CN115452759B - River and lake health index evaluation method and system based on satellite remote sensing data - Google Patents
River and lake health index evaluation method and system based on satellite remote sensing data Download PDFInfo
- Publication number
- CN115452759B CN115452759B CN202211115913.9A CN202211115913A CN115452759B CN 115452759 B CN115452759 B CN 115452759B CN 202211115913 A CN202211115913 A CN 202211115913A CN 115452759 B CN115452759 B CN 115452759B
- Authority
- CN
- China
- Prior art keywords
- lake
- remote sensing
- river
- data
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 51
- 230000036541 health Effects 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 claims abstract description 42
- 238000004458 analytical method Methods 0.000 claims abstract description 28
- 230000008569 process Effects 0.000 claims abstract description 19
- 238000011160 research Methods 0.000 claims abstract description 19
- 238000013210 evaluation model Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 6
- 238000012360 testing method Methods 0.000 claims description 36
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 19
- 230000011218 segmentation Effects 0.000 claims description 18
- 206010003694 Atrophy Diseases 0.000 claims description 10
- 230000037444 atrophy Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 8
- 238000013500 data storage Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000012795 verification Methods 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 2
- 238000005286 illumination Methods 0.000 claims description 2
- 238000012549 training Methods 0.000 claims description 2
- 230000002087 whitening effect Effects 0.000 claims description 2
- 238000007405 data analysis Methods 0.000 claims 1
- 230000008859 change Effects 0.000 abstract description 7
- 238000012544 monitoring process Methods 0.000 description 11
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 10
- 208000035475 disorder Diseases 0.000 description 10
- 238000002310 reflectometry Methods 0.000 description 6
- 238000001228 spectrum Methods 0.000 description 6
- 238000000605 extraction Methods 0.000 description 4
- 230000006378 damage Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 239000002689 soil Substances 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002902 bimodal effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 229930002875 chlorophyll Natural products 0.000 description 1
- 235000019804 chlorophyll Nutrition 0.000 description 1
- ATNHDLDRLWWWCB-AENOIHSZSA-M chlorophyll a Chemical compound C1([C@@H](C(=O)OC)C(=O)C2=C3C)=C2N2C3=CC(C(CC)=C3C)=[N+]4C3=CC3=C(C=C)C(C)=C5N3[Mg-2]42[N+]2=C1[C@@H](CCC(=O)OC\C=C(/C)CCC[C@H](C)CCC[C@H](C)CCCC(C)C)[C@H](C)C2=C5 ATNHDLDRLWWWCB-AENOIHSZSA-M 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 230000012010 growth Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000001771 impaired effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000008635 plant growth Effects 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
- 238000003911 water pollution Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/42—Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation
- G06V10/422—Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation for representing the structure of the pattern or shape of an object therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/70—Labelling scene content, e.g. deriving syntactic or semantic representations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N2021/1793—Remote sensing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Chemical & Material Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Biochemistry (AREA)
- Evolutionary Computation (AREA)
- Analytical Chemistry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Remote Sensing (AREA)
- Astronomy & Astrophysics (AREA)
- Image Processing (AREA)
Abstract
The application provides a river and lake health index evaluation method and system based on satellite remote sensing data, and belongs to the technical field of remote sensing data processing and analysis. The method specifically comprises the following steps: step 1, reading remote sensing index analysis data in a database based on a research period; step 2, constructing an index evaluation model and receiving read remote sensing index analysis data; and step 3, evaluating the health condition of the river and the lake based on the analysis result of the index evaluation model. The application effectively reduces the river and lake health evaluation cost, improves the evaluation timeliness and reduces the supervision difficulty through the capability of the high-resolution remote sensing satellite in large scale, all weather, strong real-time performance and the like, and simultaneously provides technical support for the subsequent supervision of the whole ecological health change process of river and lake objects.
Description
Technical Field
The application relates to the technical field of remote sensing data processing analysis, in particular to a river and lake health index evaluation method and system based on satellite remote sensing data.
Background
River in different areas has great difference in natural geography and economic and social backgrounds, and water resource maldistribution phenomenon can exist in water use due to different population distribution density degrees near the river basin. With the rapid development of the economic society, the water resource utilization intensity is continuously increased, the ecological system of the river and the lake is gradually damaged or even destroyed, the problems of water pollution, hydrologic condition deterioration, morphological structure destruction of the river and the lake, biodiversity damage, ecological function degradation of the river and the lake and the like generally occur in the global scope, and the economic development is seriously impaired.
