CN113177979B - Multispectral image-based water pollution area identification method and multispectral image-based water pollution area identification system - Google Patents
Multispectral image-based water pollution area identification method and multispectral image-based water pollution area identification system Download PDFInfo
- Publication number
- CN113177979B CN113177979B CN202110624211.2A CN202110624211A CN113177979B CN 113177979 B CN113177979 B CN 113177979B CN 202110624211 A CN202110624211 A CN 202110624211A CN 113177979 B CN113177979 B CN 113177979B
- Authority
- CN
- China
- Prior art keywords
- spectrum
- image
- difference
- area
- pollution
- 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 28
- 238000003911 water pollution Methods 0.000 title claims abstract description 13
- 238000001228 spectrum Methods 0.000 claims abstract description 90
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 32
- 230000000877 morphologic effect Effects 0.000 claims description 15
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000002310 reflectometry Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 238000011109 contamination Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 abstract description 10
- 230000008859 change Effects 0.000 abstract description 4
- 230000003595 spectral effect Effects 0.000 description 8
- 238000012544 monitoring process Methods 0.000 description 7
- 238000010276 construction Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 239000000443 aerosol Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2132—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on discrimination criteria, e.g. discriminant analysis
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10052—Images from lightfield camera
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20076—Probabilistic image processing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Geometry (AREA)
- Image Processing (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a water pollution area identification method and a system based on multispectral images, which are used for acquiring a spectrum image of a target water area and acquiring a spectrum difference image representing the spectrum variation degree of each grid unit through a spectrum difference function; based on the spectrum difference image, a pollution probability distribution map is obtained by utilizing a difference classification function; setting a threshold again, and extracting the pollution pattern spots from the pollution probability distribution map. The identification method provided by the invention directly detects the pollution area according to the change characteristics of the spectrum in space without priori knowledge, does not need ground calibration, does not need atmospheric correction, does not need a large number of sample supports, has less influence on the result from the atmosphere, improves the utilization rate of multispectral images, and has wide application scenes.
Description
Technical Field
The invention belongs to the field of pollution monitoring, and particularly relates to a water pollution area identification method and system based on multispectral images.
Background
The traditional water pollution monitoring adopts a point monitoring method, namely a plurality of points are selected in a river basin, an automatic water quality monitoring station is arranged or a manual sampling and testing method is adopted to evaluate the water quality of the points regularly. The method only reflects the water quality condition of the sampling point location, but cannot reflect the distribution condition of pollution in the whole river basin.
With the development of remote sensing technology, multispectral and hyperspectral satellite remote sensing is used for identifying polluted areas in watersheds. The method belongs to surface monitoring, the whole river basin is divided into grid units with continuous space, the water quality parameter values of grids of each unit are calculated by utilizing a water quality parameter inversion model, and finally, a pollution area is identified by grid statistics or comparison with a standard value. The method can comprehensively reflect the pollution distribution condition of the whole river basin, but the construction of the used water quality parameter inversion model needs a sufficient amount of sample support with reliable quality, and the historical images at any moment are difficult to be used for pollution area analysis under the condition of insufficient experimental accumulation.
The quantitative inversion model of the water quality parameters is a key for identifying a polluted area, the model construction takes a data pair of 'water quality parameters-multispectral reflectivity' as a support, the number of required sample points is enough, and the quality of the water quality parameter test result and the multispectral reflectivity calculation result is reliable, but the following problems often exist in actual work:
(1) The atmospheric correction process for calculating the multispectral reflectance products is not suitable for all areas at present, a common 6S, MODTRAN atmospheric correction model needs a large amount of atmospheric parameters as input, such as the concentration of CO 2, the thickness of aerosol and the like, and the parameters are difficult to obtain in practical application, often the model default values are used as substitutes, and the local and then atmospheric conditions cannot be completely simulated, so that a certain error exists in the multispectral reflectance calculation result;
(2) The water quality parameters can be obtained by a water quality automatic monitoring station or a manual test mode, the samples for modeling need satellite image matching in time and space, and the sampling data are of the same type, such as the data of the water quality automatic monitoring station or the test results of the same mechanism. Under the general condition, the number of samples meeting the use condition in one river basin is less than 10, and the construction of a water quality parameter inversion model is limited.
