CN117312973B - Inland water body optical classification method and system - Google Patents
Inland water body optical classification method and system Download PDFInfo
- Publication number
- CN117312973B CN117312973B CN202311253664.4A CN202311253664A CN117312973B CN 117312973 B CN117312973 B CN 117312973B CN 202311253664 A CN202311253664 A CN 202311253664A CN 117312973 B CN117312973 B CN 117312973B
- Authority
- CN
- China
- Prior art keywords
- water
- water bodies
- bodies
- spectrum
- class
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 292
- 230000003287 optical effect Effects 0.000 title claims abstract description 76
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000001228 spectrum Methods 0.000 claims abstract description 82
- 238000002310 reflectometry Methods 0.000 claims abstract description 54
- 230000003595 spectral effect Effects 0.000 claims abstract description 48
- 238000005259 measurement Methods 0.000 claims abstract description 6
- 238000012545 processing Methods 0.000 claims description 26
- 239000013598 vector Substances 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 14
- 241000192710 Microcystis aeruginosa Species 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- XLYOFNOQVPJJNP-ZSJDYOACSA-N Heavy water Chemical compound [2H]O[2H] XLYOFNOQVPJJNP-ZSJDYOACSA-N 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 7
- 238000000985 reflectance spectrum Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 7
- 238000011160 research Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 230000019771 cognition Effects 0.000 description 2
- 238000012804 iterative process Methods 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention provides an inland water body optical classification method and system. The method comprises the following steps: based on a K-means method, taking the spectral angle distance as a measurement, roughly dividing the normalized remote sensing reflectivity spectrum of all water bodies into 20 water bodies; calculating the intra-class distance of the 20 classes of water bodies, and splitting the class with the intra-class distance larger than a preset value by adopting a K-means method to obtain 25 classes of water bodies after splitting; calculating the average spectrum of 25 water bodies, classifying K-means of gradual iteration of the average spectrum, gradually reducing the average spectrum from 25 water bodies to 10 water bodies, and respectively calculating the spectral angle distance after each iteration; and classifying the water bodies into 13 types according to the spectral angle distances from the 25 types of water bodies to the 10 types of water bodies. The scheme provided by the invention can establish a complete inland water body optical classification system, and provides a method for establishing the system, so that the blank of the inland water body optical classification system in the water environment remote sensing field is filled.
Description
Technical Field
The invention belongs to the field of optical classification of water bodies, and particularly relates to an inland water body optical classification method and system.
Background
Inland water bodies such as lakes, rivers, reservoirs and the like are important components of natural ecosystems for which human beings depend to survive and develop. The water color remote sensing parameter inversion is an important technical means for monitoring, evaluating and predicting the early warning water environment and water ecology, the water body optical type is an important parameter for macroscopically knowing the current situation and the change trend of the water environment, and the water color remote sensing parameter inversion method is a basis for improving the inversion precision of the common water color remote sensing parameter. Classifying the water body is helpful for identifying the optical complex water area and analyzing the environmental change of the water body. Recent studies have demonstrated the importance of optical classification of water bodies, but water body classification studies still have some problems: the existing class II water body classification research lacks to establish a complete water body optical classification system aiming at the inland water body of China. In order to solve the problem, the invention provides an inland water optical classification system, which is used for further researching spectral reflectivity characteristics of inland water of different types and providing theoretical basis and technical support for inversion of water quality parameters of inland water of various types.
At present, domestic and foreign scholars do a great deal of work on water body classification research, and most of water body optical classification research objects are ocean water bodies, near-shore and inland combined water bodies, single lakes, a plurality of typical lakes and the like, and lack of a special water body optical type frame and system for inland water bodies; the objectivity of the method can not be maintained by determining the number of clusters in the used clustering method, the data set selected by the existing research and the assumed number of clusters are different in interval, and the commonly accepted water body type classification standard is lacked.
Disclosure of Invention
In order to solve the technical problems, the invention provides a technical scheme of an inland water body optical classification method so as to solve the technical problems.
The invention discloses an inland water body optical classification method in a first aspect, which comprises the following steps:
S1, selecting a remote sensing reflectivity spectrum of an inland water body with a wave band of 400-900 nm, and carrying out normalization processing on the remote sensing reflectivity spectrum;
S2, roughly dividing the normalized remote sensing reflectivity spectrum of all the water bodies into 20 water bodies by taking the spectral angle distance as a measurement based on a K-means method;
S3, calculating the intra-class distance of the 20 water bodies, and splitting the water bodies with the intra-class distance larger than a preset value by adopting a K-means method to obtain 25 water bodies;
S4, calculating an average spectrum of the 25 water bodies, gradually iterating the average spectrum to classify the K-means, gradually reducing the average spectrum from the 25 water bodies to the 10 water bodies, and respectively calculating the spectral angle distance after each iteration;
and S5, classifying the water bodies into 13 types according to the spectral angle distances from the 25 types of water bodies to the 10 types of water bodies.