In the prior art, the river and lake health concept is defined by focusing the basin and water of the river and lake, and an evaluation system is established, but in the actual application process, the evaluation method and the actual process have certain access due to the problems of adaptability, convenience and the like.
Disclosure of Invention
The application aims to: a river and lake health index evaluation method and system based on satellite remote sensing data are provided to solve the problems existing in the prior art. By utilizing the observation capability of the high-resolution remote sensing satellite in large scale, all weather, quasi real time and other aspects, the dynamic evaluation and supervision application research of the health of the river and the lake is developed, and the dynamic evaluation of the health single index and the health condition of the river and the lake is realized, so that the health evaluation cost of the river and the lake is effectively reduced, the evaluation efficiency is improved, the supervision difficulty is reduced, and meanwhile, the technical support is provided for the subsequent whole process supervision of the ecological health change of the river and the lake.
The technical scheme is as follows: in a first aspect, a method for evaluating health indexes of rivers and lakes based on satellite remote sensing data is provided, and the method specifically comprises the following steps:
step 1, constructing a satellite remote sensing data storage database;
step 2, reading remote sensing index analysis data in a satellite remote sensing data storage database within a preset time period and a space range through a data reading module;
step 3, constructing an index evaluation model by a model construction module, and receiving read remote sensing index analysis data;
and 4, based on the remote sensing index analysis data read in the step 3, evaluating the health condition of the river and the lake by an evaluation module.
In some implementations of the first aspect, the method further includes the following steps in the process of comprehensively evaluating the health condition of the river and the lake based on the analysis result of the index evaluation model:
step 3.1, analyzing vegetation coverage of the river and lake shoreline;
step 3.2, obtaining the area atrophy proportion of the lake;
and 3.3, comparing the river and lake appearance to present the situation.
The method specifically comprises the following steps of:
step 3.1.1, segmenting a river and lake shoreline according to a preset distance;
step 3.1.2, calculating vegetation coverage of each shore section according to the sections;
step 3.1.3, carrying out weight weighting calculation on the length of the shore section based on the whole shore line;
and 3.1.4, obtaining the vegetation coverage of the shoreline population through weighted summation.
When the lake area atrophy proportion is obtained, the method specifically comprises the following steps:
step 3.2.1, historical data are obtained;
step 3.2.2, acquiring a water body range in the research area through the difference of illumination wave bands;
and 3.2.3, calculating the lake atrophy proportion of the research area in a proportion mode based on the historical data.
When the river and lake manifestations are compared, the method specifically comprises the following steps:
step 3.3.1, acquiring remote sensing image data of a research area;
step 3.3.2, preprocessing the remote sensing image data to obtain a test image;
step 3.3.3, constructing a segmentation model, and converting a test image of the target area into an image with a corresponding category label by using the segmentation model;
step 3.3.4, extracting the outline of the research area based on the converted image data;
and 3.3.5, analyzing the image characteristics in the research area, comparing the image characteristics with the historical characteristics of the research area, generating a final comparison result, and outputting the final comparison result.
In some implementations of the first aspect, the process of acquiring the target area test image specifically includes the steps of:
step 3.3.2.1, reading remote sensing data;
step 3.3.2.2, obtaining a format conforming to required image data through data preprocessing;
3.3.2.3, constructing a reflection matrix according to the image data format;
and 3.3.2.4, constructing a projection coordinate system and generating a test image according to a preset wave band.
The process of converting the test image of the target area into the label image with the corresponding category by using the segmentation model specifically comprises the following steps:
step 3.3.3.1, obtaining a test image;
a step 3.3.3.2 of labeling each pixel in the test image;
step 3.3.3.3, slicing the test image according to a preset specification to obtain pixel blocks;
step 3.3.3.4, dividing the pixel block into a verification data set and a test set according to the proportion;
3.3.3.5, constructing a segmentation model, and performing model training by using the verification data set and the test set;
and 3.3.3.6, converting the test image of the target area into an image of the corresponding category label by using the trained segmentation model.
Based on the converted image data, the process of extracting the outline of the research area specifically comprises the following steps:
3.3.4.1, performing binarization processing on various labels in the test image;
step 3.3.4.2, selecting the pixel points of the corresponding labels as target pixel points according to the requirements, defining the values of the target pixel points as a first value, and defining the values of the remaining pixel points as a second value;
3.3.4.3, gathering the binarized class labels to regionalize adjacent and same class pixel points;
and 3.3.4.4, finding the difference between the inner pixel value and the residual pixel value according to the region, acquiring coordinates of points at the boundary of the region and forming a contour.
