Orchard sample generation method, device, system, equipment and medium

Abstract

The invention provides an orchard sample generation method, device and system, equipment and a medium. The method comprises the following steps: acquiring time sequence remote sensing data and annual vegetation pixel data; determining a tree cartographic index and an orchard phenol phenology index according to the time sequence remote sensing data; determining orchard position distribution information in the annual vegetation pixel data by using the tree cartographic index and the orchard phenol phenological index; and determining an orchard sample based on the orchard position distribution information. According to the method, the problem of orchard sample missing in large-scale orchard mapping tasks in related technologies is solved, the advantages of the remote sensing technology are fully played, large-scale orchard spatial distribution mapping at any time and place is served, and the data size and the data accuracy are improved for large-scale and multi-year orchard mapping through supervision classification.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, system, equipment and medium for generating an orchard sample. Background Art

[0002] In recent years, with the continuous advancement of agricultural science and technology, satellite remote sensing technology has made remarkable achievements in agricultural and forestry crop monitoring, especially in large-scale seasonal food crop distribution monitoring, and the technology has become more mature. For horticultural crops such as apples, peaches and pears, accurate orchard distribution information not only helps to optimize resource allocation and adjust planting structure, but also provides important data support for carbon sequestration potential assessment and environmental impact assessment. However, existing remote sensing crop mapping methods, including multimodal features combined with supervised classification, phenological feature threshold method and growth curve similarity classification method, have certain limitations. In particular, supervised classification methods rely on a large number of training labels, and high-quality crop growth curves are difficult to obtain in similarity classification, which will directly affect the mapping accuracy. In addition, traditional sample sources such as field surveys and visual interpretation are inefficient, costly and difficult to guarantee sample accuracy. Therefore, it is urgent to develop new methods to effectively extract orchard samples to improve the monitoring accuracy of orchard distribution. Summary of the invention

[0003] The present invention provides a method, device, equipment and medium for generating an orchard sample, so as to solve the problem of missing orchard samples in large-scale orchard mapping tasks in the related art.

[0004] The present invention provides a method for generating an orchard sample, comprising the following steps: Obtain time series remote sensing data and annual vegetation pixel data; Determine the tree mapping index and orchard phenolic phenology index based on time series remote sensing data; The tree mapping index and orchard phenolic phenology index were used to determine the orchard location distribution information in the annual vegetation pixel data; Based on the orchard location distribution information, orchard samples are determined.

[0005] According to a method for generating an orchard sample provided by the present invention, time series remote sensing data and annual vegetation pixel data are obtained, including: Obtain multispectral satellite image information; Preprocess multispectral satellite image information to obtain time series remote sensing data and annual maximum normalized vegetation index images; The annual maximum normalized vegetation index image whose annual maximum normalized vegetation index is greater than a preset value is determined as the annual vegetation pixel data.

[0006] According to a method for generating an orchard sample provided by the present invention, a tree mapping index and an orchard phenolic phenological index are determined according to time series remote sensing data, comprising: The tree phenology cumulative index, tree greenness difference index and phenol compound index were obtained based on time series remote sensing data. The tree mapping index was determined using the tree phenology cumulative index and the tree greenness difference index; The phenolic compound index was used to determine the orchard phenolic phenological index.

[0007] According to a method for generating an orchard sample provided by the present invention, the orchard phenolic phenological index is determined by using the phenolic compound index, comprising: Based on the phenol compound index, the cumulative change of phenol compounds in the middle growth period, the degree of variation of phenol compounds in the middle growth period and the average level of phenol compounds in the middle growth period were determined; The orchard phenolic phenological index was determined based on the cumulative change of phenolic compounds in the middle growth period, the degree of variation of phenolic compounds in the middle growth period and the average level of phenolic compounds in the middle growth period.

[0008] According to a method for generating orchard samples provided by the present invention, the orchard phenolic phenological index is determined by the following formula based on the cumulative change of phenolic compounds in the middle growth period, the degree of variation of phenolic compounds in the middle growth period and the average level of phenolic compounds in the middle growth period:

[0009] in, is the value of the phenol compound index at time k, is the value of the phenol compound index at time k+1, ~ is the middle growth period of trees, PA is the cumulative change of phenolic compounds in the middle growth period, PV is the variation degree of phenolic compounds in the middle growth period, PM is the average level of phenolic compounds in the middle growth period, and OPPI is the orchard phenolic phenological index.