Disclosure of Invention
The invention aims at overcoming the defects of the prior art and provides a water pollution area identification method and system based on multispectral images.
In order to achieve the above purpose, the present invention adopts the following technical scheme: the water pollution area identification method based on the multispectral image is characterized by comprising the following steps of:
Step 1: acquiring a spectrum image of a target water area, and converting the spectrum image into a spectrum difference image D through a spectrum difference function D (lambda 1,λ2,λ3,...,λn);
step 2: based on the spectrum difference image, a pollution probability distribution map P is obtained by utilizing a difference classification function F;
step 3: setting a threshold value, and extracting a target pollution pattern from the pollution probability distribution map P.
Further, the spectrum difference function D (lambda 1,λ2,λ3,...,λn) in the step 1 is extracted from n kinds of spectrum data of the spectrum image, wherein n is more than or equal to 1.
Further, the spectrum difference image D (λ i) of the i-th band in the spectrum difference function D (λ 1,λ2,λ3,...,λn) in step 1 is obtained by calculating the difference of the spectrum data of each grid unit.
Further, in the step 2, the difference classification function F eliminates interference factors of the spectrum difference image through image features of the target.
A multispectral image-based water-contaminated zone identification system, comprising:
The spectrum difference analysis module is used for acquiring a spectrum image of the target water area and converting the spectrum image into a spectrum difference image D through a spectrum difference function D (lambda 1,λ2,λ3,...,λn);
The difference classification module is used for acquiring a pollution probability distribution map P by utilizing a difference classification function F based on the spectrum difference image; and the pollution area extraction module is used for setting a threshold value and extracting target pollution patterns from the pollution probability distribution map P.
Further, a spectrum difference function D (lambda 1,λ2,λ3,...,λn) in the spectrum difference analysis module is extracted from n kinds of spectrum data of the spectrum image, wherein n is more than or equal to 1.
Further, the spectrum difference image D (λ i) of the ith band in the spectrum difference function D (λ 1,λ2,λ3,...,λn) in the spectrum difference analysis module is obtained by calculating the difference of the spectrum data of each grid unit.
Further, the difference classification function F in the difference classification module eliminates interference factors of the light difference image through image features of the target.
A computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method of any of the preceding claims.
The water pollution area identification method directly judges the area possibly polluted by the change characteristics of the spectrum in space, avoids the problem of water quality parameter inversion model construction caused by incomplete atmospheric correction and insufficient sample quantity, and improves the utilization rate of multispectral images.
And abnormal noise is removed through the spectrum and morphological characteristics of different objects, so that the accuracy of distinguishing the polluted area is improved.
The water pollution area identification method and system have the beneficial effects that: under the condition of no priori knowledge, the pollution area is directly detected according to the change characteristics of the spectrum in space, a large number of sample supports are not needed, the result is less influenced by the atmosphere, and the utilization rate of the multispectral image is improved.
Drawings
Fig. 1 is a flowchart of an embodiment of a method for identifying a water-contaminated area based on a multispectral image.
Fig. 2 is a satellite image of example 1.
Fig. 3 is a geometrically corrected multispectral reflectance product of example 1.
Fig. 4 is a multispectral image of the water region of example 1.
Fig. 5 is a multispectral image of example 1 indicating a contaminated area.
Detailed Description
In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.
It is noted that the terms "comprises" and "comprising," and any variations thereof, in the description and claims of the present application and in the foregoing figures, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
A water pollution area identification method based on multispectral images, the flow of which is shown in figure 1, comprises the following steps:
step 1: acquiring a spectrum image of a target water area, and acquiring a spectrum difference image D representing the spectrum change degree of each grid unit through a spectrum difference function D (lambda 1,λ2,λ3,...,λn);
Step 2: based on the spectrum difference image, using a difference classification function F (I, A, C, D) to obtain a pollution probability distribution map P;
Step 3: setting a threshold value, and extracting pollution spots from the pollution probability distribution map.
