Method, device and measurement system for obtaining crop distribution information

Abstract

The present application discloses a method, device and measurement system for obtaining crop distribution information. The method includes: obtaining image information of a target area, wherein the image information is used to display crop information in the target area; inputting the image information into a neural network model for analysis to obtain indication information of each pixel position in the image information, and pixel information corresponding to pixel positions where the crop exists, wherein the indication information is used to indicate whether there is a crop at each pixel position; performing cluster analysis on the pixel information to obtain clustering results; and determining crop distribution information in the target area based on the clustering results. The present application solves the technical problem that the collected samples have many random factors and are time-consuming and labor-intensive due to artificial sampling statistics.

Description

Technical Field

[0001] The present application relates to the field of plant protection, and in particular, to a method, device and measurement system for acquiring crop distribution information. Background Art

[0002] Crop analysis is a very important part of agricultural production. Early basic crop analysis can help farmers evaluate the status of emerging crops and replant or cull crops early. Currently, the analysis of basic crops mostly requires people to go to the fields for sampling and statistics. This method has more random factors and is time-consuming and labor-intensive.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide a method, device and measurement system for obtaining crop distribution information, so as to at least solve the technical problem that the collected samples have many random factors and are time-consuming and labor-intensive due to manual sampling statistics.

[0005] According to one aspect of an embodiment of the present application, a method for obtaining crop distribution information is provided, comprising: obtaining image information of a target area, wherein the image information is used to display crop information in the target area; inputting the image information into a neural network model for analysis to obtain indication information of each pixel position in the image information, and pixel information corresponding to pixel positions where crops exist, wherein the indication information is used to indicate whether there are crops at each pixel position; performing cluster analysis on the pixel information to obtain clustering results; and determining the crop distribution information in the target area based on the clustering results.

[0006] Optionally, the image information is input into a neural network model for analysis to obtain indication information of each pixel position in the image information, including: storing pixel information indicating the presence of crops in the indication information into a preset set; performing cluster analysis on the pixel information to obtain clustering results, including: selecting part of the pixel information from the preset set for cluster analysis to obtain multiple clusters; and classifying the remaining pixel information in the preset set based on the multiple clusters to obtain clustering results.

[0007] Optionally, the remaining pixel information in the preset set is classified based on multiple clusters, including: determining a classification label corresponding to each cluster; determining the classification label to which the remaining pixel information belongs, and obtaining a clustering result.

[0008] Optionally, multiple clusters classify the remaining pixel information in a preset set to obtain clustering results, including: calculating the similarity between each pixel information in the remaining pixel information and each pixel information in a specified cluster to obtain multiple similarities, and the specified cluster is any one of the multiple clusters; determining the average value of the multiple similarities; determining the cluster to which each pixel information in the remaining pixel information belongs based on the average value to obtain a clustering result.

[0009] Optionally, the average value is used to determine the cluster to which each pixel information in the remaining pixel information belongs, and a clustering result is obtained, including: comparing the average value with the similarity value range corresponding to the specified cluster; determining the similarity value range to which the average value belongs, and taking the cluster corresponding to the determined value range as the cluster to which each pixel information belongs, wherein the similarity value ranges corresponding to each cluster are continuous.

[0010] Optionally, the similarity value range is determined based on the similarity between each pixel information in the remaining pixel information and the pixel information in each cluster.

[0011] Optionally, after determining the crop distribution information in the target area based on the clustering results, the method also includes: determining a baseline leaf number of a single crop in the target area; counting the total number of leaves of all crops in the target area based on the indication information; determining the number of crops in the target area based on the total number of leaves and the baseline number of leaves; and determining a target operation strategy for the target area based on at least one of the crop number and the crop distribution information.

[0012] Optionally, the pixel information includes: relative distance information between pixels and pixel position information.

[0013] Optionally, obtaining image information of the target area includes: receiving image information of the target area photographed by a drone.

[0014] According to one aspect of an embodiment of the present application, another method for obtaining crop distribution information is provided, including: obtaining image information of a target area, wherein the image information is used to display crop information in the target area; inputting the image information into a neural network model for analysis to obtain effective pixel information in the image information, wherein the effective pixel information is used to indicate each pixel in the image information belonging to the target crop; performing cluster analysis on the effective pixel information to obtain clustering results; and determining the crop distribution information in the target area based on the clustering results.