[0010] According to a method for generating an orchard sample provided by the present invention, the orchard location distribution information is determined in the annual vegetation pixel data by using the tree mapping index and the orchard phenol phenology index, comprising: Using the tree mapping index, the tree location distribution is determined in the annual vegetation pixel data; Orchard phenolic phenological index was used to determine orchard location distribution information in tree location distribution.

[0011] The present invention also provides a device for generating orchard samples, comprising the following units: An acquisition unit, used to acquire time series remote sensing data and annual vegetation pixel data; a computational unit for determining the tree mapping index and orchard phenolic phenology index from time series remote sensing data; Determine a unit for determining orchard location distribution information in annual vegetation pixel data using the tree mapping index and orchard phenolic phenology index; The processing unit is used to determine the orchard sample based on the orchard location distribution information.

[0012] According to the device for generating an orchard sample provided by the present invention, the acquisition unit is specifically used for: Obtain multispectral satellite image information; Preprocess multispectral satellite image information to obtain time series remote sensing data and annual maximum normalized vegetation index images; The annual maximum normalized vegetation index image whose annual maximum normalized vegetation index is greater than a preset value is determined as the annual vegetation pixel data.

[0013] According to the device for generating an orchard sample provided by the present invention, the computing unit is specifically used for: The tree phenology cumulative index, tree greenness difference index and phenol compound index were obtained based on time series remote sensing data. The tree mapping index was determined using the tree phenology cumulative index and the tree greenness difference index; The phenolic compound index was used to determine the orchard phenolic phenological index.

[0014] According to the device for generating an orchard sample provided by the present invention, the computing unit is specifically used for: Based on the phenol compound index, the cumulative change of phenol compounds in the middle growth period, the degree of variation of phenol compounds in the middle growth period and the average level of phenol compounds in the middle growth period were determined; The orchard phenolic phenological index was determined based on the cumulative change of phenolic compounds in the middle growth period, the degree of variation of phenolic compounds in the middle growth period and the average level of phenolic compounds in the middle growth period.

[0015] According to the device for generating orchard samples provided by the present invention, the calculation unit is further used to determine the orchard phenolic phenological index according to the following formula based on the cumulative change of phenolic compounds in the middle growth period, the degree of variation of phenolic compounds in the middle growth period and the average level of phenolic compounds in the middle growth period:

[0016] in, is the value of the phenol compound index at time k, is the value of the phenol compound index at time k+1, ~ is the middle growth period of trees, PA is the cumulative change of phenolic compounds in the middle growth period, PV is the variation degree of phenolic compounds in the middle growth period, PM is the average level of phenolic compounds in the middle growth period, and OPPI is the orchard phenolic phenological index.

[0017] According to the device for generating an orchard sample provided by the present invention, the determination unit is specifically used for: Using the tree mapping index, the tree location distribution is determined in the annual vegetation pixel data; Orchard phenolic phenological index was used to determine orchard location distribution information in tree location distribution.

[0018] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any of the above-mentioned methods for generating orchard samples is implemented.

[0019] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for generating an orchard sample as described above is implemented.

[0020] The method for generating orchard samples provided by the present invention first obtains time series remote sensing data and annual vegetation pixel data, then determines the tree mapping index and the orchard phenol phenology index according to the time series remote sensing data, then uses the tree mapping index and the orchard phenol phenology index to determine the orchard location distribution information in the annual vegetation pixel data, and finally determines the orchard sample based on the orchard location distribution information. The advantages of remote sensing technology are fully utilized, thereby serving the large-scale orchard spatial distribution mapping at any time and place, and improving the data volume and data accuracy for using supervised classification to achieve large-scale, multi-year orchard mapping. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 It is a flow chart of a method for generating orchard samples provided by the present invention.

[0023] Figure 2 It is a schematic diagram of the principle of a tree mapping index provided by the present invention.

[0024] Figure 3 The invention provides an index data statistical chart of orchards and food crops.

[0025] Figure 4 It is a schematic diagram of the principle of an orchard phenolic phenological index provided by the present invention.

[0026] Figure 5 It is a structural schematic diagram of the device for generating orchard samples provided by the present invention.