According to the method of the first aspect of the present invention, in the step S1, the method for normalizing the remote sensing reflectivity includes:
Where NR rs (λ) represents the normalized spectrum integrated between 400nm and 900nm and R rs (λ) represents the remote sensing reflectance spectrum.
According to the method of the first aspect of the present invention, in the step S2, the calculation formula of the spectral angular distance is:
Where SAD is the spectral angular distance, x s and x t are the two spectral reflectance vectors, And/>Is the transpose vector of x s and x t.
According to the method of the first aspect of the present invention, in the step S3, the calculation formula of the intra-class distance is:
Wherein D is the intra-class distance, N i is the number of samples of the ith class of water body, Is the kth spectral reflectance vector of the ith water body, X i is the average spectrum of the ith water body,/>Is the square of the result of the calculation of the angular distance of the spectrum.
According to the method of the first aspect of the present invention, in the step S3, the preset value is 0.08.
According to the method of the first aspect of the present invention, in the step S5, the method for classifying the water bodies into 13 classes according to the analysis of the spectral angular distances from the 25 classes of water bodies to the 10 classes of water bodies includes: the spectrum angle distance from the 25-class water bodies to the 10-class water bodies is analyzed, and the spectrum angle distance is greatly changed when the spectrum angle distance is divided into 13 classes and 15 classes, so that the spectrum angle distance is suitable for being used as the final classification number. According to the comparison of the final merging effect, the water bodies classified into 13 types are more practical and physical significance, so that all the water bodies are finally classified into 13 types. Specifically, analysis of the change in the spectral angle distance from 25 to 10 kinds shows that the spectral angle value greatly changes when the classification is made into 13 and 15 kinds, and is suitable as the final classification number. According to the comparison of the final merging effect, the water bodies classified into 13 types are found to have more practical physical significance, so that all the water bodies are finally classified into 13 types.
According to the method of the first aspect of the present invention, in the step S5, the water body type of the 13 kinds of water bodies is:
Highly clean water, generally clean water, light turbid water, medium turbid water, highly turbid water, light eutrophic water, medium eutrophic water, heavy eutrophic water, turbid eutrophic water, black and odorous water, light water bloom and heavy water bloom.
The second aspect of the invention discloses an inland water body optical classification system, which comprises:
the first processing module is configured to select a remote sensing reflectivity spectrum of the inland water body with the wave band of 400-900 nm and normalize the remote sensing reflectivity spectrum;
The second processing module is configured to roughly divide the normalized remote sensing reflectivity spectrum of all the water bodies into 20 water bodies by taking the spectrum angle distance as a measurement based on a K-means method;
The third processing module is configured to calculate the intra-class distances of the 20 classes of water bodies, split the classes with the intra-class distances larger than a preset value by adopting a K-means method, and turn into 25 classes of water bodies after splitting;
The fourth processing module is configured to calculate average spectrums of 25 water bodies, gradually iterate the average spectrums, classify K-means, gradually reduce the average spectrums from the 25 water bodies to 10 water bodies, and respectively calculate spectral angle distances after each iteration;
a fifth processing module configured to divide the water bodies into 13 classes based on analyzing the spectral angular distances of the 25 classes of water bodies to the 10 classes of water bodies.
A third aspect of the invention discloses an electronic device. The electronic device comprises a memory storing a computer program and a processor implementing the steps in a method of optical classification of an inland body of water of any one of the first aspects of the present disclosure when the processor executes the computer program.
A fourth aspect of the invention discloses a computer-readable storage medium. A computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps in a method of optical classification of inland water bodies of any of the first aspects of the present disclosure.