The spectrum difference function D in the step 1 is used for obtaining the variation degree of the spectrum of each grid unit;
In the step 1, the spectrum difference function D is extracted from n spectrum data of a multispectral image, wherein n is more than or equal to 1;
The spectrum difference image D (lambda i) of the ith wave band is obtained by calculating the difference of the spectrum data of each grid unit through basic function operation;
The spectrum data of each grid unit is obtained by calculating the spectrum difference of each grid and m grids around each grid, wherein m is more than or equal to 2; the difference acquisition is obtained by basic function operation, and the calculation mode is not limited to ratio, difference, square root, arithmetic square root and the like.
And (2) a difference classification function F in the step (2) for eliminating interference factors through characteristic differences of the images.
The method of excluding step 2 is not limited to morphological features, optical features, and the like based on the target contamination pattern.
And 3, setting a threshold value, namely, extracting pollution patterns from the pollution probability distribution map according to the results and practical application settings of the step 1 and the step 2.
One embodiment of the spectral difference function D (λ 1,λ2,λ3,...,λn) in step 1 is:
D＝max(D(λ1),D(λ2),D(λ3),...,D(λn)) (1)
wherein, D is the final spectrum difference image, D (λ i) is the spectrum difference image of the ith band, and D (λi) is calculated as follows:
D(λi)＝D0(λi)+D1(λi)+D2(λi)+D3(λi)+D4(λi) (2)
D0(λi)＝(R(λi)x,y-μ(λi))2 (3)
D1(λi)＝(R(λi)x+1,y-1-R(λi)x,y)+(R(λi)x,y-R(λi)x-1,y+1) (4)
D2(λi)＝(R(λi)x+1,y-R(λi)x,y)+(R(λi)x,y-R(λi)x-1,y) (5)
D3(λi)＝(R(λi)x+1,y+1-R(λi)x,y)+(R(λi)x,y-R(λi)x-1,y-1) (6)
D4(λi)＝(R(λi)x,y+1-R(λi)x,y)+(R(λi)x,y-R(λi)x,y-1) (7)
wherein R (lambda i)x,y is the spectral value of a pixel (x, y) on the band of the spectral image lambda i, mu (lambda i) is the spectral mean value of the ith band, and D is smaller than the threshold value and is set to 0.
In the step 2, the difference classification function is F (I, A, C, D), wherein one expression form is that I is a component representing the reflection intensity, A, C is area and perimeter respectively and is used for counting morphological characteristics.
Step 2.1: setting the pixel with the spectrum difference value larger than 0 as 1, performing open operation on the image, eliminating the isolated pixel, and communicating adjacent image spots;
step 2.2: calculating the area A and the perimeter C of the pattern spots, and calculating the morphological index S=A/C;
step 2.3: the calculated intensity component I, I can be near infrared reflectivity or brightness component;
step 2.5: calculating a pollution probability distribution map p=d×s (1-I).
The image features in step 3 include, but are not limited to, morphological features of the image, brightness distribution features of the image after color conversion, or some other common image feature recognition method. The interference factors can be eliminated by one or a combination of the modes, and the communication map spots can be further processed.
The step3 is realized by the following steps:
(1) Calculating a morphological index C of a communicating pattern spot, wherein C=A/L, A is the area of the pattern spot, L is the perimeter of the pattern spot, the pixel where the pattern spot with C being larger than C1 is positioned is set as 0 for removing water surface noise, and the value range of C1 is 0-0.05;
(2) Performing RGB-HSV conversion on the connected image spots, wherein H is a tone component, S is a saturation component, V is a brightness component, pixels of the saturation component S > S1 and the brightness component V > V1 are set to be 0, and the value range of S1 and V1 is 0-0.4;
(3) And the non-0 pixel is the identification result of the polluted area.
