CN116071651B - Voltage equalizing field identification method and device, storage medium and terminal - Google Patents
Voltage equalizing field identification method and device, storage medium and terminal Download PDFInfo
- Publication number
- CN116071651B CN116071651B CN202310133051.0A CN202310133051A CN116071651B CN 116071651 B CN116071651 B CN 116071651B CN 202310133051 A CN202310133051 A CN 202310133051A CN 116071651 B CN116071651 B CN 116071651B
- Authority
- CN
- China
- Prior art keywords
- field
- equalizing
- model
- weather
- voltage
- 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
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000011218 segmentation Effects 0.000 claims abstract description 49
- 238000010586 diagram Methods 0.000 claims abstract description 33
- 238000004590 computer program Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 6
- 238000013178 mathematical model Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
-
- 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
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/245—Aligning, centring, orientation detection or correction of the image by locating a pattern; Special marks for positioning
-
- 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
- G06V10/267—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 by performing operations on regions, e.g. growing, shrinking or watersheds
-
- 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
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The application discloses a voltage equalizing field identification method, a device, a storage medium and a terminal, wherein the method comprises the following steps: constructing a first weather map corresponding to the region to be identified according to weather original data of the region to be identified at the moment to be predicted; inputting the first weather map into a pre-trained equalizing field positioning model, and outputting a second weather map corresponding to the meteorological original data, wherein the second weather map comprises a positioning frame of an equalizing field area; and taking out an image area corresponding to a positioning frame containing the equalizing field area in the second weather map, inputting a pre-trained equalizing field segmentation model, and outputting an equalizing field image corresponding to meteorological original data. According to the application, the positioning frame of the equalizing field is positioned in the weather diagram through the model, and then the image area corresponding to the positioning frame is further segmented by adopting the model, so that the local specific equalizing field image in the image area is determined, the automatic recognition mode of the model can improve the recognition efficiency of the equalizing field, and meanwhile, the accuracy of the equalizing field is improved from thick to thin.
Description
Technical Field
The application relates to the technical field of automatic identification of weather systems, in particular to a method and a device for identifying a voltage equalizing field, a storage medium and a terminal.
Background
The pressure equalizing field is ground weather which is extremely small in air pressure change within a range and cannot be formed by wind formed by air pressure gradient force, and important weather systems and weather phenomena are often accompanied nearby, for example, weak wind power occurs within the range, so that dust haze weather occurs. Along with frequent disaster events caused by the equalizing field, the equalizing field activity is widely focused, so that equalizing field analysis becomes an important work in weather forecast business.
In the existing equalizing field analysis scheme, the equalizing field analysis is still mainly manual analysis, namely, a forecaster is relied on to judge whether the weather situation of an urban point is an equalizing field or not on a weather map. Because manual analysis takes valuable business time from a forecaster and is subjective, accuracy of the grading field is reduced.
Disclosure of Invention
The embodiment of the application provides a voltage equalizing field identification method, a device, a storage medium and a terminal. 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 method for identifying a voltage equalizing field, where the method includes:
constructing a first weather map corresponding to the region to be identified according to weather original data of the region to be identified at the moment to be predicted;
inputting the first weather map into a pre-trained equalizing field positioning model, and outputting a second weather map corresponding to the meteorological original data, wherein the second weather map comprises a positioning frame of an equalizing field area;
and taking out an image area corresponding to a positioning frame containing the equalizing field area in the second weather map, inputting a pre-trained equalizing field segmentation model, and outputting an equalizing field image corresponding to meteorological original data.
Optionally, before the weather original data at the time to be predicted according to the region to be identified, the method further includes:
constructing a third weather map set corresponding to the region to be identified according to the historical meteorological data of the region to be identified;
marking a positioning frame containing a voltage-sharing field area for each third weather diagram in the third weather diagram set according to the received voltage-sharing field marking instruction to obtain a fourth weather diagram set;
model training of the positioning model is carried out according to the fourth weather diagram set, and a pre-trained equalizing field positioning model is obtained;
The image area corresponding to the positioning frame of each fourth standard weather image in the fourth weather image set is scratched, and a plurality of first equalizing field images are obtained;
and performing model training of the segmentation model according to the plurality of first voltage-sharing field images to obtain a pre-trained voltage-sharing field segmentation model.
Optionally, constructing a third weather map set corresponding to the region to be identified according to the historical meteorological data of the region to be identified, including:
determining a historical time period to be acquired, and equally dividing the historical time period into a plurality of sub-historical time periods;
collecting historical meteorological data of each sub-historical time period;
and constructing a standard weather map corresponding to each sub-historical time period according to the historical meteorological data of each sub-historical time period, and obtaining a third weather map set corresponding to the region to be identified.
Optionally, constructing a standard weather map corresponding to each sub-historical time period according to the historical meteorological data of each sub-historical time period, including:
interpolating wind field data of the historical meteorological data of each sub-historical time period into grids with preset first longitude and latitude intervals to obtain wind field grid point data;
constructing arrow symbols representing wind field data according to the wind field point data, and projecting the arrow symbols onto a plan to obtain a fifth weather diagram;
And drawing isobars with preset intervals according to the air pressure data of the historical meteorological data of each sub-historical time period, and projecting the isobars onto a fifth weather map to obtain a standard weather map corresponding to each sub-historical time period.