In conclusion, the scheme provided by the invention can establish a complete inland water body optical classification system, and provides a method for establishing the system, fills the blank of the inland water body optical classification system in the water environment remote sensing field, provides a new index for macroscopic cognition global and national wide-range inland water body conditions, and provides theoretical and technical support for global and national wide-range water quality parameter remote sensing classification inversion.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for optical classification of inland bodies of water according to an embodiment of the present invention;
FIG. 2 is a schematic intra-class distance diagram of 20 and 25 class water types of K-means clusters according to an embodiment of the present invention;
FIG. 3 is a graph showing the relationship between average SAD and cluster number according to an embodiment of the present invention;
FIG. 4 is an average spectrum of an inland water optical classification system according to an embodiment of the present invention;
FIG. 5 is an optical signature of a highly cleaned body of water in accordance with an embodiment of the present invention;
FIG. 6 is an optical signature of a body of clean water according to an embodiment of the invention;
FIG. 7 is a diagram of optical characteristics of a general body of clean water in accordance with an embodiment of the present invention;
FIG. 8 is a graph of optical characteristics of a slightly turbid water body according to an embodiment of the invention;
FIG. 9 is an optical signature of a moderately turbid body of water according to an embodiment of the invention;
FIG. 10 is a diagram of the optical characteristics of a highly turbid body of water according to an embodiment of the invention;
FIG. 11 is an optical signature of a lightly eutrophicated water body according to an embodiment of the present invention;
FIG. 12 is an optical signature of a medium eutrophic water body according to an embodiment of the present invention;
FIG. 13 is an optical signature of a heavily eutrophicated water body according to an embodiment of the present invention;
FIG. 14 is an optical signature of a turbid eutrophic water body according to an embodiment of the present invention;
FIG. 15 is a diagram of optical characteristics of a body of black and odorous water in accordance with an embodiment of the present invention;
Fig. 16 is an optical signature of light bloom in accordance with an embodiment of the present invention;
Fig. 17 is an optical signature of heavy bloom in accordance with an embodiment of the present invention;
FIG. 18 is a block diagram of an inland water optical classification system according to an embodiment of the present invention;
Fig. 19 is a block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention discloses an inland water body optical classification method in a first aspect. FIG. 1 is a flow chart of a method for optical classification of inland water according to an embodiment of the present invention, as shown in FIG. 1, the method includes:
S1, selecting a remote sensing reflectivity spectrum of an inland water body with a wave band of 400-900 nm, and carrying out normalization processing on the remote sensing reflectivity spectrum;
S2, roughly dividing the normalized remote sensing reflectivity spectrum of all the water bodies into 20 water bodies by taking the spectral angle distance as a measurement based on a K-means method;
S3, calculating the intra-class distance of the 20 water bodies, and splitting the water bodies with the intra-class distance larger than a preset value by adopting a K-means method to obtain 25 water bodies;
S4, calculating an average spectrum of the 25 water bodies, gradually iterating the average spectrum to classify the K-means, gradually reducing the average spectrum from the 25 water bodies to the 10 water bodies, and respectively calculating the spectral angle distance after each iteration;
and S5, classifying the water bodies into 13 types according to the spectral angle distances from the 25 types of water bodies to the 10 types of water bodies.
In the step S1, remote sensing reflectivity spectrum of inland water body with 400-900 nm wave band is selected, and normalization processing is carried out on the remote sensing reflectivity spectrum.
In some embodiments, in the step S1, the method for normalizing the remote sensing reflectivity includes:
Where NR rs (λ) represents the normalized spectrum integrated between 400nm and 900nm and R rs (λ) represents the remote sensing reflectance spectrum.
In step S2, based on the K-means method, taking the spectral angle distance as a measure, roughly dividing the normalized remote sensing reflectivity spectrum of all the water bodies into 20 water bodies.
In some embodiments, in the step S2, the calculation formula of the spectral angular distance is:
Where SAD is the spectral angular distance, x s and x t are the two spectral reflectance vectors, And/>Is the transpose vector of x s and x t. The smaller the SAD, the higher the similarity of the two spectra.
And step S3, calculating the intra-class distance of the 20 water bodies, and splitting the water bodies with the intra-class distance larger than a preset value by adopting a K-means method to obtain 25 water bodies after splitting.
In some embodiments, in the step S3, the intra-class distance is a root mean square distance between sample points of each mode of the same class, and the calculation formula of the intra-class distance is:
Wherein D is the intra-class distance, N i is the number of samples of the ith class of water body, Is the kth spectral reflectance vector of the ith water body, X i is the average spectrum of the ith water body,/>Is the square of the result of the calculation of the angular distance of the spectrum.
The preset value is 0.08.
Specifically, by observing and analyzing the obtained spectra of 20 categories, it was found that there were some cases of erroneous classification. To solve this problem, the present embodiment calculates the intra-class distances of 20 categories, as shown in fig. 2, and finds that the intra-class distances of those categories in which there is an erroneous classification are all greater than 0.08. Therefore, the splitting threshold is set to 0.08, and 25 categories are obtained finally, and the intra-category distances of the categories are smaller than 0.08, as shown in fig. 2.