A multispectral image-based water-contaminated zone identification system, comprising:
the spectrum difference analysis module is used for acquiring a spectrum image of the target water area and converting the spectrum image into a spectrum difference image D through a spectrum difference function;
the difference classification module is used for acquiring a pollution probability distribution map P by utilizing a difference classification function F based on the spectrum difference image;
and the pollution area extraction module is used for setting a threshold value and extracting target pollution patterns from the pollution probability distribution map P.
One of the specific manifestations of the spectral difference function D (λ 1,λ2,λ3,...,λn) is:
D＝max(D(λ1),D(λ2),D(λ3),...,D(λn)) (1)
wherein, D is the final spectrum difference image, D (λ i) is the spectrum difference image of the ith band, and D (λi) is calculated as follows:
D(λi)＝D0(λi)+D1(λi)+D2(λi)+D3(λi)+D4(λi) (2)
D0(λi)＝(R(λi)x,y-μ(λi))2 (3)
D1(λi)＝(R(λi)x+1,y-1-R(λi)x,y)+(R(λi)x,y-R(λi)x-1,y+1) (4)
D2(λi)＝(R(λi)x+1,y-R(λi)x,y)+(R(λi)x,y-R(λi)x-1,y) (5)
D3(λi)＝(R(λi)x+1,y+1-R(λi)x,y)+(R(λi)x,y-R(λi)x-1,y-1) (6)
D4(λi)＝(R(λi)x,y+1-R(λi)x,y)+(R(λi)x,y-R(λi)x,y-1) (7)
wherein R (lambda i)x,y is the spectral value of a pixel (x, y) on the band of the spectral image lambda i, mu (lambda i) is the spectral mean value of the ith band, and D is smaller than the threshold value and is set to 0.
The difference classification function in the difference classification module is F (I, A, C, D) =D.S. (1-I), wherein I is a component representing the reflection intensity, A, C is an area and a perimeter respectively, D is a spectrum difference image, a pollution probability distribution map P is formed by setting a pixel with a spectrum difference value larger than 0 in the spectrum difference image as 1, performing an open operation on the image, eliminating isolated pixels and communicating adjacent image spots; calculating the area A and the perimeter C of the communicating map spots, and calculating the morphological index S=A/C; calculating intensity components I of the connected pattern spots, wherein the I is near infrared reflectivity or brightness component; the contamination probability distribution map was calculated by P=D.S. (1-I).
The polluted region extraction module includes: the morphological analysis submodule is used for calculating morphological indexes C, C=A/L of the pollution probability distribution map communicated pattern spots, wherein A is the area of the pattern spots, L is the perimeter of the pattern spots, the pixel where the pattern spots with the C larger than C1 are located is set to be 0 and used for eliminating water surface noise, and the value range of C1 is 0-0.05; the color analysis sub-module is used for carrying out RGB-HSV conversion on the communicated image spots, wherein H is a tone component, S is a saturation component, V is a brightness component, pixels of the saturation component S > S1 and the brightness component V > V1 are set to be 0, and the value range of S1 and V1 is 0-0.4; and the identification sub-module is used for identifying the non-0 pixel as the target pollution pattern.
A computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method of any of the preceding claims.
Example 1
(1) Acquiring a first satellite image of 9 months in 2020 (as shown in fig. 2);
(2) Performing radiation correction on the satellite image by using a radiation calibration coefficient, performing atmospheric correction on the satellite image by using a FLAASH atmospheric correction method, performing orthographic correction on the satellite image by using RPC parameters, and performing geometric fine correction on the image by manually selecting a control point to obtain a multispectral reflectivity product subjected to geometric correction (as shown in figure 3);
(3) Extracting a water area range by using the NDWI water body index, and extracting a multispectral image of the water area range by using the water area range as a mask (as shown in figure 4);
(4) Calculating variance of each pixel, and setting pixels with variance smaller than 50 to 0;
(5) After carrying out communication treatment on non-0 pixels, calculating the morphological index of each image spot, and setting the pixels with the morphological index larger than 0.018 (different area values are determined according to empirical values) to be 0;
(6) Performing RGB-HSV conversion on non-0 pixels, and setting the pixels with saturation (S) greater than 0.18 and brightness (V) greater than 0.2 to 0;
(7) A non-0 patch is output, i.e., the identified contaminated area (region) (see fig. 5).