Optionally, performing model training of the segmentation model according to the plurality of first voltage-sharing field images to obtain a pre-trained voltage-sharing field segmentation model, including:
marking boundaries corresponding to the grid point data of the wind field meeting preset conditions in each first voltage-sharing field image to obtain a plurality of second voltage-sharing field images;
binarizing each second equalizing field image to obtain a plurality of third equalizing field images;
creating a voltage-sharing field segmentation model;
taking each third equalizing field image as a label of a second equalizing field image corresponding to the third equalizing field image, inputting each second equalizing field image with the label into an equalizing field segmentation model, and outputting a first model loss value;
when the loss value of the first model reaches the minimum, generating a pre-trained equalizing field segmentation model; or when the first model loss value does not reach the minimum, adjusting the model parameters, and continuing to perform the steps of taking each third equalizing field image as the label of the corresponding second equalizing field image, and inputting each second equalizing field image after the label is set into the equalizing field dividing model.
Optionally, marking a boundary corresponding to the wind field grid point data meeting a preset condition in each first voltage-sharing field image to obtain a plurality of second voltage-sharing field images, including:
determining a center point of each first grading field image;
taking the center point of each first voltage-sharing field image as an origin, and acquiring arrow symbols representing wind field data corresponding to the wind field grid point data in the first step range in each first voltage-sharing field image according to a preset step range;
calculating a first vector average value of arrow symbols representing the wind field data corresponding to the wind field grid point data in the first step range;
taking the central point of each first voltage-sharing field image as an origin, and acquiring arrow symbols representing wind field data corresponding to the wind field grid point data in the second step range in each first voltage-sharing field image according to the preset step range;
calculating a second vector average value of arrow symbols representing the wind field data corresponding to the wind field grid point data in a second step range;
when the difference value between the second vector average value and the first vector average value is larger than or equal to a preset threshold value, marking the boundary of an arrow symbol representing the wind field data corresponding to the wind field grid point data in the first step range, and obtaining a plurality of second voltage-sharing field images; wherein,
The second step range is greater than the first step range.
Optionally, performing model training of the positioning model according to the fourth weather diagram set to obtain a pre-trained equalizing field positioning model, including:
creating a voltage equalizing field positioning model;
inputting the fourth weather diagram set into a voltage equalizing field positioning model, and outputting a second model loss value;
when the loss value of the second model reaches the minimum, generating a pre-trained equalizing field positioning model; or when the loss value of the second model does not reach the minimum, adjusting the model parameters, and continuing to perform the step of inputting the fourth weather map set into the equalizing field positioning model.
In a second aspect, an embodiment of the present application provides a voltage equalizing field identifying apparatus, including:
the weather map construction module is used for constructing a first weather map corresponding to the region to be identified according to the weather original data of the region to be identified at the moment to be predicted;
the weather map output module is used for inputting the first weather map into a pre-trained equalizing field positioning model and outputting a second weather map corresponding to the original meteorological data, wherein the second weather map comprises a positioning frame of an equalizing field area;
and the voltage-sharing field image output module is used for taking out the image area corresponding to the positioning frame containing the voltage-sharing field area in the second weather image, inputting a pre-trained voltage-sharing field segmentation model and outputting a voltage-sharing field image corresponding to the meteorological original data.
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 a terminal, 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, a voltage-sharing field recognition device firstly constructs a first weather map corresponding to a region to be recognized according to weather original data of the region to be recognized at a moment to be predicted, secondly inputs the first weather map into a pre-trained voltage-sharing field positioning model, outputs a second weather map corresponding to the weather original data, wherein the second weather map comprises a positioning frame of a voltage-sharing field region, finally takes out an image region corresponding to the positioning frame of the voltage-sharing field region in the second weather map, inputs the pre-trained voltage-sharing field segmentation model, and outputs a voltage-sharing field image corresponding to the weather original data. According to the application, the positioning frame of the equalizing field is positioned in the weather diagram through the model, and then the image area corresponding to the positioning frame is further segmented by adopting the model, so that the local specific equalizing field image in the image area is determined, the automatic recognition mode of the model can improve the recognition efficiency of the equalizing field, and meanwhile, the accuracy of the equalizing field is improved from thick to thin.
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 schematic flow chart of a method for identifying a voltage equalizing field according to an embodiment of the present application;
FIG. 2 is a schematic illustration of a weather map provided by an embodiment of the present application;
FIG. 3 is a schematic flow chart of a model training method according to an embodiment of the present application;
FIG. 4 is a schematic diagram of a grading field marked in a weather map according to an embodiment of the present application;
fig. 5 is a schematic diagram of a voltage equalizing field in a weather map extracted by matting according to an embodiment of the present application;
fig. 6 is a schematic diagram of a boundary labeling process for a voltage-sharing field image extracted by matting according to an embodiment of the present application;
FIG. 7 is a schematic diagram of binarizing a boundary-marked grading field image according to an embodiment of the present application;
fig. 8 is a schematic structural diagram of a voltage equalizing field identifying device according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of a terminal according to an embodiment of the present application.
Detailed Description
The following description and the drawings sufficiently illustrate specific embodiments of the invention 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 invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
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 invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention as detailed in the accompanying claims.
In the description of the present invention, 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 invention will be understood in specific cases by those of ordinary skill in the art. Furthermore, in the description of the present invention, 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 voltage equalizing field identification method, a voltage equalizing field identification device, a storage medium and a terminal, which are used for solving the problems existing in the related technical problems. According to the technical scheme provided by the application, the positioning frame of the voltage-sharing field is positioned in the weather diagram through the model, then the image area corresponding to the positioning frame is further segmented by adopting the model to determine the local specific voltage-sharing field image in the image area, the automatic recognition mode of the model can improve the recognition efficiency of the voltage-sharing field, and meanwhile, the accuracy of the voltage-sharing field is improved from a thick mode to a thin mode, and the method is described in detail by adopting an exemplary embodiment.
