CN113837078B - Determination method for artemia distribution in water body - Google Patents
Determination method for artemia distribution in water body Download PDFInfo
- Publication number
- CN113837078B CN113837078B CN202111119322.4A CN202111119322A CN113837078B CN 113837078 B CN113837078 B CN 113837078B CN 202111119322 A CN202111119322 A CN 202111119322A CN 113837078 B CN113837078 B CN 113837078B
- Authority
- CN
- China
- Prior art keywords
- artemia
- index
- image
- distribution
- wave band
- 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 84
- 238000000034 method Methods 0.000 title claims abstract description 34
- 241001247197 Cephalocarida Species 0.000 title abstract 9
- 208000031513 cyst Diseases 0.000 claims abstract description 35
- 239000011159 matrix material Substances 0.000 claims abstract description 18
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims abstract description 7
- 241000238582 Artemia Species 0.000 claims description 123
- 238000002310 reflectometry Methods 0.000 claims description 33
- 238000012937 correction Methods 0.000 claims description 14
- 238000011160 research Methods 0.000 claims description 13
- 230000000007 visual effect Effects 0.000 claims description 10
- 230000003595 spectral effect Effects 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 8
- 238000012952 Resampling Methods 0.000 claims description 4
- 238000003066 decision tree Methods 0.000 claims description 4
- 230000004927 fusion Effects 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 3
- 235000013601 eggs Nutrition 0.000 claims 4
- 241001672739 Artemia salina Species 0.000 claims 2
- 238000000605 extraction Methods 0.000 abstract description 15
- 238000004364 calculation method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 150000003839 salts Chemical class 0.000 description 4
- 241000238631 Hexapoda Species 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 239000012267 brine Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- HPALAKNZSZLMCH-UHFFFAOYSA-M sodium;chloride;hydrate Chemical compound O.[Na+].[Cl-] HPALAKNZSZLMCH-UHFFFAOYSA-M 0.000 description 2
- 241000238426 Anostraca Species 0.000 description 1
- PMZURENOXWZQFD-UHFFFAOYSA-L Sodium Sulfate Chemical compound [Na+].[Na+].[O-]S([O-])(=O)=O PMZURENOXWZQFD-UHFFFAOYSA-L 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000010446 mirabilite Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/80—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in fisheries management
- Y02A40/81—Aquaculture, e.g. of fish
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The application discloses a method for determining artemia distribution in a water body, which comprises the following steps: s1, acquiring and processing a data source, namely acquiring an image data source distributed by artemia in a water body and preprocessing the data source; s2, constructing and calculating indexes, namely constructing artemia indexes based on the characteristics of water bodies and artemia ooworm reflected waves, and carrying out band operation based on the constructed artemia indexes to obtain an index gray scale image to determine artemia distribution; s3, evaluating the precision, namely extracting artemia cysts from the artemia distribution index gray level images, randomly selecting sample points on the basis of the extraction result, and verifying the precision of the classification result of the images by adopting a confusion matrix method.
Description
Technical Field
The application relates to the technical field of image recognition, in particular to a method for determining the distribution of artemia in a water body.
Background
Artemia, also known as brine artemia, are widely distributed in salt lakes and brine ponds in salt fields around the world, and have different forms and colors, and appear white in low salinity water bodies and red in high salinity water bodies. In recent years, environmental damage and excessive fishing caused by artemia ooworm resource fishing, for example, the 2018 Aibi lake is remedied, and artemia salvage by any unit and person is prohibited. Artemia as "soft gold" are expensive in international markets, and if reasonably caught, they can bring considerable economic benefits.
Aiming at the dynamic monitoring of the water body, scholars at home and abroad propose various algorithms such as a single-band method, a difference value method, a ratio method, a normalized vegetation index method, an enhanced vegetation index method and the like.
The algorithms are essentially developed by combining the remote sensing technology, but at present, researches on the combination of artemia and the remote sensing technology at home and abroad are not reported.