[0015] According to another aspect of an embodiment of the present application, a device for acquiring crop distribution information is also provided, including: an acquisition module, used to acquire image information of a target area, wherein the image information is used to display crop information in the target area; an analysis module, used to input the image information into a neural network model for analysis, to obtain indication information of each pixel position in the image information, and pixel information corresponding to pixel positions where crops exist, the indication information is used to indicate whether there are crops at each pixel position; a clustering module, used to perform cluster analysis on the pixel information to obtain clustering results; and a first determination module, used to determine the crop distribution information in the target area based on the clustering results.

[0016] According to another aspect of the present application, a system for measuring crop distribution information is also provided, including: a surveying drone, used to obtain image information of a target area, wherein the image information is used to display crop information in the target area; a network-side device, used to input the image information into a neural network model for analysis, to obtain indication information of each pixel position in the image information, and pixel information corresponding to pixel positions where crops exist, the indication information is used to indicate whether there are crops at each pixel position; clustering analysis is performed on the pixel information to obtain clustering results; and the crop distribution information in the target area is determined based on the clustering results.

[0017] According to one aspect of an embodiment of the present application, a non-volatile storage medium is also provided, the storage medium including a stored program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute any method for obtaining crop distribution information.

[0018] According to one aspect of an embodiment of the present application, a processor is further provided, the processor being used to run a program stored in a storage medium, wherein the program executes any method for acquiring crop distribution information when the program is running.

[0019] In the embodiment of the present application, the image information of the target area is obtained by using a drone at ultra-low altitude or other equipment such as a ground robot, and the image information is input into a neural network model for analysis to obtain the indication information of each pixel position in the image information and the pixel information corresponding to the pixel position where the crop exists. The indication information is used to indicate whether there is a crop at each pixel position, and the pixel information is clustered to obtain the clustering result; the crop distribution information in the target area is determined based on the clustering result. Since the image information of the target area obtained can be annotated based on the deep learning algorithm, the technical effect of obtaining the crop distribution information in the target area using a drone or other shooting equipment can be achieved, thereby solving the technical problem that the collected samples have many random factors and are time-consuming and labor-intensive due to artificial sampling statistics. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0021] Figure 1a is a flow chart of a method for acquiring crop distribution information according to an embodiment of the present application;

[0022] Figure 1b is a schematic diagram of an optional marking method according to an embodiment of the present application;

[0023] Figure 1c is a schematic diagram of an optional clustering method according to an embodiment of the present application;

[0024] Figure 1d is a schematic diagram of an optional segmentation network structure that can be selected according to an embodiment of the present application;

[0025] Figure 2 is a flow chart of another method for acquiring crop distribution information according to an embodiment of the present application;

[0026] Figure 3 is a schematic diagram of the structure of a device for acquiring crop distribution information according to an embodiment of the present application;

[0027] Figure 4 is a schematic diagram of a system for measuring crop distribution information according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] In order to better understand the above embodiments, the technical terms involved in the embodiments of the present application are briefly described as follows:

[0031] Basic seedling: A crop individual that germinates from a seed and contains at least one main branch.

[0032] According to an embodiment of the present application, a method embodiment for obtaining crop distribution information is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0033] Figure 1a The method for obtaining crop distribution information according to an embodiment of the present application is as follows: Figure 1a As shown, the method comprises the following steps:

[0034] Step S102, acquiring image information of the target area, wherein the image information is used to display crop information in the target area;

[0035] Step S104, inputting the image information into the neural network model for analysis, obtaining indication information of each pixel position in the image information, and pixel information corresponding to the pixel position where the crop exists, wherein the indication information is used to indicate whether there is a crop at each pixel position;

[0036] Step S106, performing cluster analysis on the pixel information to obtain a clustering result;

[0037] Step S108, determining crop distribution information in the target area based on the clustering result.

[0038] Specifically, in the above-mentioned method for obtaining crop distribution information, image information of the target area is obtained by using an ultra-low-altitude drone or other equipment such as a ground robot, and then the image information is input into a neural network model for analysis to obtain indication information of each pixel position in the image information and pixel information corresponding to the pixel position where crops exist. The indication information is used to indicate whether there are crops at each pixel position, and cluster analysis is performed on the pixel information to obtain clustering results, thereby realizing the determination of crop distribution information in the target area based on the clustering results. This method solves the technical problem that the collected samples have many random factors and are time-consuming and labor-intensive due to artificial sampling statistics.

