CN111695530A - River water replenishing effect intelligent monitoring and evaluation method based on high-resolution remote sensing - Google Patents
River water replenishing effect intelligent monitoring and evaluation method based on high-resolution remote sensing Download PDFInfo
- Publication number
- CN111695530A CN111695530A CN202010545567.2A CN202010545567A CN111695530A CN 111695530 A CN111695530 A CN 111695530A CN 202010545567 A CN202010545567 A CN 202010545567A CN 111695530 A CN111695530 A CN 111695530A
- Authority
- CN
- China
- Prior art keywords
- river
- image
- water
- water replenishing
- remote sensing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 192
- 238000012544 monitoring process Methods 0.000 title claims abstract description 39
- 230000000694 effects Effects 0.000 title claims abstract description 37
- 238000011156 evaluation Methods 0.000 title claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 23
- 238000000034 method Methods 0.000 claims abstract description 22
- 238000003062 neural network model Methods 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 230000008569 process Effects 0.000 claims abstract description 5
- 238000012892 rational function Methods 0.000 claims description 24
- 239000013598 vector Substances 0.000 claims description 14
- 230000008859 change Effects 0.000 claims description 12
- 238000012937 correction Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 8
- 210000002569 neuron Anatomy 0.000 claims description 7
- 238000013519 translation Methods 0.000 claims description 5
- 238000003384 imaging method Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 238000007500 overflow downdraw method Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 239000000443 aerosol Substances 0.000 claims description 3
- 238000001035 drying Methods 0.000 claims description 2
- 238000011158 quantitative evaluation Methods 0.000 abstract description 2
- 239000013589 supplement Substances 0.000 description 14
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000003673 groundwater Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 239000002352 surface water Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/182—Network patterns, e.g. roads or rivers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a river water replenishing effect intelligent monitoring and evaluating method based on high-resolution remote sensing, which utilizes multi-source high-resolution satellite cooperative observation, adopts a preprocessing process to obtain a river region high-resolution remote sensing image set with space-time consistency, further constructs high-precision training sample points and a deep neural network model to intelligently extract a water surface range of multi-temporal river water replenishing, and provides quantitative evaluation indexes for river water replenishing effects. The intelligent monitoring and evaluation method for the river water replenishing effect is high in applicability, can be suitable for monitoring and evaluating the river water replenishing effect of different basin scales, and can be expanded to business applications such as strong supervision of rivers and lakes.
Description
Technical Field
The invention belongs to the technical field of intelligent identification of remote sensing images, and particularly relates to a design of an intelligent monitoring and evaluating method for river water replenishing effect based on high-resolution remote sensing.
Background
Rivers are important ties that connect different geographic units and ecological units, and are also important carriers of material flows and information flows. Under the influence of factors such as climate change, human social development and the like, river water resources are over-developed and utilized and are difficult to be supplemented in time, so that a large amount of rivers are dried and cut off, the ecological health of the river water, the connectivity of rivers and lakes and groundwater supply are seriously influenced, and the deterioration of the rivers and the surrounding ecological environment is inevitably caused.
Aiming at the ecological environment problem caused by the dry river, the water replenishing across river basin and across regions is the most direct and effective solving way, and the water surface of the river is continuously restored by adopting measures such as river regulation and cleaning, river water replenishing and the like, so that the gradual restoration of the ecological functions of rivers and lakes is facilitated. At present, river water supplement is already carried out in partial regions, the connectivity of the river is recovered, certain effect is achieved, but an intelligent monitoring and evaluating method is not formed for the river water supplement effect, a traditional hydrological monitoring station is an important means for monitoring river water resources, but the number of hydrological monitoring stations is limited, and the overall water supplement condition of the whole river is difficult to reflect; although the precision of manual inspection is high, the manual inspection is time-consuming, labor-consuming and long in period, and is difficult to be suitable for monitoring and evaluating the water replenishing effect of rivers in a large range.
The satellite remote sensing can macroscopically, accurately and truly acquire the earth surface information, and is an important means for carrying out large-scale water resource, water environment and water ecology investigation. With the implementation of a great special item of a high-resolution earth observation system in China, a plurality of high-resolution satellites from a high-resolution one satellite to a high-resolution seven satellite and the like are successfully transmitted, a high-resolution multisource satellite collaborative observation system in China is initially formed, a rich, timely and high-quality remote sensing data source is provided for river monitoring, and dynamic monitoring and evaluation of a river-opening water replenishing effect are facilitated.