In a second aspect, a system for evaluating health indexes of rivers and lakes based on satellite remote sensing data is provided, and the system specifically comprises the following modules:
the data reading module is used for acquiring remote sensing index analysis data;
the model construction module is used for constructing an index evaluation model;
and the evaluation module is used for evaluating the health condition of the river and the lake.
In a third aspect, a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement an index evaluation method is provided.
The beneficial effects are that: the application provides a river and lake health index evaluation method and system based on satellite remote sensing data, which effectively reduce the river and lake health evaluation cost, improve the timeliness of evaluation and reduce the supervision difficulty through the capability of a high-resolution remote sensing satellite in large scale, all weather, strong real-time performance and the like, and simultaneously provide technical support for the subsequent overall process supervision of ecological health change of river and lake objects.
Drawings
FIG. 1 is a flow chart of data processing according to the present application.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a more thorough understanding of the present application. It will be apparent, however, to one skilled in the art that the application may be practiced without one or more of these details. In other instances, well-known features have not been described in detail in order to avoid obscuring the application.
With importance to ecological environment, the judgment of corresponding water environment indexes is also gradually becoming a life index which cannot be ignored in the life of the masses, and the acquisition mode aiming at the indexes to be evaluated in the prior art is generally a field detection mode, a manual visual inspection mode and the like, so that the problems of timeliness, great difficulty and the like of detection exist. Therefore, the application provides the river and lake health index evaluation method and system based on the satellite remote sensing data, which effectively reduce the river and lake health evaluation cost, improve the timeliness of evaluation and reduce the supervision difficulty through the capability of the high-resolution remote sensing satellite in large scale, all weather, strong real-time performance and other aspects, and simultaneously provide technical support for the subsequent overall process supervision of ecological health change of river and lake objects.
Example 1
In one embodiment, a method for evaluating health indexes of rivers and lakes based on satellite remote sensing data is provided, as shown in fig. 1, and the method specifically comprises the following steps:
step 1, constructing a satellite remote sensing data storage database;
step 2, reading remote sensing index analysis data in a satellite remote sensing data storage database within a preset time period and a space range through a data reading module;
step 3, constructing an index evaluation model by a model construction module, and receiving read remote sensing index analysis data;
and 4, based on the remote sensing index analysis data read in the step 3, evaluating the health condition of the river and the lake by an evaluation module.
In a further embodiment, the indicators for performing river and lake health assessment specifically include: the vegetation coverage rate of the shoreline of the river and the lake, the shrinkage proportion of the area of the lake and the appearance of the river and the lake are in conditions.
Specifically, when the vegetation coverage of the river and lake shoreline is obtained, firstly segmenting the river and lake shoreline according to a preset distance, and calculating the vegetation coverage of each shoreside according to the segmented shoreside; and then, carrying out weight weighting calculation on the length of the shore section based on the whole shore line to obtain vegetation coverage rate of the whole shore line of the river and the lake, wherein the corresponding expression is as follows:
in PC r Representing a shoreline vegetation coverage evaluation score; a is that ci Representing the vegetation coverage area of land section i; a is that ai Representing the land area of the land section i; l (L) vci Representing the length of land section i; l represents the total length of the evaluation land section; n represents the total number of river bank segments within the evaluation range.
When the lake area atrophy proportion is calculated, the proportion expression of the lake water surface atrophy area in the evaluation year and the lake water surface area in the historical reference year is adopted, and the corresponding calculation expression is as follows:
wherein ASI represents the area atrophy proportion of lakes; AC represents the lake water surface area of the evaluation year; AR represents the surface area of a lake in the historical reference year.
When the state of the river and lake appearance is judged, remote sensing data are adopted to carry out multi-period long-time sequence monitoring, pattern spot extraction is carried out on behaviors such as moving soil, buildings and piles, and the like, and comparison analysis is carried out on the pattern spot extraction and the historical reference period data, so that change data are obtained, and the manual judgment is assisted to carry out four disorder condition judgment.
According to the method, the system and the device, the river and lake health conditions in the research field are analyzed by constructing the index evaluation model, and the ecological condition in the research field is effectively obtained, so that an effective analysis basis is provided for subsequent environment improvement. Meanwhile, based on the capability of the high-resolution remote sensing satellite in large scale, all weather, strong real-time performance and the like, the river and lake health evaluation cost is effectively reduced, the evaluation timeliness is improved, the supervision difficulty is reduced, and meanwhile, the technical support is provided for the subsequent overall process supervision of ecological health change of river and lake objects.