[0039] For example, after the mapping drone takes a high-definition image, it can segment the leaves of each crop based on the high-definition image, and then calculate the number of crops based on the current leaf age of the crop, such as Figure 1b As shown, this type of wheat seedling is identified as a basic seedling. Basic wheat seedlings can tiller, that is, one plant with one main branch can be divided into multiple branches. The basic wheat seedlings will branch out new tillers when they grow the fourth leaf. At a specific growth stage, the number of basic seedlings can be monitored to guide the next management strategy. For example, Figure 1a The steps shown determine the number of basic seedlings and crop distribution information. Based on the crop distribution information, the situation of the basic seedlings can be determined, so as to carry out reasonable regulation and management, and ultimately achieve the purpose of increasing production and income. For example, for plots with fewer basic seedlings, their tillering can be promoted by changing the amount of water, the amount of fertilizer, the length of light, etc., so as to achieve the purpose of increasing the number of ears and increasing income.

[0040] It should be noted that the method of acquiring image information is not limited to the above two methods, and it can be obtained through other shooting devices, or by combining multiple shooting devices to acquire image information.

[0041] The crop information includes but is not limited to at least one of the following: crop type, cultivated area, seedling size, and leaf shape.

[0042] When cluster analysis is performed, since it is a pixel-level cluster analysis, the number of pixels involved in the cluster analysis is relatively large, which will reduce the efficiency of the cluster analysis. To solve this problem, in some embodiments of the present application, the pixel information indicating the presence of crops in the above-mentioned indication information can be stored in a preset set; Figure 1cAs shown, when cluster analysis is performed, part of the pixel information is selected from the preset set for cluster analysis to obtain multiple clusters; the remaining pixel information in the preset set is classified based on the multiple clusters to obtain a clustering result. Since only part of the pixel information is clustered, the number of pixels involved in the cluster analysis is reduced, thereby improving the clustering efficiency.

[0043] Specifically, Figure 1d As shown, the image information Image is passed through the encoder and decoder convolutional neural network models, and segmentation and pixel embedding are output respectively, that is, the indication information of each pixel position in the image information is obtained. Segmentation is used as a mask to determine whether the current pixel position needs to be retained, and pixel embedding is to convert each pixel of the image into a higher-dimensional vector data and store it in a preset set; clustering is to group some data objects in the preset set into multiple clusters, and then classify the remaining pixel information in the preset set based on the above multiple clusters to obtain clustering results. Among them, the neural network model is obtained by training the machine learning model through multiple sets of training data. For example, each set of training data includes: sample images and labels for marking basic seedlings in the sample images.

[0044] It should be noted that a high-dimensional vector refers to a pixel represented by adding the relative distance between pixels and the pixel position information on the basis of the pixels represented by the three components of R, G, and B.

[0045] Since the number of remaining pixels in the preset set is relatively large, in order to further reduce the computational complexity of clustering analysis, in an optional embodiment of the present application, the remaining pixels in the preset set can be classified in the following manner: determine the classification label corresponding to each cluster; determine the classification label to which the remaining pixel information belongs based on the classification label corresponding to each cluster, and obtain the clustering result, which further greatly reduces the computational complexity of clustering analysis.

[0046] In some embodiments of the present application, the classification label to which the remaining pixel information belongs is determined to obtain a clustering result, including: calculating the similarity between each pixel information in the remaining pixel information and each pixel information in a specified cluster to obtain multiple similarities, and the specified cluster is any one of the multiple clusters; determining the average value of the multiple similarities; and determining the cluster to which each pixel information in the remaining pixel information belongs based on the average value to obtain a clustering result.

[0047] When determining the cluster to which each pixel information in the remaining pixel information belongs based on the average value, it can be achieved in the following manner, but is not limited to: comparing the average value with the similarity value range corresponding to the specified cluster; determining the similarity value range to which the average value belongs, and taking the cluster corresponding to the determined value range as the cluster to which each pixel information belongs, wherein the similarity value ranges corresponding to each cluster are continuous.

