CN117994661A - Land line identification method, system, medium and electronic equipment - Google Patents
Land line identification method, system, medium and electronic equipment Download PDFInfo
- Publication number
- CN117994661A CN117994661A CN202410174958.6A CN202410174958A CN117994661A CN 117994661 A CN117994661 A CN 117994661A CN 202410174958 A CN202410174958 A CN 202410174958A CN 117994661 A CN117994661 A CN 117994661A
- Authority
- CN
- China
- Prior art keywords
- data
- wind field
- identified
- map
- land line
- 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
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000001914 filtration Methods 0.000 claims abstract description 34
- 238000013507 mapping Methods 0.000 claims abstract description 32
- 238000010801 machine learning Methods 0.000 claims abstract description 18
- 230000000007 visual effect Effects 0.000 claims description 62
- 238000012512 characterization method Methods 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 230000004807 localization Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000013506 data mapping Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005381 potential energy Methods 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
Landscapes
- Processing Or Creating Images (AREA)
- Image Processing (AREA)
Abstract
The application discloses a land line identification method, a land line identification system, a land line identification medium and electronic equipment, wherein the land line identification method comprises the following steps: acquiring grid point data and high-altitude potential meter data of an area to be identified, wherein each grid point in the grid point data is used for representing high-altitude wind field data on each longitude and latitude; constructing a contour map of the region to be identified according to the high-vacancy potential meter data; noise filtering is carried out on the high-altitude wind field data to obtain a plurality of filtered target wind field data; mapping each target wind field data into an image with preset resolution through a preset sign which can be recognized visually to obtain a wind field weather map of the region to be recognized; and determining longitude and latitude coordinates of the corresponding groove ridge line based on the contour map and the wind farm weather map. Therefore, the application carries out noise filtering on the high-altitude wind field data so as to make the land line area more obvious; meanwhile, the wind field data is abstracted into visually distinguishable symbols, and the most direct information is provided for machine learning, so that the error recognition rate of land line recognition is reduced, and the recognition accuracy of groove ridge lines is improved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a land line identification method, a land line identification system, a land line identification medium, and an electronic device.
Background
In the weather field, land lines include groove lines, which refer to a section of low pressure area in the atmosphere that exhibits a curved southerly or northward bulge, typically associated with weather activity such as cold front, rainfall, etc. The ridge line refers to a high-pressure area which protrudes to the south or the north, and is usually connected with weather activities such as sunny days, high temperature and the like, so that accurate identification of the groove ridge line is a very important thing in weather forecast.
In the related art, the analysis of the groove ridge line is basically realized by adopting a manual analysis method, and the efficiency of manually analyzing weather objects is low; meanwhile, in the prior art, an example of processing a weather map by using a software algorithm exists, the software algorithm enables a machine learning model to automatically extract image features in a data driving mode, and then an identification process of a groove ridge line region is provided.
Disclosure of Invention
The embodiment of the application provides a land line identification method, a land line identification system, a land line identification medium and electronic equipment. The following presents a simplified summary in order to provide a basic understanding of some aspects of the disclosed embodiments. This summary is not an extensive overview and is intended to neither identify key/critical elements nor delineate the scope of such embodiments. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is presented later.
In a first aspect, an embodiment of the present application provides a land line identification method, including:
Acquiring meteorological data of an area to be identified, wherein the meteorological data comprises grid point data and high-altitude potential meter data, and each grid point in the grid point data is used for representing high-altitude wind field data on each longitude and latitude;
constructing a contour map of the region to be identified according to the high-vacancy potential meter data;
noise filtering is carried out on the high-altitude wind field data to obtain a plurality of filtered target wind field data;
mapping each target wind field data into an image with preset resolution through a preset sign which can be recognized visually to obtain a wind field weather map of the region to be recognized;
And determining longitude and latitude coordinates of the land line corresponding to the area to be identified based on the contour map and the wind field meteorological map of the area to be identified.
Optionally, noise filtering is performed on the high altitude wind field data to obtain a plurality of filtered target wind field data, including:
scanning the high-altitude wind field data of adjacent preset number of points according to lines from the high-altitude wind field data;
Determining the scanned high-altitude wind field data of adjacent preset number points as a group of high-altitude wind field data to be filtered, and obtaining a plurality of groups of high-altitude wind field data to be filtered;
and carrying out mean value calculation on the abscissa and the ordinate contained in each group of high-altitude wind field data to be filtered so as to carry out noise filtering on the high-altitude wind field data and obtain a plurality of filtered target wind field data.
Optionally, the visually identifiable preset symbol includes a visually identifiable wind direction identifier and a wind field type identifier;
Mapping each target wind field data to an image with preset resolution through a preset sign which can be recognized visually to obtain a wind field weather map of an area to be recognized, wherein the method comprises the following steps:
acquiring the wind direction in the data of each target wind field;
Linearly mapping a wind direction mark for representing the wind direction in each target wind field data in an image with preset resolution to obtain a wind direction map of the region to be identified;
Acquiring positive and negative parameters of a vertical component in each target wind field data to determine a wind field type represented by each target wind field data;
Linearly mapping a wind field type identifier for representing the wind field type in each target wind field data in an image with preset resolution to obtain a wind direction type map of the region to be identified;
and taking the wind direction map and the wind direction type map of the area to be identified as a wind field weather map of the area to be identified.