In step S5, the water bodies are classified into 13 types according to the spectral angular distances from the 25 types of water bodies to the 10 types of water bodies.
In some embodiments, in the step S5, the method for classifying the water bodies into 13 classes according to analyzing the spectral angular distances of the 25-class water bodies to the 10-class water bodies includes: the spectrum angle distance from the 25-class water bodies to the 10-class water bodies is analyzed, and the spectrum angle distance is greatly changed when the spectrum angle distance is divided into 13 classes and 15 classes, so that the spectrum angle distance is suitable for being used as the final classification number. According to the comparison of the final merging effect, the water bodies classified into 13 types are more practical and physical significance, so that all the water bodies are finally classified into 13 types. .
Specifically, analysis of the change in spectral angle distance from class 25 to class 10 shows that there is a large change in spectral angle value when classified into class 13 and class 15, and is suitable as the final classification number. According to the comparison of the final merging effect, the water bodies classified into 13 types are found to have more practical physical significance, so that all the water bodies are finally classified into 13 types.
The water body types of the 13-type water bodies are as follows:
Highly clean water, generally clean water, light turbid water, medium turbid water, highly turbid water, light eutrophic water, medium eutrophic water, heavy eutrophic water, turbid eutrophic water, black and odorous water, light water bloom and heavy water bloom.
Specifically, the average spectrum of 25 classes is calculated, the 25 average spectra are combined by using the step-by-step iteration K-means, fig. 3 shows that the step-by-step iteration K-means is adopted in the iterative process from 25 to 10 classes, and as can be seen from the figure, the class spacing from 15 to 25 classes has little variation, no obvious characteristic, and is typically classified into 13 classes and 15 classes, the class spacing has large variation in both classes, and the class spacing can be used as the final classification number. According to the comparison of the final merging effect, the 13 types of water bodies are found to have more practical physical significance, so that all remote sensing reflectivity data are divided into 13 types by the research. The inland water optical classification system is shown in fig. 4.
As shown in fig. 5, the optical characteristics of a highly clean body of water are: lan Boduan has higher reflectivity and low red and near infrared;
as shown in fig. 6, the optical characteristics of the clean water body are: the reflectivity of the deep blue band is reduced, but the reflectivity peak is still in the blue band;
As shown in fig. 7, the general clean water body is characterized optically by: lan Boduan reflectance is reduced, and a reflection peak is formed in a green wave band;
as shown in fig. 8, the optical characteristics of the slightly turbid water body are: the reflectivity from the green wave band to the red wave band is in a descending trend, and the near infrared wave band starts to rise;
as shown in fig. 9, the optical characteristics of a moderately turbid water body are: the reflectivity of the red and near infrared bands is obviously increased;
as shown in fig. 10, the optical characteristics of a highly turbid water body are: the reflectivity of the red wave band and the near infrared wave band are obviously increased, and the reflectivity of the red wave band and the green wave band are equal to or higher than those of the green wave band;
As shown in fig. 11, the optical characteristics of the slightly eutrophic water body are: the reflection peak of the green wave band is obvious, and the reflection peak of the red wave band is lower;
As shown in fig. 12, the optical characteristics of the moderately eutrophic water body are: the reflection peak of the green wave band is obvious, and the reflection peak of the red wave band is increased;
as shown in fig. 13, the optical characteristics of the heavily eutrophic water body are: the reflection peak of the red band is higher, and the height is equivalent to that of the green band;
as shown in fig. 14, the optical characteristics of the turbid eutrophic water body are: the reflectivity of the red wave band and the near infrared wave band is higher, and the reflection peak of the red wave band is obvious;
as shown in fig. 15, the black and odorous water body has the optical characteristics that: the reflectivity is lower than that of a common water body, the curve is flat, and no obvious peak-valley characteristic exists;
As shown in fig. 16, the optical characteristics of mild water bloom are: the reflectivity of the red band is highest, the near infrared band is reduced, but the reflectivity is higher than the red band;
as shown in fig. 17, the optical characteristics of heavy bloom are: the reflectivity of the red side and the near infrared band is high, the curve is flat, and the trend of the near infrared band is not obvious.
In conclusion, the scheme provided by the invention can establish a complete inland water body optical classification system, and provides a method for establishing the system, fills the blank of the inland water body optical classification system in the water environment remote sensing field, provides a new index for macroscopic cognition global and national wide-range inland water body conditions, and provides theoretical and technical support for global and national wide-range water quality parameter remote sensing classification inversion.