Disclosure of Invention
The invention aims to solve the problem that a set of monitoring and evaluating method aiming at the river water replenishing effect is lacked in the prior art, and provides an intelligent monitoring and evaluating method for the river water replenishing effect based on high-resolution remote sensing.
The technical scheme of the invention is as follows: a river water replenishing effect intelligent monitoring and evaluation method based on high-resolution remote sensing comprises the following steps:
and S1, collecting multi-source high-grade remote sensing data before and after water supplement and in the water supplement process according to the water supplement range of the river to be monitored.
And S2, preprocessing the multi-source high-resolution remote sensing data according to space-time consistency to obtain a river region high-resolution remote sensing image.
S3, intelligently monitoring the river water replenishing according to the high-resolution remote sensing image of the river region, and forming a multi-temporal river water surface range data set.
And S4, evaluating the river water replenishing effect according to the multi-temporal river water surface range data set.
Further, in step S1, the selection criterion of the multi-source high-score remote sensing data is as follows:
(1) selecting a cloud-free or few-cloud coverage image, wherein the river range is cloud-free;
(2) the image has no missing, noise and abnormal pixel;
(3) no obvious aerosol coverage of the image;
(4) no ice and snow cover exists in the image;
(5) there was no rainfall before and after the imaging date of the image.
Further, step S2 includes the following substeps:
and S21, collecting DEM data and Landsat8 data of an image coverage area in the multi-source high-resolution remote sensing data.
And S22, taking the Landsat8 data as a reference image, and collecting high-precision control points.
And S23, optimizing rational function model coefficients of the image by combining DEM data of the image coverage area and the acquired high-precision control points, and performing geometric correction on the full-color image and the multi-spectral image in the high-resolution remote sensing data by using the rational function model.
And S24, fusing the full-color image and the multispectral image after geometric correction by adopting a Panship fusion method to obtain a multispectral image with high spatial resolution.
And S25, adjusting the color tone of the multispectral image with high spatial resolution by adopting an image histogram matching method, and constructing a splicing line according to the image characteristic points to realize region image mosaic.
S26, constructing a buffer area according to the river center line vector and the river width, and cutting the river range in the image by combining the mosaic image and the buffer area range to obtain the river area high-resolution remote sensing image.
Further, the expression of the rational function model in step S23 is:
wherein (L)n,Sn) Representing the regularized coordinates of the pixel row-column coordinates (L, S) in the image after translation and scaling, (X)n,Yn,Zn) Representing the ground coordinates (X,y, Z) translated and scaled regularized coordinates, Pl(. DEG) a molecular polynomial, Q, representing a rational function of the row pixelsl(. -) A denominator polynomial, P, representing a row pixel rational functions(. DEG) a molecular polynomial, Q, representing a column pixel rational functions(. cndot.) represents the denominator polynomial of the column pixel rational function.
Further, step S3 includes the following substeps:
and S31, marking water body and non-water body high-precision training samples on the pixel layer by adopting an artificial interest area method according to the river region high-resolution remote sensing image.
And S32, inputting the high-precision training samples of the water body and the non-water body into the deep neural network model, and performing optimization training on model parameters so as to extract the water surface range of the river water supplement.
And S33, dynamically monitoring the water surface range of the river water replenishing, and forming a multi-temporal river water surface range data set.
Further, step S32 includes the following substeps:
s321, constructing training sample feature vectors according to water body and non-water body high-precision samples
Wherein
Representing the characteristic vector of the water body training sample,
representing non-water training sample feature vectors, BnThe nth characteristic wave band is represented, wherein N is 1, 2.
S322, training sample feature vector
Inputting into a deep neural network model, and iteratively calculating a net function G (x) through a plurality of hidden layer neurons:
wherein ω isijRandom initial weight value, x, representing class i characteristics of layer j neuronsiRepresenting class i characteristics, bjRepresenting the bias of layer j neurons, and k represents the total number of features.