Example two
In a further embodiment based on the first embodiment, since the surface vegetation shows the growth status of horizontal and vertical distribution, and the colors and shapes of different kinds of vegetation are different, the information about vegetation in the remote sensing image is mainly obtained by changing the characteristics of the vegetation spectral bands and the differences thereof, and the characteristics of different vegetation are identified and analyzed through different spectral bands. In the process of analyzing the vegetation coverage of the river and lake shoreline, a vegetation index method is adopted for extracting the vegetation coverage condition of the river and lake shoreline.
Specifically, the difference of chlorophyll absorption between a green leaf near infrared band spectrum channel and a red band spectrum channel in vegetation is increased, and vegetation coverage is estimated through the existence of the difference, so that vegetation information is obtained. The vegetation index expression is obtained as follows:
wherein, the value range of NDVI is-1 to 1; IR indicates the reflectivity in the near infrared band; r represents the infrared band reflectivity. When the value of NDVI is less than 0, the ground is water, snow, glacier and other components; when the value of NDVI is 0, the components on the ground, such as deserts, rocks or bare ground, are represented; when the value of NDVI is greater than 0, the ground is vegetation. The normalized vegetation index and the vegetation coverage have a positive correlation, wherein the value range of the green vegetation index is 0.2 to 0.8.
Grid extraction of green vegetation index is carried out by obtaining grid data through NDVI (non-linear density coefficient) calculation expression, so that coverage of green vegetation in an evaluation range can be obtained, and then final shoreline vegetation coverage is obtained after one-by-one calculationCover rate evaluation score PC r 。
In the preferred embodiment, the vegetation coverage index of the river and lake shoreline is selected to be researched in the month of the most vigorous plant growth in 3 months to 10 months, compared with the mode of adopting field investigation or manual visual interpretation of the river and lake shoreline in a large range in the prior art, the method in the embodiment reduces the requirement on a large amount of manpower and improves the interpretation efficiency to a large extent, in addition, the observation frequency is improved, the efficiency is improved, and meanwhile, the method also provides technical support for intelligent river and lake health monitoring.
The vegetation index adopted in the embodiment obtains vegetation coverage conditions of river and lake shorelines, utilizes different spectrum bands and combines different calculation methods to estimate vegetation coverage, and simultaneously selects spectrum bands with large information quantity and weak correlation to estimate vegetation coverage, so that larger deviation does not exist when the spectrum bands are extracted for analysis, and higher accuracy of the vegetation coverage can be ensured. In addition, the method of normalizing the vegetation index is adopted, so that the requirements of high efficiency and rapidness in extraction and research of regional vegetation coverage and no limitation of regions and time are met.
Example III
In a further embodiment based on the first embodiment, in the process of calculating the shrinkage ratio of the lake area, the water surface area of the lake in the history reference year is obtained by inquiring the history year, and when the related history records are not inquired, the manual approval is performed by obtaining the duration images. In the preferred embodiment, the query history data acquisition history refers to the water surface area of a lake in the year, preferably in the last 80 years of the 20 th century, with a similar hydrologic frequency as the evaluation year.
In a further embodiment, since most of the light in the near infrared band is reflected by the plant when the light irradiates the plant, and most of the light in the visible light band is absorbed by the plant, the influence of the ground object spectrum can be eliminated and the water body can be distinguished by the linear or nonlinear combination of the reflectivity of the near infrared band and the reflectivity of the red band, and therefore, the normalized vegetation index model is utilized to extract the water body range when evaluating the area of the annual lake surface. Wherein the corresponding normalized vegetation index calculation expression is:
wherein IR represents the reflectivity in the near infrared band; r represents the infrared band reflectivity. When the value of NDVI is negative, the current water body is indicated; otherwise, the water body can be obtained in a threshold mode by using vegetation soil with a larger NDVI value and a bimodal distribution form of the integral histogram of the NDVI.
And obtaining data obtained based on the NDVI calculation expression, obtaining a water body grid surface by adopting grid calculation, and obtaining the lake water surface area of the evaluation year after vector conversion, thereby realizing the calculation of the lake area atrophy proportion.