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (5)
1. The water pollution area identification method based on the multispectral image is characterized by comprising the following steps of:
Step 1: acquiring a spectrum image of a target water area, and converting the spectrum image into a spectrum difference image D through a spectrum difference function D (lambda 1,λ2,λ3,...,λn);
step 2: based on the spectrum difference image, a pollution probability distribution map P is obtained by utilizing a difference classification function F;
step 3: setting a threshold value, and extracting a target pollution map spot from the pollution probability distribution map P;
The spectrum difference function D (lambda 1,λ2,λ3,...,λn) in the step 1 is extracted from n spectrum data of a spectrum image, wherein n is more than or equal to 1;
The difference classification function F in the step 2 eliminates interference factors of the spectrum difference image through image features of the target; the difference classification function F is F (I, A, C, D), wherein I is a component representing the reflection intensity, A, C is the area and perimeter respectively;
The pollution probability distribution map P is obtained by the following steps:
Step 2.1: setting the pixel with the spectrum difference value larger than 0 as 1, performing open operation on the image, eliminating the isolated pixel, and communicating adjacent image spots;
step 2.2: calculating the area A and the perimeter C of the pattern spots, and calculating the morphological index S=A/C;
Step 2.3: calculating an intensity component I, wherein I is near infrared reflectivity or brightness component;
Step 2.4: calculating a pollution probability distribution map p=d×s (1-I);
the step 3 is specifically performed by the following steps:
Step 3.1: calculating a morphological index C of a communicating pattern spot, wherein C=A/L, A is the area of the pattern spot, L is the perimeter of the pattern spot, the pixel where the pattern spot with C being larger than C1 is positioned is set as 0 for removing water surface noise, and the value range of C1 is 0-0.05;
Step 3.2: performing RGB-HSV conversion on the connected image spots, wherein H is a tone component, S is a saturation component, V is a brightness component, pixels of the saturation component S > S1 and the brightness component V > V1 are set to be 0, and the value range of S1 and V1 is 0-0.4;
step 3.3: and the non-0 pixel is the identification result of the polluted area.
2. The multispectral image-based water-contaminated area identification method according to claim 1, wherein: the spectrum difference image D (lambda i) of the ith wave band in the spectrum difference function D (lambda 1,λ2,λ3,...,λn) in the step 1 is obtained by calculating the difference of the spectrum data of each grid unit.
3. A multi-spectral image-based water contamination zone identification system, comprising:
The spectrum difference analysis module is used for acquiring a spectrum image of the target water area and converting the spectrum image into a spectrum difference image D through a spectrum difference function D (lambda 1,λ2,λ3,...,λn);
the difference classification module is used for acquiring a pollution probability distribution map P by utilizing a difference classification function F based on the spectrum difference image;
the pollution area extraction module is used for setting a threshold value and extracting a target pollution map spot from the pollution probability distribution map P;
The spectrum difference function D (lambda 1,λ2,λ3,...,λn) in the spectrum difference analysis module is extracted from n spectrum data of a spectrum image, wherein n is more than or equal to 1;
The difference classification function F is F (I, A, C, D), wherein I is a component representing the reflection intensity, A, C is the area and perimeter respectively;
The pollution probability distribution map P is obtained by the following steps:
Step 2.1: setting the pixel with the spectrum difference value larger than 0 as 1, performing open operation on the image, eliminating the isolated pixel, and communicating adjacent image spots;
step 2.2: calculating the area A and the perimeter C of the pattern spots, and calculating the morphological index S=A/C;
Step 2.3: calculating an intensity component I, wherein I is near infrared reflectivity or brightness component;
Step 2.4: calculating a pollution probability distribution map p=d×s (1-I);
The difference classification function F in the difference classification module eliminates interference factors of the light difference image through image features of the target;
the polluted region extraction module specifically adopts the following steps:
Step 3.1: calculating a morphological index C of a communicating pattern spot, wherein C=A/L, A is the area of the pattern spot, L is the perimeter of the pattern spot, the pixel where the pattern spot with C being larger than C1 is positioned is set as 0 for removing water surface noise, and the value range of C1 is 0-0.05;
Step 3.2: performing RGB-HSV conversion on the connected image spots, wherein H is a tone component, S is a saturation component, V is a brightness component, pixels of the saturation component S > S1 and the brightness component V > V1 are set to be 0, and the value range of S1 and V1 is 0-0.4;
step 3.3: and the non-0 pixel is the identification result of the polluted area.