The second aspect of the invention discloses an inland water body optical classification system. FIG. 18 is a block diagram of an inland water optical classification system according to an embodiment of the present invention; as shown in fig. 18, the system 100 includes:
The first processing module 101 is configured to select a remote sensing reflectivity spectrum of an inland water body with a wave band of 400-900 nm and perform normalization processing on the remote sensing reflectivity spectrum;
the second processing module 102 is configured to coarsely divide the normalized remote sensing reflectivity spectrum of all the water bodies into 20 water bodies based on the K-means method and by taking the spectral angle distance as a measure;
The third processing module 103 is configured to calculate the intra-class distance of the 20 classes of water bodies, split the class with the intra-class distance larger than a preset value by adopting a K-means method, and change the split class into 25 classes of water bodies;
a fourth processing module 104 configured to calculate an average spectrum of 25 water bodies, gradually iterate the average spectrum to classify K-means, gradually reduce the average spectrum from 25 water bodies to 10 water bodies, and respectively calculate spectral angle distances after each iteration;
A fifth processing module 105 is configured to divide the water bodies into 13 classes based on analyzing the spectral angular distance of the 25-class water bodies to the 10-class water bodies.
According to the system of the second aspect of the present invention, the first processing module 101 is specifically configured to perform the normalization processing on the remote sensing reflectivity, where the method includes:
Where NR rs (λ) represents the normalized spectrum integrated between 400nm and 900nm and R rs (λ) represents the remote sensing reflectance spectrum.
According to the system of the second aspect of the present invention, the second processing module 102 is specifically configured to calculate the spectral angular distance according to the formula:
Where SAD is the spectral angular distance, x s and x t are the two spectral reflectance vectors, And/>Is the transpose vector of x s and x t. The smaller the SAD, the higher the similarity of the two spectra.
According to the system of the second aspect of the present invention, the third processing module 103 is specifically configured to obtain an intra-class distance, that is, a root mean square distance between sample points of each mode in the same class, where a calculation formula of the intra-class distance is:
Wherein D is the intra-class distance, N i is the number of samples of the ith class of water body, Is the kth spectral reflectance vector of the ith water body, X i is the average spectrum of the ith water body,/>Is the square of the result of the calculation of the angular distance of the spectrum.
The preset value is 0.08.
Specifically, by observing and analyzing the obtained spectra of 20 categories, it was found that there were some cases of erroneous classification. To solve this problem, the present embodiment calculates the intra-class distances of 20 categories, as shown in fig. 2, and finds that the intra-class distances of those categories in which there is an erroneous classification are all greater than 0.08. Therefore, the splitting threshold is set to 0.08, and 25 categories are obtained finally, and the intra-category distances of the categories are smaller than 0.08, as shown in fig. 2.
According to the system of the second aspect of the present invention, the fifth processing module 105 is specifically configured such that the method for classifying the water body into 13 classes according to the analysis of the spectral angular distances of the 25 classes of water bodies to the 10 classes of water bodies includes: the spectrum angle distance from the 25-class water bodies to the 10-class water bodies is analyzed, and the spectrum angle distance is greatly changed when the spectrum angle distance is divided into 13 classes and 15 classes, so that the spectrum angle distance is suitable for being used as the final classification number. According to the comparison of the final merging effect, the water bodies classified into 13 types are more practical and physical significance, so that all the water bodies are finally classified into 13 types.
The water body types of the 13-type water bodies are as follows:
Highly clean water, generally clean water, light turbid water, medium turbid water, highly turbid water, light eutrophic water, medium eutrophic water, heavy eutrophic water, turbid eutrophic water, black and odorous water, light water bloom and heavy water bloom.
Specifically, the average spectrum of 25 classes is calculated, the 25 average spectra are combined by using the step-by-step iteration K-means, fig. 3 shows that the step-by-step iteration K-means is adopted in the iterative process from 25 to 10 classes, and as can be seen from the figure, the class spacing from 15 to 25 classes has little variation, no obvious characteristic, and is typically classified into 13 classes and 15 classes, the class spacing has large variation in both classes, and the class spacing can be used as the final classification number. According to the comparison of the final merging effect, the 13 types of water bodies are found to have more practical physical significance, so that all remote sensing reflectivity data are divided into 13 types by the research. The inland water optical classification system is shown in fig. 4.