In a preferred embodiment, the monitoring frequency is 1 time/year for the evaluation of the atrophy ratio of the lake area. Compared with the prior art, the method for obtaining the lake area through the visual interpretation method has stronger subjectivity. The method provided by the embodiment is simple and feasible, is suitable for remote sensing data of various data sources, has strong universality and high operation efficiency, and achieves the purposes of improving the accuracy and the evaluation efficiency of index evaluation.
Example IV
In a further embodiment based on the first embodiment, the current state of the river and lake is determined by performing image analysis on the remote sensing data, and the current state of the river and lake health is assessed by comparing the current state with the historical state.
Specifically, for remote sensing data in a historical reference period and an evaluation period, firstly extracting the outline of an analysis area, and obtaining a test image of a target area after data preprocessing; and then comparing the analyzed data with historical data to obtain change data, thereby realizing evaluation of the appearance state.
In a further embodiment, the process of acquiring the test image of the target area specifically includes the following steps:
step 1, reading remote sensing data;
step 2, obtaining a format conforming to the required image data through data preprocessing;
step 3, constructing a reflection matrix according to the image data format;
and 4, constructing a projection coordinate system, and generating a test image according to a preset wave band.
Specifically, after decompressing the original data downloaded by the high-resolution satellite, traversing the search file to find the file in which the required information is located, and reading the required information from the file, for example, the data storage path of each wave band, the data resolution of each wave band, the information of the upper left corner coordinates of the data and the remote sensing image information such as NoData represented by countless value points; then, integrating and acquiring required information, integrating the acquired upper left corner coordinates, the resolution in the east-west direction and the rotation angle information of the map to construct a reflection matrix required by remote sensing image data in a Geotiff format, selecting a corresponding coordinate system as a projection coordinate system, selecting wave band data to generate a test image, and selecting red, green and blue wave bands to generate a remote sensing data RGB image; and finally, acquiring target region boundary information according to the target region shp file, acquiring maximum and minimum longitude coordinates and maximum and minimum latitude coordinates of a target city boundary, forming a rectangular frame according to the maximum and minimum longitude and latitude coordinates, cutting test data and RGB images according to the rectangular frame, and performing null whitening treatment on data outside the target region boundary.
In a further embodiment, after the test image is obtained, the test image is subjected to semantic segmentation, and the test image data of the target area is tested by using the trained first classification network model, so that the image that each pixel in the test image of the target area is converted into the corresponding class label is obtained.
Specifically, firstly classifying things in a remote sensing image, and labeling all pixels of the remote sensing image; secondly, slicing the whole remote sensing image to obtain pixel blocks; dividing the acquired pixel blocks into a verification data set and a test set; and constructing a region segmentation model from time to time, wherein the region segmentation model is used for segmenting the target region and acquiring an image with a corresponding category label.
In the process of acquiring the pixel blocks through slicing, each pixel in the image is taken as a center point, the pixel blocks with the sizes of m multiplied by c are cut, wherein m is the side length of the pixel block, c is the band number of the pixel block, and c is more than 3.
The constructed region segmentation model is a first classification network model, is based on a convolutional neural network structure and can be also called a pixel-based four-disorder region segmentation model. The model structure is a 3D-2D convolution structure, and the whole network is formed by connecting 3 layers of 3-dimensional convolution layers, two layers of 2-dimensional convolution layers and 3 layers of full-connection layers in series. In a preferred embodiment, the convolution kernel sizes of the 3D convolution layers may be (3 x 3), (3×3×5), (1×1×4), the convolution kernel size of the 2D convolution layer may be (3×3); the 3D convolution layer is connected with the 2D convolution layer through dimension reduction, and the 2D convolution layer is connected with the full connection layer through dimension reduction of input to one dimension.
In a further embodiment, region contour selection is performed on the test image after semantic segmentation, binarization processing is performed on each type label in the image, pixel points with type labels of bare land type are selected as target pixel points, the value of the target pixel points is set to be a first value, and the values of the other pixel points are set to be a second value; and (3) gathering the binarized class labels, regionalizing adjacent pixel points of the same class, finding out the difference between an inner pixel value and other pixel values according to the region, and acquiring coordinates of points at the boundary of the region to form a contour.
Specifically, when the second classification network model is used for carrying out region contour selection on the test image after semantic segmentation, a maximum value and a minimum value of an abscissa and an ordinate are found in points forming the contour to form a rectangular region, coordinates of a central point of the rectangular region are found, a data block of h multiplied by w multiplied by 3 is intercepted by taking the coordinates of the point as the center, the data block is input into the second classification network model to judge whether a region corresponding to the data block is a four-disorder region or not, and if the data block is not the four-disorder region, the contour corresponding to the data block is deleted.