The voltage equalizing field identifying method provided by the embodiment of the application is described in detail below with reference to fig. 1 to 7. The method can be implemented by means of a computer program and can be run on a voltage-sharing field recognition device based on von neumann 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 voltage equalizing field 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, constructing a first weather map corresponding to a region to be identified according to weather original data of the region to be identified at a moment to be predicted;
the region to be identified is a certain region, such as a certain province, a certain city or a certain county, which needs to be identified by the equalizing field. The time to be predicted is a future period of time after the current time when the voltage-sharing field identification needs to be performed, and the time to be predicted can be set according to a specific identification scene. The weather original data is the weather original data of the time to be predicted, which is estimated according to site data observed a period of time before the current time, and can be determined based on the existing weather data estimation technology.
In the embodiment of the application, when a first weather map corresponding to a region to be identified is constructed according to weather original data of the region to be identified at a moment to be predicted, firstly, weather data of the region to be identified at the moment to be predicted is obtained, wind field data of the weather data are interpolated into grids with preset first longitude and latitude intervals to obtain wind field point data, the wind field point data comprise horizontal components and vertical components, the horizontal components and the vertical components are converted into arrow symbols representing the wind field data and projected onto a plane map to obtain a target weather map, and finally, isobars of the preset intervals drawn by the air pressure data of the weather data are projected onto the target weather map to obtain the first weather map corresponding to the region to be identified.
Specifically, the algorithm adopted when the wind field data is interpolated into the grid with the preset first longitude and latitude interval is an inverse distance weighted interpolation algorithm, and the algorithm for projection at least comprises any one of a mercator projection algorithm, a wgs84 projection algorithm and a lambert projection algorithm.
In one possible implementation, firstly, weather data of a region to be identified at a moment to be predicted is acquired, the weather data are interpolated into grids with longitude and latitude intervals of 0.5 degrees through an inverse distance weighted interpolation algorithm, wind field data of each grid point have a horizontal component u and a vertical component v, and the components u and v are abstracted into arrows to be projected onto a target plane through a mercator projection algorithm. And then, the barometric pressure data of the meteorological data are drawn into equal pressure lines with the interval of 2.5hpa, the equal pressure lines are projected onto a target plane by using an ink-card-holder projection algorithm, and finally, a first barometric map corresponding to the region to be identified is obtained, for example, as shown in fig. 2.
When generating the weather data of the region to be identified at the moment to be predicted, firstly acquiring the site data of a section of preset history period of the region to be identified before the current moment, then pushing out the site data under the moment to be predicted according to the site data, merging the site data according to a certain geometric form grid, calculating the average value of the data in each grid, and placing the average value in the center of the grid, thereby generating the weather data of the region to be identified at the moment to be predicted. The application converts the discrete site data into the space continuous and regular grid point sequence by utilizing the space interpolation technology, can effectively reflect the space information of the climate elements, and greatly improves the climate representativeness of the climate data sequence in the corresponding grid range.
S102, inputting a first weather map into a pre-trained equalizing field positioning model, and outputting a second weather map corresponding to weather original data, wherein the second weather map comprises a positioning frame of an equalizing field area;
wherein the pre-trained equalization field positioning model is a mathematical model capable of positioning a positioning frame comprising an equalization field region from the first atmospheric map.
In the embodiment of the application, when a pre-trained equalizing field positioning model is generated, a third weather map set corresponding to a region to be identified is firstly constructed according to historical meteorological data of the region to be identified, then a positioning frame containing an equalizing field area is marked for each third weather map in the third weather map set according to a received equalizing field marking instruction to obtain a fourth weather map set, and finally model training of the positioning model is carried out according to the fourth weather map set to obtain the pre-trained equalizing field positioning model.
In one possible implementation manner, after the first weather map is obtained, the first weather map needs to be input into a pre-trained voltage-sharing field positioning model for processing, and a second weather map corresponding to the meteorological original data is output, wherein the second weather map comprises a positioning frame of a voltage-sharing field area.
And S103, taking out an image area corresponding to a positioning frame containing the equalizing field area in the second weather map, inputting a pre-trained equalizing field segmentation model, and outputting an equalizing field image corresponding to meteorological original data.
The pre-trained equalizing field segmentation model is a mathematical model capable of further segmenting equalizing field images in a positioning frame containing equalizing field areas.
In the embodiment of the application, when a pre-trained equalizing field segmentation model is generated, firstly, an image area corresponding to a positioning frame of each fourth standard weather image in a fourth weather image set is scratched to obtain a plurality of first equalizing field images, and then model training of the segmentation model is carried out according to the plurality of first equalizing field images to obtain the pre-trained equalizing field segmentation model.
In one possible implementation manner, after the second weather map is obtained, the image area corresponding to the positioning frame containing the equalizing field area in the second weather map is taken out, a pre-trained equalizing field segmentation model is input, and an equalizing field image corresponding to the meteorological original data is output.
In the embodiment of the application, a voltage-sharing field recognition device firstly constructs a first weather map corresponding to a region to be recognized according to weather original data of the region to be recognized at a moment to be predicted, secondly inputs the first weather map into a pre-trained voltage-sharing field positioning model, outputs a second weather map corresponding to the weather original data, wherein the second weather map comprises a positioning frame of a voltage-sharing field region, finally takes out an image region corresponding to the positioning frame of the voltage-sharing field region in the second weather map, inputs the pre-trained voltage-sharing field segmentation model, and outputs a voltage-sharing field image corresponding to the weather original data. According to the application, the positioning frame of the equalizing field is positioned in the weather diagram through the model, and then the image area corresponding to the positioning frame is further segmented by adopting the model, so that the local specific equalizing field image in the image area is determined, the automatic recognition mode of the model can improve the recognition efficiency of the equalizing field, and meanwhile, the accuracy of the equalizing field is improved from thick to thin.