S323, through repeated iteration, a classification discriminant function P (x) is constructed to determine that each pixel is of a water body or a non-water body type:
wherein p (x) 1 indicates that the pixel type is a water body, that is, a water surface range of river water replenishing, and p (x) 0 indicates that the pixel type is a non-water body, that is, a non-water surface range.
Further, step S4 includes the following substeps:
s41, calculating the river surface area change value according to the multi-temporal river surface range data set
Wherein ST1Showing the surface area of the river before replenishing water, ST2Showing the surface area of the river after water replenishing.
S42, calculating the water width change value of the river water surface according to the multi-temporal river water surface range data set
Wherein DT1Indicates the width of river water surface before water replenishment, DT2Indicating that the river water surface after water replenishing is wide.
S43, calculating the change value of the river length of the dry river according to the multi-time-phase river water surface range data set
Wherein L isT1Indicating the length of the river to be dried before replenishing water, LT2Indicating the length of the dried river after replenishing water.
S44, if the river surface area changes
Greater than 0, water width variation value of river water surface
Change value of river length greater than 0 and drying up
And if the water replenishing rate is less than 0, the river water replenishing effect is obtained, otherwise, the river water replenishing effect is not obtained.
The invention has the beneficial effects that: according to the method, the river regional high-resolution remote sensing image set with space-time consistency is obtained by utilizing multi-source high-resolution satellite cooperative observation and adopting a preprocessing process, so that a high-precision training sample point and a deep neural network model are constructed to intelligently extract the water surface range of multi-temporal river water supplement, and a quantitative evaluation index for river water supplement effect is provided. The intelligent monitoring and evaluation method for the river water replenishing effect is high in applicability, can be suitable for monitoring and evaluating the river water replenishing effect of different basin scales, and can be expanded to business applications such as strong supervision of rivers and lakes.
Drawings
Fig. 1 is a flow chart of an intelligent monitoring and evaluation method for river water replenishing effect based on high-resolution remote sensing according to an embodiment of the invention.
Fig. 2 is a flow chart of an intelligent monitoring and evaluating method for river water replenishing effect based on high-resolution remote sensing according to an embodiment of the invention.
Fig. 3 is a schematic view of a monitoring result of a water surface range before river water replenishing according to an embodiment of the invention.
Fig. 4 is a schematic view of a water surface range monitoring result after river water replenishing according to an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It is to be understood that the embodiments shown and described in the drawings are merely exemplary and are intended to illustrate the principles and spirit of the invention, not to limit the scope of the invention.
The embodiment of the invention provides a river water replenishing effect intelligent monitoring and evaluating method based on high-resolution remote sensing, which comprises the following steps of S1-S4 as shown in fig. 1-2:
and S1, collecting multi-source high-grade remote sensing data before and after water supplement and in the water supplement process according to the water supplement range of the river to be monitored.
In the embodiment of the invention, the multi-source high-resolution remote sensing data is high-resolution optical satellite remote sensing data such as a first high-resolution satellite, a second high-resolution satellite and a sixth high-resolution satellite which are inquired and downloaded from a China resource satellite center, the downloaded data is a 1A product, and the data is processed by systems such as data analysis, uniform radiation correction, noise removal, transfer function compensation CCD splicing, waveband registration and the like.
In the embodiment of the invention, the selection standard of the multi-source high-resolution remote sensing data in the step S1 is as follows:
(1) selecting a cloud-free or few-cloud coverage image, wherein the river range is cloud-free;
(2) the image has no missing, noise and abnormal pixel;
(3) no obvious aerosol coverage of the image;
(4) no ice and snow cover exists in the image;
(5) there was no rainfall before and after the imaging date of the image.
And S2, preprocessing the multi-source high-resolution remote sensing data according to space-time consistency to obtain a river region high-resolution remote sensing image.
Since the high-resolution remote sensing data acquired in step S1 has not been geometrically refined, it needs to be preprocessed for time-space consistency, so as to ensure the spatial accuracy of the multi-temporal high-resolution remote sensing image.
The step S2 includes the following substeps S21-S26:
and S21, acquiring DEM (digital elevation model) data and Landsat8 data of an image coverage area in the multi-source high-resolution remote sensing data.
