall expected enhancement effect of the gray level interval after each division, and obtaining an expected enhancement effect set
Taking the maximum value in the set as
At this time, the process of the present invention,
and the corresponding w-th gray level histogram division mode is the optimal division mode, so that the gray level interval division mode of the gray level histogram when m = w in the step S1 is selected, the target gray level intervals after the w-th division are respectively enhanced by using a histogram equalization algorithm to obtain the enhanced target gray level intervals, and the optimal enhanced image is obtained according to the enhanced target gray level intervals.
The concrete steps of judging the ecological restoration effect of the homeland space according to the optimal enhanced image are as follows: obtaining the optimal enhanced image of the remote sensing images of the same ecological restoration area acquired year by year in the same period by utilizing the steps S1-S5; and obtaining the ecological restoration effect of the homeland space according to the number of the pixel points of the forest region in the optimal enhanced image of the remote sensing image of the same ecological restoration region in the same period year by year, wherein when the number of the pixel points of the forest region in the optimal enhanced image of the remote sensing image of the same ecological restoration region in the same period year by year is increased, the ecological restoration effect of the homeland space is good.
The invention has the beneficial effects that: according to the method, the initial length of the gray level interval of the gray level histogram is obtained according to the number of peak points of the gray level histogram of the remote sensing image, the divided gray level interval range is too small, the merging and widening effect of the gray level is poor, and the contrast enhancement effect of the remote sensing image is insufficient, so that on the basis of the primary division by using the peak points, the highest peak points in the primary interval are counted, the interval is divided again according to the adjacent highest peak points, the division is performed to avoid the problem that the divided gray level interval range is too small to a certain extent, however, in order to enable the final enhancement effect of the remote sensing image to be optimal, the overall expected enhancement effect of the gray level interval after each division is calculated, the step realizes the self-adaption of the division of the gray level interval, ensures that the final equalized effect of each remote sensing image is optimal, the optimal interval self-adaption division is performed on the gray level histogram of the gray level image, and then the equalization enhancement is performed on each interval, the number of the gray level interval is reduced during the equalization, the ecological detail part of the image is protected, the ecological detail enhancement effect of the remote sensing image is ensured, and the final repair effect of the remote sensing image is more accurate according to the remote sensing image is judged;
meanwhile, due to the fact that the optimal image is obtained, when the restoration effect of the soil space ecology is judged according to the optimal image, the judgment efficiency can be improved, and finally the efficiency and the capability of natural resource supervision are improved.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (4)
1. The remote sensing interpretation method suitable for homeland space ecological restoration is characterized by comprising the following steps:
acquiring a gray level image and a gray level histogram of a remote sensing image of an ecological restoration area, and dividing the gray level histogram for multiple times according to the number of wave crests of the gray level histogram to obtain multiple gray level intervals after each division;
the method comprises the following specific steps of obtaining a gray level image and a gray level histogram of a remote sensing image of an ecological restoration area: acquiring remote sensing images of the same ecological restoration area at the same period every year;
graying and denoising the remote sensing image to obtain a grayscale image and a grayscale histogram of the remote sensing image;
acquiring the number of pixel points corresponding to each gray level, acquiring the gray value of each pixel point in 8 neighborhoods of the pixel points corresponding to each gray level, and acquiring the contrast ratio of the pixel point corresponding to each gray level and the pixel point in 8 neighborhoods of the pixel points according to the number of the pixel points corresponding to each gray level and the gray value of each pixel point in 8 neighborhoods of the pixel points corresponding to each gray level;