Optionally, determining longitude and latitude coordinates of a land line corresponding to the area to be identified based on the contour map and the wind farm weather map of the area to be identified includes:
combining the contour map, the wind direction map and the wind direction type map of the area to be identified to obtain visual characterization data of the area to be identified;
inputting visual representation data of a region to be identified into a pre-trained land line region positioning model, and outputting a land line region corresponding to the region to be identified;
inputting a land line region corresponding to the region to be identified into a pre-trained land line regression model, and outputting a land line corresponding to the region to be identified;
And inversely mapping the positions of the groove ridge lines corresponding to the area to be identified to determine longitude and latitude coordinates of the land lines corresponding to the area to be identified.
Optionally, generating the pre-trained land line region localization model and the pre-trained land line regression model according to the steps comprising:
Acquiring historical meteorological data of each potential meter in each sub-time period in a preset time period; the historical meteorological data under each potential meter comprises historical grid point data and historical high-altitude potential meter data, and each grid point in the historical grid point data is used for representing historical high-altitude wind field data on each longitude and latitude;
constructing a contour map of each sub-time period according to the historical high-vacancy potential meter data;
noise filtering is carried out on the historical high-altitude wind field data to obtain a plurality of filtered historical wind field data;
mapping each historical wind field data into an image with preset resolution through a preset sign which can be recognized visually to obtain a wind direction map and a wind direction type map of each sub-time period;
combining the contour map of each sub-time period, the wind direction map of each sub-time period and the wind direction type map to obtain visual characterization data of each sub-time period;
based on the visual representation data for each sub-period, a pre-trained land line area positioning model and a pre-trained land line regression model are generated.
Optionally, generating a pre-trained land line region localization model and a pre-trained land line regression model based on the visual representation data for each sub-period, comprising:
Marking and picking out a groove line region and a ridge line region from the visual representation data of each sub-time period to obtain a groove line region visual image and a ridge line region visual image of each sub-time period;
Creating a land line area positioning model;
Machine learning is carried out on the groove ridge line region positioning model according to the groove line region visual image and the ridge line region visual image of each sub-time period to obtain a pre-trained land line region positioning model;
acquiring the longitude and latitude of a groove ridge line from the groove line area visual image and the ridge line area visual image of each sub-time period to obtain land line data of each sub-time period;
creating a groove ridge regression model;
machine learning is performed on the land line regression model based on the land line data for each sub-period to obtain a pre-trained land line regression model.
Optionally, constructing a contour map of the region to be identified according to the high vacancy potential meter data, including:
Drawing a contour line through a contour line drawing algorithm and high-vacancy potential meter data of the area to be identified, and obtaining a potential meter contour line of the area to be identified;
And linearly mapping the potential contour line of the region to be identified onto a single-channel image with preset resolution to obtain a contour line map of the region to be identified.
In a second aspect, an embodiment of the present application provides a land line identification system, the system comprising:
The weather data acquisition module is used for acquiring weather data of an area to be identified, wherein the weather data comprises grid point data and high-altitude potential meter data, and each grid point in the grid point data is used for representing high-altitude wind field data on each longitude and latitude;
the contour map construction module is used for constructing a contour map of the area to be identified according to the high-altitude potential meter data;
the noise filtering module is used for carrying out noise filtering on the high-altitude wind field data to obtain a plurality of filtered target wind field data;
the wind field data mapping module is used for mapping each target wind field data into an image with preset resolution through a preset sign which can be recognized visually to obtain a wind field weather map of the area to be recognized;
and the groove ridge line determining module is used for determining longitude and latitude coordinates of a land line corresponding to the area to be identified based on the contour map and the wind field weather map of the area to be identified.
In a third aspect, embodiments of the present application provide a computer storage medium having stored thereon a plurality of instructions adapted to be loaded by a processor and to perform the above-described method steps.
In a fourth aspect, an embodiment of the present application provides an electronic device, which may include: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the method steps described above.
The technical scheme provided by the embodiment of the application can have the following beneficial effects:
In the embodiment of the application, the noise in the wind field data of the height layer which is close to the ground and is affected by the terrain is filtered in a noise filtering mode for the high-altitude wind field data, so that the land line area is more obvious; meanwhile, the most focused wind field data during land line recognition is abstracted into visually distinguishable symbols, and the most direct information is provided for machine learning, so that the error recognition rate of land line recognition is reduced, and the recognition accuracy of the groove ridge line is improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
FIG. 1 is a flow chart of a land line identification method provided by an embodiment of the present application;
FIG. 2 is a contour map provided by an embodiment of the present application;
FIG. 3 is a wind direction map provided by an embodiment of the present application;
FIG. 4 is a wind direction type map provided by an embodiment of the present application;
FIG. 5 is a schematic representation of visual characterization data provided by an embodiment of the present application;
FIG. 6 is a schematic diagram of a slotline region according to an embodiment of the present disclosure;
FIG. 7 is a schematic diagram of a ridgeline area according to an embodiment of the present application;
FIG. 8 is a flow chart of a training method for model training according to an embodiment of the present application;
FIG. 9 is a schematic diagram of a land line identification system according to an embodiment of the present application;
fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The following description and the drawings sufficiently illustrate specific embodiments of the application to enable those skilled in the art to practice them.
It should be understood that the described embodiments are merely some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of systems and methods that are consistent with aspects of the application as detailed in the accompanying claims.