In the embodiment of the invention, DEM data is used for subsequently correcting the positioning error caused by the terrain, and Landsat8 data selects a Landsat8 full-color 15m spatial resolution image for subsequently being used as a reference image to acquire a high-precision control point.
And S22, taking the Landsat8 data as a reference image, and collecting high-precision control points.
In the embodiment of the invention, the selected positions of the control points are generally positioned at the road intersections and are uniformly distributed on the images, the number of the control points of each image in the plain area is 15-20, the number of the control points of each image in the mountain area is 25-30, and the error of the control points in the X direction and the error of the control points in the Y direction are not higher than 1 pixel.
And S23, optimizing rational function model coefficients of the image by combining DEM data of the image coverage area and the acquired high-precision control points, and performing geometric correction on the full-color image and the multi-spectral image in the high-resolution remote sensing data by using the rational function model.
The rational function model is a general geometric correction model for the current high-resolution images, the pixel coordinate of the rational function model is expressed as the ratio of a rational polynomial taking the corresponding ground point space coordinate as an independent variable, and the high-precision image geometric correction is realized by introducing the coefficient in the rational function after the high-precision control point optimization. The expression of the rational function model is:
wherein (L)n,Sn) Representing the regularized coordinates of the pixel row-column coordinates (L, S) in the image after translation and scaling, (X)n,Yn,Zn) Representing the regularized coordinates, P, of the ground coordinates (X, Y, Z) in the image after translation and scalingl(. DEG) a molecular polynomial, Q, representing a rational function of the row pixelsl(. -) A denominator polynomial, P, representing a row pixel rational functions(. DEG) a molecular polynomial, Q, representing a column pixel rational functions(. cndot.) represents the denominator polynomial of the column pixel rational function.
And S24, fusing the full-color image and the multispectral image after geometric correction by adopting a Panship fusion method to obtain a multispectral image with high spatial resolution.
After geometric correction, the full-color image of the high-resolution remote sensing data has higher spatial resolution, the multispectral image has rich spectral characteristics, the multispectral fused image with high spatial resolution can be obtained by adopting a Panship fusion method, and the method has better retention effect on image information, details and spectrum.
And S25, because the image imaging conditions are inconsistent, the fused multispectral image has large chromatic aberration, and therefore the image needs to be homogenized, so that the overall color tone can be kept consistent. In the embodiment of the invention, the multispectral image with high spatial resolution is subjected to tone adjustment by adopting an image histogram matching method, and splicing lines are constructed according to image characteristic points to realize regional image mosaic.
S26, constructing a buffer area according to the river center line vector and the river width, and cutting the river range in the image by combining the mosaic image and the buffer area range to obtain the river area high-resolution remote sensing image.
S3, intelligently monitoring the river water replenishing according to the high-resolution remote sensing image of the river region, and forming a multi-temporal river water surface range data set.
The step S3 includes the following substeps S31-S33:
and S31, marking water body and non-water body high-precision training samples on the pixel layer by adopting an artificial interest area method according to the river region high-resolution remote sensing image.
In the embodiment of the invention, the water body high-precision sample comprises all surface water body types, including types of lakes, rivers, pools, silt water bodies and the like. The non-water body high-precision sample comprises ground objects such as farmlands, forests, cities, bare land, bushes, mountain shadows, cloud shadows and the like.
And S32, inputting the high-precision training samples of the water body and the non-water body into the deep neural network model, and performing optimization training on model parameters so as to extract the water surface range of the river water supplement.
The deep neural network algorithm is a neural network model comprising a plurality of hidden layers, all neurons are fully connected, and the deep neural network algorithm belongs to one of machine learning supervised classification algorithms.
Step S32 includes the following substeps S321 to S323:
s321, constructing training sample feature vectors according to water body and non-water body high-precision samples
Wherein
Representing the characteristic vector of the water body training sample,
representing non-water training sample feature vectors, BnThe nth characteristic wave band is represented, wherein N is 1, 2.
In the embodiment of the invention, each image input waveband is taken as one characteristic, for example, four characteristic wavebands are provided for high-grade first and second, when high-grade first or second high-grade satellite remote sensing data is selected, N is 4, and when high-grade sixth high-grade satellite remote sensing data is selected, N is 8.