4. A multispectral image-based water contamination zone identification system in accordance with claim 3, wherein: the spectrum difference image D (lambda i) of the ith wave band in the spectrum difference function D (lambda 1,λ2,λ3,...,λn) in the spectrum difference analysis module is obtained by calculating the difference of the spectrum data of each grid unit.
5. A computer-readable storage medium having stored thereon a computer program, characterized by: the computer program implementing the steps of the method of any of claims 1 or 2 when executed by a processor.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110624211.2A CN113177979B (en) | 2021-06-04 | 2021-06-04 | Multispectral image-based water pollution area identification method and multispectral image-based water pollution area identification system |
| PCT/CN2021/098513 WO2022252242A1 (en) | 2021-06-04 | 2021-06-07 | Multispectral image-based water pollution area identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110624211.2A CN113177979B (en) | 2021-06-04 | 2021-06-04 | Multispectral image-based water pollution area identification method and multispectral image-based water pollution area identification system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113177979A CN113177979A (en) | 2021-07-27 |
| CN113177979B true CN113177979B (en) | 2024-07-09 |
Family
ID=76927449
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110624211.2A Active CN113177979B (en) | 2021-06-04 | 2021-06-04 | Multispectral image-based water pollution area identification method and multispectral image-based water pollution area identification system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113177979B (en) |
| WO (1) | WO2022252242A1 (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114993965B (en) * | 2022-05-13 | 2023-04-18 | 中煤嘉沣(湖南)环保科技有限责任公司 | Automatic pollution source identification method and system |
| CN116310870A (en) * | 2023-03-16 | 2023-06-23 | 江苏电子信息职业学院 | Object detection classification method, system and storage medium based on hyperspectral image |
| CN116109946B (en) * | 2023-04-13 | 2023-08-01 | 中国人民解放军战略支援部队航天工程大学 | Hyperspectral image anomaly detection method and system for ocean background |
| CN116187204B (en) * | 2023-04-23 | 2023-08-04 | 武汉新烽光电股份有限公司 | Risk decision method for water area remote sensing inversion water environment pollution |
| CN117036222B (en) * | 2023-08-18 | 2024-04-19 | 广东省水利水电科学研究院 | Water body detection method, device and medium for fusing multi-scale polarized SAR images |
| CN117030634B (en) * | 2023-10-09 | 2023-12-12 | 深圳市盘古环保科技有限公司 | Quick detection and repair method for groundwater pollution |
| CN117233116B (en) * | 2023-11-09 | 2024-02-02 | 江西鼎智检测有限公司 | Water quality analysis method and system based on machine vision |
| CN117330521B (en) * | 2023-12-01 | 2024-02-20 | 黑龙江中医药大学 | Clinical laboratory uses blood smear system |
| CN117671300B (en) * | 2023-12-07 | 2024-04-26 | 广东晨晖新材料科技有限公司 | Quality inspection early warning method and system for melamine impregnated paper production |
| CN118447028B (en) * | 2024-07-10 | 2024-09-24 | 浙江大学长三角智慧绿洲创新中心 | Membrane surface pollution monitoring method, device, equipment and medium based on image analysis |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109284709A (en) * | 2018-09-19 | 2019-01-29 | 南京大学 | A kind of offshore spilled oil optical remote sensing detection method different based on credit light reflection difference |
| CN111307727A (en) * | 2020-03-13 | 2020-06-19 | 生态环境部卫星环境应用中心 | Water body water color abnormity identification method and device based on time sequence remote sensing image |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105761286A (en) * | 2016-02-29 | 2016-07-13 | 环境保护部卫星环境应用中心 | Water color exception object extraction method and system based on multi-spectral remote sensing image |
| CN107992891B (en) * | 2017-12-01 | 2022-01-25 | 西安电子科技大学 | Multispectral remote sensing image change detection method based on spectral vector analysis |