[0027] Figure 6 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] With the continuous development of agricultural science and technology, satellite remote sensing technology has made significant progress in the monitoring of agricultural and forestry crops, especially in the monitoring of large-scale seasonal food crop distribution. For horticultural crops such as apples, peaches and pears, accurate orchard distribution information not only helps to optimize resource allocation and adjust planting structure, but also provides important data support for carbon sink potential assessment, ecological service value estimation and environmental impact assessment. However, the current remote sensing monitoring research on large-scale orchard distribution is still insufficient, and related remote sensing monitoring products are scarce, which to a certain extent limits the in-depth study of orchard management and ecology.

[0030] Existing remote sensing crop mapping methods mainly include multimodal features combined with supervised classification, phenological feature threshold method, and growth curve similarity classification method. However, these methods all have certain limitations. Supervised classification requires a large number of training labels, and high-quality crop growth curves are difficult to obtain, which directly affects the accuracy of mapping. At the same time, the current sample sources mainly rely on field surveys, visual interpretation based on high-definition images, and existing mapping products. These traditional methods are inefficient, costly, and difficult to guarantee the accuracy of samples.

[0031] In addition, the phenological characteristics of fruit trees are unique in time series remote sensing data. Fruit trees usually sprout earlier than seasonal crops and remain green during the harvest period and throughout early winter, which makes their stay-green characteristics significantly different from those of single-season crops. Therefore, how to use satellite time series remote sensing data to explore the unique phenological and stay-green characteristics of fruit trees and realize the automatic extraction and accurate classification of orchard samples is still a technical problem that needs to be solved. At present, the intelligent sample generation method for orchard remote sensing classification is still in a blank stage, which provides broad application prospects for future research.

[0032] Therefore, there is an urgent need for a method for generating orchard samples to solve the above problems.

[0033] Combine the following Figure 1-Figure 6 The invention describes a method, device, equipment and medium for generating orchard samples.

[0034] Figure 1 is one of the flow charts of the method for generating orchard samples provided by the present invention, such as Figure 1 As shown, the method includes the following: Step 101: Acquire time series remote sensing data and annual vegetation pixel data.

[0035] In the specific implementation, time series remote sensing data and annual vegetation pixel data are obtained respectively. Both of these data can be obtained by processing multispectral satellite image information. Specifically, multispectral satellite image information is first obtained. The multispectral satellite image information can be Sentinel-2 multispectral image data, or Landsat data, domestic high-resolution data, WorldView-1, WorldView-2, WorldView-3, Himawari-8 and other forms of image data. The embodiment of the present invention takes Sentinel-2 as an example for explanation. After acquisition, the multispectral satellite image information is preprocessed to obtain time series remote sensing data and annual maximum normalized vegetation index image. The preprocessing includes resampling, cloud removal, vegetation index calculation, median and annual maximum value synthesis and other operation steps. The median calculation can select the half-month median, or other time intervals can be selected for calculation. Finally, the annual maximum normalized vegetation index image with an annual maximum normalized vegetation index greater than a preset value is determined as the annual vegetation pixel data.

[0036] In one example, taking the half-moon synthesis method as an example, after preprocessing the multispectral satellite image information, the half-moon synthesis time series remote sensing data and the normalized vegetation index image (Normalized DifferenceVegetation Index, NDVI) annual maximum NDVI image are obtained. The specific calculation formula is as follows:

[0037] in, and and are the reflectances of the red band and the near-infrared band respectively. Pixels with an annual maximum NDVI greater than 0.4 are identified as annual vegetation pixel data, which serve as the base map for subsequent steps. Of course, other suitable values ​​can also be selected, such as 0.5, 0.3, etc., which are not limited to the embodiments of the present invention.

[0038] Step 102: Determine the tree mapping index and orchard phenolic phenological index based on the time series remote sensing data.