In a preferred embodiment, the evaluation of the appearance state of the river and the lake comprises four disorder phenomena, namely disorder stacking, disorder occupation, disorder collection and disorder construction, the monitoring of the four disorder condition indexes of the river and the lake needs to cover the whole year, dynamic monitoring and even real-time monitoring are needed, and the monitoring frequency is required to be high. The current monitoring method mainly depends on field investigation and erection of sensing equipment, and has the advantages of small observation range and high labor cost. The analysis method in the embodiment is used for monitoring, has more advantages in spatial scale and monitoring frequency, has high algorithm operation efficiency, and can provide support for automatic monitoring and evaluation of river and lake health.
Example five
In one embodiment, a system for evaluating health indexes of rivers and lakes based on satellite remote sensing data is provided, and the system specifically comprises the following modules:
the data reading module is used for acquiring remote sensing index analysis data;
the model construction module is used for constructing an index evaluation model;
and the evaluation module is used for evaluating the health condition of the river and the lake.
In a further embodiment, first, based on a study period, remote sensing index analysis data in a database is read by a data reading module; then, a model construction module is adopted to construct an index evaluation model, and read remote sensing index analysis data is received; and finally, based on the analysis result of the index evaluation model, evaluating the health condition of the river and the lake by adopting an evaluation module.
Example five
In one embodiment, a computer-readable storage medium having stored thereon computer program instructions that when executed by a processor implement an index evaluation method is presented.
As described above, although the present application has been shown and described with reference to certain preferred embodiments, it is not to be construed as limiting the application itself. Various changes in form and details may be made therein without departing from the spirit and scope of the application as defined by the appended claims.
Claims (7)
1. A river and lake health index evaluation method based on satellite remote sensing data is characterized by comprising the following steps:
step 1, constructing a satellite remote sensing data storage database;
step 2, reading remote sensing index analysis data in a satellite remote sensing data storage database within a preset time period and a space range through a data reading module;
step 3, constructing an index evaluation model by a model construction module, and receiving read remote sensing index analysis data;
step 4, based on the remote sensing index analysis data read in the step 3, evaluating the health condition of the river and the lake by an evaluation module;
the process of performing remote sensing index data analysis by using the index evaluation model comprises the following steps: analyzing the vegetation coverage rate of the shoreline of the river and the lake, obtaining the shrinkage proportion of the area of the lake and comparing the appearance of the river and the lake;
the analysis process of the river and lake appearance presentation condition comprises the following steps:
acquiring remote sensing image data of a research area, preprocessing the remote sensing image data, and acquiring a geotif image data format meeting the requirements by integrating the left upper corner coordinates of the remote sensing image data, the resolution in the east-west direction and the rotation angle information of a map;
constructing a reflection matrix according to a Geotiff image data format, constructing a projection coordinate system at the same time, and obtaining a test image according to a preset wave band;
selecting red, green and blue wave bands in the test image to generate a remote sensing data RGB image, and forming a rectangular frame according to the position information of the target analysis area;
the rectangular frame is utilized to cut the test image and the RGB image, and the data outside the target area is subjected to null whitening treatment;
constructing a region segmentation model, and converting a test image of a target region into an image with a corresponding category label by using the region segmentation model; the region segmentation model is based on a convolutional neural network structure and comprises a 3D-2D convolutional structure, and the whole network is formed by connecting a 3-layer 3-dimensional convolutional layer, two 2-dimensional convolutional layers and a 3-layer full-connection layer in series; wherein the convolution kernel sizes of the 3D convolution layers are (3 x 3), (3 x 5), (1×1×4), the convolution kernel size of the 2D convolution layer may be (3×3); the 3D convolution layer is connected with the 2D convolution layer through dimension reduction, and the 2D convolution layer is connected with the full connection layer through dimension reduction of input to one dimension;
extracting the outline of the research area based on the converted image data;
analyzing the image characteristics in the research area, comparing the obtained image characteristics with the historical characteristics of the research area, generating a final comparison result, and outputting the final comparison result.