[0048] It should be noted that the similarity value ranges corresponding to the clusters are continuous, which means that the maximum value of the value range of the previous cluster is equal to the minimum value of the value range of the next cluster in the value ranges of two adjacent clusters.

[0049] In some embodiments of the present application, in order to ensure that all remaining pixel information can be classified into corresponding clusters, the similarity value range is determined based on the similarity between each pixel information in the remaining pixel information and the pixel information in each cluster.

[0050] In addition, if the above scheme is adopted, there are still unclassified pixels in the remaining pixel information. At this time, a conventional classification algorithm can be used for classification. For example, a pixel point is selected from each cluster as the central pixel point, and the Euclidean distance between the central pixel point and the unclassified pixel is calculated. The cluster with the smallest Euclidean distance between the central pixel point and the unclassified pixel in each cluster is taken as the class or cluster to which the unclassified pixel belongs.

[0051] In some embodiments of the present application, after determining the crop distribution information in the target area based on the clustering results, the method also includes: determining the baseline leaf number of a single crop in the target area; counting the total number of leaves of all crops in the target area based on the indication information; determining the number of crops in the target area based on the total number of leaves and the baseline number of leaves; and determining the target operation strategy for the target area based on at least one of the crop number and the crop distribution information.

[0052] Specifically, taking wheat as an example, basic seedlings such as wheat can tiller, that is, one plant with one main branch can be divided into one plant with multiple branches and leaves. The basic seedlings of wheat will branch out new tillers when the fourth leaf grows. After the surveying and mapping drone has taken the high-definition image, the leaves of a single wheat basic seedling can be segmented according to the high-definition image, and the number of leaves of a single crop can be calculated. Then, combined with the indication information, the total amount of wheat leaves in the target area can be obtained. At different growth stages, the number of basic seedlings can be monitored to guide the next management strategy. For those plots with fewer basic seedlings, tillering can be promoted by changing the amount of water, the amount of fertilizer, and the length of light, so as to increase the number of ears and increase income.

[0053] In a preferred embodiment of the present application, the pixel information includes: relative distance information between pixels and pixel position information.

[0054] In some embodiments of the present application, obtaining image information of a target area includes: receiving image information of the target area photographed by a drone, wherein the image information carrier may be a picture, a video image, etc.; the image information includes displayed crop information: crop type, cultivated area, size of seedlings, and leaf shape, etc.

[0055] In some embodiments of the present application, a method for obtaining crop distribution information is also provided, such as Figure 2 As shown, the navigation method includes the following steps:

[0056] Step S202, acquiring image information of the target area, wherein the image information is used to display crop information in the target area;

[0057] Step S204, inputting the image information into a neural network model for analysis to obtain effective pixel information in the image information, wherein the effective pixel information is used to indicate each pixel in the image information that belongs to the target crop;

[0058] Step S206, performing cluster analysis on the effective pixel information to obtain a clustering result;

[0059] Step S208: determining crop distribution information in the target area based on the clustering result.

[0060] Specifically, in the above-mentioned method for obtaining crop distribution information, image information of the target area is obtained by using an ultra-low altitude drone or other equipment such as a ground robot, wherein the image information is used to display the crop information in the target area, such as the type of crop, cultivated area, size of seedlings, and leaf shape, etc., and then the image information is input into a neural network model for analysis to obtain effective pixel information in the image information, wherein the effective pixel information is used to indicate each pixel in the image information belonging to the target crop; cluster analysis is performed on the effective pixel information to obtain clustering results, thereby realizing the determination of crop distribution information in the target area based on the clustering results. This method solves the technical problem that the collected samples have many random factors and are time-consuming and labor-intensive due to artificial sampling statistics.

[0061] In some embodiments of the present application, a device for obtaining crop distribution information is also provided, such as Figure 3 As shown, the device for acquiring crop division information includes:

[0062] An acquisition module 30, used for acquiring image information of a target area, wherein the image information is used for displaying crop information in the target area;

[0063] The analysis module 32 is used to input the image information into the neural network model for analysis, and obtain the indication information of each pixel position in the image information, and the pixel information corresponding to the pixel position where the crop exists, and the indication information is used to indicate whether there is a crop at each pixel position;

[0064] A clustering module 34 is used to perform clustering analysis on pixel information to obtain clustering results;

[0065] The first determination module 36 is used to determine the crop distribution information in the target area based on the clustering result.