Referring to fig. 3, a flow chart of a model training method is provided in an embodiment of the present application. As shown in fig. 3, the method according to the embodiment of the present application may include the following steps:
s201, constructing a third weather map set corresponding to the region to be identified according to historical meteorological data of the region to be identified;
in the embodiment of the application, the weather map can be constructed according to the historical meteorological data of the region to be identified in various modes, and a specific implementation mode can be selected according to actual application requirements.
In a preferred implementation manner, when a third weather map set corresponding to a region to be identified is constructed according to historical weather data of the region to be identified, firstly, a historical time period to be acquired is determined, the historical time period is equally divided into a plurality of sub-historical time periods, then the historical weather data of each sub-historical time period is acquired, and finally, a standard weather map corresponding to each sub-historical time period is constructed according to the historical weather data of each sub-historical time period, so that the third weather map set corresponding to the region to be identified is obtained.
In particular, the historical period to be acquired may be a five year standard weather map of 17 years to 21 years.
Specifically, when a standard weather map corresponding to each sub-historical time period is constructed according to the historical meteorological data of each sub-historical time period, firstly, wind field data of the historical meteorological data of each sub-historical time period is interpolated into grids with preset first longitude and latitude intervals to obtain wind field grid point data, then arrow symbols representing the wind field data are constructed according to the wind field grid point data and projected onto a plane map to obtain a fifth weather map, and finally, isobars with preset intervals are drawn according to the air pressure data of the historical meteorological data of each sub-historical time period and projected onto the fifth weather map to obtain the standard weather map corresponding to each sub-historical time period, for example, as shown in fig. 2. The wind field data of the historical meteorological data of each sub-historical time period can be interpolated into grids with preset first longitude and latitude intervals by adopting an inverse distance weighted interpolation algorithm, and other difference algorithms can be adopted.
S202, marking a positioning frame containing a voltage-sharing field area for each third weather map in the third weather map set according to the received voltage-sharing field marking instruction, and obtaining a fourth weather map set;
in the embodiment of the application, after a received grading field labeling instruction, a positioning frame containing a grading field area is labeled for each third weather map in the third weather map set to obtain a fourth weather map set. The marked positioning frame containing the equalizing field area is shown in fig. 4, for example.
S203, performing model training of a positioning model according to a fourth weather diagram set to obtain a pre-trained equalizing field positioning model;
in the embodiment of the application, when model training of a positioning model is performed according to a fourth weather diagram set to obtain a pre-trained equalizing field positioning model, firstly creating the equalizing field positioning model, then inputting the fourth weather diagram set into the equalizing field positioning model, outputting a second model loss value, and finally generating the pre-trained equalizing field positioning model when the second model loss value reaches the minimum; or when the loss value of the second model does not reach the minimum, adjusting the model parameters, and continuing to perform the step of inputting the fourth weather map set into the equalizing field positioning model.
Specifically, the voltage-sharing field positioning model can be created by adopting a yolo series neural network, and other neural networks can also be adopted.
S204, the image area corresponding to the positioning frame of each fourth standard weather image in the fourth weather image set is scratched, and a plurality of first voltage-sharing field images are obtained;
in the embodiment of the present application, after the fourth weather pattern set is obtained, an image area corresponding to a positioning frame of each fourth standard weather pattern in the fourth weather pattern set needs to be scratched to obtain a plurality of first voltage-sharing field images, where the first voltage-sharing field images are shown in fig. 5, for example.
S205, performing model training of a segmentation model according to the plurality of first voltage-sharing field images to obtain a pre-trained voltage-sharing field segmentation model.
In the embodiment of the application, when model training of a segmentation model is carried out according to a plurality of first voltage-sharing field images to obtain a pre-trained voltage-sharing field segmentation model, firstly, marking boundaries corresponding to wind field point data meeting preset conditions in each first voltage-sharing field image to obtain a plurality of second voltage-sharing field images, then, carrying out binarization processing on each second voltage-sharing field image to obtain a plurality of third voltage-sharing field images, then, creating the voltage-sharing field segmentation model, secondly, taking each third voltage-sharing field image as a label of the corresponding second voltage-sharing field image, inputting each second voltage-sharing field image with the label set into the voltage-sharing field segmentation model, outputting a first model loss value, and finally, when the first model loss value reaches the minimum, generating the pre-trained voltage-sharing field segmentation model; or when the first model loss value does not reach the minimum, adjusting the model parameters, and continuing to perform the steps of taking each third equalizing field image as the label of the corresponding second equalizing field image, and inputting each second equalizing field image after the label is set into the equalizing field dividing model. The voltage-sharing field segmentation model can be created by adopting a unet neural network, and can also be created by adopting other neural networks. Each second grading field picture is for example shown in fig. 6 and each third grading field picture is for example shown in fig. 7. The binarization process is to set 255 inside the boundary region (i.e., the equalizing field region) and 0 outside the boundary region.
