CN110390277A - Complex Underlying Surface identifying water boy method and black and odorous water prediction technique - Google Patents
Complex Underlying Surface identifying water boy method and black and odorous water prediction technique Download PDFInfo
- Publication number
- CN110390277A CN110390277A CN201910599445.9A CN201910599445A CN110390277A CN 110390277 A CN110390277 A CN 110390277A CN 201910599445 A CN201910599445 A CN 201910599445A CN 110390277 A CN110390277 A CN 110390277A
- Authority
- CN
- China
- Prior art keywords
- water
- vector quantization
- area
- patch
- grid
- 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.)
- Granted
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 273
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000001228 spectrum Methods 0.000 claims abstract description 28
- 239000013598 vector Substances 0.000 claims description 181
- 238000013139 quantization Methods 0.000 claims description 175
- 238000002310 reflectometry Methods 0.000 claims description 28
- 238000004891 communication Methods 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 10
- 210000000746 body region Anatomy 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 7
- 230000001052 transient effect Effects 0.000 claims description 6
- 244000025254 Cannabis sativa Species 0.000 claims description 3
- 230000003595 spectral effect Effects 0.000 abstract description 5
- 244000144977 poultry Species 0.000 description 16
- 244000144972 livestock Species 0.000 description 15
- 239000003344 environmental pollutant Substances 0.000 description 9
- 231100000719 pollutant Toxicity 0.000 description 9
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000002474 experimental method Methods 0.000 description 5
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 3
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 description 3
- 210000000476 body water Anatomy 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000013604 expression vector Substances 0.000 description 3
- 229910052757 nitrogen Inorganic materials 0.000 description 3
- 229910052698 phosphorus Inorganic materials 0.000 description 3
- 239000011574 phosphorus Substances 0.000 description 3
- VMXUWOKSQNHOCA-UKTHLTGXSA-N ranitidine Chemical compound [O-][N+](=O)\C=C(/NC)NCCSCC1=CC=C(CN(C)C)O1 VMXUWOKSQNHOCA-UKTHLTGXSA-N 0.000 description 3
- 239000002689 soil Substances 0.000 description 3
- 241000218691 Cupressaceae Species 0.000 description 2
- 238000012271 agricultural production Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 241000208340 Araliaceae Species 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 241001494479 Pecora Species 0.000 description 1
- 241000282898 Sus scrofa Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 239000010426 asphalt Substances 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000029142 excretion Effects 0.000 description 1
- 239000003337 fertilizer Substances 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- JEGUKCSWCFPDGT-UHFFFAOYSA-N h2o hydrate Chemical compound O.O JEGUKCSWCFPDGT-UHFFFAOYSA-N 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- -1 meadow Substances 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/194—Terrestrial scenes using hyperspectral data, i.e. more or other wavelengths than RGB
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The embodiment of the invention provides a kind of Complex Underlying Surface identifying water boy method and Complex Underlying Surface black and odorous water prediction techniques, the SPECTRAL DIVERSITY and temperature difference of water body and background information in target area are fully considered, the highway information figure in combining target region, Land-use figure, multi-spectrum remote sensing image and Thermal Remote Sensing Image, identify the water body distributed intelligence in target area, pitchy highway is eliminated in obtained water body distributed intelligence, the roof of black, the information such as burn pattern, keep recognition result more accurate, and Accurate Prediction goes out black and odorous water on this basis.
Description
Technical field
The present invention relates to eco hydrologies and remote sensing technology field, more particularly, to Complex Underlying Surface identifying water boy side
Method and black and odorous water prediction technique.
Background technique
Urbanization region includes the building areas such as bridge, house, office, the vegetation-covered areas such as meadow, forest land, river, lake
Equal Humid Areas, the road areas such as cement road, dirt road and asphalt road, complicated urbanization region causes its underlying surface also very multiple
It is miscellaneous.Towards water and eco-environmental management, carry out Complex Underlying Surface accurately water body information, and carries out on this basis black smelly
Water body prediction is extremely important.
Remote sensing technology is considered as the maximally efficient method of identifying water boy.Currently, about identifying water boy Remote Sensing Model with
It mainly include land use classes method, water body index method, artificial intelligence, water colour parameter inversion method etc. in method, these
Method plays very big effect in different regions and using angle.However, these methods face Complex Underlying Surface identifying water boy
When, it is easy to propose the target of spectrum phase Sihe bar shaped, such as the roof of pitchy highway, black, burn pattern information as water body
It takes out.
Therefore in the remote sensing technique of current various identifying water boys, when towards Complex Underlying Surface, water body is easy to cause to mention
Taking has very big uncertainty.
Summary of the invention
In order to overcome the problems referred above or it at least is partially solved the above problem, the embodiment of the invention provides under a kind of complexity
Pad face identifying water boy method and black and odorous water prediction technique.
In a first aspect, the embodiment of the invention provides a kind of Complex Underlying Surface identifying water boy methods, comprising:
Obtain highway information figure, Land-use figure, multi-spectrum remote sensing image and the thermal infrared remote sensing of target area
Image；
Based on the multi-spectrum remote sensing image, the initial water area in the target area is determined, and be based on the public affairs
Road hum pattern, the Land-use figure and the Thermal Remote Sensing Image, are identified from the initial water area
Water body distributed intelligence in the target area.
Preferably, described to be based on the multi-spectrum remote sensing image, it determines the initial water area in the target area, has
Body includes:
Calculate the corresponding improved normalized difference water body index of each grid in the multi-spectrum remote sensing image or water body
Extracting index；
If judgement knows that the improved normalized difference water body index is more than or equal to the first preset threshold or the water
Body extracting index is more than or equal to the second preset threshold, and corresponding grid is made first kind label, all grid for making first kind label
Trellis is at the initial water area.
Preferably, described to be based on the highway information figure, the Land-use figure and the thermal infrared remote sensing shadow
Picture identifies the water body distributed intelligence in the target area from the initial water area, specifically includes:
The highway information figure and the Land-use figure are subjected to rasterizing, it is each in the highway information figure
In the size of grid, the Land-use figure in the size Yu the initial water area of each grid each grid ruler
It is very little all the same；
The highway information figure is superimposed in the initial water area, and by the initial water area with it is described
The grid of highway overlapping in highway information figure makees the second class label, obtains the second water area after label；By second water
Body region is superimposed in the Land-use figure, and by the Land-use figure with the second water area weight
Folded grid makees the second class label, obtains third water area after label；
The Thermal Remote Sensing Image is superimposed in the third water area, in the third water area
Each grid calculates the average temperature value of the normalized differential vegetation index and water body in the grid, if the grid are known in judgement
The average temperature value of water body is more than or equal to third predetermined threshold value in lattice, and the normalized differential vegetation index is within a preset range, then
The grid is made into third class label；
Make the grid that third class marks from removal in all grids that the first kind marks is made in the third water area, and
Remaining grid is made into the 4th class label, the grid for making the 4th class label in the third water area is subjected to vector quantization, is obtained
Vector quantization is as a result, the vector quantization result includes multiple vector quantization patches；
Default shade overlay area is deducted from all vector quantization patches in the vector quantization result, is deducted described default
The distributed intelligence of all vector quantization patches obtained behind shade overlay area is the water body distributed intelligence in the target area；
Wherein, the default shade overlay area is based on the vector quantization result and digital elevation on multiple and different time points
Model determines that the average temperature value of water body is greater than the 4th preset threshold and is less than the third in the default shade overlay area
Preset threshold.