In the description of the present application, it should be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. The specific meaning of the above terms in the present application will be understood in specific cases by those of ordinary skill in the art. Furthermore, in the description of the present application, unless otherwise indicated, "a plurality" means two or more. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship.
The application provides a land line identification method, a land line identification system, a land line identification medium and electronic equipment, which are used for solving the problems in the related technical problems. According to the technical scheme provided by the application, noise in the wind field data of the altitude layer which is close to the ground and is affected by the terrain is filtered in a noise filtering mode for the high altitude wind field data, so that the land line area is more obvious; meanwhile, the most focused wind field data during land line recognition is abstracted into visually distinguishable symbols, and the most direct information is provided for machine learning, so that the error recognition rate of land line recognition is reduced, the recognition accuracy of groove ridge lines is improved, and the method is described in detail below by adopting an exemplary embodiment.
The method for identifying the land line according to the embodiment of the present application will be described in detail with reference to fig. 1 to 8. The method may be implemented in dependence on a computer program and may be run on a von neumann system-based land line identification system. The computer program may be integrated in the application or may run as a stand-alone tool class application.
Referring to fig. 1, a flow chart of a land line identification method is provided in an embodiment of the present application.
As shown in fig. 1, the method according to the embodiment of the present application may include the following steps:
S101, acquiring meteorological data of an area to be identified, wherein the meteorological data comprises grid point data and high-altitude potential meter data, and each grid point in the grid point data is used for representing high-altitude wind field data on each longitude and latitude;
The area to be identified is an area needing to be identified by a land line, the grid point data is a data format commonly used in the fields of meteorology and climatology, the data is characterized in that the surface of the earth is equally divided into a series of grid points with fixed size and fixed longitude and latitude intervals, physical quantities in all directions are discretely described on each grid point, a three-dimensional physical field in space and time is constructed according to the discrete description, each grid point in the grid point data corresponds to a longitude and latitude coordinate, and the numerical values of meteorological elements such as air temperature, precipitation and wind speed in the place can be represented. The high-vacancy potential meter (Geopotential Height) refers to the height corresponding to the gravitational potential energy of unit mass in a certain atmosphere, and is used for describing the vertical thickness and air pressure distribution of the atmosphere, and in meteorology and climate, high-vacancy potential meter data are often used for analyzing and predicting weather conditions. The preset condition may be a latitude range of 40-170 degrees, a latitude range of 5-80 degrees, and a height of 500hpa. The high altitude wind field data refers to wind speed and wind direction data measured at different heights of the atmosphere.
In the embodiment of the application, when the land line identification is carried out on the area to be identified, firstly, grid point data and high-vacancy potential meter data of the area to be identified in a specified scene are obtained, and meteorological data of the area to be identified are obtained.
S102, constructing a contour map of an area to be identified according to high-vacancy potential meter data;
In the embodiment of the application, in the process of constructing the contour map of the area to be identified according to the high-altitude potential meter data, the method specifically comprises the following steps: drawing a contour line through a contour line drawing algorithm and high-vacancy potential meter data of the area to be identified, and obtaining a potential meter contour line of the area to be identified; and linearly mapping the potential contour line of the region to be identified onto a single-channel image with preset resolution to obtain a contour line map of the region to be identified.
Specifically, longitude and latitude parameters adopted by the contour line algorithm are respectively as follows: the latitude ranges from 40 degrees to 170 degrees and the latitude ranges from 5 degrees to 80 degrees.
In one embodiment, a potential meter contour is obtained according to the high-altitude potential meter data and the contour drawing algorithm, and the potential meter contour is linearly mapped onto a single-channel image with a preset resolution in such a way that the lowest latitude corresponds to the bottom of the image, the highest latitude corresponds to the top of the image, the lowest longitude corresponds to the left part of the image, and the highest longitude corresponds to the right part of the image. For example, can be mapped onto a single channel image at a resolution of 1000 x 1000 as shown in fig. 2.
S103, noise filtering is carried out on the high-altitude wind field data, and a plurality of filtered target wind field data are obtained;
In the embodiment of the application, in the process of carrying out noise filtering on high-altitude wind field data to obtain a plurality of filtered target wind field data, the method specifically comprises the following steps: scanning the high-altitude wind field data of adjacent preset number of points according to lines from the high-altitude wind field data; determining the scanned high-altitude wind field data of adjacent preset number points as a group of high-altitude wind field data to be filtered, and obtaining a plurality of groups of high-altitude wind field data to be filtered; and carrying out mean value calculation on the abscissa and the ordinate contained in each group of high-altitude wind field data to be filtered so as to carry out noise filtering on the high-altitude wind field data and obtain a plurality of filtered target wind field data.
In one embodiment, for example, a specific method of filtering high altitude wind field data to eliminate noise in a wind field horizontal direction is as follows, the lattice point data is scanned by rows, assuming that point0, point1, point2 are three adjacent points of a certain row, the wind field data are (u 0, v 0), (u 1, v 1), (u 2, v 2), respectively, and then each target wind field data after the filtering of point1 is
S104, mapping each target wind field data into an image with preset resolution through a preset sign which can be recognized visually, and obtaining a wind field weather map of the region to be recognized;
the visually distinguishable preset symbols comprise visually distinguishable wind direction identifiers and wind field type identifiers.