2. The method for evaluating river and lake health index based on satellite remote sensing data according to claim 1, wherein when analyzing the vegetation coverage of the river and lake shoreline, the method specifically comprises the following steps:
step 3.1.1, segmenting a river and lake shoreline according to a preset distance;
step 3.1.2, calculating vegetation coverage of each shore section according to the sections;
step 3.1.3, carrying out weight weighting calculation on the length of the shore section based on the whole shore line;
and 3.1.4, obtaining the vegetation coverage of the shoreline population through weighted summation.
3. The method for evaluating river and lake health index based on satellite remote sensing data according to claim 1, wherein when the lake area atrophy proportion is obtained, the method specifically comprises the following steps:
step 3.2.1, historical data are obtained;
step 3.2.2, acquiring a water body range in the research area through the difference of illumination wave bands;
and 3.2.3, calculating the lake atrophy proportion of the research area in a proportion mode based on the historical data.
4. The method for evaluating river and lake health index based on satellite remote sensing data according to claim 1, wherein the process of converting the test image of the target area into the label image with the corresponding category by using the segmentation model comprises the following steps:
step 3.3.3.1, obtaining a test image;
a step 3.3.3.2 of labeling each pixel in the test image;
step 3.3.3.3, slicing the test image according to a preset specification to obtain pixel blocks;
step 3.3.3.4, dividing the pixel block into a verification data set and a test set according to the proportion;
3.3.3.5, constructing a segmentation model, and performing model training by using the verification data set and the test set;
and 3.3.3.6, converting the test image of the target area into an image of the corresponding category label by using the trained segmentation model.
5. The river and lake health index evaluation method based on satellite remote sensing data of claim 1, wherein the process of extracting the outline of the research area based on the converted image data specifically comprises the following steps:
3.3.4.1, performing binarization processing on various labels in the test image;
step 3.3.4.2, selecting the pixel points of the corresponding labels as target pixel points according to the requirements, defining the values of the target pixel points as a first value, and defining the values of the remaining pixel points as a second value;
3.3.4.3, gathering the binarized class labels to regionalize adjacent and same class pixel points;
and 3.3.4.4, finding the difference between the inner pixel value and the residual pixel value according to the region, acquiring coordinates of points at the boundary of the region and forming a contour.
6. A river and lake health index evaluation system based on satellite remote sensing data, which is used for realizing the index evaluation method of any one of claims 1-5, and is characterized by comprising the following modules:
the data reading module is used for acquiring remote sensing index analysis data;
the model construction module is used for constructing an index evaluation model;
and the evaluation module is used for evaluating the health condition of the river and the lake.
7. A computer readable storage medium, wherein computer program instructions are stored on the computer readable storage medium, which when executed by a processor, implement the index evaluation method according to any one of claims 1-5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211115913.9A CN115452759B (en) | 2022-09-14 | 2022-09-14 | River and lake health index evaluation method and system based on satellite remote sensing data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211115913.9A CN115452759B (en) | 2022-09-14 | 2022-09-14 | River and lake health index evaluation method and system based on satellite remote sensing data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115452759A CN115452759A (en) | 2022-12-09 |
CN115452759B true CN115452759B (en) | 2023-08-22 |
Family
ID=84302867
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211115913.9A Active CN115452759B (en) | 2022-09-14 | 2022-09-14 | River and lake health index evaluation method and system based on satellite remote sensing data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115452759B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115953687B (en) * | 2023-01-18 | 2023-11-10 | 生态环境部卫星环境应用中心 | Small micro water body damage grade classification method and device based on remote sensing technology |
CN116704197B (en) * | 2023-08-07 | 2023-10-17 | 水利部珠江水利委员会水文局 | Processing method and system for river and lake remote sensing image |
CN117054349B (en) * | 2023-10-11 | 2023-12-26 | 中国水利水电科学研究院 | Water network water quality pressure evaluation method based on remote sensing data |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102221551A (en) * | 2011-06-02 | 2011-10-19 | 中国科学院计算技术研究所 | Blue algae monitoring device and blue algae monitoring method |