Specifically, when the boundaries corresponding to the wind field point data meeting the preset conditions are marked to obtain a plurality of second voltage-sharing field images, firstly determining the center point of each first voltage-sharing field image, then taking the center point of each first voltage-sharing field image as the original point, acquiring the arrow mark representing the wind field data corresponding to the wind field point data in the first ladder range in each first voltage-sharing field image according to the preset ladder range, then calculating the first vector average value of the arrow mark representing the wind field data corresponding to the wind field point data in the first ladder range, secondly taking the center point of each first voltage-sharing field image as the original point, acquiring the arrow mark representing the wind field data corresponding to the wind field point data in the second ladder range in each first voltage-sharing field image according to the preset ladder range, then calculating the second vector average value representing the arrow mark representing the wind field data corresponding to the wind field point data in the second ladder range, and finally marking the boundaries of the arrow mark representing the wind field data corresponding to the wind field point data in the first ladder range when the difference value between the second vector average value and the first vector average value is greater than or equal to the threshold value; wherein the second step range is greater than the first step range.
Further, when the difference between the second vector average value and the first vector average value is smaller than a preset threshold value, at this time, according to a preset step range, acquiring an arrow symbol representing wind field data corresponding to wind field grid point data in a next step range in each first voltage-sharing field image, calculating a vector average value corresponding to the arrow symbol representing wind field data corresponding to the wind field grid point data in the next step range, and calculating a vector average value corresponding to the arrow symbol representing wind field data corresponding to the wind field grid point data in a previous step range until the difference value is larger than or equal to the preset threshold value, and stopping traversing.
In the embodiment of the application, a voltage-sharing field recognition device firstly constructs a first weather map corresponding to a region to be recognized according to weather original data of the region to be recognized at a moment to be predicted, secondly inputs the first weather map into a pre-trained voltage-sharing field positioning model, outputs a second weather map corresponding to the weather original data, wherein the second weather map comprises a positioning frame of a voltage-sharing field region, finally takes out an image region corresponding to the positioning frame of the voltage-sharing field region in the second weather map, inputs the pre-trained voltage-sharing field segmentation model, and outputs a voltage-sharing field image corresponding to the weather original data. According to the application, the positioning frame of the equalizing field is positioned in the weather diagram through the model, and then the image area corresponding to the positioning frame is further segmented by adopting the model, so that the local specific equalizing field image in the image area is determined, the automatic recognition mode of the model can improve the recognition efficiency of the equalizing field, and meanwhile, the accuracy of the equalizing field is improved from thick to thin.
The following are examples of the apparatus of the present invention that may be used to perform the method embodiments of the present invention. For details not disclosed in the embodiments of the apparatus of the present invention, please refer to the embodiments of the method of the present invention.
Referring to fig. 8, a schematic structural diagram of a voltage equalizing field identifying device according to an exemplary embodiment of the present invention is shown. The voltage equalizing field identifying device can be realized into all or part of the terminal through software, hardware or a combination of the two. The device 1 comprises a weather map construction module 10, a weather map output module 20 and a voltage-sharing field image output module 30.
The weather map construction module 10 is configured to construct a first weather map corresponding to the region to be identified according to weather original data of the region to be identified at the moment to be predicted;
the weather map output module 20 is configured to input the first weather map into a pre-trained equalizing field positioning model, and output a second weather map corresponding to the weather raw data, where the second weather map includes a positioning frame of an equalizing field area;
and the voltage-sharing field image output module 30 is used for taking out the image area corresponding to the positioning frame containing the voltage-sharing field area in the second weather map, inputting a pre-trained voltage-sharing field segmentation model, and outputting a voltage-sharing field image corresponding to the meteorological original data.
It should be noted that, when the equalizing field identifying device provided in the foregoing embodiment performs the equalizing field identifying method, only the division of the foregoing functional modules is used as an example, in practical application, the foregoing functional allocation may be performed by different functional modules according to needs, that is, the internal structure of the apparatus is divided into different functional modules, so as to complete all or part of the functions described above. In addition, the voltage-sharing field recognition device and the voltage-sharing field recognition method provided in the foregoing embodiments belong to the same concept, which embody the implementation process in detail with reference to the method embodiment, and are not repeated here.
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, a voltage-sharing field recognition device firstly constructs a first weather map corresponding to a region to be recognized according to weather original data of the region to be recognized at a moment to be predicted, secondly inputs the first weather map into a pre-trained voltage-sharing field positioning model, outputs a second weather map corresponding to the weather original data, wherein the second weather map comprises a positioning frame of a voltage-sharing field region, finally takes out an image region corresponding to the positioning frame of the voltage-sharing field region in the second weather map, inputs the pre-trained voltage-sharing field segmentation model, and outputs a voltage-sharing field image corresponding to the weather original data. According to the application, the positioning frame of the equalizing field is positioned in the weather diagram through the model, and then the image area corresponding to the positioning frame is further segmented by adopting the model, so that the local specific equalizing field image in the image area is determined, the automatic recognition mode of the model can improve the recognition efficiency of the equalizing field, and meanwhile, the accuracy of the equalizing field is improved from thick to thin.
The application also provides a computer readable medium, on which program instructions are stored, which program instructions, when executed by a processor, implement the method for identifying a voltage-sharing field provided by the above-mentioned method embodiments.
The application also provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of grading field identification of the various method embodiments described above.
Referring to fig. 9, a schematic structural diagram of a terminal is provided in an embodiment of the present application. As shown in fig. 9, terminal 1000 can 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 device located remotely from the processor 1001. As shown in fig. 9, an operating system, a network communication module, a user interface module, and a farm-uniform identification application may be included in the memory 1005, which is a type of computer storage medium.
In the terminal 1000 shown in fig. 9, 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 farm-identifying application stored in the memory 1005 and specifically perform the following operations:
Constructing a first weather map corresponding to the region to be identified according to weather original data of the region to be identified at the moment to be predicted;
inputting the first weather map into a pre-trained equalizing field positioning model, and outputting a second weather map corresponding to the meteorological original data, wherein the second weather map comprises a positioning frame of an equalizing field area;
and taking out an image area corresponding to a positioning frame containing the equalizing field area in the second weather map, inputting a pre-trained equalizing field segmentation model, and outputting an equalizing field image corresponding to meteorological original data.