[0039] In the specific implementation, the tree mapping index and orchard phenolic phenology index are calculated step by step according to the time series remote sensing data for subsequent calculations. Specifically, the tree phenological accumulation index (TPAI), tree greenness difference index (TGDI) and phenolic compound index (PCI) are first obtained based on the time series remote sensing data, and then the tree phenological accumulation index and tree greenness difference index are used to determine the tree mapping index, and the phenolic compound index is used to determine the orchard phenolic phenology index. The tree mapping index is used to distinguish trees from food crops, and the calculation formula is as follows:

[0040] NSS, ASS, ENS and FHS represent the new shoot stop period, autumn shoot stop period, new shoot stop early period and harvest period of fruit trees respectively. These four periods are defined as May 16 to July 15, July 16 to August 31, May 16 to June 15, October 16 to November 15. The period can be adjusted according to demand, Sum, Min, Max are calculated cumulative value, minimum value, maximum value respectively.

[0041] The Orchard Phenolic Phenology Index (OPPI) is used to further distinguish fruit trees from other low-phenolic trees. Specifically, the cumulative change of phenolic compounds in the middle of growth, the degree of variation of phenolic compounds in the middle of growth, and the average level of phenolic compounds in the middle of growth are determined based on the phenolic compound index. Then, the orchard phenolic phenology index is determined based on the cumulative change of phenolic compounds in the middle of growth, the degree of variation of phenolic compounds in the middle of growth, and the average level of phenolic compounds in the middle of growth. First, the phenolic compound index is calculated, and its calculation formula is as follows:

[0042] in, and are the reflectances of the green band and the shortwave infrared band, respectively.

[0043] The orchard phenolic phenological index is then determined based on the phenolic compound index, and the calculation formula is as follows:

[0044] in, is the value of the phenol compound index at time k, is the value of the phenol compound index at time k+1, ~ is the middle growth period of trees, PA is the cumulative change of phenolic compounds in the middle growth period, PV is the variation degree of phenolic compounds in the middle growth period, PM is the average level of phenolic compounds in the middle growth period, and OPPI is the orchard phenolic phenological index.

[0045] Step 103: Determine the orchard location distribution information in the annual vegetation pixel data using the tree mapping index and the orchard phenol phenology index.

[0046] In specific implementation, the tree mapping index is used to determine the tree location distribution in the annual vegetation pixel data, and then the orchard phenolic phenological index is used to determine the orchard location distribution information in the tree location distribution.

[0047] Specifically, in order to distinguish trees from food crops, we innovatively constructed a tree mapping index (TMI) based on the time series NDVI index. The index is composed of the Tree Phenological Accumulation Index (TPAI) and the Tree Greenness Difference Index (TGDI). TPAI is used to characterize the phenological characteristics of early leafing and late leaf fall of trees, and TGDI is used to characterize the phenological characteristics of long saturated green time of trees. The schematic diagram of the index is shown below. Figure 2 As shown. According to the calculation in step 103, we get Figure 3 The index statistics of fruit trees and grain crops measured in the field are shown. It can be seen that there are obvious differences in the TMI index between trees and grain crops, which proves that the TMI index can distinguish between trees and grain crops.

[0048] Furthermore, in order to distinguish fruit trees from other low-phenolic trees, the Orchard Phenolic Phenology Index (OPPI) is used. This index mainly characterizes the degree of phenolic compounds in vegetation, among which fruit trees contain high phenolic compounds, while other trees such as forests contain low phenolic compounds. Fruit trees are distinguished from other trees based on this difference. PA (Accumulation of Phenolic) represents the cumulative change of phenolic compounds (PCI) in the middle of growth, PV (Variation of Phenolic) represents the degree of variation of phenolic compounds (PCI) in the middle of growth, and PM (Mean of Phenolic) represents the average level of phenolic compounds (PCI) in the middle of growth. Figure 4 As shown, the PCI time series curves and index diagrams of fruit trees and other trees are shown. It can be seen that the PA, PV and PM values ​​of orchards are all smaller than those of forests. Therefore, the multiplication of the three magnifies the difference, so the index can distinguish fruit trees from other forest trees.

[0049] Step 104: Determine orchard samples based on the orchard location distribution information.

[0050] During the specific implementation, through step 102 and step 103, the tree mapping index and the orchard phenolic phenological index are calculated respectively, so as to distinguish trees from other food crops, and accurately distinguish fruit tree and non-fruit tree pixels, and obtain the binary image of the orchard and non-orchard. Based on the binary image, the orchard and non-orchard sample pixels of any year and location can be obtained by random sampling. Taking into account the existence of isolated pixels or potential errors in the training samples, in order to ensure the high quality of the samples, the area of ​​all orchard pixels in the 3 pixel × 3 pixel window is selected as the final orchard sample. Of course, other pixel format data methods can also be selected, and the embodiment of the present invention is not limited to this.