[0066] The above-mentioned device for acquiring crop distribution information, the acquisition module acquires image information of the target area by using an ultra-low altitude drone or other equipment such as a ground robot, wherein the image information is used to display the crop information in the target area; the analysis module is used to input the image information into a neural network model for analysis, and obtain indication information of each pixel position in the image information, and pixel information corresponding to the pixel position where crops exist, and the indication information is used to indicate whether there are crops at each pixel position; the clustering module is used to perform cluster analysis on the pixel information to obtain clustering results; the first determination module is used to determine the crop distribution information in the target area based on the clustering results. This device solves the technical problem that the collected samples have many random factors and are time-consuming and labor-intensive due to artificial sampling statistics.

[0067] For example, after the mapping drone takes high-definition images, it can segment the leaves of each crop based on the high-definition images. Then, according to the current leaf age of the crop, basic seedlings such as wheat can be tillered, that is, one plant with one main branch can be divided into multiple branches. The basic seedlings of wheat will branch out new tillers when they grow the fourth leaf. At a specific growth stage, the number of basic seedlings can be monitored to guide the next management strategy. For example, Figure 1a The steps shown determine the number of basic seedlings and crop distribution information. Based on the crop distribution information, the situation of the basic seedlings can be determined, so as to carry out reasonable regulation and management, and ultimately achieve the purpose of increasing production and income. For example, for plots with fewer basic seedlings, their tillering can be promoted by changing the amount of water, the amount of fertilizer, the length of light, etc., so as to achieve the purpose of increasing the number of ears and increasing income.

[0068] It should be noted that the method of obtaining image information is not limited to the above two methods, and it can be obtained by other shooting devices, or by combining multiple shooting devices to obtain image information;

[0069] The crop information includes but is not limited to at least one of the following: crop type, cultivated area, seedling size, and leaf shape.

[0070] When cluster analysis is performed, since it is a pixel-level cluster analysis, the number of pixels involved in the cluster analysis is relatively large, which will reduce the efficiency of the cluster analysis. To solve this problem, in some embodiments of the present application, the analysis module includes a storage submodule, which is used to input the image information into the neural network model for analysis to obtain indication information of each pixel position in the image information, including: storing the pixel information indicating the presence of crops in the indication information into a preset set; the clustering module includes a clustering submodule, which is used to perform cluster analysis on the pixel information to obtain clustering results, including: selecting part of the pixel information from the preset set for cluster analysis to obtain multiple clusters; and classifying the remaining pixel information in the preset set based on the multiple clusters to obtain clustering results. Since only part of the pixel information is clustered, the number of pixels involved in the cluster analysis is reduced, and the clustering efficiency is improved.

[0071] Since the number of remaining pixels in the preset set is also relatively large, in order to further reduce the computational complexity of clustering analysis, in an optional embodiment of the present application, the clustering submodule includes a first determination submodule and a second determination submodule. The first determination submodule is used to determine the classification label corresponding to each cluster; the second determination submodule is used to determine the classification label to which the remaining pixel information belongs according to the classification label corresponding to each cluster, and obtain the clustering result, which further greatly reduces the computational complexity of clustering analysis.

[0072] In some embodiments of the present application, the clustering submodule also includes a first calculation submodule and a third determination submodule, and a fourth determination submodule. The first calculation submodule is used to calculate the similarity between each pixel information in the remaining pixel information and each pixel information in the specified cluster to obtain multiple similarities, and the specified cluster is any one of the multiple clusters; the third determination submodule is used to determine the average value of the multiple similarities; the fourth determination submodule is used to determine the cluster to which each pixel information in the remaining pixel information belongs based on the average value to obtain the clustering result.

[0073] In a preferred embodiment of the present application, the fourth determination submodule includes a fifth determination submodule, and the fifth determination submodule is used to compare the average value with the similarity value range corresponding to the specified cluster; determine the similarity value range to which the average value belongs, and use the cluster corresponding to the determined value range as the cluster to which each pixel information belongs, wherein the similarity value ranges corresponding to each cluster are continuous.

[0074] It should be noted that the similarity value ranges corresponding to the clusters are continuous, which means that the maximum value of the value range of the previous cluster is equal to the minimum value of the value range of the next cluster in the value ranges of two adjacent clusters.