In the embodiment of the present application, in a process of mapping each target wind field data to an image with a preset resolution through a preset symbol that can be recognized visually, a wind field weather map of an area to be recognized is obtained, specifically including: acquiring the wind direction in the data of each target wind field; linearly mapping a wind direction mark for representing the wind direction in each target wind field data in an image with preset resolution to obtain a wind direction map of the region to be identified; acquiring positive and negative parameters of a vertical component in each target wind field data to determine a wind field type represented by each target wind field data; linearly mapping a wind field type identifier for representing the wind field type in each target wind field data in an image with preset resolution to obtain a wind direction type map of the region to be identified; and taking the wind direction map and the wind direction type map of the area to be identified as a wind field weather map of the area to be identified.
It should be noted that, the wind direction identifier may be an arrow, and the wind field type identifier may be represented by positive and negative vertical components in the wind field data, or may be represented by any identifier that can be distinguished by other human vision.
In one embodiment, the wind direction in each target wind field data may be mapped onto a 1000 x 1000 resolution single channel image in the manner of an arrow, such as shown in fig. 3. The positive and negative of the vertical component in each target wind field data may indicate whether the wind field is southward or northward, for example using the notation + representing southward wind, -representing the northward wind, the wind field type is mapped onto a 1000 x 1000 resolution single channel image, as shown in fig. 4.
S105, determining longitude and latitude coordinates of a land line corresponding to the area to be identified based on the contour map and the wind farm weather map of the area to be identified.
In the embodiment of the application, in the process of determining the longitude and latitude coordinates of the land line corresponding to the area to be identified based on the contour map and the wind field meteorological map of the area to be identified, the method specifically comprises the following steps: combining the contour map, the wind direction map and the wind direction type map of the area to be identified to obtain visual characterization data of the area to be identified; inputting visual representation data of a region to be identified into a pre-trained land line region positioning model, and outputting a land line region corresponding to the region to be identified; inputting a land line region corresponding to the region to be identified into a pre-trained land line regression model, and outputting a land line corresponding to the region to be identified; and inversely mapping the positions of the groove ridge lines corresponding to the area to be identified to determine longitude and latitude coordinates of the land lines corresponding to the area to be identified.
In one embodiment, the single-channel images (the contour map, the wind direction map and the wind direction type map) are respectively combined into a 3-channel image to obtain the final visual characterization data of the region to be identified, as shown in fig. 5, wherein the contour map can embody the contour curvature information of the potential rice, the wind direction map can embody the wind direction information, and the wind direction type map can embody the north-south information of the wind field.
In an embodiment of the present application, a pre-trained land line region localization model and a pre-trained land line regression model are generated according to the following steps, including: acquiring historical meteorological data of each potential meter in each sub-time period in a preset time period; the historical meteorological data under each potential meter comprises historical grid point data and historical high-altitude potential meter data, and each grid point in the historical grid point data is used for representing historical high-altitude wind field data on each longitude and latitude; constructing a contour map of each sub-time period according to the historical high-vacancy potential meter data; noise filtering is carried out on the historical high-altitude wind field data to obtain a plurality of filtered historical wind field data; mapping each historical wind field data into an image with preset resolution through a preset sign which can be recognized visually to obtain a wind direction map and a wind direction type map of each sub-time period; combining the contour map of each sub-time period, the wind direction map of each sub-time period and the wind direction type map to obtain visual characterization data of each sub-time period; based on the visual representation data for each sub-period, a pre-trained land line area positioning model and a pre-trained land line regression model are generated.
The preset time period is 2013 year-round, and each potential meter data is 500hpa,700hpa and 850hpa high-level data respectively.
In one embodiment, for example, the visual representation data for a certain sub-period is FIG. 5, where FIG. 6 is the groove line region and FIG. 7 is the ridge line region, the region of the groove ridge line may be marked on the visual representation data.
In an embodiment of the present application, in generating a pre-trained land line area positioning model and a pre-trained land line regression model based on visual representation data for each sub-period, the method comprises: marking and picking out a groove line region and a ridge line region from the visual representation data of each sub-time period to obtain a groove line region visual image and a ridge line region visual image of each sub-time period; creating a land line area positioning model; machine learning is carried out on the groove ridge line region positioning model according to the groove line region visual image and the ridge line region visual image of each sub-time period to obtain a pre-trained land line region positioning model; acquiring the longitude and latitude of a groove ridge line from the groove line area visual image and the ridge line area visual image of each sub-time period to obtain land line data of each sub-time period; creating a groove ridge regression model; machine learning is performed on the land line regression model based on the land line data for each sub-period to obtain a pre-trained land line regression model.
Therein, a land line area location model may be created using a location algorithm in deep learning, including but not limited to the ssd, yolo series of neural network algorithms.
The land line area positioning model is a mathematical model capable of positioning a groove line area and a ridge line area, the land line regression model can be constructed by adopting a regression algorithm, and the land line regression model is a mathematical model capable of regressing the longitude and the latitude of the land line.
In the embodiment of the application, the noise in the wind field data of the height layer which is close to the ground and is affected by the terrain is filtered in a noise filtering mode for the high-altitude wind field data, so that the land line area is more obvious; meanwhile, the most focused wind field data during land line recognition is abstracted into visually distinguishable symbols, and the most direct information is provided for machine learning, so that the error recognition rate of land line recognition is reduced, and the recognition accuracy of the groove ridge line is improved.