In one embodiment, the processor 1001, before the weather raw data at the time to be predicted according to the region to be identified, further performs the following operations:
constructing a third weather map set corresponding to the region to be identified according to the historical meteorological data of the region to be identified;
marking a positioning frame containing a voltage-sharing field area for each third weather diagram in the third weather diagram set according to the received voltage-sharing field marking instruction to obtain a fourth weather diagram set;
model training of the positioning model is carried out according to the fourth weather diagram set, and a pre-trained equalizing field positioning model is obtained;
the image area corresponding to the positioning frame of each fourth standard weather image in the fourth weather image set is scratched, and a plurality of first equalizing field images are obtained;
And performing model training of the segmentation model according to the plurality of first voltage-sharing field images to obtain a pre-trained voltage-sharing field segmentation model.
In one embodiment, the processor 1001, when executing the construction of the third weather map set corresponding to the region to be identified according to the historical meteorological data of the region to be identified, specifically executes the following operations:
determining a historical time period to be acquired, and equally dividing the historical time period into a plurality of sub-historical time periods;
collecting historical meteorological data of each sub-historical time period;
and constructing a standard weather map corresponding to each sub-historical time period according to the historical meteorological data of each sub-historical time period, and obtaining a third weather map set corresponding to the region to be identified.
In one embodiment, the processor 1001, when executing the construction of the standard weather map corresponding to each sub-historical time period according to the historical meteorological data of each sub-historical time period, specifically performs the following operations:
interpolating wind field data of the historical meteorological data of each sub-historical time period into grids with preset first longitude and latitude intervals to obtain wind field grid point data;
constructing arrow symbols representing wind field data according to the wind field point data, and projecting the arrow symbols onto a plan to obtain a fifth weather diagram;
And drawing isobars with preset intervals according to the air pressure data of the historical meteorological data of each sub-historical time period, and projecting the isobars onto a fifth weather map to obtain a standard weather map corresponding to each sub-historical time period.
In one embodiment, the processor 1001, when performing model training of a segmentation model from a plurality of first grading field images to obtain a pre-trained grading field segmentation model, specifically performs the following operations:
marking boundaries corresponding to the grid point data of the wind field meeting preset conditions in each first voltage-sharing field image to obtain a plurality of second voltage-sharing field images;
binarizing each second equalizing field image to obtain a plurality of third equalizing field images;
creating a voltage-sharing field segmentation model;
taking each third equalizing field image as a label of a second equalizing field image corresponding to the third equalizing field image, inputting each second equalizing field image with the label into an equalizing field segmentation model, and outputting a first model loss value;
when the loss value of the first model reaches the minimum, generating a pre-trained equalizing field segmentation model; or when the first model loss value does not reach the minimum, adjusting the model parameters, and continuing to perform the steps of taking each third equalizing field image as the label of the corresponding second equalizing field image, and inputting each second equalizing field image after the label is set into the equalizing field dividing model.
In one embodiment, when the processor 1001 marks boundaries corresponding to the wind field point data meeting the preset conditions in each first voltage-sharing field image to obtain a plurality of second voltage-sharing field images, the processor specifically performs the following operations:
determining a center point of each first grading field image;
taking the center point of each first voltage-sharing field image as an origin, and acquiring arrow symbols representing wind field data corresponding to the wind field grid point data in the first step range in each first voltage-sharing field image according to a preset step range;
calculating a first vector average value of arrow symbols representing the wind field data corresponding to the wind field grid point data in the first step range;
taking the central point of each first voltage-sharing field image as an origin, and acquiring arrow symbols representing wind field data corresponding to the wind field grid point data in the second step range in each first voltage-sharing field image according to the preset step range;
calculating a second vector average value of arrow symbols representing the wind field data corresponding to the wind field grid point data in a second step range;
when the difference value between the second vector average value and the first vector average value is larger than or equal to a preset threshold value, marking the boundary of an arrow symbol representing the wind field data corresponding to the wind field grid point data in the first step range, and obtaining a plurality of second voltage-sharing field images; wherein,
The second step range is greater than the first step range.
In one embodiment, the processor 1001, when performing model training of the positioning model according to the fourth weather map set, obtains a pre-trained equalizing field positioning model, specifically performs the following operations:
creating a voltage equalizing field positioning model;
inputting the fourth weather diagram set into a voltage equalizing field positioning model, and outputting a second model loss value;
when the loss value of the second model reaches the minimum, generating a pre-trained equalizing field positioning model; or when the loss value of the second model does not reach the minimum, adjusting the model parameters, and continuing to perform the step of inputting the fourth weather map set into the equalizing field positioning model.
In the embodiment of the application, a voltage-sharing field recognition device firstly constructs a first weather map corresponding to a region to be recognized according to weather original data of the region to be recognized at a moment to be predicted, secondly inputs the first weather map into a pre-trained voltage-sharing field positioning model, outputs a second weather map corresponding to the weather original data, wherein the second weather map comprises a positioning frame of a voltage-sharing field region, finally takes out an image region corresponding to the positioning frame of the voltage-sharing field region in the second weather map, inputs the pre-trained voltage-sharing field segmentation model, and outputs a voltage-sharing field image corresponding to the weather original data. According to the application, the positioning frame of the equalizing field is positioned in the weather diagram through the model, and then the image area corresponding to the positioning frame is further segmented by adopting the model, so that the local specific equalizing field image in the image area is determined, the automatic recognition mode of the model can improve the recognition efficiency of the equalizing field, and meanwhile, the accuracy of the equalizing field is improved from thick to thin.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in the embodiments may be accomplished by computer programs to instruct related hardware, and the programs for equalizing field identification may be stored in a computer readable storage medium, and the programs may include the above-described methods in the embodiments when executed. The storage medium of the program for equalizing field identification can be a magnetic disk, an optical disk, a read-only memory or a random access memory.