Preferably, each grid in the third water area calculates being averaged for water body in the grid
Temperature value specifically includes:
Vegetation based on every kind of vegetation for including in the corresponding temperature value of the grid, the grid under different coverages
Area value, vegetation average temperature value, building area area value, building area average temperature value, the grid for including in the grid
In include pitchy highway area value, pitchy highway average temperature value and the grid in include coverage of water value, calculate
The average temperature value of water body in the grid.
Preferably for each grid in the third water area, if the flat of water body in the grid is known in judgement
Equal temperature value is less than or equal to the 4th preset threshold, then the grid is made the second class label.
Second aspect provides in the embodiment of the present invention a kind of based on Complex Underlying Surface identifying water boy described in first aspect
The Complex Underlying Surface black and odorous water prediction technique that method is realized, comprising:
For deducting each vector quantization patch obtained behind the default shade overlay area, the vector quantization patch is made
5th class label, if the vector quantization patch is known in judgement, the relative area changing value at adjacent two moment is more than or equal to the 5th in advance
If threshold value, and the area at the vector quantization patch forward moment in adjacent two moment is less than or equal to the 6th preset threshold, and institute
The average temperature value for stating water body in vector quantization patch is greater than the 4th preset threshold and is less than the third predetermined threshold value, then the arrow
Quantization patch corresponds to black and odorous water, and the vector quantization patch is made the 6th class label；From all vector quantizations for making the 5th class label
The vector quantization patch for making the 6th class label is deducted in patch, and remainder vector patch is made into the 7th class label；
For making each vector quantization patch of the 7th class label, if judgement knows that the area of the vector quantization patch is less than
In the 6th preset threshold, and in the vector quantization patch, the average temperature value of water body is greater than the 4th preset threshold and small
In the third predetermined threshold value, and in the target area, the non-point pollution source strength of water body is arrived with corresponding non-point pollution source
Each the sum of ratio of distance of vector quantization patch for making the 7th class label is less than or equal to the 7th preset threshold, then the vector quantization
Patch corresponds to black and odorous water, and the vector quantization patch is made the 6th class label.
Preferably, Complex Underlying Surface black and odorous water prediction technique further include:
For making each vector quantization patch of the 7th class label, if the ratio of the vector quantization patch perimeter and area is less than
Equal to the 8th preset threshold, the ratio between the area variance and area mean value of the vector quantization patch within a preset period of time is big
In being equal to the 9th preset threshold, temperature mean value of the vector quantization patch in the preset time period is more than or equal to the described 8th
The length of preset threshold, the preset time period is more than or equal to the tenth preset threshold, then the vector quantization patch corresponds to black smelly water
The vector quantization patch is made the 6th class label by body.
Preferably, Complex Underlying Surface black and odorous water prediction technique further include:
All vector quantization patches for making the 6th class label in all vector quantization patches for making the 7th class label are deducted, it will be remaining
Vector quantization patch makees the 8th class label；
It obtains and makees the Multi-spectral Remote Sensing Data that all vector quantization patches of the 8th class label include, for making the 8th class label
Each vector quantization patch, calculate the vector quantization patch the of the reflectivity of green light band and the reflectivity of near infrared band
Second difference of the reflectivity of the reflectivity and blue wave band of one difference and green light band, and acquire first difference and
The result of product of second difference；If the result of product is less than or equal to the 11st preset threshold, the vector quantization patch
The vector quantization patch is made the 6th class label by corresponding black and odorous water.
The third aspect, the embodiment of the invention provides a kind of electronic equipment, comprising:
At least one processor, at least one processor, communication interface and bus；Wherein,
The processor, memory, communication interface complete mutual communication by the bus；
The memory is stored with the program instruction that can be executed by the processor, and the processor calls described program to refer to
It enables, it is black smelly to execute the Complex Underlying Surface identifying water boy method that first aspect provides or the Complex Underlying Surface that second aspect provides
Water body prediction technique.
Fourth aspect, the embodiment of the invention provides a kind of non-transient computer readable storage medium, the non-transient meter
Calculation machine readable storage medium storing program for executing stores computer instruction, and the computer instruction makes the computer to execute first aspect offer
The Complex Underlying Surface black and odorous water prediction technique that Complex Underlying Surface identifying water boy method or second aspect provide.
A kind of Complex Underlying Surface identifying water boy method provided in an embodiment of the present invention and the prediction of Complex Underlying Surface black and odorous water
Method has fully considered the SPECTRAL DIVERSITY and temperature difference of water body and background information in target area, combining target region
Highway information figure, Land-use figure, multi-spectrum remote sensing image and Thermal Remote Sensing Image, are identified in target area
Water body distributed intelligence eliminates the information such as pitchy highway, the roof of black, burn pattern in obtained water body distributed intelligence, makes
Recognition result is more accurate.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of flow diagram of Complex Underlying Surface identifying water boy method provided in an embodiment of the present invention；
Fig. 2 is a kind of flow diagram of Complex Underlying Surface black and odorous water prediction technique provided in an embodiment of the present invention；
Fig. 3 is the structural schematic diagram of a kind of electronic equipment provided in an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
In the description of the embodiment of the present invention, it should be noted that term " first ", " second ", " third " are only used for retouching
Purpose is stated, relative importance is not understood to indicate or imply.
As shown in Figure 1, the embodiment of the invention provides a kind of Complex Underlying Surface identifying water boy methods, comprising:
S11 obtains highway information figure, Land-use figure, multi-spectrum remote sensing image and the thermal infrared of target area
Remote sensing image；
S12 is based on the multi-spectrum remote sensing image, determines the initial water area in the target area, and be based on institute
Highway information figure, the Land-use figure and the Thermal Remote Sensing Image are stated, is known from the initial water area
It Chu not water body distributed intelligence in the target area.
Specifically, the Complex Underlying Surface identifying water boy method provided in the embodiment of the present invention, it is therefore an objective to accurately determine mesh
The water body distributed intelligence in region is marked, the information such as pitchy highway, the roof of black, burn pattern is avoided to go out as Clean water withdraw
Come.Wherein, underlying surface is the solid-state ground of atmosphere and its lower bound or the interface of the liquid water surface, is the main heating source and water of atmosphere
Vapour source and the boundary face of lower atmosphere layer movement.An important factor for underlying surface is weather formation, refers in heat, momentum and water
In vapour exchange process with the earth surface of atmospheric interaction (soil, meadow, water body etc.), underlay surface properties to atmospheric temperature,
Humidity, wind etc. have a significant impact.Target area refers to area to be studied, and target area includes highway, house, river, mountains and rivers etc.
Object needs the water body by river in target area to be different from the quilts such as pitchy highway, the roof of black and burn pattern
Accurately extract.
Step S11 is first carried out, obtains the highway information figure, Land-use figure, multispectral remote sensing shadow of target area
Picture and Thermal Remote Sensing Image.Wherein, include in highway information figure is the highway information in target area, including highway is long
Degree, width and trend etc..Include in Land-use figure is the Land-use in target area, and land use is
Refer to that the mankind purposefully develop and use the activities of land resource, Land-use may include the house in target area
Position and area, the position of vegetation and area, the position of exposed soil and area etc..The target area obtained in the embodiment of the present invention
Highway information figure, the size of Land-use figure and resolution ratio are all the same.Multi-spectrum remote sensing image refers to using with two
The sensor in a above wave spectrum channel synchronizes the image that imaging obtains, multi-spectrum remote sensing image to the atural object in target area
In may include the wave bands such as feux rouges, green light, blue light and short-wave infrared, near-infrared remotely-sensed data.Thermal Remote Sensing Image is
Refer to that carrying out infrared imaging to the atural object in target area using satellite obtains image, may include that heat is red in Thermal Remote Sensing Image
The remotely-sensed data of wave section, and carry the temperature value of corresponding position.Remotely-sensed data in the embodiment of the present invention refers to target area
The reflectivity of earth's surface in domain.It should be noted that multi-spectrum remote sensing image and thermal infrared remote sensing shadow in the embodiment of the present invention
Image as being a kind of rasterizing, wherein each pixel is a grid.