CN106354992A (en) * | 2016-08-12 | 2017-01-25 | 中国水利水电科学研究院 | Lake water volume storage variable assessment method based on multi-temporal remote-sensing image and DEM |
CN107977765A (en) * | 2017-07-07 | 2018-05-01 | 江西省科学院 | A kind of lake and marshland Landscape health status evaluation method based on remote Sensing Interpretation technology |
CN109840516A (en) * | 2019-03-06 | 2019-06-04 | 福州大学 | A kind of water body variation automatic identifying method based on timing remote sensing image |
CN110738187A (en) * | 2019-10-24 | 2020-01-31 | 中国科学院城市环境研究所 | quick remote sensing estimation method for dynamic change of lake area based on Google Earth Engine |
KR20220112590A (en) * | 2021-02-04 | 2022-08-11 | 창원대학교 산학협력단 | Artificial Intelligence-based Water Quality Contaminant Monitoring System and Method |
-
2022
- 2022-09-14 CN CN202211115913.9A patent/CN115452759B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102221551A (en) * | 2011-06-02 | 2011-10-19 | 中国科学院计算技术研究所 | Blue algae monitoring device and blue algae monitoring method |
CN106354992A (en) * | 2016-08-12 | 2017-01-25 | 中国水利水电科学研究院 | Lake water volume storage variable assessment method based on multi-temporal remote-sensing image and DEM |
CN107977765A (en) * | 2017-07-07 | 2018-05-01 | 江西省科学院 | A kind of lake and marshland Landscape health status evaluation method based on remote Sensing Interpretation technology |
CN109840516A (en) * | 2019-03-06 | 2019-06-04 | 福州大学 | A kind of water body variation automatic identifying method based on timing remote sensing image |
CN110738187A (en) * | 2019-10-24 | 2020-01-31 | 中国科学院城市环境研究所 | quick remote sensing estimation method for dynamic change of lake area based on Google Earth Engine |
KR20220112590A (en) * | 2021-02-04 | 2022-08-11 | 창원대학교 산학협력단 | Artificial Intelligence-based Water Quality Contaminant Monitoring System and Method |
Also Published As
Publication number | Publication date |
---|---|
CN115452759A (en) | 2022-12-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Rosentreter et al. | Towards large-scale mapping of local climate zones using multitemporal Sentinel 2 data and convolutional neural networks | |
CN115452759B (en) | River and lake health index evaluation method and system based on satellite remote sensing data | |
CN109190538B (en) | Sediment-laden river delta coastal zone evolution analysis method based on remote sensing technology | |
Trier et al. | Automatic detection of mound structures in airborne laser scanning data | |
CN111028255B (en) | Farmland area pre-screening method and device based on priori information and deep learning | |
Matasci et al. | Mapping tree canopies in urban environments using airborne laser scanning (ALS): a Vancouver case study | |
CN114444791A (en) | Flood disaster remote sensing monitoring and evaluation method based on machine learning | |
CN112070056A (en) | Sensitive land use identification method based on object-oriented and deep learning | |
Nagel et al. | High-resolution land cover and impervious surface classifications in the twin cities metropolitan area with NAIP imagery | |
CN116385867A (en) | Ecological land block monitoring, identifying and analyzing method, system, medium, equipment and terminal | |
Diep et al. | Assessment on controlling factors of urbanization possibility in a newly developing city of the Vietnamese Mekong delta using logistic regression analysis | |
CN110175638B (en) | Raise dust source monitoring method | |
CN116206210A (en) | NAS-Swin-based remote sensing image agricultural greenhouse extraction method | |
Dogon-Yaro et al. | Semi-automated approach for mapping urban trees from integrated aerial lidar point cloud and digital imagery datasets | |
Kato | Integrating openstreetmap data in object based landcover and landuse classification for disaster recovery | |
GÖKSEL et al. | Land Use and Land Cover Changes Using Spot 5 Pansharpen Images; A Case Study in Akdeniz District, Mersin-Turkey | |
Goetzke et al. | A method to map land-use change and urban growth in North Rhine-Westphalia (Germany) | |
Wang et al. | An effective road extraction method from remote sensing images based on self-adaptive threshold function | |
Agustin et al. | Identification of oil palm plantation in IKONOS images using radially averaged power spectrum values | |
Kyzivat et al. | Contemporary and historical detection of small lakes using super resolution Landsat imagery: promise and peril | |
Sun et al. | Object-level change detection based on high-resolution remote-sensing images and its application in Japanese earthquake on March 11, 2011 | |
Vivek Nanda | Estimating and Modeling Structural Characteristics of Trees within Aerial LiDAR Data. | |
Neogi et al. | Change detection of exposed sandbars around Kaziranga national park | |
Nanda | Estimating and Modeling Structural Characteristics of Trees Within Aerial LiDar Data | |
Lanza et al. | EXPANDING COASTSAT SHORELINE DETECTION ALGORITHM TO TRACK COASTAL VEGETATION AND URBAN CHARACTERISTICS FROM SATELLITE DATA |
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 |