S322, training sample characteristicsVector quantity
Inputting into a deep neural network model, and iteratively calculating a net function G (x) through a plurality of hidden layer neurons:
wherein ω isijRandom initial weight value, x, representing class i characteristics of layer j neuronsiRepresenting class i characteristics, bjRepresenting the bias of layer j neurons, and k represents the total number of features.
S323, through repeated iteration, a classification discriminant function P (x) is constructed to determine that each pixel is of a water body or a non-water body type:
wherein p (x) 1 indicates that the pixel type is a water body, that is, a water surface range of river water replenishing, and p (x) 0 indicates that the pixel type is a non-water body, that is, a non-water surface range.
And S33, dynamically monitoring the water surface range of the river water replenishing, and forming a multi-temporal river water surface range data set.
In the embodiment of the invention, the monitoring result of the water surface range before the river water replenishing is shown in fig. 3, and the monitoring result of the water surface range after the river water replenishing is shown in fig. 4, so that the accurate and clear monitoring result of the water surface range of the river water replenishing can be obtained according to fig. 3 and 4.
And S4, evaluating the river water replenishing effect according to the multi-temporal river water surface range data set.
The step S4 includes the following substeps S41-S44:
s41, calculating the river surface area change value according to the multi-temporal river surface range data set
Wherein ST1Showing the surface area of the river before replenishing water, ST2Showing the surface area of the river after replenishing water, ST1And ST2Can be obtained from the multi-phase river water surface range data in a centralized way.
S42, calculating the water width change value of the river water surface according to the multi-temporal river water surface range data set
Wherein DT1Indicates the width of river water surface before water replenishment, DT2Indicates the width of river water surface after water supplement, DT1And DT2Can be obtained from the multi-phase river water surface range data in a centralized way.
S43, calculating the change value of the river length of the dry river according to the multi-time-phase river water surface range data set
Wherein L isT1Indicating the length of the river to be dried before replenishing water, LT2Shows the dry river length after water replenishment, LT1And LT2Can be obtained from the multi-phase river water surface range data in a centralized way.
S44, if the river surface area changes
Greater than 0 (i.e. the water surface area of the river is increased) and the water width change value of the river water surface
Greater than 0 (i.e. river surface widening)) And the change value of the length of the dry river
If the water replenishing rate is less than 0 (namely the dry river length is reduced), the river water replenishing effect is achieved, otherwise, the river water replenishing effect is not achieved.
It will be appreciated by those of ordinary skill in the art that the embodiments described herein are intended to assist the reader in understanding the principles of the invention and are to be construed as being without limitation to such specifically recited embodiments and examples. Those skilled in the art can make various other specific changes and combinations based on the teachings of the present invention without departing from the spirit of the invention, and these changes and combinations are within the scope of the invention.
Claims (7)
1. A river water replenishing effect intelligent monitoring and evaluation method based on high-resolution remote sensing is characterized by comprising the following steps:
s1, collecting multi-source high-grade remote sensing data before and after water replenishing and in the water replenishing process according to the water replenishing range of the river to be monitored;
s2, preprocessing the multi-source high-resolution remote sensing data in a time-space consistency mode to obtain a river region high-resolution remote sensing image;
s3, intelligently monitoring river water replenishing according to the high-resolution remote sensing image of the river region, and forming a multi-temporal river water surface range data set;
and S4, evaluating the river water replenishing effect according to the multi-temporal river water surface range data set.
2. The river water replenishing effect intelligent monitoring and evaluating method according to claim 1, wherein the selection standard of the multi-source high-grade remote sensing data in the step S1 is as follows:
(1) selecting a cloud-free or few-cloud coverage image, wherein the river range is cloud-free;
(2) the image has no missing, noise and abnormal pixel;
(3) no obvious aerosol coverage of the image;
(4) no ice and snow cover exists in the image;
(5) there was no rainfall before and after the imaging date of the image.