Disclosure of Invention
The application provides a method for determining the distribution of artemia in a water body, which comprises the following steps:
s1, acquiring and processing a data source, namely acquiring an image data source distributed by artemia in a water body and preprocessing the data source;
s2, constructing and calculating indexes, namely constructing artemia indexes based on the characteristics of water bodies and artemia egg and insect reflectivity, and performing band operation based on the constructed artemia indexes to obtain an index gray scale image to determine artemia distribution;
s3, evaluating the precision, namely determining artemia distribution index gray level images to extract artemia cysts, randomly selecting sample points on the basis of the extraction result, and verifying the precision of the classification result of the images by adopting a confusion matrix method.
Further, in the step S1, the data source acquisition and processing includes the image of the investigation region photographed from GF-1WFV sensor, sentinel No. 2 MSI sensor, HY-1C CZI sensor and Landsat 8OLI sensor, and the data source preprocessing includes the resampling of the image, the orthographic correction, the radiometric calibration, the image cropping and the atmospheric correction.
Further, in the data source obtained from the GF-1WFV sensor, the green light wave band is 0.5-0.6 μm, the near infrared wave band is 0.76-0.9 μm, and the central wavelength of the reflection wave band comprises 0.485 μm, 0.555 μm, 0.660 μm and 0.830 μm.
Further, from the data sources obtained from the sentinel No. 2 MSI sensor and the HY-1C CZI sensor, the green light wave band is 0.5-0.6 μm, the near infrared wave band is 0.76-0.9 μm, and the center wavelength of the reflection wave band comprises 0.460 μm, 0.560 μm, 0.650 μm, 0.825 μm, 0.490 μm, 0.560 μm, 0.665 μm and 0.842 μm.
Further, in the acquisition of the data source from the Landsat 8OLI sensor, the green light band is 0.5-0.6 μm, the near infrared band is 0.76-0.9 μm, and the center wavelength of the reflection band includes 0.440 μm, 0.480 μm, 0.560 μm, 0.655 μm, 0.865 μm, 1.610 μm, 2.200 μm.
Further, in the step S2, the artemia index is constructed based on the characteristics of the water body and artemia cysts in the index construction and operation, specifically, the difference of the water body is larger than the difference of artemia cysts areas based on the difference of the reflectivities of the green light wave band and the near infrared wave band; after the reflection values of the green light wave band and the near infrared wave band are added, the value of the artemia cysts area is larger than the value of the water body, and the mathematical expression is constructed as follows:
wherein R is GBS 、R NBS The reflectivity of artemia cysts at green light and near infrared wave bands; r is R GEbi 、R NEbi The reflectivity of the water area in green light and near infrared wave bands is obtained;
after normalization operation, a result is obtained
In the green light and near infrared wave bands, whether the difference value operation or the normalization operation is carried out, the artemia values are smaller than the water body values;
performing square operation on the basis of the existing difference value, and further expanding the difference between the two categories to construct an index;
artemia index was constructed as follows:
R Green 、R NIR the reflectivity of green light and near infrared wave bands in the image are respectively;
normalized water index
The artemia index BSI can be reduced to: bsi= (R Green -R NIR )*NDWI。
Further, in the step S2, the band operation is performed based on the constructed artemia index in the index construction and operation to obtain an index gray image, so as to determine artemia distribution, specifically, the band Math function in ENVI5.3 is utilized to perform the band operation according to the BSI artemia index, so as to obtain a gray image of the research area, the lake water is in a brighter state as a whole, the position of the highlight lake water is brightest, the dark lake water area is gray, and the clearly visible black area is the artemia ooworm zone.
Step S3, randomly selecting sample points in the precision evaluation, namely randomly selecting the sample points on the basis of the sample points by combining artemia indexes with different ground object spectral characteristics through decision tree functions in ENVI and carrying out extraction of artemia egg worm bands by matching with visual interpretation; the method comprises the steps of carrying out accuracy verification on the classification result of the image by adopting a Confusion Matrix method, specifically utilizing a fusion Matrix function in ENVI software, carrying out category discrimination on each sample point by combining visual interpretation to obtain a mixed Matrix of the image, and then determining whether the overall classification accuracy of the image is higher than a threshold value or not so as to determine whether artemia indexes effectively extract artemia egg worm information or not.
The method has the beneficial effects that the method can analyze the spectral characteristics of the artemia cysts in the images, construct the artemia cysts extraction index suitable for multispectral images, analyze the extraction precision and effect of the artemia cysts extraction index, and can provide assistance for the reasonable capturing and yield estimation of the subsequent artemia cysts resources.