Then, step S12 is executed, multi-spectrum remote sensing image is based on, determines the initial water area in the target area,
The Water-Body Information in target area is primarily determined out by the Multi-spectral Remote Sensing Data for including in multi-spectrum remote sensing image.This can
To be determined according to the method provided in the prior art, this is not especially limited in the embodiment of the present invention.
Finally, in conjunction with highway information figure, Land-use figure and Thermal Remote Sensing Image, from initial water area
The water body distributed intelligence in target area is recognized accurately.In conjunction with highway information figure, the public affairs in initial water area can be excluded
Road part can exclude the land use part in initial water area, in conjunction with thermal infrared remote sensing in conjunction with Land-use figure
Image can exclude the part of initial water area medium temperature degree exception, and finally obtained water body distributed intelligence is compared to initial water
Water body distributed intelligence in body region is more accurate.
The Complex Underlying Surface identifying water boy method provided in the embodiment of the present invention, fully considered in target area water body and
The SPECTRAL DIVERSITY and temperature difference of background information, it is the highway information figure in combining target region, Land-use figure, multispectral
Remote sensing image and Thermal Remote Sensing Image identify the water body distributed intelligence in target area, obtained water body distributed intelligence
In eliminate the information such as pitchy highway, the roof of black, burn pattern, keep recognition result more accurate.
On the basis of the above embodiments, the Complex Underlying Surface identifying water boy method provided in the embodiment of the present invention, it is described
Based on the multi-spectrum remote sensing image, determines the initial water area in the target area, specifically includes:
Calculate the corresponding improved normalized difference water body index of each grid in the multi-spectrum remote sensing image or water body
Extracting index；
If judgement knows that the improved normalized difference water body index is more than or equal to the first preset threshold or the water
Body extracting index is more than or equal to the second preset threshold, and corresponding grid is made first kind label, all grid for making first kind label
Trellis is at the initial water area.
Specifically, in the embodiment of the present invention, initial water area is obtained by multi-spectrum remote sensing image, to obtain initial water
Body region, the first corresponding improved normalized difference water body index of each grid in calculating multi-spectrum remote sensing image
(Normalized Difference Water Index, MNDWI) and Clean water withdraw index.
The corresponding MNDWI of each grid can reflectivity based on green light band in Multi-spectral Remote Sensing Data and shortwave it is red
The reflectivity of wave section determines, specific as shown in formula (1).
Wherein, RgFor the reflectivity of green light band, RswirFor the reflectivity of short infrared wave band.
For the multi-spectrum remote sensing image of high-resolution, feux rouges, green light, blue light and near-infrared four comprising visible light
The Multi-spectral Remote Sensing Data of a wave band.The corresponding Clean water withdraw index (WI) of each grid can be based on the reflection of green light band
The reflectivity of rate, the reflectivity of red spectral band and near infrared band determines, specific as shown in formula (2).
Wherein, RnirFor the reflectivity of near infrared band, RrFor the reflectivity of red spectral band.
For each grid c in multi-spectrum remote sensing image, (1≤c≤C, C are to wrap in multi-spectrum remote sensing image after rasterizing
The grid quantity contained), if judgement knows that the corresponding MNDWI of grid c is more than or equal to the first preset threshold a1Or grid c is corresponding
WI is more than or equal to the second preset threshold a2, then grid c is made into first kind label, the attribute for making grid after first kind label can be denoted as
ST1.The grid that all properties are ST1 forms initial water body region.Wherein, a1It is to be determined by the value of single parameter MNDWI
Threshold value when whether being water body, a2It is the threshold value determined whether when being water body by the value of single parameter WI.a1And a2It is specific
Value can be determined by experiment, and be not specifically limited herein in the embodiment of the present invention.
On the basis of the above embodiments, the Complex Underlying Surface identifying water boy method provided in the embodiment of the present invention, it is described
Based on the highway information figure, the Land-use figure and the Thermal Remote Sensing Image, from the initial water body area
The water body distributed intelligence in the target area is identified in domain, is specifically included:
The highway information figure and the Land-use figure are subjected to rasterizing, it is each in the highway information figure
In the size of grid, the Land-use figure in the size Yu the initial water area of each grid each grid ruler
It is very little all the same；
The highway information figure is superimposed in the initial water area, and by the initial water area with it is described
The grid of highway overlapping in highway information figure makees the second class label, obtains the second water area after label；By second water
Body region is superimposed in the Land-use figure, and by the Land-use figure with the second water area weight
Folded grid makees the second class label, obtains third water area after label；
The Thermal Remote Sensing Image is superimposed in the third water area, in the third water area
Each grid calculates the average temperature value of the normalized differential vegetation index and water body in the grid, if the grid are known in judgement
The average temperature value of water body is more than or equal to third predetermined threshold value in lattice, and the normalized differential vegetation index is within a preset range, then
The grid is made into third class label；
Make the grid that third class marks from removal in all grids that the first kind marks is made in the third water area, and
Remaining grid is made into the 4th class label, the grid for making the 4th class label in the third water area is subjected to vector quantization, is obtained
Vector quantization is as a result, the vector quantization result includes multiple vector quantization patches；
Default shade overlay area is deducted from all vector quantization patches in the vector quantization result, is deducted described default
The distributed intelligence of all vector quantization patches obtained behind shade overlay area is the water body distributed intelligence in the target area；
Wherein, the default shade overlay area is based on the vector quantization result and digital elevation on multiple and different time points
Model determines that the average temperature value of water body is greater than the 4th preset threshold and is less than the third in the default shade overlay area
Preset threshold.
Specifically, highway information figure, Land-use figure and Thermal Remote Sensing Image are combined in the embodiment of the present invention,
When water body distributed intelligence in identification object region, executes following steps and realize.
1) highway information figure and Land-use figure are subjected to rasterizing, for guarantee subsequent step go on smoothly and
Highway information figure, Land-use figure and initial water area can be overlapped, when carrying out rasterizing, grid
Size should all be identical.
2) highway information figure is superimposed in initial water area, and will be in initial water area and in highway information figure
The grid of highway overlapping makees the second class label, and the attribute for making grid after the second class marks can be denoted as ST2.The second water is obtained after label
Body region, the second water area at this time can regard dark target information as.
3) the second water area is superimposed in Land-use figure, replaces same position in Land-use figure
Atural object, uncovered terrain object attribute is constant in Land-use figure, then by Land-use figure with the second water body
The grid of region overlapping makees the second class label, and attribute ST2 obtains third water after Land-use figure is marked
Body region.Third water area is actually updated Land-use figure.
The grid and vector that can be specifically ST1 by attribute, if the grid that attribute is ST2 falls on the arrow that attribute is ST1
When in spirogram, i.e., it is ST2 that declared attribute, which is the attribute of all grids of the vector map combining of ST1,.