3. The river water replenishing effect intelligent monitoring and evaluation method according to claim 1, wherein the step S2 comprises the following sub-steps:
s21, collecting DEM data and Landsat8 data of an image coverage area in multi-source high-resolution remote sensing data;
s22, taking Landsat8 data as a reference image, and collecting high-precision control points;
s23, optimizing rational function model coefficients of the image by combining DEM data of an image coverage area and acquired high-precision control points, and performing geometric correction on full-color images and multi-spectral images in high-resolution remote sensing data by using a rational function model;
s24, fusing the full-color image and the multispectral image after geometric correction by adopting a Panship fusion method to obtain a multispectral image with high spatial resolution;
s25, adjusting the color tone of the multispectral image with high spatial resolution by adopting an image histogram matching method, constructing a splicing line according to the image characteristic points, and realizing region image mosaic;
s26, constructing a buffer area according to the river center line vector and the river width, and cutting the river range in the image by combining the mosaic image and the buffer area range to obtain the river area high-resolution remote sensing image.
4. The river water replenishing effect intelligent monitoring and evaluating method according to claim 3, wherein the expression of the rational function model in the step S23 is as follows:
wherein (L)n,Sn) Representing the regularized coordinates of the pixel row-column coordinates (L, S) in the image after translation and scaling, (X)n,Yn,Zn) Representing translation and scaling of ground coordinates (X, Y, Z) in an imageNormalized coordinates of the last, Pl(. DEG) a molecular polynomial, Q, representing a rational function of the row pixelsl(. -) A denominator polynomial, P, representing a row pixel rational functions(. DEG) a molecular polynomial, Q, representing a column pixel rational functions(. cndot.) represents the denominator polynomial of the column pixel rational function.
5. The river water replenishing effect intelligent monitoring and evaluation method according to claim 1, wherein the step S3 comprises the following sub-steps:
s31, marking water body and non-water body high-precision training samples on a pixel layer by adopting an artificial interest area method according to the river region high-resolution remote sensing image;
s32, inputting high-precision training samples of the water body and the non-water body into the deep neural network model, and performing optimization training on model parameters so as to extract a water surface range for river water replenishing;
and S33, dynamically monitoring the water surface range of the river water replenishing, and forming a multi-temporal river water surface range data set.
6. The river water replenishing effect intelligent monitoring and evaluation method according to claim 5, wherein the step S32 comprises the following sub-steps:
s321, constructing training sample feature vectors according to water body and non-water body high-precision samples
Wherein
Representing the characteristic vector of the water body training sample,
to representNon-water body training sample feature vector, BnRepresenting the nth characteristic wave band, wherein N is 1,2, and N represents the total number of the characteristic wave bands of the remote sensing image;
s322, training sample feature vector
Inputting into a deep neural network model, and iteratively calculating a net function G (x) through a plurality of hidden layer neurons:
wherein ω isijRandom initial weight value, x, representing class i characteristics of layer j neuronsiRepresenting class i characteristics, bjRepresenting the bias of layer j neurons, k representing the total number of features;
s323, through repeated iteration, a classification discriminant function P (x) is constructed to determine that each pixel is of a water body or a non-water body type:
wherein p (x) 1 indicates that the pixel type is a water body, that is, a water surface range of river water replenishing, and p (x) 0 indicates that the pixel type is a non-water body, that is, a non-water surface range.