The present application is further illustrated below with reference to examples.
Detailed Description
The embodiment of the application discloses a method for determining the distribution of artemia in a water body, which comprises the following steps:
s1, acquiring and processing a data source, namely acquiring an image data source distributed by artemia in a water body and preprocessing the data source;
s2, constructing and calculating indexes, namely constructing artemia indexes based on the characteristics of water bodies and artemia ooworm reflected waves, and carrying out band operation based on the constructed artemia indexes to obtain an index gray scale image to determine artemia distribution;
s3, evaluating the precision, namely extracting artemia cysts from the artemia distribution index gray level images, randomly selecting sample points on the basis of the extraction result, and verifying the precision of the classification result of the images by adopting a confusion matrix method.
The method can analyze spectral characteristics of artemia cysts in the images, construct an extraction index of artemia cysts suitable for multispectral images, analyze extraction precision and effect of the artemia cysts index, and can provide assistance for reasonable fishing of subsequent artemia cysts and estimation of yield.
In a specific implementation, in the step S1, the data source acquisition and processing includes image resampling, orthographic correction, radiometric calibration, image cropping and atmospheric correction of the research area captured by GF-1WFV sensor, sentry No. 2 MSI sensor, HY-1C CZI sensor and Landsat 8OLI sensor.
In the data source obtained from GF-1WFV sensor, the green light wave band is 0.5-0.6 μm, the near infrared wave band is 0.76-0.9 μm, and the central wavelength of the reflection wave band comprises 0.485 μm, 0.555 μm, 0.660 μm and 0.830 μm. In the data sources obtained from the sentinel No. 2 MSI sensor and the HY-1C CZI sensor, the green light wave band is 0.5-0.6 μm, the near infrared wave band is 0.76-0.9 μm, and the central wavelength of the reflection wave band comprises 0.460 μm, 0.560 μm, 0.650 μm, 0.825 μm, 0.490 μm, 0.560 μm, 0.665 μm and 0.842 μm. The data source is obtained from Landsat 8OLI sensor, the green light wave band is 0.5-0.6 μm, the near infrared wave band is 0.76-0.9 μm, and the central wavelength of the reflection wave band comprises 0.440 μm, 0.480 μm, 0.560 μm, 0.655 μm, 0.865 μm, 1.610 μm, 2.200 μm.
In the specific implementation, in the step S2, the artemia index is constructed based on the characteristics of the reflected wave of the artemia cysts and the water body in the index construction and operation, specifically, the difference of the water body is larger than the difference of the artemia cysts and the water body based on the difference of the reflectivity of the green light wave band and the reflectivity of the near infrared wave band; after the reflection values of the green light wave band and the near infrared wave band are added, the value of the artemia cysts area is larger than the value of the water body, and the mathematical expression is constructed as follows:
wherein R is GBS 、R NBS The reflectivity of artemia cysts at green light and near infrared wave bands; r is R GEbi 、R NEbi The reflectivity of the water area in green light and near infrared wave bands is obtained;
after normalization operation, a result is obtainedIn the green light and near infrared wave bands, whether the difference value operation or the normalization operation is carried out, the artemia values are smaller than the water body values;
performing square operation on the basis of the existing difference value, and further expanding the difference between the two categories to construct an index;
artemia index was constructed as follows:
R Green 、R NIR the reflectivity of green light and near infrared wave bands in the image are respectively;
normalized water indexThe artemia index BSI can be reduced to: bsi= (R Green -R NIR )*NDWI。
In a specific implementation, in the step S2, the Band operation is performed based on the constructed artemia index in the index construction and operation to obtain an index gray scale image to determine artemia distribution, specifically, the Band Math function in ENVI5.3 is utilized to perform the Band operation according to the BSI artemia index to obtain a gray scale image of the research area, the lake water is in a brighter state as a whole, the position of the highlight lake water is brightest, the dark lake water area is gray, and the clearly visible black colored area is the artemia ooworm zone.