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 method for identifying a voltage equalizing field, the method comprising:
constructing a first weather map corresponding to a region to be identified according to weather original data of the region to be identified at a moment to be predicted;
inputting the first weather map into a pre-trained equalizing field positioning model, and outputting a second weather map corresponding to the original meteorological data, wherein the second weather map comprises a positioning frame of an equalizing field area; the pre-trained equalizing field positioning model is a mathematical model capable of positioning a positioning frame containing an equalizing field area from a first atmospheric map;
Taking out an image area corresponding to a positioning frame containing a voltage-sharing field area in the second weather map, inputting a pre-trained voltage-sharing field segmentation model, and outputting a voltage-sharing field image corresponding to the meteorological original data; the pre-trained equalizing field segmentation model is a mathematical model capable of further segmenting equalizing field images in a positioning frame containing equalizing field areas.
2. The method of claim 1, wherein the identifying the region prior to the weather raw data at the time to be predicted further comprises:
constructing a third weather map set corresponding to the region to be identified according to historical meteorological data of the region to be identified;
marking a positioning frame containing a voltage-sharing field area for each third weather map in the third weather map set according to the received voltage-sharing field marking instruction to obtain a fourth weather map set;
model training of a positioning model is carried out according to the fourth weather diagram set, and a pre-trained equalizing field positioning model is obtained;
the image area corresponding to the positioning frame of each fourth standard weather image in the fourth weather image set is scratched, and a plurality of first equalizing field images are obtained;
and carrying out model training of the segmentation model according to the plurality of first equalizing field images to obtain a pre-trained equalizing field segmentation model.
3. The method according to claim 2, wherein the constructing a third weather map set corresponding to the region to be identified according to the historical meteorological data of the region to be identified includes:
determining a historical time period to be acquired, and equally dividing the historical time period into a plurality of sub-historical time periods;
collecting historical meteorological data of each sub-historical time period;
and constructing a standard weather map corresponding to each sub-historical time period according to the historical meteorological data of each sub-historical time period, and obtaining a third weather map set corresponding to the region to be identified.
4. The method of claim 3, wherein constructing a standard weather map corresponding to each sub-historical time period according to the historical meteorological data of each sub-historical time period comprises:
interpolating wind field data of the historical meteorological data of each sub-historical time period into grids with preset first longitude and latitude intervals to obtain wind field grid point data;
constructing arrow symbols representing the wind field data according to the wind field grid point data, and projecting the arrow symbols onto a plan view to obtain a fifth weather diagram;
and drawing isobars with preset intervals according to the air pressure data of the historical meteorological data of each sub-historical time period, and projecting the isobars with preset intervals onto the fifth weather map to obtain a standard weather map corresponding to each sub-historical time period.
5. The method according to claim 2, wherein the model training of the segmentation model based on the plurality of first grading field images results in a pre-trained grading field segmentation model, comprising:
marking boundaries corresponding to the grid point data of the wind field meeting preset conditions in each first voltage-sharing field image to obtain a plurality of second voltage-sharing field images;
binarizing each second equalizing field image to obtain a plurality of third equalizing field images;
creating a voltage-sharing field segmentation model;
taking each third equalizing field image as a label of a second equalizing field image corresponding to the third equalizing field image, inputting each second equalizing field image with the label into an equalizing field segmentation model, and outputting a first model loss value;
when the loss value of the first model reaches the minimum, generating a pre-trained equalizing field segmentation model; or when the first model loss value does not reach the minimum, adjusting the model parameters, and continuing to perform the steps of taking each third equalizing field image as the label of the corresponding second equalizing field image, and inputting each second equalizing field image after the label is set into the equalizing field dividing model.
6. The method according to claim 5, wherein marking boundaries corresponding to the grid point data of the wind field meeting the preset condition in each of the first voltage-sharing field images, and obtaining a plurality of second voltage-sharing field images, includes:
Determining a center point of each first grading field image;
taking the center point of each first voltage-sharing field image as an origin, and acquiring arrow symbols representing wind field data corresponding to the wind field grid point data in the first step range in each first voltage-sharing field image according to a preset step range;
calculating a first vector average value of arrow symbols representing the wind field data corresponding to the wind field grid point data in the first step range;
taking the central point of each first voltage-sharing field image as an origin, and acquiring arrow symbols representing wind field data corresponding to the wind field grid point data in a second step range in each first voltage-sharing field image according to a preset step range;
calculating a second vector average value of arrow symbols representing the wind field data corresponding to the wind field grid point data in the second step range;
when the difference value between the second vector average value and the first vector average value is larger than or equal to a preset threshold value, marking the boundary of an arrow symbol representing the wind field data corresponding to the wind field grid point data in the first step range, and obtaining a plurality of second voltage-sharing field images; wherein,
the second step range is greater than the first step range.
7. The method according to claim 2, wherein the model training of the positioning model according to the fourth weather map set, to obtain a pre-trained equalizing field positioning model, comprises:
Creating a voltage equalizing field positioning model;
inputting the fourth weather chart set into the equalizing field positioning model, and outputting a second model loss value;
when the loss value of the second model reaches the minimum, generating a pre-trained equalizing field positioning model; or when the loss value of the second model does not reach the minimum, adjusting the model parameters, and continuing to execute the step of inputting the fourth weather map set into the equalizing field positioning model.