obtaining the contrast ratio in each gray scale interval according to all gray scales in each gray scale interval and the contrast ratio between the pixel point corresponding to each gray scale in the corresponding gray scale interval and the pixel point in the neighborhood of the pixel point 8;
the contrast in the gray scale interval is determined as follows:
accumulating the contrast of the pixel point corresponding to each gray level in each gray level interval and the pixel point in the neighborhood of the pixel point 8, and calculating the average value, wherein the average value is used as a first average value;
acquiring a difference value of adjacent gray levels in each gray level interval, accumulating all the difference values obtained in each gray level interval, calculating an average value, and taking the average value as a second average value;
subtracting the first average value and the second average value in each gray scale interval to obtain the contrast in the gray scale interval;
obtaining an expected enhancement effect of the gray level in each gray level interval according to the contrast in each gray level interval, the number of pixel points corresponding to each gray level in each gray level interval and the number of gray levels in each gray level interval;
the desired enhancement effect of the grey levels in the grey scale interval is determined as follows:
acquiring the variance of the number of pixel points corresponding to each gray level in a gray level interval;
acquiring the quantity difference of the quantity of pixel points corresponding to the adjacent gray levels in the gray level interval, accumulating all the quantity differences obtained in the gray level interval to obtain an accumulated sum, calculating an average value, and taking the average value as a third average value;
taking the contrast in the gray scale interval as a numerator, and taking the product of a third mean value in the gray scale interval and the variance of the number of the pixel points corresponding to each gray scale as a denominator to obtain an expected enhancement effect of the gray scale in the gray scale interval;
obtaining an optimal division mode according to the expected enhancement effect of the gray level in each divided gray level interval, dividing a gray level histogram of the remote sensing image of the ecological restoration area according to the optimal division mode to obtain a plurality of target gray level intervals, enhancing each target gray level interval by utilizing histogram equalization to obtain an optimal enhancement image, and judging the ecological restoration effect of the homeland space according to the optimal enhancement image;
the optimal division mode is determined according to the following method:
and acquiring the average value of the expected enhancement effect of the gray levels in all the divided gray level intervals, and taking the corresponding division mode when the average value is maximum as the optimal division mode.
2. The remote sensing interpretation method for homeland space ecological restoration according to claim 1, wherein judging the homeland space ecological restoration effect according to the best enhanced image further comprises:
acquiring remote sensing images of the same ecological restoration area acquired at the same period year by year;
acquiring an optimal enhanced image of the remote sensing image of the same ecological restoration area acquired at the same period year by using the remote sensing image of the same ecological restoration area acquired at the same period year by year;
and obtaining the ecological restoration effect of the homeland space according to the number of pixel points in the forest region in the optimal enhanced image of the remote sensing image of the same ecological restoration region in the same period year by year.
3. The remote sensing interpretation method suitable for homeland space ecological restoration according to claim 1, wherein the plurality of gray scale intervals after each division are determined as follows:
obtaining the ratio of a numerator and a denominator by taking 255 as a numerator and taking the number of wave crests of the gray level histogram as a denominator;
obtaining the interval length of the division according to the multiplication of the ratio of the numerator and the denominator and the division times, and obtaining a plurality of divided gray level intervals by dividing the gray level histogram according to the interval length of the division times, wherein the division times of the gray level histogram are
，
The number of the peak points in the gray level histogram is represented, and the number of the gray level intervals obtained by each division is different.