In the specific implementation, in the step S3, sample points are randomly selected in the precision evaluation through a decision tree function in the ENVI, artemia indexes are combined with different ground object spectral characteristics, visual interpretation is matched for extracting artemia egg worm belts, and the sample points are randomly selected on the basis; the method comprises the steps of carrying out accuracy verification on the classification result of the image by adopting a Confusion Matrix method, specifically utilizing a fusion Matrix function in ENVI software, carrying out category discrimination on each sample point by combining visual interpretation to obtain a mixed Matrix of the image, and then determining whether the overall classification accuracy of the image is higher than a threshold value or not so as to determine whether artemia indexes effectively extract artemia egg worm information or not.
The application of the present application is illustrated by the following specific examples: in the implementation, the water body is selected from the Xinjiang Aibi lake as a research area, wherein the Aibi lake is the salt water lake with the largest Xinjiang, the area is 1443.7km2, the area of the lake water is 562.2km2, the elevation of the lake surface is 189m, and the water body is the core area of the economic zone of the silk road. The artemia cysts of the Aibi lake are rich in resources, and along with the rising of the fishery cultivation industry in China, the demand for artemia cysts is increased, so that the economic development of the Aibi lake is driven. In implementation, S1, data source acquisition and processing, specifically, acquiring an image data source of artemia distribution in a water body and preprocessing the data source: the multi-source remote sensing satellite image of the Aibi lake in 5.30.2019 is selected for extracting artemia cysts and the used multi-source satellite data source information is shown in table 1.
TABLE 1 data Source information
Image data preprocessing is accomplished with ENVI5.3 software, including resampling, orthographic correction, radiometric scaling, image cropping, and atmospheric correction. The L1 level data of domestic series satellites are not subjected to aggregate correction and have a certain deviation from the actual ground object, so that the high-resolution first-order image is required to be subjected to orthographic correction through an RPC parameter file carried by the downloaded data and the digital elevation data with the global 900m resolution of ENVI software, and the correction precision is controlled within 1 pixel. The high-resolution first image is obtained through a China resource satellite application center (http:// www.cresda.com/CN /); the HY-1C image is downloaded from a China sea satellite data service system (https:// osdds. Nsoas. Org. Cn /); landsat-8 satellite images were obtained from usgs netting (https:// earthoxplorer. Usgs. Gov /). The research area is cut out on the downloaded satellite image by utilizing the cutting function, the radiometric calibration and the atmospheric correction are performed by utilizing the Radiometric Calibration and FLAASH Atmospheric Correction functions of ENVI5.3, and the parameters are acquired from the image data file. The sentinel No. 2 data used in the application are L1C-level data provided by the European-air office network (https:// scihub. Copernicus. Eu /), and the sentinel No. 2 image is required to be converted into L2A-level data through Sen2Cor software. The data of the sentinel number 2L 2A contains the atmospheric bottom layer reflectivity data after the atmospheric correction.
In the implementation, S2, constructing and operating indexes, specifically constructing artemia indexes based on the characteristics of water bodies and artemia ooworm reflected waves, and performing band operation based on the constructed artemia indexes to obtain an index gray scale image to determine artemia distribution:
in order to facilitate the construction and research of artemia indexes, four types of ground objects such as lake water, highlight lake water, dark lake water, artemia egg and insect belts and the like are selected for visual interpretation of a high-score first, a sentinel second and an Aibi lake water area research area in a Landsat 8 image in 5 months and 30 days of 2019. The highlight lake water and the dark lake water are divided according to the brightness of the lake water in the image. The method comprises the steps of collecting 100 groups of samples of four ground objects on images of a research area shot by three sensors, calculating average reflectivity of each ground object in each wave band of the three sensors, drawing a multi-source satellite image spectral reflectivity curve of each ground object, and obtaining the trend of the reflectivity of each ground object from the spectral reflectivity curves of the ground objects of different sensors to be in a trend of rising and then falling in a blue-near infrared wave band. From the overall reflectivity, the reflectivity of all features is generally highest in the green light wave band, the reflectivity of the high-resolution first-order and second-order sentry images is lowest in the near infrared wave band, and the reflectivity of the Landsat-8 image is lowest in the short-wave infrared 2. Because the water body has the characteristic of strong absorption in the infrared and near infrared bands, the reflectivity of the water body is reduced from the red light band, and the high-brightness lake water has stronger reflection effect due to solar flare and mirabilite precipitation due to higher salt content of the Aibi lake, even if the reflectivity of the water body is slightly higher than that of artemia cysts in the red light band. The reflectivity value of the artemia cysts is higher than that of the water body at the near infrared band. According to the analysis and the spectral characteristics of different ground objects, the main biological artemia in the Aibi lake region have obvious reflectivity difference between a green light wave band and a near infrared wave band and the Aibi lake water, and the construction of the normalized water body index NDWI is also based on the green light wave band and the near infrared wave band, so that the difference can be enlarged by carrying out wave band operation on the combination of the green light wave band and the near infrared wave band and the normalized water body index NDWI, thereby extracting artemia strips in the Aibi lake.