As shown in fig. 5, the optical characteristics of a highly clean body of water are: lan Boduan has higher reflectivity and low red and near infrared;
as shown in fig. 6, the optical characteristics of the clean water body are: the reflectivity of the deep blue band is reduced, but the reflectivity peak is still in the blue band;
As shown in fig. 7, the general clean water body is characterized optically by: lan Boduan reflectance is reduced, and a reflection peak is formed in a green wave band;
as shown in fig. 8, the optical characteristics of the slightly turbid water body are: the reflectivity from the green wave band to the red wave band is in a descending trend, and the near infrared wave band starts to rise;
as shown in fig. 9, the optical characteristics of a moderately turbid water body are: the reflectivity of the red and near infrared bands is obviously increased;
as shown in fig. 10, the optical characteristics of a highly turbid water body are: the reflectivity of the red wave band and the near infrared wave band are obviously increased, and the reflectivity of the red wave band and the green wave band are equal to or higher than those of the green wave band;
As shown in fig. 11, the optical characteristics of the slightly eutrophic water body are: the reflection peak of the green wave band is obvious, and the reflection peak of the red wave band is lower;
As shown in fig. 12, the optical characteristics of the moderately eutrophic water body are: the reflection peak of the green wave band is obvious, and the reflection peak of the red wave band is increased;
as shown in fig. 13, the optical characteristics of the heavily eutrophic water body are: the reflection peak of the red band is higher, and the height is equivalent to that of the green band;
as shown in fig. 14, the optical characteristics of the turbid eutrophic water body are: the reflectivity of the red wave band and the near infrared wave band is higher, and the reflection peak of the red wave band is obvious;
as shown in fig. 15, the black and odorous water body has the optical characteristics that: the reflectivity is lower than that of a common water body, the curve is flat, and no obvious peak-valley characteristic exists;
As shown in fig. 16, the optical characteristics of mild water bloom are: the reflectivity of the red band is highest, the near infrared band is reduced, but the reflectivity is higher than the red band;
As shown in fig. 17, the optical characteristics of heavy bloom are: the reflectivity of the red side and the near infrared band is high, the curve is flat, and the trend of the near infrared band is not obvious. A third aspect of the invention discloses an electronic device. The electronic device comprises a memory and a processor, the memory storing a computer program, the processor implementing the steps in an inland water body optical classification method according to any one of the first aspects of the present disclosure when executing the computer program.
Fig. 19 is a block diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 19, the electronic device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Wherein the processor of the electronic device is configured to provide computing and control capabilities. The memory of the electronic device includes a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the electronic device is used for conducting wired or wireless communication with an external terminal, and the wireless communication can be achieved through WIFI, an operator network, near Field Communication (NFC) or other technologies. The display screen of the electronic equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the electronic equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 19 is merely a structural diagram of a portion related to the technical solution of the present disclosure, and does not constitute a limitation of the electronic device to which the technical solution of the present application is applied, and a specific electronic device may include more or less components than those shown in the drawings, or may combine some components, or have different component arrangements.
A fourth aspect of the invention discloses a computer-readable storage medium. A computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of a method of optical classification of inland water bodies according to any of the first aspect of the present disclosure.
Note that the technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be regarded as the scope of the description. The foregoing examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (5)
1. An inland water body optical classification method, characterized in that the method comprises:
s1, selecting a remote sensing reflectivity spectrum of an inland water body with a wave band of 400-900 nm, and carrying out normalization processing on the remote sensing reflectivity spectrum;
S2, roughly dividing the normalized remote sensing reflectivity spectrum of all the water bodies into 20 water bodies by taking the spectral angle distance as a measurement based on a K-means method;
S3, calculating the intra-class distance of the 20 water bodies, and splitting the water bodies with the intra-class distance larger than a preset value by adopting a K-means method to obtain 25 water bodies;
S4, calculating an average spectrum of the 25 water bodies, gradually iterating the average spectrum to classify the K-means, gradually reducing the average spectrum from the 25 water bodies to the 10 water bodies, and respectively calculating the spectral angle distance after each iteration;
S5, classifying the water bodies into 13 types according to the spectral angle distances from the 25 types of water bodies to the 10 types of water bodies; the water body types of the 13 kinds of water bodies are as follows:
Highly-clean water bodies, general clean water bodies, slightly-turbid water bodies, moderately-turbid water bodies, highly-turbid water bodies, slightly-eutrophic water bodies, moderately-eutrophic water bodies, severely-eutrophic water bodies, turbid eutrophic water bodies, black and odorous water bodies, light water bloom and heavy water bloom;
in the step S1, the method for normalizing the remote sensing reflectivity includes:
Wherein NR rs (λ) represents the normalized spectrum integrated between 400nm and 900nm, and R rs (λ) represents the remote sensing reflectance spectrum;
in the step S2, the calculation formula of the spectrum angle distance is as follows:
Where SAD is the spectral angular distance, x s and x t are two spectral reflectance vectors, And/>Transpose vectors for x s and x t;
In the step S3, the calculation formula of the intra-class distance is:
Wherein D is the intra-class distance, N i is the number of samples of the ith class of water body, Is the kth spectral reflectance vector of the ith water body, X i is the average spectrum of the ith water body,/>Is the square of the result of the calculation of the spectral angular distance.