[0075] In some embodiments of the present application, in order to ensure that all remaining pixel information can be classified into corresponding clusters, the similarity value range of the fifth determination submodule is determined based on the similarity between the remaining pixel information and the pixel information in each cluster.

[0076] The above-mentioned device also includes a second determination module, a statistical module, a third determination module and a fourth determination module. The second determination module is used to determine the baseline number of leaves of a single crop in the target area after determining the crop distribution information in the target area through clustering results; the statistical module is used to count the total number of leaves of all crops in the target area based on the indication information; the third determination module is used to determine the number of crops in the target area based on the total number of leaves and the baseline number of leaves; the fourth determination module is used to determine the target operation strategy of the target area based on at least one of the crop number and the crop distribution information.

[0077] In a preferred embodiment of the present application, the pixel information includes: relative distance information between pixels and pixel position information.

[0078] In some embodiments of the present application, the image information of the target area obtained by the acquisition module includes image information of the target area photographed by a drone, wherein the image information carrier may be a picture, a video, etc.; the image information includes the displayed crop information: crop type, cultivated area, size of seedlings, and shape of leaves, etc.

[0079] According to some embodiments of the present application, a system for measuring crop distribution information is also provided, such as Figure 4 As shown, the measurement system includes:

[0080] A surveying and mapping drone 40 is used to obtain image information of a target area 10, wherein the image information is used to display crop information in the target area 10;

[0081] The network side device 42 is used to input the image information into the neural network model for analysis, obtain the indication information of each pixel position in the image information, and the pixel information corresponding to the pixel position where the crop exists, the indication information is used to indicate whether there is a crop at each pixel position; perform cluster analysis on the pixel information to obtain a clustering result; determine the crop distribution information in the target area 10 based on the clustering result.

[0082] Specifically, the above-mentioned crop distribution information measurement system and the surveying and mapping drone are used to obtain image information of the target area, wherein the image information is used to display the crop information in the target area, and the crop information may be: crop type, cultivated area, size of seedlings, etc. The shooting equipment on the surveying and mapping drone sends the crop information to the network side device in the form of images, and the above-mentioned network side device is used to input the image information into the neural network model for analysis, and obtain the indication information of each pixel position in the image information, and the pixel information corresponding to the pixel position where the crop exists, and the indication information is used to indicate whether there is a crop at each pixel position; cluster analysis is performed on the pixel information to obtain clustering results; and the crop distribution information in the target area is determined based on the clustering results. This measurement system can realize unmanned operation of the drone throughout the process, and the collected samples are highly representative, thereby solving the problem that the collected samples in the prior art have many random factors and are time-consuming and labor-intensive due to manual sampling statistics.

[0083] In some embodiments of the present application, a non-volatile storage medium is further provided, the storage medium including a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute any method for obtaining crop distribution information.

[0084] In some embodiments of the present application, a processor is further provided, and the processor is used to run a program stored in a storage medium, wherein any method for obtaining crop distribution information is executed when the program is run.

[0085] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0086] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0087] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0088] 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, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0089] In addition, each functional unit in each embodiment of the present application 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.

[0090] 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. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or 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 to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0091] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for obtaining crop distribution information, characterized in that: include: Acquiring image information of a target area, wherein the image information is used to display crop information in the target area; Inputting the image information into a neural network model for analysis to obtain indication information of each pixel position in the image information and pixel information corresponding to the pixel position where the crop exists, wherein the indication information is used to indicate whether there is a crop at each pixel position; The pixel information indicating the presence of crops in the indication information is stored in a preset set, and the pixel information is clustered and analyzed to obtain a clustering result, including: selecting part of the pixel information from the preset set for cluster analysis to obtain a plurality of clusters; and classifying the remaining pixel information in the preset set based on the plurality of clusters to obtain the clustering result; Wherein, classifying the remaining pixel information in the preset set based on the multiple clusters includes: determining the classification label corresponding to each cluster; determining the classification label to which the remaining pixel information belongs, including: calculating the similarity between each pixel information in the remaining pixel information and each pixel information in a specified cluster to obtain multiple similarities, wherein the specified cluster is any one of the multiple clusters; determining the average value of the multiple similarities; determining the cluster to which each pixel information in the remaining pixel information belongs based on the average value, and determining the classification label to which each pixel information in the remaining pixel information belongs based on the determined cluster; The crop distribution information in the target area is determined based on the clustering result.