The difference of the water body and the artemia cysts is larger than the difference of artemia cysts in the green light wave band and the near infrared wave band as can be seen by the difference of the reflectivities of the water body and the artemia cysts; and after the reflection value of the green light wave band and the near infrared wave band is added, the value of the artemia cysts area is larger than the value of the water body, and the mathematical expression is as follows:
wherein R is GBS 、R NBS The reflectivity of artemia cysts at green light and near infrared wave bands; r is R GEbi 、R NEbi Is the reflectivity of the Aibi lake water in green light and near infrared bands. After normalization operation, a result is obtainedThe difference value calculation or normalization calculation can be carried out on the green light and the near infrared wave bands, and the artemia cysts are smaller than the water body, so that square calculation can be carried out on the basis of the existing difference value, and the difference between the two types of values is further enlarged, so that an index is constructed.
In summary of the above analysis, artemia index (Brine Shrimp Index, BSI) was constructed as follows:
the BSI is artemia index constructed based on GF-1WFV image, R Green 、R NIR The reflectivity of green light and near infrared band in GF-1WFV image. Normalized water indexThe artemia index BSI can be reduced to:
BSI＝(R Green -R NIR )*NDWI。
in order to avoid visual influence of surrounding ground objects and tidal beaches in lakes after index calculation, water area mask extraction is carried out on research areas of different sensor satellite images in 5 months and 30 days in 2019. And (3) carrying out Band Math function in ENVI5.3 software based on the extracted Aibi lake water domain, and carrying out Band operation according to BSI artemia indexes to obtain a gray scale image of the research area. The lake water is in a brighter state as a whole, the highlight lake water is the brightest, and the dark lake water area appears gray. The black colored area which is clearly visible in the image is the artemia cysts area, and is positioned at the northeast part of the lake and near the river bank in the image.
In the implementation, S3, evaluating the precision, namely extracting artemia cysts from the artemia distribution index gray level images, randomly selecting sample points on the basis of the extraction result, and performing precision verification on the classification result of the images by adopting a confusion matrix method:
through decision tree function in ENVI, use BSI artemia index to combine different ground object spectral characteristics, cooperate with visual interpretation to carry out the extraction of artemia ooworm area, can clearly judge through the local amplification of extraction result diagram, three kinds of sensors are good to the artemia ooworm area extraction result in the image of 5 months of 2019 30, and wherein the extraction effect of Landsat-8 OLI satellite is the best.
300 sample points are randomly selected in a research area of the three images, and classification results of the three images are respectively verified in precision by adopting a confusion matrix method. And carrying out category discrimination on each sample point by using a fusion Matrix tool in ENVI software in combination with visual interpretation to obtain a mixed Matrix of three images, wherein the mixed Matrix is shown in tables 2-4. The overall accuracy of the high-resolution first-order image is 89.40%, and the Kappa coefficient is 0.82; the overall accuracy of the sentinel number 2 image is 89.97%, and the Kappa coefficient is 0.83; the overall precision of the Landsat-8 image was 91.69% and the Kappa coefficient was 0.86.
The overall classification accuracy of the images obtained by the three sensors is higher than 89%, which indicates that the BSI artemia index can effectively extract artemia ooworm information.