4) Thermal Remote Sensing Image is superimposed in third water area, for each grid d in third water area
(1≤d≤D, D are the grid quantity in third water area), the normalized differential vegetation index (Normalized in computation grid d
Difference Vegetation Index, NDVI) and water body average temperature value Twd.Wherein, NDVI can be according to existing
The method provided in technology determines that the water body in grid d refers to first in the target area determined based on multi-spectrum remote sensing image
Region of the beginning water area in grid n, the average temperature value T of water body in grid dwnIt can be according to the corresponding thermal infrared of grid d
Remotely-sensed data is determined.If the average temperature value T of water body in grid dwdMore than or equal to third predetermined threshold value a3, i.e. Twd≥
a3, NDVI within a preset range, i.e. b1≤NDVI≤b2, then grid d is made into third class label, the attribute of grid d is ST3.Its
In, a3、b1And b2It is constant, can be determined according to experiment, a3For characterizing the minimum value of the corresponding mean temperature of non-water body, b1
And b2For characterizing the minimum value and maximum value of the corresponding NDVI of non-water body.Thus obtained attribute is all grid of ST3
Lattice indicate non-water body.
5) grid that attribute is ST3 is removed from all grids that attribute in third water area is ST1, and by remaining grid
Lattice make the 4th class label, and the attribute of remaining grid is ST4.At this point, all grids that attribute is ST4 indicate water body.By third
The grid that attribute is ST4 in water area carries out vector quantization, obtains vector quantization as a result, since the type of water body in target area can
To include different types of water body such as lake water, river, it includes multiple in predeterminable area that every kind of water body, which also may include multiple,
Lake, a plurality of river etc..Therefore vector quantization result includes multiple vector quantization patches, each vector quantization patch indicates a water body water
The attribute in face, each vector quantization patch is ST4.
6) vector quantization on multiple and different time points is obtained as a result, the change of each water body water surface of different time points can be compared
Change situation, the region that the region bigger for hypsography, i.e. the water body water surface change greatly, by being superimposed digital elevation model
(DEM) it can determine a shade overlay area, and can further estimate shade area coverage.If in shade overlay area
The average temperature value of water body is greater than the 4th preset threshold a4And it is less than third predetermined threshold value a3, then shade overlay area is defined as
Default shade overlay area.a4For constant, can be determined according to experiment, the maximum value of the mean temperature for characterizing water body.
Default shade overlay area is deducted in all vector quantization patches in vector quantization result from 5), deducts default yin
The distributed intelligence of all vector quantization patches obtained behind shadow overlay area is the water body distributed intelligence in target area.
It should be noted that in the embodiment of the present invention 4) in can also generate spatial resolution with Thermal Remote Sensing Image
The identical grid of specification, i.e., the size of a pixel is identical in the size with Thermal Remote Sensing Image of each grid in grid, this
In grid be a vector quantization grid.Then Thermal Remote Sensing Image is superimposed in grid, and grid is superimposed to
In three water areas.
On the basis of the above embodiments, the Complex Underlying Surface identifying water boy method provided in the embodiment of the present invention, it is described
For each grid d in the third water area, the average temperature value of water body in computation grid d is specifically included:
Tree and grass coverage based on every kind of vegetation for including in the corresponding temperature value of grid d, grid d under different coverages
Value, vegetation average temperature value, the building area area value for including in grid d, building area average temperature value, the cypress for including in grid d
The coverage of water value for including in oily highway area value, pitchy highway average temperature value and grid d, water body in computation grid d
Average temperature value Twd。
Specifically, if mainly by the forest land, meadow, building of different coverages in each pixel of Thermal Remote Sensing Image
Object, road and water body composition, since the spatial resolution of multi-spectrum remote sensing image is higher than the spatial discrimination of Thermal Remote Sensing Image
Rate, therefore can indicate a thermal infrared pixel of Thermal Remote Sensing Image in the embodiment of the present invention by following formula (3)
Temperature value.
Wherein,TmixFor thermal infrared pixel
Temperature value, SvijFor tree and grass coverage value of i-th of vegetation type under j-th of coverage for including in thermal infrared pixel, Tvij
For vegetation mean temperature of i-th of vegetation type under j-th of coverage for including in thermal infrared pixel, m is thermal infrared pixel
In include vegetation type sum, n be thermal infrared pixel in include coverage value quantity；ScTo include in thermal infrared pixel
Building area area value, TcFor the building area average temperature value for including in thermal infrared pixel, SbFor the cypress for including in thermal infrared pixel
Oily highway area value, TbFor the pitchy highway average temperature value for including in thermal infrared pixel, SwFor the water for including in thermal infrared pixel
Honorable product value, TwFor the water body average temperature value for including in thermal infrared pixel, ε is global error value, SpFor the face of thermal infrared pixel
Product value, εcFor the temperature error of building area, εbFor the temperature error of pitch, εvFor the temperature error of vegetation, εwFor the temperature of water body
Error, ε, εc、εb、εv、εwIt is constant.
By formula (3) it is found that the water body average temperature value T for including in thermal infrared pixelwSpecifically:
Due to Thermal Remote Sensing Image spatial resolution be greater than multi-spectrum remote sensing image spatial resolution, one
Multiple grids can be corresponded in thermal infrared pixel, determine that the water body for including in each thermal infrared pixel is average according to formula (4)
Temperature value Tw, then in the thermal infrared pixel corresponding each grid water body average temperature value TwdIt is all the same, it is Tw。
On the basis of the above embodiments, the Complex Underlying Surface identifying water boy method provided in the embodiment of the present invention, for
Each grid d in the third water area, if the average temperature value T of water body in grid d is known in judgementwdLess than or equal to the 4th
Preset threshold a4, i.e. Twd≤a4, illustrate that grid d indicates water body, and be non-black and odorous water, then grid d made into the second class label,
The attribute of grid d is ST2.
As shown in Fig. 2, providing one kind on the basis of the above embodiments, in the embodiment of the present invention based on the above embodiment
The Complex Underlying Surface black and odorous water prediction technique that the Complex Underlying Surface identifying water boy method of middle offer is realized, comprising:
S21, for deducting each vector quantization patch obtained behind the default shade overlay area, by the vector quantization spot
Block makees the 5th class label, if the vector quantization patch is known in judgement, the relative area changing value at adjacent two moment is more than or equal to the
Five preset thresholds, and the area at the vector quantization patch forward moment in adjacent two moment is less than or equal to the 6th preset threshold,
And the average temperature value of water body is greater than the 4th preset threshold and is less than the third predetermined threshold value, then institute in the vector quantization patch
It states vector quantization patch and corresponds to black and odorous water, the vector quantization patch is made into the 6th class label；From all arrows for making the 5th class label
Quantify to deduct the vector quantization patch for making the 6th class label in patch, remainder vector patch is made into the 7th class label；
S22, for making each vector quantization patch of the 7th class label, if judgement knows that the area of the vector quantization patch is small
In equal to the 6th preset threshold, and in the vector quantization patch, the average temperature value of water body is greater than the 4th preset threshold
And it is less than the third predetermined threshold value, and the non-point pollution source strength of water body and corresponding non-point pollution in the target area
The sum of the ratio of distance of vector quantization patch of source to each work the 7th class label is less than or equal to the 7th preset threshold, then the arrow
Quantization patch corresponds to black and odorous water, and the vector quantization patch is made the 6th class label.
Specifically, it covers in the embodiment of the present invention deducting default shade from all vector quantization patches in vector quantization result
It is realized on the basis of cover area.