Referring to fig. 8, a flow chart of a weather situation classification model training method is provided in an embodiment of the application. As shown in fig. 8, the method according to the embodiment of the present application may include the following steps:
S201, acquiring historical meteorological data of each potential meter in each sub-time period in a preset time period;
The historical meteorological data under each potential meter comprises historical grid point data and historical high-altitude potential meter data, and each grid point in the historical grid point data is used for representing historical high-altitude wind field data on each longitude and latitude.
S202, constructing visual representation data of each sub-time period according to each historical meteorological data;
In the embodiment of the application, the process of constructing the visual representation data of each sub-time period according to each historical meteorological data comprises the following steps: constructing a contour map of each sub-time period according to the historical high-vacancy potential meter data; noise filtering is carried out on the historical high-altitude wind field data to obtain a plurality of filtered historical wind field data; mapping each historical wind field data into an image with preset resolution through a preset sign which can be recognized visually to obtain a wind direction map and a wind direction type map of each sub-time period; and merging the contour map of each sub-time period, the wind direction map of each sub-time period and the wind direction type map to obtain visual characterization data of each sub-time period.
S203, marking and picking out a groove line area and a ridge line area from the visual representation data of each sub-time period to obtain a groove line area visual image and a ridge line area visual image of each sub-time period;
s204, creating a land line area positioning model;
S205, machine learning is carried out on the groove ridge line region positioning model according to the groove line region visual image and the ridge line region visual image of each sub-time period to obtain a pre-trained land line region positioning model;
S206, obtaining the longitude and latitude of the groove ridge line from the groove line area visual image and the ridge line area visual image of each sub-time period to obtain the land line data of each sub-time period;
S207, creating a groove ridge regression model;
And S208, performing machine learning on the land line regression model based on the land line data of each sub-time period to obtain a pre-trained land line regression model.
In the embodiment of the application, the noise in the wind field data of the height layer which is close to the ground and is affected by the terrain is filtered in a noise filtering mode for the high-altitude wind field data, so that the land line area is more obvious; meanwhile, the most focused wind field data during land line recognition is abstracted into visually distinguishable symbols, and the most direct information is provided for machine learning, so that the error recognition rate of land line recognition is reduced, and the recognition accuracy of the groove ridge line is improved.
The following are system embodiments of the present application that may be used to perform method embodiments of the present application. For details not disclosed in the system embodiments of the present application, please refer to the method embodiments of the present application.
Referring to fig. 9, a schematic diagram of a land line recognition system according to an exemplary embodiment of the present application is shown. The land line identification system may be implemented as all or part of an electronic device by software, hardware, or a combination of both. The system 1 includes a meteorological data acquisition module 10, a contour map construction module 20, a noise filtering module 30, a wind farm data mapping module 40, and a land line determination module 50.
The weather data acquisition module 10 is configured to acquire weather data of an area to be identified, where the weather data includes grid point data and high-altitude potential meter data, and each grid point in the grid point data is used for representing high-altitude wind field data on each longitude and latitude;
the contour map construction module 20 is used for constructing a contour map of the area to be identified according to the high-altitude potential meter data;
the noise filtering module 30 is configured to perform noise filtering on the high-altitude wind field data to obtain filtered multiple target wind field data;
the wind field data mapping module 40 is configured to map each target wind field data to an image with a preset resolution through a preset symbol that can be recognized visually, so as to obtain a wind field weather map of the area to be recognized;
the land line determining module 50 is configured to determine longitude and latitude coordinates of a land line corresponding to the area to be identified based on the contour map and the wind farm weather map of the area to be identified.
It should be noted that, in the land line recognition system provided in the above embodiment, only the division of the above functional modules is used for illustration when executing the land line recognition method, in practical application, the above functional allocation may be performed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the land line recognition system provided in the above embodiment and the land line recognition method embodiment belong to the same concept, and the implementation process is embodied in the method embodiment, which is not described herein again.
The foregoing embodiment numbers of the present application are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
In the embodiment of the application, the noise in the wind field data of the height layer which is close to the ground and is affected by the terrain is filtered in a noise filtering mode for the high-altitude wind field data, so that the land line area is more obvious; meanwhile, the most focused wind field data during land line recognition is abstracted into visually distinguishable symbols, and the most direct information is provided for machine learning, so that the error recognition rate of land line recognition is reduced, and the recognition accuracy of the groove ridge line is improved.
The present application also provides a computer readable medium having stored thereon program instructions which, when executed by a processor, implement the land line identification method provided by the various method embodiments described above.
The application also provides a computer program product containing instructions which, when run on a computer, cause the computer to perform the land line identification method of the various method embodiments described above.
Referring to fig. 10, a schematic structural diagram of an electronic device is provided in an embodiment of the present application. As shown in fig. 10, the electronic device 1000 may include: at least one processor 1001, at least one network interface 1004, a user interface 1003, a memory 1005, at least one communication bus 1002.
Wherein the communication bus 1002 is used to enable connected communication between these components.
The user interface 1003 may include a Display screen (Display) and a Camera (Camera), and the optional user interface 1003 may further include a standard wired interface and a wireless interface.
The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), among others.