TABLE 2 GF-1 image classification accuracy
TABLE 3 Sentinel-2 image classification accuracy
TABLE 4 Landsat-8 image classification accuracy
Claims (7)
1. The method for determining the artemia distribution of the water body is characterized by comprising the following steps:
s1, acquiring and processing a data source, namely acquiring an image data source distributed by artemia in a water body and preprocessing the data source;
s2, constructing and calculating indexes, namely constructing artemia indexes based on the characteristics of water bodies and artemia ooworm reflected waves, and carrying out band operation based on the constructed artemia indexes to obtain an index gray scale image to determine artemia distribution;
s3, evaluating the precision, namely randomly selecting sample points on the basis of determining artemia distribution index gray level images, and verifying the precision of the classification result of the images by adopting a confusion matrix method;
step S2, constructing artemia indexes based on the characteristics of the reflectivity of the water body and artemia eggs in the index construction and operation, and using the difference between the reflectivity of the green light wave band and the reflectivity of the near infrared wave band, wherein the difference of the water body is larger than the difference of the artemia eggs areas; after the reflection values of the green light wave band and the near infrared wave band are added, the value of the artemia cysts area is larger than the value of the water body, and the mathematical expression is constructed as follows:
wherein R is GBS 、R NBS The reflectivity of artemia cysts at green light and near infrared wave bands; r is R GEbi 、R NEbi The reflectivity of the water area in green light and near infrared wave bands is obtained;
after normalization operation, a result is obtained
In the green light and near infrared wave bands, whether the difference value operation or the normalization operation is carried out, the artemia values are smaller than the water body values;
performing square operation on the basis of the existing difference value, and further expanding the difference between the two categories to construct an index;
artemia index was constructed as follows:
R Green 、R NIR the reflectivity of green light and near infrared wave bands in the image are respectively;
normalized water index
Artemia index BSIThe simplification is as follows: bsi= (R Green -R NIR )*NDWI。
2. The method for determining artemia distribution in water according to claim 1, wherein in step S1, the data source is obtained and processed, wherein the data source includes study area images obtained from GF-1WFV sensor, sentinel No. 2 MSI sensor, HY-1C CZI sensor, and Landsat 8OLI sensor, and the data source preprocessing includes image resampling, orthographic correction, radiometric calibration, image cropping, and atmospheric correction.
3. The method for determining the artemia distribution in the water body according to claim 2, wherein the green light wave band is 0.5-0.6 μm, the near infrared wave band is 0.76-0.9 μm, and the central wavelength of the reflection wave band comprises 0.485 μm, 0.555 μm, 0.660 μm and 0.830 μm in the data source obtained from the GF-1WFV sensor.
4. The method for determining the artemia distribution in the water body according to claim 2, wherein the green light wave band is 0.5-0.6 μm, the near infrared wave band is 0.76-0.9 μm, the central wavelength of the reflection wave band comprises 0.460 μm, 0.560 μm, 0.650 μm, 0.825 μm, 0.490 μm, 0.560 μm, 0.665 μm, 0.842 μm in the data source obtained from the sentinel No. 2 MSI sensor and the HY-1C CZI sensor.
5. The method for determining artemia salina distribution in water according to claim 2, wherein the green light wave band is 0.5-0.6 μm, the near infrared wave band is 0.76-0.9 μm, and the central wavelength of the reflection wave band comprises 0.440 μm, 0.480 μm, 0.560 μm, 0.655 μm, 0.865 μm, 1.610 μm, 2.200 μm in the data source obtained from the Landsat 8OLI sensor.
6. The method for determining the artemia distribution in water according to claim 1, wherein in the step S2, the artemia distribution is determined by performing Band operation based on the constructed artemia index in the index construction and operation to obtain an index gray image, specifically, by using Band Math function in ENVI5.3, performing Band operation according to BSI artemia index to obtain a gray image of a research area, wherein the lake water is in a brighter state as a whole, the highlight lake water is brightest, the dark lake water area is gray, and the clearly visible black color area is the artemia egg worm zone.