Firstly, execute S21, for deduct each vector quantization patch e obtained behind default shade overlay area (1≤e≤E,
E is the quantity of vector quantization patch in vector quantization result), vector quantization patch e is made into the 5th class label, attribute ST5, if judgement
Know that vector quantization patch e meets following formula (5), (6), (7), then vector quantization patch e corresponds to black and odorous water, by vector quantization patch
E makees the 6th class label, attribute HC1.
|Se,t-Se,t+1|/Se,t≥a5 (5)
Se,t≤a6 (6)
a4< Twe< a3 (7)
Wherein, Se,tArea for vector quantization patch e in t moment, Se,t+1Area for vector quantization patch e at the t+1 moment,
a5For the 5th preset threshold, a6For the 6th preset threshold, a5And a6It is constant, specific value, which can according to need, to be set,
This is not especially limited in the embodiment of the present invention.Formula (5) indicates that vector quantization patch e becomes in the relative area at adjacent two moment
Change value is more than or equal to a5, the area of formula (6) expression vector quantization patch e forward moment t in adjacent two moment is less than or equal to a6,
Formula (7) indicates the average temperature value T of water body in vector quantization patch eweGreater than a4And it is less than a3。
The vector quantization patch that attribute is HC1 is deducted in all vector quantization patches that dependence is ST5, by remainder vector spot
Block makees the 7th class label, and the attribute of remainder vector patch is ST6.
Analyze the vector quantization patch that attribute is ST6:
By the residential area in land-use map, farmland, culture zone equal distribution area vector quantization；
Using the binary model of non-point pollution, the non-point pollution source strength Q of each non-point pollution source r is estimatedr(1≤r≤
R, R are the quantity in the non-point pollution source of water body in target area)；
The basin perimeter figure comprising non-point pollution area and water body distributed area is obtained, while analyzing non-point pollution source place
Region and water body flow direction analyze, analysis non-point pollution source and water body whether there is connectivity, if non-point pollution source
The runoff of generation can not flow to vector quantization patch, then determine that the vector quantization patch is non-black and odorous water, attribute is changed to ST2.
If non-point pollution source generate runoff may flow to vector quantization patch, need to judge non-point pollution source with
The distance between vector quantization patch.Execute S22.
S22, (1≤e1≤E1, E1 are the vector quantization spots that attribute is ST6 to each vector quantization patch e1 for being ST6 for attribute
The quantity of block), if judgement knows that vector quantization patch e1 meets following formula (8), (9), (10), vector quantization patch e1 corresponds to black
Vector quantization patch e1 is made the 6th class label, attribute HC1 by smelly water body.
Se1,t≤a6 (9)
a4< Twe1< a3 (10)
Wherein, Le1For non-point pollution source r to the distance of vector quantization patch e1, a7It is constant, tool for the 7th preset threshold
Body value, which can according to need, to be set, and is not especially limited in the embodiment of the present invention to this.Se1,tFor vector quantization patch e1
In the area of t moment, Twe1For the average temperature value of water body in vector quantization patch e1.Formula (8) indicates water body in target area
Non-point pollution source strength QrThe vector quantization patch e1 distance L for being ST6 with corresponding non-point pollution source r to attributee1Ratio
The sum of be less than or equal to a7, the area of formula (9) expression vector quantization patch e1 is less than or equal to a6, formula (10) expression vector quantization patch
The average temperature value T of water body in e1we1Greater than a4And it is less than a3。
Non-point pollution source strength QrThe discharge amount of as each pollution type is the ginseng that solubilised state pollutional load calculates
Number.The pollution of farmland production, 4 kinds of rural residential area, urban runoff and livestock and poultry cultivation pollution types is carried out in the embodiment of the present invention
Source strength calculates.
(1) agricultural production
Wherein, Qr1The Non-point Source Pollutants total emission volumn generated for agricultural production；F1 is agrotype, and F1 is agrotype
Quantity；G1 is agriculture pollutants pointer type, mainly includes 3 seed type of total nitrogen, total phosphorus and ammonia nitrogen, and G1 is pollutant index class
The quantity of type；Af1For the area of the f1 agrotype, ωf1g1It is the f1 agrotype in g1 kind pollutant pointer type
Under source strength coefficient；M is correction factor, including the gradient, soil, chemical fertilizer and precipitation amendment.
(2) livestock and poultry cultivation
Wherein, Qr2The Non-point Source Pollutants total emission volumn generated for livestock and poultry cultivation；F2 is livestock and poultry cultivation type, mainly includes
Draught animal, 4 seed type of pig, sheep and poultry, F2 are the quantity of livestock and poultry cultivation type；G2 is Pollution from livestock and poultry object pointer type,
It mainly include total nitrogen, 4 seed type of total phosphorus, COD and ammonia nitrogen, G2 is the quantity of Pollution from livestock and poultry object pointer type；Cf2For f2
The livestock and poultry quantity of a livestock and poultry cultivation type；Df2For the breeding cycle of the f2 livestock and poultry cultivation type, kf2For the f2 livestock and poultry cultivation
The excrement excretion index of type, ωf2g2It is the f2 livestock and poultry cultivation type under g2 kind Pollution from livestock and poultry object pointer type
Source strength coefficient；ηf2g2For turnover rate of the f2 livestock and poultry cultivation type under g2 kind Pollution from livestock and poultry object pointer type.
(3) rural residential area and urban settlement
Wherein, Qr2The Non-point Source Pollutants total emission volumn generated for rural residential area and urban settlement；G3 is rural area residence
People's point and urban settlement pollutant pointer type, mainly include total nitrogen, 4 seed type of total phosphorus, COD and ammonia nitrogen, and G3 is rural area residence
The quantity of people's point and urban settlement pollutant pointer type；P is the size of population of rural residential area and urban settlement；ωg3
For the source strength coefficient under g3 kind rural residential area and urban settlement pollutant pointer type.
A kind of Complex Underlying Surface black and odorous water prediction technique is provided in the embodiment of the present invention, based on the above embodiment in mention
The Complex Underlying Surface identifying water boy method of confession is realized, can go out black and odorous water with Accurate Prediction.
On the basis of the above embodiments, the Complex Underlying Surface black and odorous water prediction technique provided in the embodiment of the present invention,
Further include:
For making each vector quantization patch of the 7th class label, if the ratio of the vector quantization patch perimeter and area is less than
Equal to the 8th preset threshold, the ratio between the area variance and area mean value of the vector quantization patch within a preset period of time is big
In being equal to the 9th preset threshold, temperature mean value of the vector quantization patch in the preset time period is more than or equal to the described 8th
The length of preset threshold, the preset time period is more than or equal to the tenth preset threshold, then the vector quantization patch corresponds to black smelly water
The vector quantization patch is made the 6th class label by body.