Wherein the processor 1001 may include one or more processing cores. The processor 1001 connects various parts within the overall electronic device 1000 using various interfaces and lines, performs various functions of the electronic device 1000 and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 1005, and invoking data stored in the memory 1005. Alternatively, the processor 1001 may be implemented in at least one hardware form of digital signal Processing (DIGITAL SIGNAL Processing, DSP), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA), programmable logic array (Programmable Logic Array, PLA). The processor 1001 may integrate one or a combination of several of a central processing unit (Central Processing Unit, CPU), an image processor (Graphics Processing Unit, GPU), and a modem, etc. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing the content required to be displayed by the display screen; the modem is used to handle wireless communications. It will be appreciated that the modem may not be integrated into the processor 1001 and may be implemented by a single chip.
The Memory 1005 may include a random access Memory (Random Access Memory, RAM) or a Read-Only Memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer readable medium (non-transitory computer-readable storage medium). The memory 1005 may be used to store instructions, programs, code, sets of codes, or sets of instructions. The memory 1005 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-described respective method embodiments, etc.; the storage data area may store data or the like referred to in the above respective method embodiments. The memory 1005 may also optionally be at least one storage system located remotely from the processor 1001. As shown in fig. 10, an operating system, a network communication module, a user interface module, and a land line recognition application may be included in the memory 1005, which is a type of computer storage medium.
In the electronic device 1000 shown in fig. 10, the user interface 1003 is mainly used for providing an input interface for a user, and acquiring data input by the user; and the processor 1001 may be configured to invoke the land line identification application stored in the memory 1005 and specifically:
Acquiring meteorological data of an area to be identified, wherein the meteorological data comprises grid point data and high-altitude potential meter data, and each grid point in the grid point data is used for representing high-altitude wind field data on each longitude and latitude;
constructing a contour map of the region to be identified according to the high-vacancy potential meter data;
noise filtering is carried out on the high-altitude wind field data to obtain a plurality of filtered target wind field data;
mapping each target wind field data into an image with preset resolution through a preset sign which can be recognized visually to obtain a wind field weather map of the region to be recognized;
And determining longitude and latitude coordinates of the land line corresponding to the area to be identified based on the contour map and the wind field meteorological map of the area to be identified.
In one embodiment, the processor 1001, when performing noise filtering on the high altitude wind field data to obtain filtered target wind field data, specifically performs the following operations:
scanning the high-altitude wind field data of adjacent preset number of points according to lines from the high-altitude wind field data;
Determining the scanned high-altitude wind field data of adjacent preset number points as a group of high-altitude wind field data to be filtered, and obtaining a plurality of groups of high-altitude wind field data to be filtered;
and carrying out mean value calculation on the abscissa and the ordinate contained in each group of high-altitude wind field data to be filtered so as to carry out noise filtering on the high-altitude wind field data and obtain a plurality of filtered target wind field data.
In one embodiment, the processor 1001, when performing mapping each target wind field data to an image with a preset resolution through a preset symbol that is visually distinguishable, obtains a wind field weather map of an area to be identified, specifically performs the following operations:
acquiring the wind direction in the data of each target wind field;
Linearly mapping a wind direction mark for representing the wind direction in each target wind field data in an image with preset resolution to obtain a wind direction map of the region to be identified;
Acquiring positive and negative parameters of a vertical component in each target wind field data to determine a wind field type represented by each target wind field data;
Linearly mapping a wind field type identifier for representing the wind field type in each target wind field data in an image with preset resolution to obtain a wind direction type map of the region to be identified;
and taking the wind direction map and the wind direction type map of the area to be identified as a wind field weather map of the area to be identified.
In one embodiment, the processor 1001, when executing determining the longitude and latitude coordinates of the slot ridge line corresponding to the area to be identified based on the contour map and the wind farm weather map of the area to be identified, specifically executes the following operations:
combining the contour map, the wind direction map and the wind direction type map of the area to be identified to obtain visual characterization data of the area to be identified;
inputting visual representation data of a region to be identified into a pre-trained land line region positioning model, and outputting a land line region corresponding to the region to be identified;
inputting a land line region corresponding to the region to be identified into a pre-trained land line regression model, and outputting a land line corresponding to the region to be identified;
And inversely mapping the positions of the groove ridge lines corresponding to the area to be identified to determine longitude and latitude coordinates of the land lines corresponding to the area to be identified.
In one embodiment, the processor 1001, when executing the generation of the pre-trained land line region localization model and the pre-trained land line regression model, specifically performs the following:
Acquiring historical meteorological data of each potential meter in each sub-time period in a preset time period; the historical meteorological data under each potential meter comprises historical grid point data and historical high-altitude potential meter data, and each grid point in the historical grid point data is used for representing historical high-altitude wind field data on each longitude and latitude;
constructing a contour map of each sub-time period according to the historical high-vacancy potential meter data;
noise filtering is carried out on the historical high-altitude wind field data to obtain a plurality of filtered historical wind field data;
mapping each historical wind field data into an image with preset resolution through a preset sign which can be recognized visually to obtain a wind direction map and a wind direction type map of each sub-time period;
combining the contour map of each sub-time period, the wind direction map of each sub-time period and the wind direction type map to obtain visual characterization data of each sub-time period;
based on the visual representation data for each sub-period, a pre-trained land line area positioning model and a pre-trained land line regression model are generated.