4. The remote sensing interpretation method suitable for homeland space ecological restoration according to claim 1, wherein the specific expression of the contrast between the pixel point corresponding to each gray level and the pixel point in the 8 neighborhoods of the pixel point is as follows:
in the formula:
representing grey levels
The contrast between the corresponding pixel and the pixel in the neighborhood of the pixel 8,
represents the g-th gray level of
The gray value of the pixel point of (a),
represents the g-th gray level of
The gray value of the h neighborhood pixel point in 8 neighborhoods of the pixel point,
represents the g-th gray level of
The number of the pixel points of (a),
representing 8 neighborhoods, g tableShow a gray scale of
The g-th pixel point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211420132.0A CN115512231B (en) | 2022-11-15 | 2022-11-15 | Remote sensing interpretation method suitable for homeland space ecological restoration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211420132.0A CN115512231B (en) | 2022-11-15 | 2022-11-15 | Remote sensing interpretation method suitable for homeland space ecological restoration |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115512231A CN115512231A (en) | 2022-12-23 |
| CN115512231B true CN115512231B (en) | 2023-02-28 |
Family
ID=84513539
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211420132.0A Active CN115512231B (en) | 2022-11-15 | 2022-11-15 | Remote sensing interpretation method suitable for homeland space ecological restoration |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115512231B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115797798B (en) * | 2023-02-10 | 2023-04-25 | 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 |
| 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 |
| CN115861135B (en) * | 2023-03-01 | 2023-05-23 | 铜牛能源科技(山东)有限公司 | Image enhancement and recognition method applied to panoramic detection of box body |
| CN116188327B (en) * | 2023-04-21 | 2023-07-14 | 济宁职业技术学院 | Image enhancement method for security monitoring video |
| CN117333504B (en) * | 2023-12-01 | 2024-03-01 | 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) | Precise segmentation method for remote sensing image of complex terrain |
| CN117593193B (en) * | 2024-01-19 | 2024-04-23 | 山东海天七彩建材有限公司 | Sheet metal image enhancement method and system based on machine learning |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0749362A1 (en) * | 1994-03-07 | 1996-12-27 | International Business Machines Corporation | Improvements in image processing |
| CN101951523A (en) * | 2010-09-21 | 2011-01-19 | 北京工业大学 | Adaptive colour image processing method and system |
| CN109345491A (en) * | 2018-09-26 | 2019-02-15 | 中国科学院西安光学精密机械研究所 | Remote sensing image enhancement method fusing gradient and gray scale information |
| CN111462024A (en) * | 2020-04-03 | 2020-07-28 | 中国科学院半导体研究所 | Bilateral self-adaptive image visualization enhancement method and imaging system |
| CN112734654A (en) * | 2020-12-23 | 2021-04-30 | 中国科学院苏州纳米技术与纳米仿生研究所 | Image processing method, device, equipment and storage medium |
| CN114049283A (en) * | 2021-11-16 | 2022-02-15 | 上海无线电设备研究所 | Self-adaptive gray gradient histogram equalization remote sensing image enhancement method |
| CN114926466A (en) * | 2022-07-21 | 2022-08-19 | 山东省土地发展集团有限公司 | Land integrated monitoring and decision-making method and platform based on big data |
| CN114998209A (en) * | 2022-04-28 | 2022-09-02 | 南通奕霖智慧医学科技有限公司 | Foreign matter detection method for infusion medicine bottle lamp detection process |
| CN115082508A (en) * | 2022-08-18 | 2022-09-20 | 山东省蓝睿科技开发有限公司 | Ocean buoy production quality detection method |
| CN115311301A (en) * | 2022-10-12 | 2022-11-08 | 江苏银生新能源科技有限公司 | PCB welding spot defect detection method |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7840066B1 (en) * | 2005-11-15 | 2010-11-23 | University Of Tennessee Research Foundation | Method of enhancing a digital image by gray-level grouping |
| KR101426242B1 (en) * | 2013-04-18 | 2014-08-05 | 삼성전자주식회사 | Method and apparatus for converting gray level of color image |
| CN115311176B (en) * | 2022-10-12 | 2023-03-07 | 江苏菲尔浦物联网有限公司 | Night image enhancement method based on histogram equalization |
-
2022