2. The method according to claim 1, characterized in that Determining the cluster to which each pixel information in the remaining pixel information belongs based on the average value to obtain the clustering result includes: Compare the average value with the similarity value range corresponding to the specified cluster; determine the similarity value range to which the average value belongs, and use the cluster corresponding to the determined value range as the cluster to which each pixel information belongs, wherein the similarity value ranges corresponding to each cluster are continuous.

3. The method according to claim 2, characterized in that The similarity value range is determined based on the similarity between each pixel information in the remaining pixel information and the pixel information in each cluster.

4. The method according to claim 1, characterized in that: After determining the crop distribution information in the target area based on the clustering result, the method further includes: determining a baseline number of leaves for a single crop in the target area; Counting the total amount of leaves of all the crops in the target area based on the indication information; determining the amount of crops in the target area based on the total amount of leaves and the baseline amount of leaves; A target operation strategy for the target area is determined based on at least one of the crop quantity and the crop distribution information.

5. The method according to claim 1, characterized in that: The pixel information includes: relative distance information between pixels and pixel position information.

6. The method according to any one of claims 1 to 5, characterized in that Obtain image information of the target area, including: Receive image information of the target area photographed by the drone.

7. A crop distribution information measurement system, characterized in that: include: A surveying and mapping drone, used to obtain image information of a target area, wherein the image information is used to display crop information in the target area; The network side device is used to input the image information into a neural network model for analysis, obtain indication information of each pixel position in the image information, and pixel information corresponding to the pixel position where the crop exists, wherein the indication information is used to indicate whether there is a crop at each pixel position; store the pixel information indicating the existence of the crop in the indication information into a preset set, perform cluster analysis on the pixel information, and obtain a clustering result, including: selecting part of the pixel information from the preset set for cluster analysis to obtain a plurality of clusters; classifying the remaining pixel information in the preset set based on the plurality of clusters to obtain the clustering result; wherein, based on the The multiple clusters classify the remaining pixel information in the preset set, including: determining the classification label corresponding to each cluster; determining the classification label to which the remaining pixel information belongs, including: calculating the similarity between each pixel information in the remaining pixel information and each pixel information in a specified cluster to obtain multiple similarities, and the specified cluster is any one of the multiple clusters; determining the average value of the multiple similarities; determining the cluster to which each pixel information in the remaining pixel information belongs based on the average value, and based on the determined cluster, determining the classification label to which each pixel information in the remaining pixel information belongs; and determining the crop distribution information in the target area based on the clustering result.

8. A device for acquiring crop distribution information, characterized in that: include: An acquisition module, used for acquiring image information of a target area, wherein the image information is used for displaying crop information in the target area; an analysis module, used for inputting the image information into a neural network model for analysis, and obtaining indication information of each pixel position in the image information, and pixel information corresponding to the pixel position where the crop exists, wherein the indication information is used for indicating whether there is a crop at each pixel position; A clustering module, for storing pixel information indicating the presence of crops in the indication information into a preset set, performing cluster analysis on the pixel information, and obtaining a clustering result, including: selecting part of the pixel information from the preset set for cluster analysis to obtain a plurality of clusters; classifying the remaining pixel information in the preset set based on the plurality of clusters to obtain the clustering result; wherein classifying the remaining pixel information in the preset set based on the plurality of clusters includes: determining a classification label corresponding to each cluster; determining the classification label to which the remaining pixel information belongs, including: calculating the similarity between each pixel information in the remaining pixel information and each pixel information in a designated cluster to obtain a plurality of similarities, the designated cluster being any one of the plurality of clusters; determining an average value of the plurality of similarities; determining the cluster to which each pixel information in the remaining pixel information belongs based on the average value, and determining the classification label to which each pixel information in the remaining pixel information belongs based on the determined cluster; The first determination module is used to determine the crop distribution information in the target area based on the clustering result.

9. A non-volatile storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is executed, the device where the storage medium is located is controlled to execute the method for obtaining crop distribution information according to any one of claims 1 to 6.

10. A processor, characterized in that: The processor is used to run a program stored in a storage medium, wherein the program, when running, executes the method for obtaining crop distribution information according to any one of claims 1 to 6.

Images