In one embodiment, the processor 1001, in executing the pre-trained land line region localization model and the pre-trained land line regression model based on the visual representation data for each sub-period, specifically performs the following:
Marking and picking out a groove line region and a ridge line region from the visual representation data of each sub-time period to obtain a groove line region visual image and a ridge line region visual image of each sub-time period;
Creating a land line area positioning model;
Machine learning is carried out on the groove ridge line region positioning model according to the groove line region visual image and the ridge line region visual image of each sub-time period to obtain a pre-trained land line region positioning model;
acquiring the longitude and latitude of a groove ridge line from the groove line area visual image and the ridge line area visual image of each sub-time period to obtain land line data of each sub-time period;
creating a groove ridge regression model;
machine learning is performed on the land line regression model based on the land line data for each sub-period to obtain a pre-trained land line regression model.
In one embodiment, the processor 1001, when executing the construction of the contour map of the area to be identified from the high-altitude potential meter data, specifically performs the following operations:
Drawing a contour line through a contour line drawing algorithm and high-vacancy potential meter data of the area to be identified, and obtaining a potential meter contour line of the area to be identified;
And linearly mapping the potential contour line of the region to be identified onto a single-channel image with preset resolution to obtain a contour line map of the region to be identified.
In the embodiment of the application, the noise in the wind field data of the height layer which is close to the ground and is affected by the terrain is filtered in a noise filtering mode for the high-altitude wind field data, so that the land line area is more obvious; meanwhile, the most focused wind field data during land line recognition is abstracted into visually distinguishable symbols, and the most direct information is provided for machine learning, so that the error recognition rate of land line recognition is reduced, and the recognition accuracy of the groove ridge line is improved.
Those skilled in the art will appreciate that implementing all or part of the above-described embodiment methods may be accomplished by computer programs to instruct the associated hardware, and that the land line identification program may be stored in a computer readable storage medium, which when executed may include the above-described embodiment methods. The storage medium of the land line identification program may be a magnetic disk, an optical disk, a read-only memory, a random access memory, or the like.
The foregoing disclosure is illustrative of the present application and is not to be construed as limiting the scope of the application, which is defined by the appended claims.
Claims (10)
1. A land line identification method, said method comprising:
Acquiring meteorological data of an area to be identified, wherein the meteorological data comprises grid point data and high-altitude potential meter data, and each grid point in the grid point data is used for representing high-altitude wind field data on each longitude and latitude;
Constructing a contour map of the region to be identified according to the high-altitude potential meter data;
noise filtering is carried out on the high-altitude wind field data to obtain a plurality of filtered target wind field data;
Mapping each target wind field data into an image with preset resolution through a preset sign which can be recognized visually, and obtaining a wind field weather map of the region to be recognized;
And determining longitude and latitude coordinates of a land line corresponding to the area to be identified based on the contour map of the area to be identified and the wind field weather map.
2. The method of claim 1, wherein noise filtering the high altitude wind field data to obtain a plurality of filtered target wind field data comprises:
scanning the high-altitude wind field data of adjacent preset number of points according to lines from the high-altitude wind field data;
Determining the scanned high-altitude wind field data of adjacent preset number points as a group of high-altitude wind field data to be filtered, and obtaining a plurality of groups of high-altitude wind field data to be filtered;
And carrying out mean value calculation on the abscissa and the ordinate contained in each group of high-altitude wind field data to be filtered so as to carry out noise filtering on the high-altitude wind field data and obtain a plurality of filtered target wind field data.
3. The method of claim 1, wherein the visually identifiable preset symbols comprise a visually identifiable wind direction identification and a wind field type identification;
Mapping each target wind field data to an image with preset resolution through a preset sign which can be recognized visually to obtain a wind field weather map of the region to be recognized, wherein the method comprises the following steps:
acquiring the wind direction in the data of each target wind field;
linearly mapping the wind direction identification for representing the wind direction in the data of each target wind field in an image with preset resolution to obtain a wind direction map of the region to be identified;
acquiring positive and negative parameters of a vertical component in each target wind field data to determine a wind field type represented by each target wind field data;
Linearly mapping the wind field type identifier for representing the wind field type in each target wind field data in an image with preset resolution to obtain a wind direction type map of the region to be identified;
and taking the wind direction map and the wind direction type map of the area to be identified as a wind field weather map of the area to be identified.
4. The method according to claim 3, wherein the determining longitude and latitude coordinates of the land line corresponding to the area to be identified based on the contour map of the area to be identified and the wind field weather map includes:
Combining the contour map of the area to be identified, the wind direction map and the wind direction type map to obtain visual characterization data of the area to be identified;
inputting the visual representation data of the area to be identified into a pre-trained land line area positioning model, and outputting a land line area corresponding to the area to be identified;
inputting the land line region corresponding to the region to be identified into a pre-trained land line regression model, and outputting the land line corresponding to the region to be identified;
and inversely mapping the positions of the groove ridge lines corresponding to the area to be identified to determine longitude and latitude coordinates of the land lines corresponding to the area to be identified.
5. The method of claim 4, wherein generating the pre-trained land line region localization model and the pre-trained land line regression model comprises:
Acquiring historical meteorological data of each potential meter in each sub-time period in a preset time period; the historical meteorological data under each potential meter comprises historical grid point data and historical high-altitude potential meter data, and each grid point in the historical grid point data is used for representing historical high-altitude wind field data on each longitude and latitude;
constructing a contour map of each sub-time period according to the historical high-vacancy potential meter data;
noise filtering is carried out on the historical high-altitude wind field data to obtain a plurality of filtered historical wind field data;
Mapping each historical wind field data into an image with preset resolution through a preset sign which can be recognized visually, and obtaining a wind direction map and a wind direction type map of each sub-time period;
combining the contour map of each sub-time period, the wind direction map of each sub-time period and the wind direction type map to obtain visual representation data of each sub-time period;
Based on the visual representation data for each sub-time period, a pre-trained land line region localization model and a pre-trained land line regression model are generated.