[0051] By using the method disclosed in the embodiment of the present invention, it is possible to utilize time series remote sensing data to fully explore the phenological differences between fruit trees and other crops. The index calculation involved in the newly proposed method for generating orchard samples is simple, and the automatic generation of high-quality orchard samples can be achieved without distinguishing between years and locations. This lays the foundation for using supervised classification to achieve large-scale, multi-year orchard mapping, and has good application prospects.

[0052] The device for generating orchard samples provided by the present invention is described below. The device for generating orchard samples described below and the method for generating orchard samples described above can refer to each other.

[0053] like Figure 5 As shown, the orchard sample generation device 500 provided by the present invention includes the following units: An acquisition unit 501 is used to acquire time series remote sensing data and annual vegetation pixel data; A calculation unit 502 is used to determine the tree mapping index and the orchard phenolic phenological index according to the time series remote sensing data; A determination unit 503 is used to determine the orchard location distribution information in the annual vegetation pixel data using the tree mapping index and the orchard phenol phenology index; The processing unit 504 is used to determine the orchard sample based on the orchard location distribution information.

[0054] According to the device for generating an orchard sample provided by the present invention, the acquisition unit 501 is specifically used for: Obtain multispectral satellite image information; Preprocess multispectral satellite image information to obtain time series remote sensing data and annual maximum normalized vegetation index images; The annual maximum normalized vegetation index image whose annual maximum normalized vegetation index is greater than a preset value is determined as the annual vegetation pixel data.

[0055] According to the device for generating an orchard sample provided by the present invention, the calculation unit 502 is specifically used for: The orchard phenology accumulation index, orchard greenness difference index and phenolic compound index were obtained based on time series remote sensing data. The tree mapping index was determined using the tree phenology cumulative index and the tree greenness difference index; The phenolic compound index was used to determine the orchard phenolic phenological index.

[0056] According to the device for generating an orchard sample provided by the present invention, the calculation unit 502 is specifically used for: Based on the phenol compound index, the cumulative change of phenol compounds in the middle growth period, the degree of variation of phenol compounds in the middle growth period and the average level of phenol compounds in the middle growth period were determined; The orchard phenolic phenological index was determined based on the cumulative change of phenolic compounds in the middle growth period, the degree of variation of phenolic compounds in the middle growth period and the average level of phenolic compounds in the middle growth period.

[0057] According to the device for generating orchard samples provided by the present invention, the calculation unit 502 is further used to determine the orchard phenolic phenological index according to the following formula based on the cumulative change of phenolic compounds in the middle growth period, the degree of variation of phenolic compounds in the middle growth period and the average level of phenolic compounds in the middle growth period:

[0058] in, is the value of the phenol compound index at time k, is the value of the phenol compound index at time k+1, ~ is the middle growth period of trees, PA is the cumulative change of phenolic compounds in the middle growth period, PV is the variation degree of phenolic compounds in the middle growth period, PM is the average level of phenolic compounds in the middle growth period, and OPPI is the orchard phenolic phenological index.

[0059] According to the device for generating an orchard sample provided by the present invention, the determining unit 503 is specifically used for: Using the tree mapping index, the tree location distribution is determined in the annual vegetation pixel data; Orchard phenolic phenological index was used to determine orchard location distribution information in tree location distribution.

[0060] Figure 6 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 6As shown, the electronic device may include: a processor 610, a communications interface 620, a memory 630 and a communication bus 640, wherein the processor 610, the communications interface 620 and the memory 630 communicate with each other through the communication bus 640. The processor 610 may call the logic instructions in the memory 630 to execute the method for generating orchard samples, and the method includes: Obtain time series remote sensing data and annual vegetation pixel data; Determine the tree mapping index and orchard phenolic phenology index based on time series remote sensing data; The tree mapping index and orchard phenolic phenology index were used to determine the orchard location distribution information in the annual vegetation pixel data; Based on the orchard location distribution information, orchard samples are determined.

[0061] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and 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 each embodiment 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, etc. Various media that can store program codes.