2. An inland water body optical classification method according to claim 1, characterized in that in the step S3, the preset value is 0.08.
3. An optical classification system for an inland body of water, the system comprising:
the first processing module is configured to select a remote sensing reflectivity spectrum of the inland water body with the wave band of 400-900 nm and normalize the remote sensing reflectivity spectrum;
the normalization processing of the remote sensing reflectivity comprises the following steps:
Wherein NR rs (λ) represents the normalized spectrum integrated between 400nm and 900nm, and R rs (λ) represents the remote sensing reflectance spectrum;
The second processing module is configured to roughly divide the normalized remote sensing reflectivity spectrum of all the water bodies into 20 water bodies by taking the spectrum angle distance as a measurement based on a K-means method;
the calculation formula of the spectrum angle distance is as follows:
Where SAD is the spectral angular distance, x s and x t are two spectral reflectance vectors, And/>Transpose vectors for x s and x t;
The third processing module is configured to calculate the intra-class distances of the 20 classes of water bodies, split the classes with the intra-class distances larger than a preset value by adopting a K-means method, and turn into 25 classes of water bodies after splitting;
The fourth processing module is configured to calculate average spectrums of 25 water bodies, gradually iterate the average spectrums, classify K-means, gradually reduce the average spectrums from the 25 water bodies to 10 water bodies, and respectively calculate spectral angle distances after each iteration;
The calculation formula of the intra-class distance is as follows:
Wherein D is the intra-class distance, N i is the number of samples of the ith class of water body, Is the kth spectral reflectance vector of the ith water body, X i is the average spectrum of the ith water body,/>Square of the calculation result of the spectrum angle distance;
A fifth processing module configured to divide the water bodies into 13 types according to analyzing the spectral angular distances of the 25 types of water bodies to the 10 types of water bodies;
The water body types of the 13 kinds of water bodies are as follows: highly clean water, generally clean water, light turbid water, medium turbid water, highly turbid water, light eutrophic water, medium eutrophic water, heavy eutrophic water, turbid eutrophic water, black and odorous water, light water bloom and heavy water bloom.
4. An electronic device comprising a memory storing a computer program and a processor implementing the steps of a method of optical classification of an inland body of water according to any one of claims 1 to 2 when the computer program is executed by the processor.
5. A computer readable storage medium, characterized in that it has stored thereon a computer program which, when executed by a processor, implements the steps of a method for optical classification of inland water bodies according to any one of claims 1 to 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311253664.4A CN117312973B (en) | 2023-09-26 | 2023-09-26 | Inland water body optical classification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311253664.4A CN117312973B (en) | 2023-09-26 | 2023-09-26 | Inland water body optical classification method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117312973A CN117312973A (en) | 2023-12-29 |
| CN117312973B true CN117312973B (en) | 2024-05-03 |
Family
ID=89286044
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311253664.4A Active CN117312973B (en) | 2023-09-26 | 2023-09-26 | Inland water body optical classification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117312973B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106650810A (en) * | 2016-12-26 | 2017-05-10 | 河海大学 | Spectrum attribute information and space information based reservoir water body classification method and device |
| CN107330875A (en) * | 2017-05-31 | 2017-11-07 | 河海大学 | Based on the forward and reverse heterogeneous water body surrounding enviroment change detecting method of remote sensing images |
| CN111179218A (en) * | 2019-12-06 | 2020-05-19 | 深圳市派科斯科技有限公司 | Conveyor belt material detection method and device, storage medium and terminal equipment |
| CN113159167A (en) * | 2021-04-19 | 2021-07-23 | 福州大学 | Inland-based chlorophyll a inversion method for different types of water bodies |
| CN113406015A (en) * | 2021-05-31 | 2021-09-17 | 内蒙古师范大学 | Transparency calculation method and system for water bodies of near-shore and inland waters |