- 2022-11-15 CN CN202211420132.0A patent/CN115512231B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0749362A1 (en) * | 1994-03-07 | 1996-12-27 | International Business Machines Corporation | Improvements in image processing |
| CN101951523A (en) * | 2010-09-21 | 2011-01-19 | 北京工业大学 | Adaptive colour image processing method and system |
| CN109345491A (en) * | 2018-09-26 | 2019-02-15 | 中国科学院西安光学精密机械研究所 | Remote sensing image enhancement method fusing gradient and gray scale information |
| CN111462024A (en) * | 2020-04-03 | 2020-07-28 | 中国科学院半导体研究所 | Bilateral self-adaptive image visualization enhancement method and imaging system |
| CN112734654A (en) * | 2020-12-23 | 2021-04-30 | 中国科学院苏州纳米技术与纳米仿生研究所 | Image processing method, device, equipment and storage medium |
| CN114049283A (en) * | 2021-11-16 | 2022-02-15 | 上海无线电设备研究所 | Self-adaptive gray gradient histogram equalization remote sensing image enhancement method |
| CN114998209A (en) * | 2022-04-28 | 2022-09-02 | 南通奕霖智慧医学科技有限公司 | Foreign matter detection method for infusion medicine bottle lamp detection process |
| CN114926466A (en) * | 2022-07-21 | 2022-08-19 | 山东省土地发展集团有限公司 | Land integrated monitoring and decision-making method and platform based on big data |
| CN115082508A (en) * | 2022-08-18 | 2022-09-20 | 山东省蓝睿科技开发有限公司 | Ocean buoy production quality detection method |
| CN115311301A (en) * | 2022-10-12 | 2022-11-08 | 江苏银生新能源科技有限公司 | PCB welding spot defect detection method |
Non-Patent Citations (2)
| Title |
|---|
| 《A Design of Dynamic Defective Pixel Correction for Image Sensor》;Liu Yongji;《2020 IEEE International Conference on Artificial Intelligence and Information Systems (ICAIIS)》;20200911;全文 * |
| 胡明 ; 葛俊锋.《 基于图像处理和K近邻算法的示温漆判读方法》.《航空发动机》.2021,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115512231A (en) | 2022-12-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115512231B (en) | Remote sensing interpretation method suitable for homeland space ecological restoration | |
| CN115829883B (en) | Surface image denoising method for special-shaped metal structural member | |
| CN107704807B (en) | Dynamic monitoring method based on multi-source remote sensing sequence image | |
| CN103226832B (en) | Based on the multi-spectrum remote sensing image change detecting method of spectral reflectivity mutation analysis | |
| CN105335965B (en) | Multi-scale self-adaptive decision fusion segmentation method for high-resolution remote sensing image | |
| CN107705314A (en) | A kind of more subject image dividing methods based on intensity profile | |
| CN103377468A (en) | Image processing device and image processing method | |
| CN115797798A (en) | Ecological restoration effect evaluation method based on abandoned mine remote sensing image | |
| CN109613531B (en) | Multi-threshold optimization deformation inversion method and system for micro-variation perception early warning radar | |
| CN110070545B (en) | Method for automatically extracting urban built-up area by urban texture feature density | |
| CN104036485A (en) | Method about image resampling tampering detection | |
| CN117368920B (en) | D-insar-based coal mining area subsidence monitoring method and system | |
| CN115797473B (en) | Concrete forming evaluation method for civil engineering | |
| CN116883408B (en) | Integrating instrument shell defect detection method based on artificial intelligence | |
| CN116542972A (en) | Wall plate surface defect rapid detection method based on artificial intelligence | |
| CN116823824A (en) | Underground belt conveyor dust fall detecting system based on machine vision | |
| CN112307803A (en) | Digital geological outcrop crack extraction method and device | |
| CN114972370A (en) | Remote sensing image self-adaptive segmentation method for neural network reasoning | |
| CN105205816A (en) | Method for extracting high-resolution SAR image building zone through multi-feature weighted fusion | |
| CN114881960A (en) | Feature enhancement-based cloth linear defect detection method and system | |
| CN116740579B (en) | Intelligent collection method for territorial space planning data | |
| CN117237396A (en) | Rail bolt rust area segmentation method based on image characteristics | |
| CN105488798B (en) | SAR image method for measuring similarity based on point set contrast | |
| CN114266899A (en) | Image target parallel detection method based on multi-core DSP | |
| CN116503426B (en) | Ultrasonic image segmentation method based on image processing |
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 |