| CN111398176B (en) * | 2020-03-13 | 2020-11-20 | 生态环境部卫星环境应用中心 | Water body water color abnormity remote sensing identification method and device based on pixel scale characteristics |
| CN111426637A (en) * | 2020-04-16 | 2020-07-17 | 江苏省环境监测中心 | Method for acquiring water quality parameters of urban black and odorous rivers by using unmanned aerial vehicle |
-
2021
- 2021-06-04 CN CN202110624211.2A patent/CN113177979B/en active Active
- 2021-06-07 WO PCT/CN2021/098513 patent/WO2022252242A1/en active Application Filing
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109284709A (en) * | 2018-09-19 | 2019-01-29 | 南京大学 | A kind of offshore spilled oil optical remote sensing detection method different based on credit light reflection difference |
| CN111307727A (en) * | 2020-03-13 | 2020-06-19 | 生态环境部卫星环境应用中心 | Water body water color abnormity identification method and device based on time sequence remote sensing image |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022252242A1 (en) | 2022-12-08 |
| CN113177979A (en) | 2021-07-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113177979B (en) | Multispectral image-based water pollution area identification method and multispectral image-based water pollution area identification system | |
| CN108009542B (en) | Weed image segmentation method in rape field environment | |
| CN109919083B (en) | Early automatic winter wheat mapping method based on Sentinel-2 image data | |
| Elvidge et al. | Relative radiometric normalization of Landsat Multispectral Scanner (MSS) data using an automatic scattergram-controlled regression | |
| CN110674735B (en) | Agricultural facility remote sensing extraction method and device based on fine classification | |
| CN112414950B (en) | Insulator equivalent salt deposit density detection method cooperating with hyperspectral and infrared technologies | |
| CN111832518B (en) | Space-time fusion-based TSA remote sensing image land utilization method | |
| CN112766075A (en) | Hyperspectral remote sensing black and odorous water body grading method based on semi-supervised learning strategy | |
| CN117115077B (en) | Lake cyanobacteria bloom detection method | |
| CN112396019A (en) | Vegetation distribution identification method and system based on unmanned aerial vehicle and readable storage medium | |
| CN112964643B (en) | Method for correcting landform falling shadow of visible light wave band of remote sensing image | |
| CN114612794A (en) | Remote sensing identification method for land covering and planting structure in finely-divided agricultural area | |
| CN109300133B (en) | Urban river network area water body extraction method | |
| CN113450425B (en) | Urban black and odorous water body remote sensing drawing method based on shadow removal | |
| CN113887324A (en) | Fire point detection method based on satellite remote sensing data | |
| CN114067222B (en) | Urban water body remote sensing classification method and device | |
| CN109682821B (en) | Citrus surface defect detection method based on multi-scale Gaussian function | |
| CN113096114B (en) | High-resolution urban water body pattern spot remote sensing extraction method combining morphology and index | |
| CN115311556A (en) | Remote sensing image processing method and system for natural resource management | |
| CN116337781A (en) | Sorghum variety identification method based on spectral image reconstruction | |
| CN117571660A (en) | Betel nut yellowing degree determination method, betel nut yellowing degree determination device, electronic equipment and medium | |
| CN116429724A (en) | Method for detecting pollution degree of composite insulator material based on infrared hyperspectral analysis | |
| CN114881984A (en) | Detection method and device for rice processing precision, electronic equipment and medium | |
| CN115792919A (en) | Method for identifying pollution hot spot area through horizontal scanning and monitoring of aerosol laser radar | |
| CN115601596B (en) | Drawing method and device for recognizing forest felling distribution after fire |
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 |