7. The method for determining artemia salina distribution in water body according to claim 1, wherein in the step S3, the sample points are randomly selected in the precision evaluation by using artemia index in combination with different ground object spectral characteristics through decision tree function in ENVI, and extracting artemia cysts strips by matching with visual interpretation, and the sample points are randomly selected on the basis; the method comprises the steps of carrying out accuracy verification on the classification result of the image by adopting a Confusion Matrix method, specifically utilizing a fusion Matrix function in ENVI software, carrying out category discrimination on each sample point by combining visual interpretation to obtain a mixed Matrix of the image, and then determining whether the overall classification accuracy of the image is higher than a threshold value or not so as to determine whether artemia indexes effectively extract artemia egg worm information or not.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111119322.4A CN113837078B (en) | 2021-09-24 | 2021-09-24 | Determination method for artemia distribution in water body |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111119322.4A CN113837078B (en) | 2021-09-24 | 2021-09-24 | Determination method for artemia distribution in water body |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113837078A CN113837078A (en) | 2021-12-24 |
| CN113837078B true CN113837078B (en) | 2024-02-02 |
Family
ID=78969626
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111119322.4A Active CN113837078B (en) | 2021-09-24 | 2021-09-24 | Determination method for artemia distribution in water body |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113837078B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018028191A1 (en) * | 2016-08-10 | 2018-02-15 | 福州大学 | Tavi calculation method based on waveband ration model and solar elevation angle |
| CN108592888A (en) * | 2018-04-23 | 2018-09-28 | 中国科学院地球化学研究所 | A kind of Residential area extraction method |
-
2021
- 2021-09-24 CN CN202111119322.4A patent/CN113837078B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018028191A1 (en) * | 2016-08-10 | 2018-02-15 | 福州大学 | Tavi calculation method based on waveband ration model and solar elevation angle |
| CN108592888A (en) * | 2018-04-23 | 2018-09-28 | 中国科学院地球化学研究所 | A kind of Residential area extraction method |
Non-Patent Citations (2)
| Title |
|---|
| 中国内陆盐湖卤虫资源开发利用的研究;马志珍，陈汇远，武振彬，张可为;海洋水产研究(第01期);全文 * |
| 基于面向对象法艾比湖卤虫信息提取;李微;刘伟男;贾越平;刘洪洋;汤勇;;国土资源遥感(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113837078A (en) | 2021-12-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105957079B (en) | Lake waters information extracting method based on Landsat OLI multispectral image | |
| CN112183209B (en) | Regional crop classification method and system based on multidimensional feature fusion | |
| CN112287871B (en) | Near-shore aquaculture area remote sensing image extraction method based on multi-feature and spectrum fusion | |
| CN113033670B (en) | Rice planting area extraction method based on Sentinel-2A/B data | |
| CN111462223B (en) | Sentinel-2 image-based planting area identification method for soybeans and corns in Jianghuai region | |
| Shi et al. | Detection of coastal saline land uses with multi-temporal Landsat images in Shangyu City, China | |
| Ahmad | A review of remote sensing data change detection: Comparison of Faisalabad and Multan Districts, Punjab Province, Pakistan | |
| Yang et al. | Evaluating AISA+ hyperspectral imagery for mapping black mangrove along the South Texas Gulf Coast | |
| CN110189043B (en) | Usable land resource analysis system based on high-score satellite remote sensing data | |
| CN112884029B (en) | Collaborative classification method integrating fully-polarized SAR and hyperspectral remote sensing | |
| CN114724049A (en) | Inland culture pond water surface identification method based on high-resolution remote sensing image data | |
| CN116883853B (en) | Crop space-time information remote sensing classification method based on transfer learning | |
| Xu et al. | Automatic detection of algal blooms using sentinel-2 MSI and Landsat OLI images | |
| Visitacion et al. | Detection of algal bloom in the coastal waters of boracay, philippines using Normalized Difference Vegetation Index (NDVI) and Floating Algae Index (FAI) | |
| CN114724035A (en) | Early water bloom detection method based on remote sensing technology | |
| KR101050067B1 (en) | Aquaculture detection from satellite image | |
| CN113837078B (en) | Determination method for artemia distribution in water body | |
| Li et al. | Development of a real-time fruit recognition system for pineapple harvesting robots | |
| Davaasuren et al. | Extent and health of mangroves in Lac Bay Bonaire using satellite data | |
| Araya et al. | A comparison of pixel and object-based land cover classification: a case study of the Asmara region, Eritrea | |
| CN116645593A (en) | Remote sensing method and device for monitoring seaweed bed distribution | |
| Zhuang et al. | A Method for water body extraction based on the tasselled cap transformation from remote sensing images | |
| Xie et al. | Object-oriented random forest classification for Enteromorpha prolifera detection with SAR images | |
| CN114119618A (en) | Remote sensing extraction method for inland salt lake artemia strips based on deep learning | |
| CN112949607A (en) | Wetland vegetation feature optimization and fusion method based on JM Relief F |
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 |