CN117237780B - Multidimensional data feature graph construction method, multidimensional data feature graph construction system, intelligent terminal and medium - Google Patents
Multidimensional data feature graph construction method, multidimensional data feature graph construction system, intelligent terminal and medium Download PDFInfo
- Publication number
- CN117237780B CN117237780B CN202311522439.6A CN202311522439A CN117237780B CN 117237780 B CN117237780 B CN 117237780B CN 202311522439 A CN202311522439 A CN 202311522439A CN 117237780 B CN117237780 B CN 117237780B
- Authority
- CN
- China
- Prior art keywords
- data
- target
- type
- feature map
- constructing
- 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
- 238000010276 construction Methods 0.000 title claims description 30
- 238000000034 method Methods 0.000 claims abstract description 34
- 239000010410 layer Substances 0.000 claims description 30
- 238000010586 diagram Methods 0.000 claims description 14
- 239000002356 single layer Substances 0.000 claims description 14
- 230000004927 fusion Effects 0.000 claims description 12
- 238000013075 data extraction Methods 0.000 claims description 5
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 abstract description 12
- 229910052799 carbon Inorganic materials 0.000 abstract description 12
- 238000012544 monitoring process Methods 0.000 abstract description 11
- 230000035945 sensitivity Effects 0.000 abstract description 7
- 238000012545 processing Methods 0.000 description 10
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 10
- 239000002689 soil Substances 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 238000011160 research Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000015556 catabolic process Effects 0.000 description 3
- 238000006731 degradation reaction Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- GVVPGTZRZFNKDS-JXMROGBWSA-N geranyl diphosphate Chemical compound CC(C)=CCC\C(C)=C\CO[P@](O)(=O)OP(O)(O)=O GVVPGTZRZFNKDS-JXMROGBWSA-N 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 239000005431 greenhouse gas Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Image Processing (AREA)
Abstract
The invention provides a method, a system, an intelligent terminal and a medium for constructing a multidimensional data feature map, and particularly relates to the technical field of forest carbon sink. Extracting data from each data set based on target types determined in advance according to actual application, and obtaining a plurality of target type data; constructing a feature map of a corresponding type based on the target type data; and fusing all the feature maps to construct a joint layer. The scheme can improve the efficiency and accuracy of constructing the feature map and improve the accuracy and sensitivity of monitoring forest variation.
Description
Technical Field
The invention relates to the technical field of forest carbon sinks, in particular to a method, a system, an intelligent terminal and a medium for constructing a multidimensional data feature map.
Background
The current project of reducing carbon emissions (Reducing Emissions from Deforestation and Forest Degradation, REDD) from deforestation and forest degradation aims to reduce greenhouse gas emissions by reducing deforestation and forest degradation. To achieve this goal, the project requires accurate, real-time monitoring of changes in forest resources.
Existing monitoring methods rely mainly on remote sensing technologies such as satellite images and high resolution images captured by unmanned aerial vehicles. However, the prior art has single data source or small data volume, or cannot effectively extract data characteristics, so that the judgment on forest variation conditions is inaccurate and the sensitivity is low.
Disclosure of Invention
In view of the shortcomings of the prior art, the invention aims to provide a multi-dimensional data feature map construction method, a multi-dimensional data feature map construction system, an intelligent terminal and a medium, and aims to solve the problems of inaccurate judgment on forest change conditions and lower sensitivity in the prior art.
In order to achieve the above object, a first aspect of the present invention provides a method for constructing a multidimensional data feature map, including:
acquiring data sources of a target forest area, classifying all the data sources based on a preset classification type, and acquiring a plurality of data sets;
extracting data from each data set based on target types determined in advance according to actual application, and obtaining a plurality of target type data;
constructing a feature map of a corresponding type based on the target type data;
and fusing all the feature images to construct a joint layer.
Optionally, before the acquiring the data source of the target forest area, the method further includes:
extracting the boundary of the target forest area;
calculating the center point coordinates of the target forest area based on the boundary of the target forest area;
and constructing an expansion boundary of the target forest area based on the center point coordinates and a preset expansion area radius to obtain an expansion area, and setting the expansion area as the target forest area.
Optionally, the extracting data in each data set based on the target type determined in advance according to the application scene to obtain a plurality of target type data includes:
cutting the target forest area to obtain a grid chart;
acquiring a target type determined in advance according to an application scene;
and extracting data in each data set corresponding to the raster pattern based on the target type to obtain a plurality of target type data.
Optionally, the constructing a feature map of a corresponding type based on the target type data includes:
if the target type data are numerical type raster data or category type raster data, raster data in a target wave band in the data source are extracted, and target data characteristics are obtained;
if the target type is a numerical type, constructing a numerical type feature map by utilizing the target data features; if the target type is a category type, a category type feature map is constructed by utilizing the target data features.
Optionally, the constructing a feature map of a corresponding type based on the target type data further includes:
if the target type data are raster data representing point entities, fusing areas with the distance between adjacent points in a target homogeneous area smaller than the preset maximum fusion distance to obtain a homogeneous vector diagram, wherein the target homogeneous area refers to an area composed of raster data with the same target type;
calculating the nearest distance from each point in the target forest area to the boundary of the homography to obtain the distance from each point to the target homography;
and constructing a distance type feature map based on the distance between each point and the target homogeneous region.
Optionally, the constructing a feature map of a corresponding type based on the target type data further includes:
if the target type data are vector data, calculating the nearest distance from each point in the target forest area to the expansion boundary to obtain the distance from each point to the expansion boundary;
and constructing a distance type feature map based on the distance between each point and the expansion boundary.
Optionally, the fusing the feature graphs to construct a joint layer includes:
acquiring a preset target spatial resolution;
scaling each feature map based on the target spatial resolution to obtain each updated feature map;
and splicing the updated feature images to obtain a joint image layer.
A second aspect of the present invention provides a multi-dimensional data feature map construction system, the system comprising:
the data set construction module is used for acquiring data sources of a target forest area, classifying all the data sources based on a preset classification type and acquiring a plurality of data sets;
the target type data extraction module is used for extracting data in each data set based on a target type determined in advance according to actual application to obtain a plurality of target type data;
the feature map construction module is used for constructing a feature map of a corresponding type based on the target type data;
and the feature map fusion module is used for fusing all the feature maps to construct a joint map layer.
The third aspect of the present invention provides an intelligent terminal, which includes a memory, a processor, and a multidimensional data feature map construction program stored in the memory and executable on the processor, wherein the multidimensional data feature map construction program, when executed by the processor, implements the steps of any one of the multidimensional data feature map construction methods described above.
A fourth aspect of the present invention provides a computer-readable storage medium having stored thereon a multi-dimensional data feature map construction program which, when executed by a processor, implements the steps of any one of the multi-dimensional data feature map construction methods described above.
Compared with the prior art, the beneficial effects of this scheme are as follows:
according to the method, the data sources of the target forest area are obtained, all the data sources are classified based on the preset classification types, a plurality of data sets are obtained, and classification processing of various data types included in the data sources is realized, so that the accuracy and the efficiency of extracting each type of data are improved; then, extracting data from each data set based on target types determined in advance according to actual application, and obtaining a plurality of target type data; constructing a feature map of a corresponding type based on the target type data; and fusing all the constructed feature graphs to construct a joint layer.
Therefore, the invention can selectively extract one or more types of data according to the target types determined by practical application, and construct a single-layer or multi-layer feature map by using the extracted data, thereby effectively improving the accuracy of identifying various complex data types in a data source, and being beneficial to improving the efficiency and accuracy of constructing the feature map; and the fusion of different types of data can be efficiently realized, so that the accuracy and the sensitivity of forest change monitoring are remarkably improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for constructing a multi-dimensional data feature map of the present invention;
FIG. 2 is a main flow chart of the present invention for constructing a single-layer feature map;
FIG. 3 is a main flow chart of the present invention for constructing a distance profile;
FIG. 4 is a feature map fusion flow chart of the present invention;
FIG. 5 is a schematic diagram of a multi-dimensional data feature map construction system according to the present invention;
fig. 6 is a schematic structural diagram of an intelligent terminal according to the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
It should be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
The following description of the embodiments of the present invention will be made more fully hereinafter with reference to the accompanying drawings, in which embodiments of the invention are shown, it being evident that the embodiments described are only 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.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.
Existing monitoring methods rely mainly on remote sensing technologies such as satellite images and high resolution images captured by unmanned aerial vehicles. However, the prior art has mainly the following drawbacks:
1) And the data source is single: the prior art mainly depends on a single or a small number of data sources, cannot fully utilize the advantages of various remote sensing data, and reduces the accuracy and sensitivity to forest changes.
2) The data processing efficiency is low: the prior art needs to download, preprocess and analyze a large amount of remote sensing data, consumes a large amount of time and computing resources, and limits the capability of real-time monitoring.
3) The feature extraction capability is limited: the prior art has poor characteristic extraction effect on complex terrains and vegetation types, and influences the judgment accuracy on forest variation.
Aiming at the problems existing in the prior art, the invention provides a multi-dimensional data feature map construction method, which mainly comprises the steps of firstly collecting data from a multi-dimensional remote sensing data source and constructing a plurality of data sets according to classification types; then, utilizing the powerful computing power and rich data resources of an Earth Engine (Earth Engine), respectively carrying out feature extraction on various types of data in a data set and constructing a plurality of feature graphs; and finally, fusing the characteristic images into a joint image layer for real-time monitoring and analysis of REDD items. According to the method, multiple remote sensing data sources are integrated together, so that the accuracy and the sensitivity of forest change monitoring are improved; by extracting the characteristics of various types of data one by one, the accuracy of identifying the complex terrain and vegetation types is effectively improved, so that the construction efficiency and accuracy of the characteristic map are improved; the powerful data processing capability based on Earth Engine avoids a great deal of data downloading, preprocessing and analyzing work, and improves the real-time monitoring capability.
The embodiment of the invention provides a method for constructing a multidimensional data feature map, which is deployed on electronic equipment such as a computer, a server and the like, wherein an application scene is a forest carbon sink project, such as a REDD project, and aims at the integration and reconstruction of forest carbon sink data. The data related to the forest carbon sink is not limited in this embodiment, and may be a data source in the Earth Engine, such as gradient, altitude, and Earth surface coverage type, or may be an offline data source, such as road type data, earth surface coverage type data, soil category data, or may be data related to climate, species, or the like, or even a combination of multiple types of data. In this embodiment, the carbon sink project is taken as an example to describe the process of extracting and integrating the features of the remote sensing data related to the carbon emission, but the process is not limited to the carbon sink project, and all the data processing modes using the concept of the present invention are within the protection scope of the present invention. Specifically, as shown in fig. 1, the steps of the method in this embodiment include:
step S100: and acquiring data sources of the target forest area, classifying all the data sources based on a preset classification type, and acquiring a plurality of data sets.
Specifically, remote sensing data related to carbon emission in a target forest area is obtained, and the remote sensing data are classified according to classification types to obtain a plurality of data sources of different types; and constructing an empty data set list corresponding to the classification types of the data sources one by one, and respectively placing the data sources into the corresponding data set list according to the classification types to obtain a plurality of data sets.
The remote sensing data related to carbon emission in a target forest area of a forest carbon sink project is acquired from a data source carried by an Earth Engine platform, for example, a data source of a global forest change (Global Forest Change, GFW), gradient, altitude, primary productivity total value (Gross Primary Productivity, GPP), earth surface coverage classification and the like, and can be used as other data source acquisition modes, or can be an off-line acquired data source, for example, a data source of a road type data, earth surface coverage type data, soil category data and the like; and the data source can be constructed based on the combination of the Earth Engine platform and the offline data.
The embodiment is based on a data source acquired by an Earth Engine platform, three types of data of numerical value type, distance type and category type are extracted from the data source to serve as research objects, other types of data can be selected to serve as research objects as other preferred embodiments, and the analysis principle is similar to that of the embodiment.
In order to store the above three types of data respectively, the present embodiment constructs three empty data set lists, namely value_data_ list, distance _data_list and type_data_list, for storing numeric Type, distance Type and category Type data respectively. Wherein value_data_list is used to store layer raster data, such as GFW, gradient, altitude, GPP, etc., with point Value data as specific values, and each point of such raster data represents a specific Value of coordinates at the point, typically a floating point number. Type_data_list is used to store point value data as layer raster data of a specific class, such as surface coverage class data, soil class, etc., each point of such raster data representing a certain class, typically an integer, on coordinates at that point. Distance_data_list is used to store point value data as a Distance to the nearest vector, such as a Distance to a road, a Distance to a certain surface coverage type, etc.
And then respectively putting the data sources of different types into three data set lists of value_data_ list, distance _data_list and type_data_list according to the classification types to obtain three data sets.
In the embodiment, three types of data of a numerical type, a distance type and a category type are called as preset classification types, namely primary classification; the various data stored in each data set list is referred to as a secondary classification, and it can be seen that by building a data set, several secondary types of data are classified into three primary data types, so that the feature map of the class is subsequently built according to the class of the primary data type, i.e. the types of feature maps built using the data in each data set are identical.
Further, since an extended area is often constructed in a larger range based on the center point coordinates of the target forest area in the actual project, and various data processing is performed based on the extended area, the embodiment constructs a multidimensional data feature map based on the extended area, but actually, various data processing may be performed only according to the data in the target forest area to construct a multidimensional data feature map. It should be stated that the difference between the various data processing based on the extended area and the target forest area is only that the data amounts in the data sources included in the two areas are different, so that the step of constructing the multidimensional data feature map based on the target forest area is not repeated.
The following describes in detail the steps of constructing a multidimensional data feature map based on an extended region, as shown in fig. 2, wherein the steps of constructing an extended region based on a target forest region are as follows:
step S110: extracting the boundary of the target forest area based on the coordinates of each point in the target forest area;
specifically, with reference to a geographic coordinate system, the boundary of the target forest area is extracted based on the coordinates of each point in the target forest area (i.e., the coordinates corresponding to the point determined by the longitude and latitude of the earth), for example, a point set on the extracted item boundary is expressed asWherein->Represents the abscissa (i.e. the longitude of the point) of each point on the boundary of the target forest area, +.>Representing the ordinate (i.e. the latitude of the point) of each point on the boundary of the target forest area,，/>and->Are all positive integers, use ∈ ->All boundary points are connected in a straight line to form a closed polygonal boundary.
Step S120: calculating the center point coordinates of the target forest area based on the boundary of the target forest area;
specifically, the coordinates of the center point of the boundary of the target forest area are solvedThe formula of (2) is:
，
wherein,represents the abscissa (i.e. the longitude of the point) of each point on the boundary of the target forest area, +.>Representing the ordinate (i.e., the latitude of the point) of each point on the boundary of the target forest area.
Step S130: and constructing an expansion boundary of the target forest area based on the center point coordinates and the preset expansion area radius to obtain an expansion area.
And constructing an expansion boundary of the target forest area based on the center point coordinates and a preset expansion area radius, and calling an area surrounded by the expansion boundary as an expansion area. For example, assuming that the radius of the extended area is 200 km, thenThe dot is 200 km as radius, and the extended area is defined as the boundary +.>Then the extension area can be expressed asAn area.
For convenience of description, the extended area is directly used as a research area to perform operations such as grid division, data extraction, and feature map construction, in fact, the extended area is equivalent to a target forest area, and as other preferred embodiments, the extended area may also be directly used for performing operations such as grid division, data extraction, and feature map construction based on the target forest area, and the principle of data processing is the same as that of the embodiment, so that a detailed description is omitted.
Step S200: and extracting data in each data set based on the target type determined in advance according to the application scene, and obtaining a plurality of target type data.
Specifically, as shown in fig. 2, clipping is performed in the extension area to obtain a raster pattern; acquiring a target type determined in advance according to an application scene; based on the target type, extracting data in each data set corresponding to the raster pattern to obtain a plurality of target type data, wherein the specific steps are as follows:
step S210: cutting the expansion area to obtain a grid chart;
specifically, the extended area is cut, and the obtained data in each raster image is one type of data in the remote sensing data. For example, for GFW data, the GFW is extracted by superimposing a raster patternData of the region. Specifically, the GFW data is used to overlap +.>The area is determined as->Data of all GFWs in->。
Step S220: acquiring a target type determined in advance according to an application scene;
specifically, it is determined that a certain type or certain types of feature graphs need to be established according to actual projects, and then corresponding types of data are extracted from the constructed data set list as target type data according to requirements.
Step S230: and extracting data in each data set corresponding to the raster pattern based on the target type to obtain a plurality of target type data.
For example, given that the data sources in the project area include GFW, gradient, elevation, earth coverage category data, soil category and other secondary types of data, wherein GFW, gradient and elevation data belong to numerical data, GFW, gradient and elevation data are all stored in value_data_list, and GFW and gradient type data are required to be extracted from value_data_list as target type data according to target type determined by the current actual project, and GFW feature map and gradient feature map constructed by using GFW and gradient type data belong to numerical feature map.
Step S300: and constructing a feature map of a corresponding type based on the target type data.
Specifically, different types of feature graphs are constructed by different target type data, for example, if the target type data is numerical value type raster data or category type raster data, raster data in a target wave band in a data source is extracted, and target data features are obtained; if the target type is a numerical type, constructing a numerical type feature map by utilizing the target data features; if the target type is the category type, constructing a category type feature map by utilizing the target data features.
For solving the numerical Type or class Type feature map, a single-layer feature map is constructed by extracting corresponding data of the corresponding position of the raster map in a preset wave band from the value_data_list or the type_data_list data set, as shown in fig. 2, wherein the numerical class single-layer feature map refers to the numerical class single-layer feature map. For example, for GFW data belonging to a numerical value, only data of all GFWs may be extractedAnd constructing a single-layer characteristic diagram of GFW data according to the layer data of a certain wave band. Similarly, for the soil category data belonging to the category, the same method is used for extracting the layer data in the preset wave band in all the soil category data, and a single-layer characteristic diagram of the soil category data is constructed.
For solving the Distance type feature map, firstly, based on a grid map obtained by cutting an extension area, extracting data corresponding to the corresponding position of the grid map from a distance_data_list data set, judging the type of the extracted data, and then, selecting different modes to construct the Distance type feature map according to the different types of the data. In this embodiment, the main flow of constructing the distance feature map based on the original data in the target forest area is shown in fig. 3 by mainly taking vector type data and raster data as examples for research.
If the extracted data belongs to the vector type, calculatingEach point in the areaNearest vector distances to the extension boundary, respectivelyHere will->As->And constructing a distance type feature map according to the distance between each point and the expansion boundary.
If the extracted data belongs to raster data representing a point entity, forming a target homogeneous region by using the type data in the raster data; fusing the regions with the distance between adjacent points in the target homogeneous region smaller than the preset maximum fusion distance to construct a homogeneous vector diagram; calculating the nearest distance from each point in the expansion area to the boundary of the homogeneous vector diagram, and obtaining the distance from each point to the target homogeneous area; and constructing a distance type feature map based on the distance between each point and the target homogeneous region.
For example, the grid data is surface coverage type data, the target type data is distance to the water body, and assuming that the type number of the water body is 210, the steps for constructing the distance feature map based on the distance between the point in the target forest area and the water body are specifically as follows:
1) Setting the area consisting of all water points with class number of 210 in the target forest area as a homogeneous areaWherein each term represents a point;
2) Setting the maximum fusion distanceThe target homogeneous region->The distance between adjacent points in (a) is smaller than the maximum fusion distance +.>Is fused to form a new region +.>Wherein each term represents a point, the region actually referring to a water vector map generated from the water data of class number 210 in the surface coverage type data;
3) Calculating the nearest distance from each point in the area surrounded by the water body vector diagram to the expansion boundary to obtain the value of each point, wherein the nearest distance refers to the minimum value of the distance from each point in the area surrounded by the water body vector diagram to each side of the expansion boundary;
4) And constructing a water body distance type feature map based on the values of the points.
In this embodiment, the distance between the point in the target forest area and the water body is taken as a research object, and a distance feature map is constructed, so that as other preferred embodiments, the distance between the point in the target forest area and other surface coverings, such as the distance between the point in the target forest area and the surface coverings of a designated farmland, a forest, a grassland, a residential land, a road and the like, can be calculated according to the same method according to the actual application requirements.
In the embodiment, the numerical feature map, the category feature map and the distance feature map constructed according to the method are all single-layer feature maps, and each type of data comprises a plurality of subclasses, so that a plurality of layers of feature maps can be constructed for each type of data. For example, the distance type data in the target forest area comprises 30 different distance types, so that 30 single-layer distance type feature images can be constructed, a 30-layer distance type feature image can be constructed, and a single-layer or multi-layer distance type feature image can be constructed by only selecting a specific type of distance type according to actual requirements.
Repeating the steps of constructing the single-layer feature map, and constructing i, j and k single-layer feature maps respectively according to three data set lists of value_data_list, type_data_list and distance_data_list, namely constructing i number Value feature maps, j category feature maps and k Distance feature maps in total.
Step S400: and fusing all the feature maps to construct a joint layer.
Specifically, as shown in fig. 4, a preset target spatial resolution is obtained; scaling each feature map based on the target spatial resolution to obtain each updated feature map; splicing the updated feature graphs to obtain a joint graph layer, wherein the joint graph layer is specifically as follows:
step S410: acquiring the spatial resolution of each feature map, and setting target spatial resolution capable of bringing good fusion effect based on the spatial resolution of each feature map;
specifically, i numerical feature maps, j category feature maps and spatial resolutions corresponding to k Distance feature maps corresponding to three data set lists value_data_list, type_data_list and distance_data_list are obtained, and based on a spatial resolution area where the spatial resolutions of the feature maps are located, one spatial resolution close to the middle part in the area is selected as a target spatial resolution GSD.
Step S420: scaling each feature map based on the target spatial resolution to obtain each updated feature map;
specifically, based on a set target spatial resolution GSD, a feature map different from the target spatial resolution GSD is converted into a feature map within the target spatial resolution GSD by spatial up-sampling or down-sampling. For example, the size of any one of the feature maps F is set to m×n, where M and N represent length and width, respectively, and the spatial resolution is. If it isNo operation is performed. If->Then find the scaling ratio +.>Wherein->Then the updated feature map is of size (M/s) x (N/s).
Step S430: and splicing the updated feature graphs to obtain a joint layer.
Specifically, the obtained i number type feature images, j category type feature images and k distance type feature images are combined to obtain a combined image layerThen join layer->All the numeric data, the category data and the distance data are contained. It should be stated that the union herein refers to merging elements in different layers, and the data features at each pixel (i.e., each point) in the union layer include the data features of all layers at that pixel. It can be seen that the joint layer can be derived from eachThe dimensions describe the REDD items and provide very comprehensive features for later item evaluation.
According to the method, multiple remote sensing data sources are integrated, so that the accuracy and the sensitivity of forest variation monitoring are improved; by extracting the characteristics of various types of data one by one, the accuracy of identifying the complex terrain and vegetation types is effectively improved, so that the construction efficiency and accuracy of the characteristic map are improved; the powerful data processing capability based on Earth Engine avoids a great deal of data downloading, preprocessing and analyzing work, and improves the real-time monitoring capability.
It should be stated that, the embodiment specifically provides a REDD project multi-data source feature map construction method based on Earth Engine, but the protection scope is not limited to the content designed in the embodiment, and all the data feature extraction and fusion methods of the same or different data sources which are conceived by adopting the method of the embodiment are within the protection scope of the invention.
As shown in fig. 5, corresponding to the above-mentioned multi-dimensional data feature map construction method, an embodiment of the present invention further provides a multi-dimensional data feature map construction system, where the multi-dimensional data feature map construction system includes:
the data set construction module 510 is configured to obtain data sources of a target forest area, classify all the data sources based on a preset classification type, and obtain a plurality of data sets;
the target type data extraction module 520 is configured to extract data in each data set based on a target type determined in advance according to an actual application, and obtain a plurality of target type data;
a feature map construction module 530, configured to construct a feature map of a corresponding type based on the target type data;
and the feature map fusion module 540 is used for fusing all feature maps to construct a joint map layer.
Specifically, in this embodiment, the specific functions of the system for constructing a multidimensional data feature map may refer to corresponding descriptions in the method for constructing a multidimensional data feature map, which are not described herein again.
Based on the above embodiment, the present invention also provides an intelligent terminal, and a functional block diagram thereof may be shown in fig. 6. The intelligent terminal comprises a processor, a memory, a network interface and a display screen which are connected through a system bus. The processor of the intelligent terminal is used for providing computing and control capabilities. The memory of the intelligent terminal comprises a nonvolatile storage medium and an internal memory. The nonvolatile storage medium stores an operating system and a multidimensional data feature map construction program. The internal memory provides an environment for an operating system in a non-volatile storage medium and for the execution of a program built based on the multidimensional data profile. The network interface of the intelligent terminal is used for communicating with an external terminal through network connection. The multi-dimensional data feature map construction program, when executed by the processor, implements the steps of any one of the multi-dimensional data feature map construction methods described above. The display screen of the intelligent terminal can be a liquid crystal display screen or an electronic ink display screen.
It will be appreciated by those skilled in the art that the schematic block diagram shown in fig. 6 is merely a block diagram of a portion of the structure associated with the present inventive arrangements and is not limiting of the smart terminal to which the present inventive arrangements are applied, and that a particular smart terminal may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, an intelligent terminal is provided, where the intelligent terminal includes a memory, a processor, and a multidimensional data feature map building program stored in the memory and capable of running on the processor, where the multidimensional data feature map building program implements the steps of any one of the multidimensional data feature map building methods provided in the embodiments of the present invention when the multidimensional data feature map building program is executed by the processor.
The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a multi-dimensional data feature map construction program, and the multi-dimensional data feature map construction program realizes the steps of any multi-dimensional data feature map construction method provided by the embodiment of the invention when being executed by a processor.
It should be understood that the sequence number of each step in the above embodiment does not mean the sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not be construed as limiting the implementation process of the embodiment of the present invention.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present invention. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other manners. For example, the apparatus/terminal device embodiments described above are merely illustrative, e.g., the division of the modules or units described above is merely a logical function division, and may be implemented in other manners, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that; the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions are not intended to depart from the spirit and scope of the various embodiments of the invention, which are also within the spirit and scope of the invention.
Claims (7)
1. The method for constructing the multidimensional data feature map is characterized by comprising the following steps of:
acquiring data sources of a target forest area, classifying all the data sources based on a preset classification type, and acquiring a plurality of data sets;
extracting data from each data set based on target types determined in advance according to application scenes, and obtaining a plurality of target type data;
constructing a feature map of a corresponding type based on the target type data;
fusing all the feature images to construct a joint layer;
the constructing a feature map of a corresponding type based on the target type data comprises the following steps:
if the target type data are numerical type raster data or category type raster data, raster data in a target wave band in the data source are extracted, and target data characteristics are obtained; if the target type is a numerical type, constructing a numerical type feature map by utilizing the target data features; if the target type is a category type, constructing a category type feature map by utilizing the target data features;
the constructing a feature map of a corresponding type based on the target type data further comprises:
if the target type data are raster data representing point entities, fusing areas with the distance between adjacent points in a target homogeneous area smaller than the preset maximum fusion distance to obtain a homogeneous vector diagram, wherein the target homogeneous area refers to an area composed of raster data with the same target type; calculating the nearest distance from each point in the target forest area to the boundary of the homography to obtain the distance from each point to the target homography; constructing a distance type feature map based on the distance between each point and the target homogeneous region, wherein the nearest distance refers to the minimum value of the distance between each point in the region surrounded by the homogeneous vector map and each side of the target forest region; the numerical type feature map, the category type feature map and the distance type feature map are all single-layer feature maps;
and fusing all the feature maps to construct a joint layer, wherein the method comprises the following steps of:
acquiring a preset target spatial resolution; scaling each feature map based on the target spatial resolution to obtain each updated feature map; and splicing the updated feature images to obtain a joint image layer.
2. The method for constructing a multi-dimensional data feature map according to claim 1, further comprising, before the acquiring the data source of the target forest area:
extracting the boundary of the target forest area;
calculating the center point coordinates of the target forest area based on the boundary of the target forest area;
and constructing an expansion boundary of the target forest area based on the center point coordinates and a preset expansion area radius to obtain an expansion area, and setting the expansion area as the target forest area.
3. The method for constructing a multi-dimensional data feature map according to claim 1 or 2, wherein the extracting data in each of the data sets based on the target type determined in advance according to the application scene, to obtain a plurality of target type data, comprises:
cutting the target forest area to obtain a grid chart;
acquiring a target type determined in advance according to an application scene;
and extracting data in each data set corresponding to the raster pattern based on the target type to obtain a plurality of target type data.
4. The method for constructing a multi-dimensional data feature map according to claim 2, wherein the constructing a feature map of a corresponding type based on the target type data, further comprises:
if the target type data are vector data, calculating the nearest distance from each point in the target forest area to the expansion boundary to obtain the distance from each point to the expansion boundary;
and constructing a distance type feature map based on the distance between each point and the expansion boundary.
5. A multi-dimensional data profile construction system, the system comprising:
the data set construction module is used for acquiring data sources of a target forest area, classifying all the data sources based on a preset classification type and acquiring a plurality of data sets;
the target type data extraction module is used for extracting data in each data set based on a target type determined in advance according to an application scene to obtain a plurality of target type data;
the feature map construction module is used for constructing a feature map of a corresponding type based on the target type data;
the constructing a feature map of a corresponding type based on the target type data comprises the following steps: if the target type data are numerical type raster data or category type raster data, raster data in a target wave band in the data source are extracted, and target data characteristics are obtained; if the target type is a numerical type, constructing a numerical type feature map by utilizing the target data features; if the target type is a category type, constructing a category type feature map by utilizing the target data features;
the constructing a feature map of a corresponding type based on the target type data further comprises: if the target type data are raster data representing point entities, fusing areas with the distance between adjacent points in a target homogeneous area smaller than the preset maximum fusion distance to obtain a homogeneous vector diagram, wherein the target homogeneous area refers to an area composed of raster data with the same target type; calculating the nearest distance from each point in the target forest area to the boundary of the homography to obtain the distance from each point to the target homography; constructing a distance type feature map based on the distance between each point and the target homogeneous region, wherein the nearest distance refers to the minimum value of the distance between each point and each side of the expansion boundary in the region surrounded by the homogeneous vector map; the numerical type feature map, the category type feature map and the distance type feature map are all single-layer feature maps;
the feature map fusion module is used for fusing all the feature maps to construct a joint map layer; and fusing all the feature maps to construct a joint layer, wherein the method comprises the following steps of: acquiring a preset target spatial resolution; scaling each feature map based on the target spatial resolution to obtain each updated feature map; and splicing the updated feature images to obtain a joint image layer.
6. Intelligent terminal, characterized in that it comprises a memory, a processor and a multi-dimensional data profile construction program stored on the memory and executable on the processor, which multi-dimensional data profile construction program, when executed by the processor, implements the steps of the multi-dimensional data profile construction method according to any one of claims 1-4.
7. A computer readable storage medium, wherein a multi-dimensional data feature map construction program is stored on the computer readable storage medium, which when executed by a processor, implements the steps of the multi-dimensional data feature map construction method according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311522439.6A CN117237780B (en) | 2023-11-15 | 2023-11-15 | Multidimensional data feature graph construction method, multidimensional data feature graph construction system, intelligent terminal and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311522439.6A CN117237780B (en) | 2023-11-15 | 2023-11-15 | Multidimensional data feature graph construction method, multidimensional data feature graph construction system, intelligent terminal and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117237780A CN117237780A (en) | 2023-12-15 |
| CN117237780B true CN117237780B (en) | 2024-03-15 |
Family
ID=89086591
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311522439.6A Active CN117237780B (en) | 2023-11-15 | 2023-11-15 | Multidimensional data feature graph construction method, multidimensional data feature graph construction system, intelligent terminal and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117237780B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117871792B (en) * | 2024-03-13 | 2024-05-14 | 河北省建筑科学研究院有限公司 | Dynamic monitoring method and system for green carbon sequestration in park |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111651545A (en) * | 2020-06-03 | 2020-09-11 | 南京图申图信息科技有限公司 | Urban marginal area extraction method based on multi-source data fusion |
| CN112054507A (en) * | 2020-08-07 | 2020-12-08 | 国网辽宁省电力有限公司沈阳供电公司 | Power distribution low-voltage distribution area theoretical line loss interval calculation method based on convolutional neural network |
| CN113807301A (en) * | 2021-09-26 | 2021-12-17 | 武汉汉达瑞科技有限公司 | Automatic extraction method and automatic extraction system for newly-added construction land |
| CN113850312A (en) * | 2021-09-17 | 2021-12-28 | 西安天和防务技术股份有限公司 | Forest ecological condition monitoring method and device, electronic equipment and storage medium |
| CN115527123A (en) * | 2022-10-21 | 2022-12-27 | 河北省科学院地理科学研究所 | Land cover remote sensing monitoring method based on multi-source feature fusion |
| CN115829118A (en) * | 2022-11-29 | 2023-03-21 | 深圳市宇驰检测技术股份有限公司 | Forest carbon sink remote sensing monitoring method, device, equipment and storage medium |
| CN115979262A (en) * | 2023-03-21 | 2023-04-18 | 峰飞航空科技(昆山)有限公司 | Aircraft positioning method, device, equipment and storage medium |
| CN116702090A (en) * | 2023-06-19 | 2023-09-05 | 浙江大学 | Multi-mode data fusion and uncertain estimation water level prediction method and system |
-
2023
- 2023-11-15 CN CN202311522439.6A patent/CN117237780B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111651545A (en) * | 2020-06-03 | 2020-09-11 | 南京图申图信息科技有限公司 | Urban marginal area extraction method based on multi-source data fusion |
| CN112054507A (en) * | 2020-08-07 | 2020-12-08 | 国网辽宁省电力有限公司沈阳供电公司 | Power distribution low-voltage distribution area theoretical line loss interval calculation method based on convolutional neural network |
| CN113850312A (en) * | 2021-09-17 | 2021-12-28 | 西安天和防务技术股份有限公司 | Forest ecological condition monitoring method and device, electronic equipment and storage medium |
| CN113807301A (en) * | 2021-09-26 | 2021-12-17 | 武汉汉达瑞科技有限公司 | Automatic extraction method and automatic extraction system for newly-added construction land |
| CN115527123A (en) * | 2022-10-21 | 2022-12-27 | 河北省科学院地理科学研究所 | Land cover remote sensing monitoring method based on multi-source feature fusion |
| CN115829118A (en) * | 2022-11-29 | 2023-03-21 | 深圳市宇驰检测技术股份有限公司 | Forest carbon sink remote sensing monitoring method, device, equipment and storage medium |
| CN115979262A (en) * | 2023-03-21 | 2023-04-18 | 峰飞航空科技(昆山)有限公司 | Aircraft positioning method, device, equipment and storage medium |
| CN116702090A (en) * | 2023-06-19 | 2023-09-05 | 浙江大学 | Multi-mode data fusion and uncertain estimation water level prediction method and system |
Non-Patent Citations (1)
| Title |
|---|
| 地球辐射收支探测的目标方向...构建：从地球卫星到月基平台_;李清泉 等;《地球信息科学学报》;第第25卷卷(第第1期期);2-14 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117237780A (en) | 2023-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105893972B (en) | Automatic monitoring method for illegal building based on image and implementation system thereof | |
| CN103389103B (en) | A kind of Characters of Geographical Environment map structuring based on data mining and air navigation aid | |
| CN107067405B (en) | Remote sensing image segmentation method based on scale optimization | |
| CN117237780B (en) | Multidimensional data feature graph construction method, multidimensional data feature graph construction system, intelligent terminal and medium | |
| Aytekın et al. | Unsupervised building detection in complex urban environments from multispectral satellite imagery | |
| CN112883900B (en) | Method and device for bare-ground inversion of visible images of remote sensing images | |
| CN115375868B (en) | Map display method, remote sensing map display method, computing device and storage medium | |
| Varma et al. | Change detection of desert sand dunes: a remote sensing approach | |
| Yan et al. | LOVD: land vehicle detection in complex scenes of optical remote sensing image | |
| Kumar et al. | A two-stage algorithm for ground filtering of airborne laser scanning data | |
| Kusetogullari et al. | Unsupervised change detection in landsat images with atmospheric artifacts: a fuzzy multiobjective approach | |
| Babu | Optimized performance and utilization analysis of real-time multi spectral data/image categorization algorithms for computer vision applications | |
| Ansari et al. | Mapping and analysis of crime in Aurangabad city using GIS | |
| Erskine et al. | Evaluating the relationship between data resolution and the accuracy of identified helicopter landing zones (HLZs) | |
| CN114418858A (en) | Remote sensing image embedding method, device, equipment and storage medium | |
| Hashim et al. | Geometric and radiometric evaluation of RazakSAT medium-sized aperture camera data | |
| CN115937673A (en) | Geographic element rapid change discovery method based on mobile terminal photo | |
| CN116188587A (en) | Positioning method and device and vehicle | |
| Ahmed et al. | High-quality building information models (BIMs) using geospatial datasets | |
| CN115424131B (en) | Cloud detection optimal threshold selection method, cloud detection method and cloud detection system | |
| Osmólska et al. | Using a GEOBIA framework for integrating different data sources and classification methods in context of land use/land cover mapping | |
| Zeng et al. | A stereo image matching method to improve the DSM accuracy inside building boundaries | |
| Du et al. | A new multi-feature approach to object-oriented change detection based on fuzzy classification | |
| CN117609411B (en) | Integration and fusion system and method for multisource geographic elevation information | |
| Caradonna et al. | Geomatic techniques for disseminating processed remotely sensed open data in an interactive WebGIS |
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 |