7. The river water replenishing effect intelligent monitoring and evaluation method according to claim 1, wherein the step S4 comprises the following sub-steps:
s41, calculating the river surface area change value according to the multi-temporal river surface range data set
Wherein ST1To representArea of river surface before replenishing water, ST2Showing the water surface area of the river after water replenishing;
s42, calculating the water width change value of the river water surface according to the multi-temporal river water surface range data set
Wherein DT1Indicates the width of river water surface before water replenishment, DT2The water width of the river water surface after water replenishing is shown;
s43, calculating the change value of the river length of the dry river according to the multi-time-phase river water surface range data set
Wherein L isT1Indicating the length of the river to be dried before replenishing water, LT2Indicating the length of the dried river after water replenishing;
s44, if the river surface area changes
Greater than 0, water width variation value of river water surface
Change value of river length greater than 0 and drying up
And if the water replenishing rate is less than 0, the river water replenishing effect is obtained, otherwise, the river water replenishing effect is not obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010545567.2A CN111695530A (en) | 2020-06-16 | 2020-06-16 | River water replenishing effect intelligent monitoring and evaluation method based on high-resolution remote sensing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010545567.2A CN111695530A (en) | 2020-06-16 | 2020-06-16 | River water replenishing effect intelligent monitoring and evaluation method based on high-resolution remote sensing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111695530A true CN111695530A (en) | 2020-09-22 |
Family
ID=72481125
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010545567.2A Pending CN111695530A (en) | 2020-06-16 | 2020-06-16 | River water replenishing effect intelligent monitoring and evaluation method based on high-resolution remote sensing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111695530A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113095213A (en) * | 2021-04-09 | 2021-07-09 | 重庆零壹空间科技集团有限公司 | Hydro-fluctuation belt change monitoring method |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7298869B1 (en) * | 2003-07-21 | 2007-11-20 | Abernathy Donald A | Multispectral data acquisition system and method |
| CN103530530A (en) * | 2013-11-01 | 2014-01-22 | 中国水利水电科学研究院 | Quantitative calculation method for lake wetland ecological water requirement in arid region |
| CN106855891A (en) * | 2017-01-13 | 2017-06-16 | 中国水利水电科学研究院 | A kind of wetland moisturizing position choosing method and device |
| CN107491758A (en) * | 2017-08-18 | 2017-12-19 | 南京林业大学 | Yangtze river basin water body information and its space encoding method |
| CN107689056A (en) * | 2017-08-24 | 2018-02-13 | 河海大学 | A kind of multi-temporal remote sensing image change detecting method of card side's conversion with reference to Level Set Method |
| CN108229425A (en) * | 2018-01-29 | 2018-06-29 | 浙江大学 | A kind of identifying water boy method based on high-resolution remote sensing image |
| CN108896117A (en) * | 2018-05-10 | 2018-11-27 | 北京师范大学 | A kind of method of Remote Sensing To Hydrology station monitoring discharge of river |
| CN109684929A (en) * | 2018-11-23 | 2019-04-26 | 中国电建集团成都勘测设计研究院有限公司 | Terrestrial plant ECOLOGICAL ENVIRONMENTAL MONITORING method based on multi-sources RS data fusion |
| US20200160029A1 (en) * | 2017-07-27 | 2020-05-21 | Airbus Defence And Space Sas | Device and method for simulating the estimation of a lag in producing satellite images of the earth |
| CN111274918A (en) * | 2020-01-17 | 2020-06-12 | 生态环境部卫星环境应用中心 | River dryout and cutoff monitoring method and device based on multi-source remote sensing image |
-
2020
- 2020-06-16 CN CN202010545567.2A patent/CN111695530A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7298869B1 (en) * | 2003-07-21 | 2007-11-20 | Abernathy Donald A | Multispectral data acquisition system and method |
| CN103530530A (en) * | 2013-11-01 | 2014-01-22 | 中国水利水电科学研究院 | Quantitative calculation method for lake wetland ecological water requirement in arid region |
| CN106855891A (en) * | 2017-01-13 | 2017-06-16 | 中国水利水电科学研究院 | A kind of wetland moisturizing position choosing method and device |
| US20200160029A1 (en) * | 2017-07-27 | 2020-05-21 | Airbus Defence And Space Sas | Device and method for simulating the estimation of a lag in producing satellite images of the earth |
| CN107491758A (en) * | 2017-08-18 | 2017-12-19 | 南京林业大学 | Yangtze river basin water body information and its space encoding method |