Specifically, in the embodiment of the present invention, each vector quantization patch e1 for being ST6 for attribute, if vector quantization patch e1
Meet following formula (14), (15), (16), (17), then vector quantization patch e1 corresponds to black and odorous water, and vector quantization patch e1 is made the
Six classes label, attribute HC1.
t2-t1≥a10 (17)
Wherein, Ce1For the perimeter of vector quantization patch e1, Se1For the area of vector quantization patch e1, a8For the 8th preset threshold,
For constant, it can according to need and set, this is not especially limited in the embodiment of the present invention.For vector quantization patch
E1 is in preset time period t2-t1Interior area variance,It is vector quantization patch e1 in preset time period t2-t1Interior area is equal
Value, a9It is constant for the 9th preset threshold, can according to need experiment and determine, this is not limited specifically in the embodiment of the present invention
It is fixed.It is vector quantization patch e1 in preset time period t2-t1Interior temperature averages, a10It is constant for the tenth preset threshold,
It can according to need experiment to determine, this be not especially limited in the embodiment of the present invention.Formula (14) indicates vector quantization patch e1
Perimeter and area ratio be less than or equal to a8, vector quantization patch e1 is in t for formula (15) expression2-t1Interior area variance and area
Ratio between mean value is more than or equal to a9, vector quantization patch e1 is in t for formula (16) expression2-t1Interior temperature mean value is more than or equal to
a8, the length t of formula (17) the expression preset time period2-t1More than or equal to a10。
On the basis of the above embodiments, the Complex Underlying Surface black and odorous water prediction technique provided in the embodiment of the present invention,
Further include:
All vector quantization patches for making the 6th class label in all vector quantization patches for making the 7th class label are deducted, it will be remaining
Vector quantization patch makees the 8th class label；
The corresponding Multi-spectral Remote Sensing Data of all vector quantization patches for making the 8th class label is obtained, for making the 8th class label
Each vector quantization patch, calculate the vector quantization patch the of the reflectivity of green light band and the reflectivity of near infrared band
Second difference of the reflectivity of the reflectivity and blue wave band of one difference and green light band, and acquire first difference and
The result of product of second difference；If the result of product is less than or equal to the 11st preset threshold, the vector quantization patch
The vector quantization patch is made the 6th class label by corresponding black and odorous water.
Specifically, it is all arrows that attribute is HC1 in all vector quantization patches of ST6 that attribute is deducted in the embodiment of the present invention
Quantify patch, remainder vector patch is made into the 8th class label, attribute ST7.Obtain all vector quantization spots that attribute is ST7
The corresponding Multi-spectral Remote Sensing Data of block, for attribute be ST7 each vector quantization patch e2 (1≤e2≤E2, E2 are that attribute is
The quantity of the vector quantization patch of ST7), vector quantization patch e2 is calculated in the reflectivity of green light band and the reflectivity of near infrared band
The first difference and green light band reflectivity and blue wave band reflectivity the second difference, and acquire the first difference and
The result of product of second difference.
As shown in formula (18),
H=(Rg-Rnir)·(Rg-Rb) (18)
Wherein, h is result of product namely black and odorous water index, RgFor the reflectivity of green light band, RnirFor near-infrared wave
The reflectivity of section, RbFor the reflectivity of blue wave band.
If result of product h is less than or equal to the 11st preset threshold a11, then vector quantization patch e2 corresponds to black and odorous water, by vector
Change patch e2 and makees the 6th class label, attribute HC1.
On the basis of the above embodiments, the Complex Underlying Surface black and odorous water prediction technique provided in the embodiment of the present invention,
Further include:
By DEM, each vector quantization patch e1 that attribute is ST6 is further analyzed, if vector quantization patch e1 is full
The following formula (19) of foot, and be connected to tributaries such as the level-one in basin, second levels, then it is determined as non-black and odorous water, by vector quantization patch
E1 makees the second class label, attribute ST2.In formula (19), DminFor the elevation minimum point in vector quantization patch e1, DmaxFor arrow
Quantify the elevation highest point in patch e1, LmaxFor the maximum distance of elevation highest point and elevation minimum point, a12It is default for the 12nd
Threshold value.
So far, it is non-black and odorous water that attribute, which is grid, grid and the vector quantization patch of ST2, in the embodiment of the present invention,
Attribute is that the vector quantization patch of HC1 is black and odorous water.
As shown in figure 3, on the basis of the above embodiments, a kind of electronic equipment is provided in the embodiment of the present invention, comprising:
Processor (processor) 301, memory (memory) 302, communication interface (Communications Interface) 303
With bus 304；Wherein,
The processor 301, memory 302, communication interface 303 complete mutual communication by bus 304.It is described to deposit
Reservoir 302 is stored with the program instruction that can be executed by the processor 301, and processor 301 is used to call the journey in memory 302
Sequence instruction, to execute method provided by above-mentioned each method embodiment.
Logical order in memory 302 can be realized by way of SFU software functional unit and as independent product pin
It sells or in use, can store in a computer readable storage medium.Based on this understanding, technical side of the invention
Substantially the part of the part that contributes to existing technology or the technical solution can be with the shape of software product in other words for case
Formula embodies, which is stored in a storage medium, including some instructions are used so that a calculating
Machine equipment (can be personal computer, server or the network equipment etc.) executes each embodiment the method for the present invention
All or part of the steps.And storage medium above-mentioned include: USB flash disk, mobile hard disk, read-only memory (Read-Only Memory,
ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. are various can store program
The medium of code.
On the basis of the above embodiments, a kind of non-transient computer readable storage medium is provided in the embodiment of the present invention
Matter, the non-transient computer readable storage medium store computer instruction, and the computer instruction executes the computer
Method provided by above-mentioned each method embodiment.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creativeness
Labour in the case where, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features；
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (10)
1. a kind of Complex Underlying Surface identifying water boy method characterized by comprising
Obtain highway information figure, Land-use figure, multi-spectrum remote sensing image and the Thermal Remote Sensing Image of target area；
Based on the multi-spectrum remote sensing image, the initial water area in the target area is determined, and believe based on the highway
Breath figure, the Land-use figure and the Thermal Remote Sensing Image identify described from the initial water area
Water body distributed intelligence in target area.
2. Complex Underlying Surface identifying water boy method according to claim 1, which is characterized in that described based on described multispectral
Remote sensing image determines the initial water area in the target area, specifically includes:
Calculate the corresponding improved normalized difference water body index of each grid in the multi-spectrum remote sensing image or Clean water withdraw
Index；
If judgement knows that the improved normalized difference water body index is more than or equal to the first preset threshold or the water body mentions
Fetching number is more than or equal to the second preset threshold, and corresponding grid is made first kind label, all grids for making first kind label
At the initial water area.
3. Complex Underlying Surface identifying water boy method according to claim 1 or 2, which is characterized in that described to be based on the public affairs
Road hum pattern, the Land-use figure and the Thermal Remote Sensing Image, are identified from the initial water area
Water body distributed intelligence in the target area, specifically includes:
The highway information figure and the Land-use figure are subjected to rasterizing, each grid in the highway information figure
Size, the size of each grid and the size of each grid in the initial water area are equal in the Land-use figure
It is identical；
The highway information figure is superimposed in the initial water area, and by the initial water area with the highway
The grid of highway overlapping in hum pattern makees the second class label, obtains the second water area after label；By second water body area
Domain is superimposed in the Land-use figure, and will be Chong Die with second water area in the Land-use figure
Grid makees the second class label, obtains third water area after label；
The Thermal Remote Sensing Image is superimposed in the third water area, for each in the third water area
Grid calculates the average temperature value of the normalized differential vegetation index and water body in the grid, if judgement is known in the grid
The average temperature value of water body is more than or equal to third predetermined threshold value, and the normalized differential vegetation index is within a preset range, then by institute
It states grid and makees third class label；
Make the grid that third class marks from removal in all grids that the first kind marks is made in the third water area, and will remain
Remaining grid makees the 4th class label, and the grid for making the 4th class label in the third water area is carried out vector quantization, obtains vector
Change as a result, the vector quantization result includes multiple vector quantization patches；
Default shade overlay area is deducted from all vector quantization patches in the vector quantization result, deducts the default shade
The distributed intelligence of all vector quantization patches obtained behind overlay area is the water body distributed intelligence in the target area；
Wherein, the default shade overlay area is based on the vector quantization result and digital elevation model on multiple and different time points
It determines, the average temperature value of water body is greater than the 4th preset threshold and is less than the third and presets in the default shade overlay area
Threshold value.