| WO2023000160A1 (en) * | 2021-07-20 | 2023-01-26 | 海南长光卫星信息技术有限公司 | Hyperspectral remote sensing image semi-supervised classification method, apparatus, and device, and storage medium |
| WO2023134626A1 (en) * | 2022-01-11 | 2023-07-20 | 北华航天工业学院 | Malodorous black water body extraction method based on cart classification model |
-
2023
- 2023-09-26 CN CN202311253664.4A patent/CN117312973B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106650810A (en) * | 2016-12-26 | 2017-05-10 | 河海大学 | Spectrum attribute information and space information based reservoir water body classification method and device |
| CN107330875A (en) * | 2017-05-31 | 2017-11-07 | 河海大学 | Based on the forward and reverse heterogeneous water body surrounding enviroment change detecting method of remote sensing images |
| CN111179218A (en) * | 2019-12-06 | 2020-05-19 | 深圳市派科斯科技有限公司 | Conveyor belt material detection method and device, storage medium and terminal equipment |
| CN113159167A (en) * | 2021-04-19 | 2021-07-23 | 福州大学 | Inland-based chlorophyll a inversion method for different types of water bodies |
| CN113406015A (en) * | 2021-05-31 | 2021-09-17 | 内蒙古师范大学 | Transparency calculation method and system for water bodies of near-shore and inland waters |
| WO2023000160A1 (en) * | 2021-07-20 | 2023-01-26 | 海南长光卫星信息技术有限公司 | Hyperspectral remote sensing image semi-supervised classification method, apparatus, and device, and storage medium |
| WO2023134626A1 (en) * | 2022-01-11 | 2023-07-20 | 北华航天工业学院 | Malodorous black water body extraction method based on cart classification model |
Non-Patent Citations (3)
| Title |
|---|
| SHUN BI 等.Optical classification of inland waters based on an improved Fuzzy C-Means method.《Optics Express》.2019,第27卷(第24期),1-19. * |
| 张方方 等.高分一号卫星浑浊水体水质参数软分类反演.《遥感学报》.2023,第27卷(第3期),第3.1、3.3节. * |
| 王相海等.一种基于2D-PLDA和小波子带的虹膜识别算法.《中国图象图形学报》.2011,第16卷(第1期),第2节. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117312973A (en) | 2023-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bioucas-Dias et al. | Hyperspectral subspace identification | |
| Yuan et al. | Factorization-based texture segmentation | |
| Guo et al. | A feature fusion based forecasting model for financial time series | |
| CN102955902B (en) | Method and system for evaluating reliability of radar simulation equipment | |
| Vladikova et al. | Selectivity study of the differential impedance analysis—Comparison with the complex non-linear least-squares method | |
| Ma et al. | Multiscale superpixelwise prophet model for noise-robust feature extraction in hyperspectral images | |
| CN107239788A (en) | The optimal selection Spectral Clustering of characteristic vector group based on degree adaptive | |
| CN111008726B (en) | Class picture conversion method in power load prediction | |
| CN111723876A (en) | Load curve integrated spectrum clustering algorithm considering double-scale similarity | |
| CN111967535A (en) | Fault diagnosis method and device for temperature sensor in grain storage management scene | |
| CN111523587B (en) | Woody plant species spectrum identification method based on machine learning | |
| CN113158935A (en) | Wine spectral kurtosis regression model year identification system and year identification method | |
| CN117312973B (en) | Inland water body optical classification method and system | |
| CN112528559B (en) | Chlorophyll a concentration inversion method combining pre-classification and machine learning | |
| KR20220122596A (en) | Method and apparatus for constructing a chromosomal aneuploidy discrimination and classification model | |
| Liu et al. | Hyperspectral band selection based on consistency-measure of neighborhood rough set theory | |
| CN113034471A (en) | SAR image change detection method based on FINCH clustering | |
| CN106323466A (en) | Leaf nitrogen content high spectral evaluation method for continuous wavelet transformation analysis | |
| CN115994327A (en) | Equipment fault diagnosis method and device based on edge calculation | |
| CN107462564B (en) | Quick label-free detection method for aflatoxin B1 based on silver nanocrystals | |
| CN115841338A (en) | Method and device for determining abnormal electricity utilization behavior and non-volatile storage medium | |
| CN115129503A (en) | Equipment fault data cleaning method and system | |
| CN111291820B (en) | Target detection method combining positioning information and classification information | |
| CN107607723A (en) | A kind of protein-protein interaction assay method based on accidental projection Ensemble classifier | |
| CN114355234A (en) | Intelligent quality detection method and system for power module |
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 |