| CN107689056A (en) * | 2017-08-24 | 2018-02-13 | 河海大学 | A kind of multi-temporal remote sensing image change detecting method of card side's conversion with reference to Level Set Method |
| CN108229425A (en) * | 2018-01-29 | 2018-06-29 | 浙江大学 | A kind of identifying water boy method based on high-resolution remote sensing image |
| CN108896117A (en) * | 2018-05-10 | 2018-11-27 | 北京师范大学 | A kind of method of Remote Sensing To Hydrology station monitoring discharge of river |
| CN109684929A (en) * | 2018-11-23 | 2019-04-26 | 中国电建集团成都勘测设计研究院有限公司 | Terrestrial plant ECOLOGICAL ENVIRONMENTAL MONITORING method based on multi-sources RS data fusion |
| CN111274918A (en) * | 2020-01-17 | 2020-06-12 | 生态环境部卫星环境应用中心 | River dryout and cutoff monitoring method and device based on multi-source remote sensing image |
Non-Patent Citations (7)
| Title |
|---|
| 付俊娥，等: "《跨时空遥感应用理论及其在水利行业的应用》", 《卫星应用》 * |
| 吴亚男，等: "《呼伦湖湿地动态变化遥感监测及驱动力分析》", 《中国水利水电科学研究院学报》 * |
| 张仰正等: "《黄河三角洲湿地生态补水探讨》", 《中国水利学会2014学术年会论文集》 * |
| 李万东: "《土地利用动态遥感监测技术与方法》", 30 September 2011 * |
| 范树印: "《土地整治遥感监测技术方法与实践》", 30 April 2016 * |
| 邵亚奎等: "《国产高分卫星遥感影像融合方法比较与评价》", 《测绘通报》 * |
| 黄国华: "《现代林业信息技术》", 30 November 2015 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113095213A (en) * | 2021-04-09 | 2021-07-09 | 重庆零壹空间科技集团有限公司 | Hydro-fluctuation belt change monitoring method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Spatio-temporal fusion for daily Sentinel-2 images | |
| Chen et al. | Spatially and temporally weighted regression: A novel method to produce continuous cloud-free Landsat imagery | |
| Song et al. | An improved surface soil moisture downscaling approach over cloudy areas based on geographically weighted regression | |
| Li et al. | Estimation of all-sky 1 km land surface temperature over the conterminous United States | |
| Getirana et al. | Improving hydrological information acquisition from DEM processing in floodplains | |
| CN103544477B (en) | Vegetation fraction estimation method based on the linear spectral mixture model improved | |
| CN112949414B (en) | Intelligent surface water body drawing method for wide-vision-field high-resolution six-satellite image | |
| CN111192282B (en) | Lake and reservoir time sequence water level reconstruction method for lakeside zone virtual station | |
| Ge et al. | Improved semisupervised unet deep learning model for forest height mapping with satellite sar and optical data | |
| Yoo et al. | Spatial downscaling of MODIS land surface temperature: Recent research trends, challenges, and future directions | |
| Huang et al. | A novel fusion method for generating surface soil moisture data with high accuracy, high spatial resolution, and high spatio‐temporal Continuity | |
| Oriani et al. | Downscaling multispectral satellite images without colocated high-resolution data: a stochastic approach based on training images | |
| Karakacan Kuzucu et al. | Testing the potential of vegetation indices for land use/cover classification using high resolution data | |
| CN117035066A (en) | Ground surface temperature downscaling method coupling geographic weighting and random forest | |
| Jiang et al. | Unmixing-based spatiotemporal image fusion accounting for complex land cover changes | |
| Herrero-Huerta et al. | Generating high-temporal and spatial resolution TIR image data | |
| He et al. | Deep learning approaches to spatial downscaling of GRACE terrestrial water storage products using EALCO model over Canada | |
| Lou et al. | An effective method for canopy chlorophyll content estimation of marsh vegetation based on multiscale remote sensing data | |
| CN113779863B (en) | Ground surface temperature downscaling method based on data mining | |
| Xiong et al. | Fusing Landsat-7, Landsat-8 and Sentinel-2 surface reflectance to generate dense time series images with 10m spatial resolution | |
| CN109840539B (en) | Remote sensing space-time data fusion method based on ground block pattern spots | |
| CN111695530A (en) | River water replenishing effect intelligent monitoring and evaluation method based on high-resolution remote sensing | |
| Sun et al. | Supervised and self-supervised learning-based cascade spatiotemporal fusion framework and its application | |
| Wang et al. | A taylor expansion algorithm for spatial downscaling of MODIS land surface temperature | |
| CN112001291A (en) | Method and system for quickly extracting main river channel in gravel distribution area of flood fan |
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 | ||
| CB02 | Change of applicant information |
Address after: 20 Chegongzhuang West Road, Haidian District, Beijing 100038 Applicant after: China Institute of Water Resources and Hydropower Research Address before: 100038, Fuxing Road 1, Beijing, Haidian District Applicant before: China Institute of Water Resources and Hydropower Research |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200922 |
|
| RJ01 | Rejection of invention patent application after publication |