4. Complex Underlying Surface identifying water boy method according to claim 3, which is characterized in that described for the third water
Each grid in body region, calculates the average temperature value of water body in the grid, specifically includes:
Tree and grass coverage based on every kind of vegetation for including in the corresponding temperature value of the grid, the grid under different coverages
Value, the building area area value for including in the grid, building area average temperature value, is wrapped in the grid vegetation average temperature value
The coverage of water value for including in pitchy highway area value, pitchy highway average temperature value and the grid included, described in calculating
The average temperature value of water body in grid.
5. Complex Underlying Surface identifying water boy method according to claim 3, which is characterized in that for third water body area
Each grid in domain, if judgement knows that the average temperature value of water body in the grid is less than or equal to the 4th preset threshold,
The grid is then made into the second class label.
6. a kind of Complex Underlying Surface realized based on Complex Underlying Surface identifying water boy method described in any one of claim 3-5
Black and odorous water prediction technique characterized by comprising
For deducting each vector quantization patch obtained behind the default shade overlay area, the vector quantization patch is made the 5th
Class label, if the vector quantization patch is known in judgement, the relative area changing value at adjacent two moment is more than or equal to the 5th default threshold
Value, and the area at the vector quantization patch forward moment in adjacent two moment is less than or equal to the 6th preset threshold, and the arrow
The average temperature value for quantifying water body in patch is greater than the 4th preset threshold and is less than the third predetermined threshold value, then the vector quantization
Patch corresponds to black and odorous water, and the vector quantization patch is made the 6th class label；From all vector quantization patches for making the 5th class label
It is middle to deduct the vector quantization patch for making the 6th class label, remainder vector patch is made into the 7th class label；
For making each vector quantization patch of the 7th class label, if judgement knows that the area of the vector quantization patch is less than or equal to institute
The 6th preset threshold is stated, and the average temperature value of water body is greater than the 4th preset threshold and is less than institute in the vector quantization patch
State third predetermined threshold value, and in the target area non-point pollution source strength of water body and corresponding non-point pollution source to each
The sum of the ratio of distance of vector quantization patch for making the 7th class label is less than or equal to the 7th preset threshold, then the vector quantization patch
The vector quantization patch is made the 6th class label by corresponding black and odorous water.
7. Complex Underlying Surface black and odorous water prediction technique according to claim 6, which is characterized in that further include:
For making each vector quantization patch of the 7th class label, if the ratio of the vector quantization patch perimeter and area is less than or equal to
8th preset threshold, the ratio between the area variance and area mean value of the vector quantization patch within a preset period of time are greater than etc.
In the 9th preset threshold, it is default that temperature mean value of the vector quantization patch in the preset time period is more than or equal to the described 8th
The length of threshold value, the preset time period is more than or equal to the tenth preset threshold, then the vector quantization patch corresponds to black and odorous water, will
The vector quantization patch makees the 6th class label.
8. Complex Underlying Surface black and odorous water prediction technique according to claim 7, which is characterized in that further include:
All vector quantization patches for making the 6th class label in all vector quantization patches for making the 7th class label are deducted, by remainder vector
Change patch and makees the 8th class label；
It obtains and makees the Multi-spectral Remote Sensing Data that all vector quantization patches of the 8th class label include, for making the every of the 8th class label
A vector quantization patch, calculate the vector quantization patch in the reflectivity of green light band and the reflectivity of near infrared band first are poor
Second difference of the reflectivity of the reflectivity and blue wave band of value and green light band, and acquire first difference and described
The result of product of second difference；If the result of product is less than or equal to the 11st preset threshold, the vector quantization patch is corresponding
The vector quantization patch is made the 6th class label by black and odorous water.
9. a kind of electronic equipment characterized by comprising
At least one processor, at least one processor, communication interface and bus；Wherein,
The processor, memory, communication interface complete mutual communication by the bus；
The memory is stored with the program instruction that can be executed by the processor, and the processor calls described program instruction,
To execute Complex Underlying Surface identifying water boy method according to any one of claims 1 to 5, or execute as in claim 6-8
Described in any item Complex Underlying Surface black and odorous water prediction techniques.
10. a kind of non-transient computer readable storage medium, which is characterized in that the non-transient computer readable storage medium is deposited
Computer instruction is stored up, the computer instruction executes the computer under complexity according to any one of claims 1 to 5
Pad face identifying water boy method, or execute the Complex Underlying Surface black and odorous water prediction technique as described in any one of claim 6-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910599445.9A CN110390277B (en) | 2019-07-04 | 2019-07-04 | Complex underlying surface water body identification method and black and odorous water body prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910599445.9A CN110390277B (en) | 2019-07-04 | 2019-07-04 | Complex underlying surface water body identification method and black and odorous water body prediction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110390277A true CN110390277A (en) | 2019-10-29 |
| CN110390277B CN110390277B (en) | 2021-07-06 |
Family
ID=68286245
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910599445.9A Active CN110390277B (en) | 2019-07-04 | 2019-07-04 | Complex underlying surface water body identification method and black and odorous water body prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110390277B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111060456A (en) * | 2019-12-27 | 2020-04-24 | 核工业北京地质研究院 | Method for identifying sandstone uranium ore structure excretion zone by using remote sensing image |
| CN112903945A (en) * | 2021-02-26 | 2021-06-04 | 珠江水利委员会珠江水利科学研究院 | Urban black and odorous water body identification method based on conventional water quality parameters |
| CN114298562A (en) * | 2021-12-29 | 2022-04-08 | 神彩科技股份有限公司 | Water environment monitoring and early warning method and device, computer equipment and storage medium |
| CN117233102A (en) * | 2023-11-15 | 2023-12-15 | 广东泓禹生态环境科技有限公司 | Water environment monitoring and processing method and system based on big data analysis |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040120857A1 (en) * | 2002-09-26 | 2004-06-24 | Honeywell Federal Manufacturing & Technologies, Llc | System and method for identifying, reporting, and evaluating presence of substance |
| CN102521598A (en) * | 2011-12-16 | 2012-06-27 | 北京市城市规划设计研究院 | Identification method based on remote-sensing image |
| CN105389559A (en) * | 2015-11-12 | 2016-03-09 | 中国科学院遥感与数字地球研究所 | System and method for identifying agricultural disaster scope based on high-resolution remote sensing image |