[0062] On the other hand, the present invention further provides a computer program product, the computer program product comprising a computer program, the computer program can be stored in a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the method for generating orchard samples provided by the above methods, the method comprising: Obtain time series remote sensing data and annual vegetation pixel data; Determine the tree mapping index and orchard phenolic phenology index based on time series remote sensing data; The tree mapping index and orchard phenolic phenology index were used to determine the orchard location distribution information in the annual vegetation pixel data; Based on the orchard location distribution information, orchard samples are determined.

[0063] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method for generating an orchard sample provided by the above methods is implemented, and the method comprises: Obtain time series remote sensing data and annual vegetation pixel data; Determine the tree mapping index and orchard phenolic phenology index based on time series remote sensing data; The tree mapping index and orchard phenolic phenology index were used to determine the orchard location distribution information in the annual vegetation pixel data; Based on the orchard location distribution information, orchard samples are determined.

[0064] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0065] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0066] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for generating orchard samples, characterized in that: The method comprises: Obtain time series remote sensing data and annual vegetation pixel data; determining a tree mapping index and an orchard phenolic phenological index based on said time series remote sensing data; Determining orchard location distribution information in the annual vegetation pixel data using the tree mapping index and the orchard phenolic phenology index; Based on the orchard location distribution information, an orchard sample is determined.

2. The method for generating orchard samples according to claim 1, characterized in that: The obtaining of time series remote sensing data and annual vegetation pixel data includes: Obtain multispectral satellite image information; Preprocessing the multispectral satellite image information to obtain time series remote sensing data and annual maximum normalized vegetation index images; The annual maximum normalized vegetation index image whose annual maximum normalized vegetation index is greater than a preset value is determined as the annual vegetation pixel data.

3. The method for generating orchard samples according to claim 2, characterized in that: Determining the tree mapping index and the orchard phenolic phenological index according to the time series remote sensing data comprises: Based on the time series remote sensing data, a tree phenology cumulative index, a tree greenness difference index and a phenol compound index are obtained; Determine the tree mapping index using the tree phenology cumulative index and the tree greenness difference index; The orchard phenolic phenological index is determined using the phenolic compound index.

4. The method for generating orchard samples according to claim 3, characterized in that: Determining the orchard phenolic phenological index by using the phenolic compound index comprises: Determining the cumulative change amount of phenolic compounds in the middle growth period, the degree of variation of phenolic compounds in the middle growth period, and the average level of phenolic compounds in the middle growth period based on the phenolic compound index; The orchard phenolic phenological index is determined according to the cumulative change of the phenolic compounds in the mid-growth period, the degree of variation of the phenolic compounds in the mid-growth period and the average level of the phenolic compounds in the mid-growth period.

5. The method for generating orchard samples according to claim 4, characterized in that: According to the cumulative change of the phenolic compounds in the middle growth period, the degree of variation of the phenolic compounds in the middle growth period and the average level of the phenolic compounds in the middle growth period, the orchard phenolic phenological index is determined by the following formula: in, is the value of the phenol compound index at time k, is the value of the phenol compound index at time k+1, ~ is the middle growth period of the tree, PA is the cumulative change of phenolic compounds in the middle growth period, PV is the variation degree of phenolic compounds in the middle growth period, PM is the average level of phenolic compounds in the middle growth period, and OPPI is the orchard phenolic phenological index.

6. The method for generating orchard samples according to claim 5, characterized in that: The method of using the tree mapping index and the orchard phenolic phenology index to determine orchard location distribution information in the annual vegetation pixel data includes: Determining tree location distribution in the annual vegetation pixel data using the tree mapping index; The orchard phenolic phenological index is used to determine orchard location distribution information in the tree location distribution.

7. A device for generating orchard samples, characterized in that: include: An acquisition unit, used to acquire time series remote sensing data and annual vegetation pixel data; a computing unit for determining a tree mapping index and an orchard phenolic phenological index based on the time series remote sensing data; a determination unit, configured to determine orchard location distribution information in the annual vegetation pixel data using the tree mapping index and the orchard phenolic phenology index; A processing unit is used to determine an orchard sample based on the orchard location distribution information.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for generating an orchard sample according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for generating an orchard sample according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for generating an orchard sample according to any one of claims 1 to 6 is implemented.

Images