8. A voltage grading field identification device, the device comprising:
the weather map construction module is used for constructing a first weather map corresponding to the region to be identified according to weather original data of the region to be identified at the moment to be predicted;
the weather map output module is used for inputting the first weather map into a pre-trained equalizing field positioning model and outputting a second weather map corresponding to the meteorological original data, wherein the second weather map comprises a positioning frame of an equalizing field area; the pre-trained equalizing field positioning model is a mathematical model capable of positioning a positioning frame containing an equalizing field area from a first atmospheric map;
the image output module of the equalizing field is used for taking out the image area corresponding to the positioning frame containing the equalizing field area in the second weather image, inputting a pre-trained equalizing field segmentation model, and outputting an equalizing field image corresponding to the meteorological original data; the pre-trained equalizing field segmentation model is a mathematical model capable of further segmenting equalizing field images in a positioning frame containing equalizing field areas.
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. A terminal, 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 |
|---|---|---|---|
| CN202310133051.0A CN116071651B (en) | 2023-02-09 | 2023-02-09 | Voltage equalizing field identification method and device, storage medium and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310133051.0A CN116071651B (en) | 2023-02-09 | 2023-02-09 | Voltage equalizing field identification method and device, storage medium and terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116071651A CN116071651A (en) | 2023-05-05 |
| CN116071651B true CN116071651B (en) | 2023-11-17 |
Family
ID=86174799
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310133051.0A Active CN116071651B (en) | 2023-02-09 | 2023-02-09 | Voltage equalizing field identification method and device, storage medium and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116071651B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116759009B (en) * | 2023-06-09 | 2024-02-02 | 中科三清科技有限公司 | Ozone forecasting method, system and medium matched with weather through machine learning |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114565057A (en) * | 2022-03-15 | 2022-05-31 | 中科三清科技有限公司 | Machine learning-based grading field identification method and device, storage medium and terminal |
| CN114565056A (en) * | 2022-03-15 | 2022-05-31 | 中科三清科技有限公司 | Machine learning-based cold-front identification method and device, storage medium and terminal |
| CN114863418A (en) * | 2022-04-29 | 2022-08-05 | 中科三清科技有限公司 | Voltage-sharing field identification method and device, storage medium and terminal |
| CN115082788A (en) * | 2022-06-21 | 2022-09-20 | 中科三清科技有限公司 | Air pressure center identification method and device, electronic equipment and storage medium |
-
2023
- 2023-02-09 CN CN202310133051.0A patent/CN116071651B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114565057A (en) * | 2022-03-15 | 2022-05-31 | 中科三清科技有限公司 | Machine learning-based grading field identification method and device, storage medium and terminal |
| CN114565056A (en) * | 2022-03-15 | 2022-05-31 | 中科三清科技有限公司 | Machine learning-based cold-front identification method and device, storage medium and terminal |
| CN114863418A (en) * | 2022-04-29 | 2022-08-05 | 中科三清科技有限公司 | Voltage-sharing field identification method and device, storage medium and terminal |
| CN115082788A (en) * | 2022-06-21 | 2022-09-20 | 中科三清科技有限公司 | Air pressure center identification method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 环渤海地区雾天气分型及预报方法;陈东辉 等;《气象》;第43卷(第1期);第46-55页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116071651A (en) | 2023-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111626947B (en) | Map vectorization sample enhancement method and system based on generation of countermeasure network | |
| CN114863418B (en) | Voltage-sharing field identification method and device, storage medium and terminal | |
| CN112989995B (en) | Text detection method and device and electronic equipment | |
| CN114565056A (en) | Machine learning-based cold-front identification method and device, storage medium and terminal | |
| CN112990086A (en) | Remote sensing image building detection method and device and computer readable storage medium | |
| CN116071651B (en) | Voltage equalizing field identification method and device, storage medium and terminal | |
| CN114565057B (en) | Machine learning-based grading field identification method and device, storage medium and terminal | |
| CN115731560B (en) | Deep learning-based slot line identification method and device, storage medium and terminal | |
| CN115861811B (en) | Wind shear region identification method and device, storage medium and terminal | |
| CN115861816B (en) | Three-dimensional low-vortex recognition method and device, storage medium and terminal | |
| CN115937690B (en) | Slotline generation method and device, storage medium and terminal | |
| CN115345895B (en) | Image segmentation method and device for visual detection, computer equipment and medium | |
| US9483846B2 (en) | Data interpolation and classification method for map data visualization | |
| CN116052097A (en) | Map element detection method and device, electronic equipment and storage medium | |
| CN114626458B (en) | High-voltage rear part identification method and device, storage medium and terminal | |
| CN116452850A (en) | Road ponding area identification method based on data mining and deep learning | |
| CN115527028A (en) | Map data processing method and device | |
| CN116091586B (en) | Slotline identification method, device, storage medium and terminal | |
| CN116681959B (en) | Machine learning-based frontal line identification method and device, storage medium and terminal | |
| CN115830380B (en) | Wind shear line identification method and device based on artificial intelligence, storage medium and terminal | |
| CN116051805B (en) | Auxiliary tropical high-voltage influence area identification method and device, storage medium and terminal | |
| CN113378850B (en) | Model training method, pavement damage segmentation device and electronic equipment | |
| CN114155508B (en) | Road change detection method, device, equipment and storage medium | |
| CN113361524B (en) | Image processing method and device | |
| CN117095140A (en) | Traffic road modeling method and device, electronic equipment and storage medium |
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 |