6. The method of claim 5, wherein generating a pre-trained land line region localization model and a pre-trained land line regression model based on the visual representation data for each sub-period comprises:
Marking and picking out a groove line region and a ridge line region from the visual representation data of each sub-time period to obtain a groove line region visual image and a ridge line region visual image of each sub-time period;
Creating a land line area positioning model;
Performing machine learning on the land line region positioning model according to the groove line region visual image and the ridge line region visual image of each sub-time period to obtain a pre-trained land line region positioning model;
Acquiring the longitude and latitude of a groove ridge line from the groove line area visual image and the ridge line area visual image of each sub-time period to obtain land line data of each sub-time period;
creating a groove ridge regression model;
and performing machine learning on the land line regression model based on the land line data of each sub-time period to obtain a pre-trained land line regression model.
7. The method according to claim 1, wherein constructing a contour map of the area to be identified from the high-altitude potential meter data comprises:
drawing a contour line through a contour line drawing algorithm and high-vacancy potential meter data of the region to be identified, and obtaining a potential meter contour line of the region to be identified;
and linearly mapping the potential contour line of the region to be identified onto a single-channel image with preset resolution to obtain a contour line map of the region to be identified.
8. A land line identification system, said system comprising:
The weather data acquisition module is used for acquiring weather data of an area to be identified, wherein the weather data comprise grid point data and high-altitude potential meter data, and each grid point in the grid point data is used for representing high-altitude wind field data on each longitude and latitude;
The contour map construction module is used for constructing a contour map of the area to be identified according to the high-altitude potential meter data;
The noise filtering module is used for carrying out noise filtering on the high-altitude wind field data to obtain a plurality of filtered target wind field data;
The wind field data mapping module is used for mapping each target wind field data into an image with preset resolution through a preset sign which can be recognized visually to obtain a wind field weather map of the region to be recognized;
And the groove ridge line determining module is used for determining longitude and latitude coordinates of a land line corresponding to the area to be identified based on the contour map of the area to be identified and the wind field weather map.
9. A computer storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform the method of any of claims 1-7.
10. An electronic device, comprising: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410174958.6A CN117994661A (en) | 2024-02-07 | 2024-02-07 | Land line identification method, system, medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410174958.6A CN117994661A (en) | 2024-02-07 | 2024-02-07 | Land line identification method, system, medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117994661A true CN117994661A (en) | 2024-05-07 |
Family
ID=90898736
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410174958.6A Pending CN117994661A (en) | 2024-02-07 | 2024-02-07 | Land line identification method, system, medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117994661A (en) |
-
2024
- 2024-02-07 CN CN202410174958.6A patent/CN117994661A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112990086A (en) | Remote sensing image building detection method and device and computer readable storage medium | |
| CN111723464A (en) | Typhoon elliptic wind field parametric simulation method based on remote sensing image characteristics | |
| CN112329789B (en) | Point cloud extraction method and device, computer equipment and storage medium | |
| Grigillo et al. | Automated building extraction from IKONOS images in suburban areas | |
| CN112180471A (en) | Weather forecasting method, device, equipment and storage medium | |
| CN113658292A (en) | Method, device and equipment for generating meteorological data color spot pattern and storage medium | |
| CN116681959B (en) | Machine learning-based frontal line identification method and device, storage medium and terminal | |
| CN115439753A (en) | Steep river bank identification method and system based on DEM | |
| CN114581464A (en) | Boundary detection method and device, electronic equipment and computer readable storage medium | |
| CN114565057A (en) | Machine learning-based grading field identification method and device, storage medium and terminal | |
| CN115861816B (en) | Three-dimensional low-vortex recognition method and device, storage medium and terminal | |
| CN115731560B (en) | Deep learning-based slot line identification method and device, storage medium and terminal | |
| CN116071651B (en) | Voltage equalizing field identification method and device, storage medium and terminal | |
| CN113593006A (en) | Meteorological data spatial interpolation refining method and system based on deep learning | |
| CN116051777B (en) | Super high-rise building extraction method, apparatus and readable storage medium | |
| CN114842356B (en) | High-resolution earth surface type sample automatic generation method, system and equipment | |
| CN117994661A (en) | Land line identification method, system, medium and electronic equipment | |
| CN116934139A (en) | Method, device and equipment for identifying ecological function space response of water in town process | |
| CN112527442B (en) | Environment data multi-dimensional display method, device, medium and terminal equipment | |
| CN112668448B (en) | Ecological process change analysis method, device, medium and terminal equipment | |
| CN110413656B (en) | Rapid flow axis automatic identification method based on high spatial resolution numerical mode | |
| CN114565854A (en) | Intelligent image cloud identification system and method | |
| CN116759009B (en) | Ozone forecasting method, system and medium matched with weather through machine learning | |
| CN108597013B (en) | Method for snapshot map filling of meteorological hydrological data in specific area | |
| CN113111793A (en) | Tree identification method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |