Vegetation type identification and classification method based on remote sensing and telemetry data, system and medium

Abstract

The present invention relates to the field of remote sensing and telemetry identification technology, and more specifically, to a vegetation type identification and classification method, system, and medium based on remote sensing and telemetry data. The method provided by the present invention mainly includes determining the target area that needs to be identified by vegetation type through telemetry image data, judging it as a green vegetation area or a non-green vegetation area, and when the target area is a green vegetation area, further obtaining the average height of the vegetation in the unit to be identified through a three-dimensional model, and obtaining the basic parameters of the unit to be identified to establish a second identification model, and outputting the third judgment result of forest vegetation or grassland vegetation through the second identification model. The above method solves the problem of the difficulty in identifying forest vegetation or grassland vegetation to a certain extent, and provides a reference basis for relevant staff in preliminary vegetation survey work.

Description

Technical Field

[0001] The present invention relates to the field of remote sensing and telemetry identification technology, and in particular to a vegetation type identification and classification method, system and medium based on remote sensing and telemetry data. Background Art

[0002] Remote sensing and telemetry is a technology that uses sensors to obtain information about the earth from a distance. It is widely used in environmental monitoring, resource surveys, climate research and other fields. Its background technologies include satellite technology, sensor technology, data processing and analysis technology, etc. Data processing and analysis involves technologies such as image processing, pattern recognition and machine learning, which can extract effective information from large amounts of remote sensing data. In addition, the development of computer network technology has also made the transmission and sharing of remote sensing data more efficient, promoting the widespread application of remote sensing technology.

[0003] In the prior art, remote sensing and telemetry technology is usually used for vegetation identification, which has good identification effect and can save a lot of manpower and material resources. However, in the process of use, it can generally only distinguish evergreen vegetation from non-green vegetation. It is difficult to distinguish other subdivided vegetation in evergreen vegetation due to their consistent colors, and the distinction is not accurate. Summary of the invention

[0004] The purpose of the present invention is to provide a vegetation type identification and classification method, system and medium based on remote sensing and telemetry data to solve the above-mentioned problems in the prior art.

[0005] The embodiments of the present invention are implemented by the following technical solutions:

[0006] In a first aspect, the present invention provides a method for identifying and dividing vegetation types based on remote sensing and telemetry data, comprising:

[0007] Obtain telemetry image data, and determine the target area where vegetation type identification is required through the telemetry image data;

[0008] Obtaining the green vegetation coverage rate of the target area, and setting a green coverage rate division threshold, outputting a first judgment result of the current target area through the green vegetation coverage rate and the green coverage rate division threshold, wherein the first judgment result is a green vegetation area and a non-green vegetation area;

[0009] When the target area is a non-green vegetation area, current weather data is obtained, a first recognition model is established through the weather data and the current green vegetation coverage rate, and a second judgment result is output through the first recognition model, wherein the second judgment result includes an unrecognizable area or desert vegetation;

[0010] When the target area is a green vegetation area, a three-dimensional model of the current target area is established through remote sensing image data, and the target area is divided into a number of units to be identified;

[0011] The average height of vegetation in the unit to be identified is obtained through the three-dimensional model, and the basic parameters of the unit to be identified are obtained to establish a second identification model. The third judgment result is output through the second identification model, and the third judgment result includes forest vegetation or grassland vegetation.

[0012] Preferably, the target area requiring vegetation type identification determined by remote sensing image data includes:

[0013] Obtain the non-building coverage area and several building coverage areas in the telemetry impact data, and determine whether the building coverage areas exceed two. If not, output the non-building coverage area as the target area and the building coverage area as the non-target area. If more, perform a secondary judgment.

[0014] Preferably, the secondary judgment includes:

[0015] Set the minimum judgment distance between the building coverage area and the adjacent building coverage area, and obtain all marked building coverage areas that meet the minimum judgment distance;

[0016] Get the center point of the building coverage area, connect several center points to get the area to be determined, and get the area of ​​the marked building coverage area and the area to be determined, establish an evaluation model and evaluation threshold, get the evaluation score through the evaluation model, and output the area to be determined as a target area or a non-target area according to the evaluation score and evaluation threshold.

[0017] Preferably, the evaluation model includes:

[0018]

[0019]

[0020]

[0021] In the formula, is the area of ​​the region to be determined, For the The area covered by the marked building, is the number of areas covered by marked buildings, is the maximum distance between the areas covered by two adjacent marked buildings, is the shortest distance between the coverage areas of two adjacent marked buildings, is the minimum judgment distance, For the evaluation score, is the evaluation threshold, To mark the maximum area covered by the building, To mark the maximum diameter of the building coverage area, Mark the minimum diameter of the area covered by the building;

[0022] when When , the current area to be determined is output as the target area. , the current area to be determined is output as a non-target area.

[0023] Preferably, obtaining the green vegetation coverage of the target area and setting the green coverage division threshold comprises:

[0024]

[0025]

[0026] In the formula, is the green vegetation coverage rate, Set the threshold for green coverage. is the green vegetation coverage area, is the target area;

[0027] when , the first output result is the green vegetation area, when , the first output result is the non-green vegetation area.

[0028] Preferably, establishing the first recognition model includes:

[0029]

[0030]

[0031] In the formula, To calculate the coefficient, when the weather data reflects snowy weather, , when the weather data reflects non-snow weather, , It is the non-green coverage area except white. is the annual rainfall rate, is the comparison value of the first recognition model, is the contrast threshold of the first recognition model;

[0032] when , the second output result is desert vegetation, when , output the second result as the unrecognizable area.

[0033] Preferably, dividing the target area into a plurality of units to be identified comprises:

[0034] Get the plane shape of the target area, and determine the plane shape as a regular geometric shape, including:

[0035] Obtain two points of the plane shape that are farthest apart, and determine a first line segment through the two points;

[0036] A regular circular geometry is formed with the first line segment as the diameter, the interval between the dividing lines is set, and the circular geometry is divided longitudinally and transversely by the dividing lines to obtain a plurality of segmentation units;

[0037] The segmented units falling within the target area are output as units to be identified.

[0038] Preferably, the step of acquiring basic parameters of the unit to be identified and establishing a second identification model comprises:

[0039]

[0040]

[0041] In the formula, For the The comparison value of the second recognition model of the unit to be recognized, For the The average height of the vegetation in the unit to be identified, is the average height of standard grassland vegetation, is the average height of standard forest vegetation, is the number of units to be identified, is the contrast threshold of the second recognition model;

[0042] when , the third output result is forest vegetation, when , the third output result is grassland vegetation.

[0043] In a second aspect, the present invention further provides a vegetation type identification and classification system based on remote sensing and telemetry data, comprising:

[0044] The acquisition module is configured to acquire telemetry image data, determine the target area for vegetation type identification through the telemetry image data; acquire the green vegetation coverage rate of the target area, and set a green coverage rate division threshold, and output a first judgment result of the current target area through the green vegetation coverage rate and the green coverage rate division threshold, wherein the first judgment result is a green vegetation area and a non-green vegetation area;

[0045] A first judgment module is configured to obtain current weather data when the target area is a non-green vegetation area, establish a first recognition model through the weather data and the current green vegetation coverage rate, and output a second judgment result through the first recognition model, wherein the second judgment result includes an unrecognizable area or desert vegetation;

[0046] The second judgment module is configured to, when the target area is a green vegetation area, establish a three-dimensional model of the current target area through the telemetry image data, and divide the target area into a plurality of units to be identified; obtain the average height of the vegetation in the units to be identified through the three-dimensional model, and obtain the basic parameters of the units to be identified to establish a second recognition model, and output a third judgment result through the second recognition model, wherein the third judgment result includes forest vegetation or grassland vegetation;

[0047] The main control module is connected with the acquisition module, the first judgment module and the second judgment module, and is used to execute the above-mentioned vegetation type identification and classification method based on remote sensing and telemetry data.

[0048] In a third aspect, the present invention further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned vegetation type identification and classification method based on remote sensing and telemetry data.

[0049] The technical solution of the embodiment of the present invention has at least the following advantages and beneficial effects:

[0050] The method provided by the present invention mainly includes determining the target area that needs to be identified for vegetation type through remote sensing image data, judging it as a green vegetation area or a non-green vegetation area, and when the target area is a green vegetation area, further obtaining the average height of the vegetation in the unit to be identified through a three-dimensional model, and obtaining the basic parameters of the unit to be identified to establish a second identification model, and outputting the third judgment result of forest vegetation or grassland vegetation through the second identification model. The above method solves the current problem of difficulty in identifying forest vegetation or grassland vegetation to a certain extent, and provides a reference basis for relevant staff in preliminary vegetation survey work. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0052] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0054] The terms "first, second" and the like in the specification and claims of this application and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. The naming or numbering of steps in this application does not mean that the steps in the method flow must be executed in the time / logical sequence indicated by the naming or numbering. The named or numbered process steps can be changed in the execution order according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved.

[0055] The modules or submodules described independently may be physically separated or not: they may be implemented by software or hardware, and some modules or submodules may be implemented by software, and the processor may call the software to implement the functions of these modules or submodules, and other modules or submodules may be implemented by hardware, such as by hardware circuits. In addition, some or all of the modules may be selected according to actual needs to achieve the purpose of the present application.

[0056] Please refer to Figure 1 The vegetation type identification and classification method based on remote sensing and telemetry data provided by the present invention includes:

[0057] S101: Acquire telemetry image data, and determine the target area where vegetation type identification is required through the telemetry image data;

[0058] In this embodiment, the remote sensing image data preferably adopts aerial telemetry, which uses sensors mounted on aircraft, unmanned aerial vehicles (UAVs) and other aerial platforms to collect ground images. Aerial telemetry has advantages in obtaining high-resolution images and detailed observation of specific areas.

[0059] The remote sensing image data includes urban activity areas and vegetation coverage areas to a certain extent. Since the vegetation coverage in cities is relatively sparse and very scattered, it is not very meaningful to analyze it through remote sensing. Therefore, it is necessary to divide the area to obtain the required target area.

[0060] S102: obtaining the green vegetation coverage of the target area, and setting a green coverage division threshold, and outputting a first judgment result of the current target area according to the green vegetation coverage and the green coverage division threshold, wherein the first judgment result is a green vegetation area and a non-green vegetation area;

[0061] In this embodiment, a preliminary division is performed to distinguish and identify green vegetation areas and non-green vegetation areas. There may be more non-green vegetation areas, but the vegetation type of green vegetation areas is generally forest vegetation or grassland vegetation. The focus is on the identification of green vegetation areas.

[0062] S103: when the target area is a non-green vegetation area, obtaining current weather data, establishing a first recognition model through the weather data and the current green vegetation coverage rate, and outputting a second judgment result through the first recognition model, wherein the second judgment result includes an unrecognizable area or desert vegetation;

[0063] In this embodiment, considering the impact of weather on remote sensing data, the target area may be covered with snow, resulting in the inability to simply distinguish the vegetation type of the current target area by the color in the remote sensing data.

[0064] Therefore, the result of the unrecognizable area is also used as an output result. Manual on-site investigation is required to obtain the vegetation type. Secondly, it is desert vegetation. Of course, non-green vegetation may also be the normal seasonal decline of forest vegetation or grassland vegetation. However, according to existing data, even if it is normal seasonal decline, there will be no large-scale non-green situation except for natural disasters. Therefore, this situation is not discussed in the present invention. The background discussed in the present invention is evergreen vegetation, and the other vegetation conditions are more complicated and are not within the scope of consideration of the present invention.

[0065] S104: When the target area is a green vegetation area, a three-dimensional model of the current target area is established through the remote sensing image data, and the target area is divided into a plurality of units to be identified;

[0066] Among them, regarding the three-dimensional model, it is preferred to perform geometric correction, atmospheric correction and radiation correction on the remote sensing image to ensure the accuracy and authenticity of the image. GIS software (such as ENVI, QGIS, etc.) can be used for processing. Stereo image algorithms (such as bundle normal (Bundle Adjustment)) are used to extract depth information from multi-view images. This can be achieved through SFM (Structure from Motion) technology. Dense point clouds are generated through stereo matching. Open source software (such as OpenMVG, OpenMVS) or commercial software (such as Pix4D, Agisoft Metashape) can be used to generate point clouds.

[0067] Classify, filter and denoise the generated point cloud to obtain more accurate data. This step can be done using point cloud processing software such as CloudCompare. Convert the processed point cloud into a 3D model. You can use 3D modeling software (such as Blender, MeshLab, Autodesk Recap, etc.) to convert the point cloud into a 3D model.

[0068] S105: Obtain the average height of vegetation in the unit to be identified through the three-dimensional model, and obtain basic parameters of the unit to be identified to establish a second identification model, and output a third judgment result through the second identification model, wherein the third judgment result includes forest vegetation or grassland vegetation.

[0069] The method provided by the present invention mainly includes determining the target area that needs to be identified for vegetation type through remote sensing image data, judging it as a green vegetation area or a non-green vegetation area, and when the target area is a green vegetation area, further obtaining the average height of the vegetation in the unit to be identified through a three-dimensional model, and obtaining the basic parameters of the unit to be identified to establish a second identification model, and outputting the third judgment result of forest vegetation or grassland vegetation through the second identification model. The above method solves the current problem of difficulty in identifying forest vegetation or grassland vegetation to a certain extent, and provides a reference basis for relevant staff in preliminary vegetation survey work.

[0070] An exemplary implementation of the present invention, in this embodiment, considering that there may be multiple building coverage areas, when several adjacent building coverage areas are close to each other, the target area enclosed between them is small and not representative, and has no meaning for investigation in this field. Therefore, if the non-building coverage area is simply divided into the target area, a lot of detection and analysis work time will be wasted. The present invention proposes the following method to solve the problem.

[0071] S201: The target area for vegetation type identification determined by remote sensing image data includes:

[0072] S202: Obtain non-building coverage areas and several building coverage areas in the telemetry impact data, and determine whether the building coverage areas exceed two. If not, output the non-building coverage area as the target area and the building coverage area as the non-target area. If more, perform a secondary judgment.

[0073] In this embodiment, since the adjacent area between two building coverage areas is limited, it will not affect the results during analysis, saving the judgment process, so only the situation of more than two building coverage areas is considered for judgment.

[0074] Specifically, the secondary judgment includes:

[0075] S301: Setting a minimum judgment distance between a building coverage area and an adjacent building coverage area, and obtaining all marked building coverage areas that meet the minimum judgment distance;

[0076] S302: Obtain the center point of the building coverage area, connect several center points to obtain the area to be determined, and obtain the area of ​​the marked building coverage area and the area to be determined, establish an evaluation model and an evaluation threshold, obtain an evaluation score through the evaluation model, and output the area to be determined as a target area or a non-target area according to the evaluation score and the evaluation threshold.

[0077] Regarding the determination of the center point, in this embodiment, the midpoint of the line segment formed by the two farthest points in the building coverage area is selected as the center point of the building coverage area. A plurality of center points are connected end to end to form a closed area to be determined.

[0078] Specifically, the evaluation model includes:

[0079]

[0080]

[0081]

[0082] In the formula, is the area of ​​the region to be determined, For the The area covered by the marked building, is the number of areas covered by marked buildings, is the maximum distance between the areas covered by two adjacent marked buildings, is the shortest distance between the coverage areas of two adjacent marked buildings, is the minimum judgment distance, For the evaluation score, is the evaluation threshold, To mark the maximum area covered by the building, To mark the maximum diameter of the building coverage area, Mark the minimum diameter of the area covered by the building;

[0083] when When , the current area to be determined is output as the target area. , the output current area to be determined is a non-target area.

[0084] In the present invention, a specific example is provided to further explain the above method:

[0085] The area of ​​the area to be determined is 15 square kilometers, the area covered by the first marked building is 3 square kilometers, the area covered by the second marked building is 2 square kilometers, the area covered by the third marked building is 1 square kilometer, the farthest distance between the coverage areas of two adjacent marked buildings is 10 kilometers, the shortest distance between the coverage areas of two adjacent marked buildings is 5 kilometers, and the minimum judgment distance is 2 kilometers.

[0086] Available, ， , indicating that the target area enclosed by several adjacent building coverage areas is relatively large, and the current area to be determined is output as the target area.

[0087] In an exemplary embodiment of the present invention, obtaining the green vegetation coverage of the target area and setting the green coverage division threshold includes:

[0088]

[0089]

[0090] In the formula, is the green vegetation coverage rate, Set the threshold for green coverage. is the green vegetation coverage area, is the target area;

[0091] when , the first output result is the green vegetation area, when , the first output result is the non-green vegetation area.

[0092] In a specific example:

[0093] The green vegetation coverage area is 10 square kilometers, and the target area is 12 square kilometers. , , the output is green vegetation area.

[0094] For example, if the green vegetation coverage area is 2 square kilometers and the target area is 12 square kilometers, we can get: , , the output is non-green vegetation area.

[0095] In an exemplary embodiment of the present invention, establishing a first recognition model includes:

[0096]

[0097]

[0098] In the formula, To calculate the coefficient, when the weather data reflects snowy weather, , when the weather data reflects non-snow weather, , is the green vegetation coverage area, It is the non-green coverage area except white. is the annual rainfall rate, is the comparison value of the first recognition model, is the contrast threshold of the first recognition model;

[0099] when , the second output result is desert vegetation, when , output the second result as the unrecognizable area.

[0100] In the present invention, a specific example is provided to further explain the above method:

[0101] When the weather data reflects snowy weather, the green vegetation coverage area is 2 square kilometers, the non-green coverage area excluding white is 8 square kilometers, and the target area is 12 square kilometers. 10%;

[0102] Available , , so the second output result is desert vegetation.

[0103] In an exemplary embodiment of the present invention, dividing the target area into a plurality of units to be identified comprises:

[0104] Get the plane shape of the target area, and determine the plane shape as a regular geometric shape, including:

[0105] Obtain two points of the plane shape that are farthest apart, and determine a first line segment through the two points;

[0106] A regular circular geometry is formed with the first line segment as the diameter, the interval between the dividing lines is set, and the circular geometry is divided longitudinally and transversely by the dividing lines to obtain a plurality of segmentation units;

[0107] The segmented units falling within the target area are output as units to be identified.

[0108] Specifically, obtaining basic parameters of the unit to be identified and establishing the second identification model includes:

[0109]

[0110]

[0111] In the formula, For the The comparison value of the second recognition model of the unit to be recognized, For the The average height of the vegetation in the unit to be identified, is the average height of standard grassland vegetation, is the average height of standard forest vegetation, is the number of units to be identified, is the contrast threshold of the second recognition model;

[0112] when , the third output result is forest vegetation, when , the third output result is grassland vegetation.

[0113] In the present invention, a specific example is provided to further explain the above method:

[0114] The average heights of the vegetation units to be identified are 0.3 meters, 0.2 meters, 1 meter, 0.1 meters, and 0.6 meters, respectively. The average height of standard grassland vegetation and the average height of standard forest vegetation can be obtained through the standards of the prior art. In this embodiment, the average height of standard grassland vegetation is 0.2 meters, the average height of standard forest vegetation is 20 meters, the number of units to be identified is 50, and the sum of the average heights of all the vegetation units to be identified is 150 meters.

[0115] Then, the average height of the unit to be identified is 0.3 meters , , so the units to be identified with an average height of 0.3 meters are grassland vegetation.

[0116] In a second aspect, the present invention further provides a vegetation type identification and classification system based on remote sensing and telemetry data, comprising:

[0117] The acquisition module is configured to acquire telemetry image data, determine the target area for vegetation type identification through the telemetry image data; acquire the green vegetation coverage rate of the target area, and set a green coverage rate division threshold, and output a first judgment result of the current target area through the green vegetation coverage rate and the green coverage rate division threshold, wherein the first judgment result is a green vegetation area and a non-green vegetation area;

[0118] A first judgment module is configured to obtain current weather data when the target area is a non-green vegetation area, establish a first recognition model through the weather data and the current green vegetation coverage rate, and output a second judgment result through the first recognition model, wherein the second judgment result includes an unrecognizable area or desert vegetation;

[0119] The second judgment module is configured to, when the target area is a green vegetation area, establish a three-dimensional model of the current target area through the telemetry image data, and divide the target area into a plurality of units to be identified; obtain the average height of the vegetation in the units to be identified through the three-dimensional model, and obtain the basic parameters of the units to be identified to establish a second recognition model, and output a third judgment result through the second recognition model, wherein the third judgment result includes forest vegetation or grassland vegetation;

[0120] The main control module is connected with the acquisition module, the first judgment module and the second judgment module, and is used to execute the above-mentioned vegetation type identification and classification method based on remote sensing and telemetry data.

[0121] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0122] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0123] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A vegetation type identification and classification method based on remote sensing and telemetry data, characterized in that: include: Obtain telemetry image data, and determine the target area where vegetation type identification is required through the telemetry image data; Obtaining the green vegetation coverage rate of the target area, and setting a green coverage rate division threshold, outputting a first judgment result of the current target area through the green vegetation coverage rate and the green coverage rate division threshold, wherein the first judgment result is a green vegetation area and a non-green vegetation area; When the target area is a non-green vegetation area, current weather data is obtained, a first recognition model is established through the weather data and the current green vegetation coverage rate, and a second judgment result is output through the first recognition model, wherein the second judgment result includes an unrecognizable area or desert vegetation; When the target area is a green vegetation area, a three-dimensional model of the current target area is established through remote sensing image data, and the target area is divided into a number of units to be identified; Obtaining the average height of vegetation in the unit to be identified through the three-dimensional model, and obtaining basic parameters of the unit to be identified to establish a second identification model, and outputting a third judgment result through the second identification model, wherein the third judgment result includes forest vegetation or grassland vegetation; The target area for vegetation type identification determined by remote sensing image data includes: Obtain non-building coverage areas and several building coverage areas in the telemetry impact data, and determine whether the building coverage areas exceed two. If not, output the non-building coverage area as the target area and the building coverage area as the non-target area. If more than two, perform a secondary judgment. The secondary judgment includes: Set the minimum judgment distance between the building coverage area and the adjacent building coverage area, and obtain all marked building coverage areas that meet the minimum judgment distance; Get the center point of the building coverage area, connect several center points to get the area to be determined, and get the area of ​​the marked building coverage area and the area to be determined, establish an evaluation model and evaluation threshold, get the evaluation score through the evaluation model, and output the area to be determined as a target area or a non-target area according to the evaluation score and evaluation threshold.

2. The vegetation type identification and classification method based on remote sensing and telemetry data according to claim 1 is characterized in that: The evaluation model includes: In the formula, is the area of ​​the region to be determined, For the The area covered by the marked building, is the number of areas covered by marked buildings, is the maximum distance between the areas covered by two adjacent marked buildings, is the shortest distance between the coverage areas of two adjacent marked buildings, is the minimum judgment distance, For the evaluation score, is the evaluation threshold, To mark the maximum area covered by the building, To mark the maximum diameter of the building coverage area, Mark the minimum diameter of the area covered by the building; when When , the current area to be determined is output as the target area. , the current area to be determined is output as a non-target area.

3. The vegetation type identification and classification method based on remote sensing and telemetry data according to claim 2 is characterized in that: The step of obtaining the green vegetation coverage rate of the target area and setting the green coverage rate division threshold comprises: In the formula, is the green vegetation coverage rate, Set the threshold for green coverage. is the green vegetation coverage area, is the target area; when , the first output result is the green vegetation area, when , the first output result is the non-green vegetation area.

4. The vegetation type identification and classification method based on remote sensing and telemetry data according to claim 3 is characterized in that: The establishing of the first recognition model comprises: In the formula, To calculate the coefficient, when the weather data reflects snowy weather, , when the weather data reflects non-snow weather, , It is the non-green coverage area except white. is the annual rainfall rate, is the comparison value of the first recognition model, is the contrast threshold of the first recognition model; when , the second output result is desert vegetation, when , output the second result as the unrecognizable area.

5. The vegetation type identification and classification method based on remote sensing and telemetry data according to claim 4 is characterized in that: The step of dividing the target area into a plurality of units to be identified includes: Get the plane shape of the target area, and determine the plane shape as a regular geometric shape, including: Obtain two points of the plane shape that are farthest apart, and determine a first line segment through the two points; A regular circular geometry is formed with the first line segment as the diameter, the interval between the dividing lines is set, and the circular geometry is divided longitudinally and transversely by the dividing lines to obtain a plurality of segmentation units; The segmented units falling within the target area are output as units to be identified.

6. The vegetation type identification and classification method based on remote sensing and telemetry data according to claim 5 is characterized in that: The step of acquiring basic parameters of the unit to be identified and establishing a second identification model comprises: In the formula, For the The comparison value of the second recognition model of the unit to be recognized, For the The average height of the vegetation in the unit to be identified, is the average height of standard grassland vegetation, is the average height of standard forest vegetation, is the number of units to be identified, is the contrast threshold of the second recognition model; when , the third output result is forest vegetation, when , the third output result is grassland vegetation.

7. Vegetation type identification and classification system based on remote sensing and telemetry data, characterized in that: include: An acquisition module is configured to acquire telemetry image data and determine a target area requiring vegetation type identification through the telemetry image data; Obtaining the green vegetation coverage rate of the target area, and setting a green coverage rate division threshold, outputting a first judgment result of the current target area through the green vegetation coverage rate and the green coverage rate division threshold, wherein the first judgment result is a green vegetation area and a non-green vegetation area; A first judgment module is configured to obtain current weather data when the target area is a non-green vegetation area, establish a first recognition model through the weather data and the current green vegetation coverage rate, and output a second judgment result through the first recognition model, wherein the second judgment result includes an unrecognizable area or desert vegetation; The second judgment module is configured to, when the target area is a green vegetation area, establish a three-dimensional model of the current target area through the telemetry image data, and divide the target area into a plurality of units to be identified; obtain the average height of the vegetation in the units to be identified through the three-dimensional model, and obtain the basic parameters of the units to be identified to establish a second recognition model, and output a third judgment result through the second recognition model, wherein the third judgment result includes forest vegetation or grassland vegetation; The main control module is connected to the acquisition module, the first judgment module and the second judgment module, and is used to execute the vegetation type identification and classification method based on remote sensing and telemetry data according to any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for identifying and dividing vegetation types based on remote sensing and telemetry data according to any one of claims 1 to 6 is implemented.

Images