| CN105488488A (en) * | 2015-12-10 | 2016-04-13 | 中国科学院遥感与数字地球研究所 | Remote sensing recognition method and apparatus for black and odorous water body in city |
| CN105631903A (en) * | 2015-12-24 | 2016-06-01 | 河海大学 | Remote sensing image water extraction method and device based on RGBW characteristic space diagram cutting algorithm |
| CN106066210A (en) * | 2016-06-12 | 2016-11-02 | 中国石油天然气股份有限公司 | The recognition methods of a kind of oily sludge water body and device |
| CN106295221A (en) * | 2016-08-19 | 2017-01-04 | 中国科学院遥感与数字地球研究所 | A kind of urban water-body classification extraction method and system |
| CN107085851A (en) * | 2017-05-26 | 2017-08-22 | 环境保护部卫星环境应用中心 | A kind of method and device of extraction waters water front |
| CN107239756A (en) * | 2017-05-23 | 2017-10-10 | 国家地理空间信息中心 | Density of population analysis system based on high score satellite remote sensing date combination type of ground objects |
| CN107247927A (en) * | 2017-05-23 | 2017-10-13 | 浙江海洋大学 | A kind of remote sensing images coastline information extracting method and system based on K-T Transformation |
| CN109374537A (en) * | 2018-09-30 | 2019-02-22 | 中国科学院遥感与数字地球研究所 | The smelly identifying water boy method and device of urban black |
| CN109508585A (en) * | 2017-09-15 | 2019-03-22 | 中国科学院城市环境研究所 | A method of urban function region is extracted based on POI and high-resolution remote sensing image |
-
2019
- 2019-07-04 CN CN201910599445.9A patent/CN110390277B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040120857A1 (en) * | 2002-09-26 | 2004-06-24 | Honeywell Federal Manufacturing & Technologies, Llc | System and method for identifying, reporting, and evaluating presence of substance |
| CN102521598A (en) * | 2011-12-16 | 2012-06-27 | 北京市城市规划设计研究院 | Identification method based on remote-sensing image |
| CN105389559A (en) * | 2015-11-12 | 2016-03-09 | 中国科学院遥感与数字地球研究所 | System and method for identifying agricultural disaster scope based on high-resolution remote sensing image |
| CN105488488A (en) * | 2015-12-10 | 2016-04-13 | 中国科学院遥感与数字地球研究所 | Remote sensing recognition method and apparatus for black and odorous water body in city |
| CN105631903A (en) * | 2015-12-24 | 2016-06-01 | 河海大学 | Remote sensing image water extraction method and device based on RGBW characteristic space diagram cutting algorithm |
| CN106066210A (en) * | 2016-06-12 | 2016-11-02 | 中国石油天然气股份有限公司 | The recognition methods of a kind of oily sludge water body and device |
| CN106295221A (en) * | 2016-08-19 | 2017-01-04 | 中国科学院遥感与数字地球研究所 | A kind of urban water-body classification extraction method and system |
| CN107239756A (en) * | 2017-05-23 | 2017-10-10 | 国家地理空间信息中心 | Density of population analysis system based on high score satellite remote sensing date combination type of ground objects |
| CN107247927A (en) * | 2017-05-23 | 2017-10-13 | 浙江海洋大学 | A kind of remote sensing images coastline information extracting method and system based on K-T Transformation |
| CN107085851A (en) * | 2017-05-26 | 2017-08-22 | 环境保护部卫星环境应用中心 | A kind of method and device of extraction waters water front |
| CN109508585A (en) * | 2017-09-15 | 2019-03-22 | 中国科学院城市环境研究所 | A method of urban function region is extracted based on POI and high-resolution remote sensing image |
| CN109374537A (en) * | 2018-09-30 | 2019-02-22 | 中国科学院遥感与数字地球研究所 | The smelly identifying water boy method and device of urban black |
Non-Patent Citations (3)
| Title |
|---|
| ROBBY YUSSAC TALLAR等: "Identification of waterbody status in Indonesia by using predictive index assessment tool", 《INTERNATIONAL SOIL AND WATER CONSERVATION RESEARCH》 * |
| 张淑霞等: "基于Landsat 8劈窗算法的地表温度空间响应关系研究: 以于田绿洲为例", 《环境科学与技术》 * |
| 郭鹏等: "MODIS影像水体监测方法研究进展", 《气象科技》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111060456A (en) * | 2019-12-27 | 2020-04-24 | 核工业北京地质研究院 | Method for identifying sandstone uranium ore structure excretion zone by using remote sensing image |
| CN111060456B (en) * | 2019-12-27 | 2022-09-20 | 核工业北京地质研究院 | Method for identifying sandstone uranium ore structure excretion zone by using remote sensing image |
| CN112903945A (en) * | 2021-02-26 | 2021-06-04 | 珠江水利委员会珠江水利科学研究院 | Urban black and odorous water body identification method based on conventional water quality parameters |
| CN112903945B (en) * | 2021-02-26 | 2022-02-22 | 珠江水利委员会珠江水利科学研究院 | Urban black and odorous water body identification method based on conventional water quality parameters |
| CN114298562A (en) * | 2021-12-29 | 2022-04-08 | 神彩科技股份有限公司 | Water environment monitoring and early warning method and device, computer equipment and storage medium |
| CN114298562B (en) * | 2021-12-29 | 2023-07-11 | 神彩科技股份有限公司 | Water environment monitoring and early warning method and device, computer equipment and storage medium |
| CN117233102A (en) * | 2023-11-15 | 2023-12-15 | 广东泓禹生态环境科技有限公司 | Water environment monitoring and processing method and system based on big data analysis |
| CN117233102B (en) * | 2023-11-15 | 2024-01-26 | 广东泓禹生态环境科技有限公司 | Water environment monitoring and processing method and system based on big data analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110390277B (en) | 2021-07-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110390277A (en) | Complex Underlying Surface identifying water boy method and black and odorous water prediction technique | |
| Haas et al. | Sentinel-1A SAR and sentinel-2A MSI data fusion for urban ecosystem service mapping | |
| Julian et al. | River water quality changes in New Zealand over 26 years: response to land use intensity | |
| Merot et al. | Testing a climato-topographic index for predicting wetlands distribution along an European climate gradient | |
| de Wit et al. | Estimating regional winter wheat yield with WOFOST through the assimilation of green area index retrieved from MODIS observations | |
| Rampi et al. | Wetland mapping in the upper midwest United States | |
| Bamutaze et al. | Intersecting RUSLE modelled and farmers perceived soil erosion risk in the conservation domain on mountain Elgon in Uganda | |
| Marzolff et al. | Dynamics and patterns of land levelling for agricultural reclamation of erosional badlands in Chambal Valley (Madhya Pradesh, India) | |
| CN115497067A (en) | Path identification and planning method for nursery patrol intelligent vehicle | |
| Babiso et al. | Land use/land cover dynamics and its implication on sustainable land management in Wallecha watershed, southern Ethiopia | |
| Thuy et al. | Using sentinel image data and plot survey for the assessment of biomass and carbon stock in coastal forests of Thai Binh province, Vietnam. | |
| CN112215098B (en) | Method and system for estimating evergreen forest land coverage based on multi-source remote sensing data | |
| Zhang et al. | Evaluating the effectiveness of forest conservation policies with multi-temporal remotely sensed imagery: a case study from Tiantangzhai Township, Anhui, China | |
| Burnside et al. | Recent historical land use change on the South Downs, United Kingdom | |
| Suh et al. | Analysis of land cover land use change in the greater Gaborone area of South Eastern Botswana | |
| Bonn et al. | Ecosystem services of peat-phase 1 | |
| Chen | Spatially explicit modelling of agricultural dynamics in semi-arid environments | |
| Estreguil et al. | Enhancing connectivity, improving green infrastructure | |
| CN110390284B (en) | Drainage basin ecological bearing capacity estimation method and system based on remote sensing image | |
| Rahimi et al. | Revealing Regime Shifts and Their Impact on Social-Ecological Systems: a Case Study on Iran | |
| Atzberger et al. | Portability of neural nets modelling regional winter crop acreages using AVHRR time series | |
| Miyake et al. | Biodiversity and Socio-economic implications of the use of abandoned agricultural land for future biomass production in Central and Eastern Europe (CEE) | |
| Sadat et al. | Journal of Environmental Studies | |
| Batelaan et al. | Improved distributed runoff modelling of urbanised catchments by integration of multi-resolution remote sensing | |
| Mukaetov et al. | Dynamic of land degradation neutrality baseline indcators in the republic of macedonia |
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 |