CN113011221A - Crop distribution information acquisition method and device and measurement system - Google Patents
Crop distribution information acquisition method and device and measurement system Download PDFInfo
- Publication number
- CN113011221A CN113011221A CN201911319115.6A CN201911319115A CN113011221A CN 113011221 A CN113011221 A CN 113011221A CN 201911319115 A CN201911319115 A CN 201911319115A CN 113011221 A CN113011221 A CN 113011221A
- Authority
- CN
- China
- Prior art keywords
- information
- pixel
- crop
- target area
- image information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000009826 distribution Methods 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000005259 measurement Methods 0.000 title abstract description 8
- 238000004458 analytical method Methods 0.000 claims abstract description 55
- 238000003062 neural network model Methods 0.000 claims abstract description 22
- 238000003860 storage Methods 0.000 claims description 18
- 238000007621 cluster analysis Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 7
- 238000005070 sampling Methods 0.000 abstract description 7
- 241000209140 Triticum Species 0.000 description 9
- 235000021307 Triticum Nutrition 0.000 description 9
- 238000010586 diagram Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 210000005069 ears Anatomy 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000003337 fertilizer Substances 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013486 operation strategy Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Multimedia (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Image Analysis (AREA)
Abstract
The application discloses a method and a device for acquiring crop distribution information and a measurement system. Wherein, the method comprises the following steps: acquiring image information of a target area, wherein the image information is used for displaying 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 for indicating whether the crop exists at each pixel position; performing clustering analysis on the pixel information to obtain a clustering result; determining crop distribution information in the target area based on the clustering result. The method and the device solve the technical problems that the collected samples have more random factors and are time-consuming and labor-consuming due to manual sampling statistics.
Description
Technical Field
The application relates to the field of plant protection, in particular to a method and a device for acquiring crop distribution information and a measurement system.
Background
Crop analysis is a very important link in the agricultural production link, early basic crop analysis can help farmers evaluate the seedling crop condition, and can perform reseeding or removing on crops as soon as possible, and at present, most of basic crop analysis methods need people to go to the field for sampling and counting have more random factors, and are time-consuming and labor-consuming.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the application provides a method, a device and a measuring system for acquiring crop distribution information, and aims to at least solve the technical problems that more random factors exist in a collected sample, and time and labor are consumed due to artificial sampling statistics.
According to an aspect of an embodiment of the present application, there is provided a method for acquiring crop distribution information, including: acquiring image information of a target area, wherein the image information is used for displaying 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 crops exist, wherein the indication information is used for indicating whether crops exist at each pixel position; carrying out clustering analysis on the pixel information to obtain a clustering result; and determining crop distribution information in the target area based on the clustering result.
Optionally, inputting the image information into the neural network model for analysis, and obtaining indication information of each pixel position in the image information, including: storing pixel information indicating that crops exist in the indicating information into a preset set; performing clustering analysis on the pixel information to obtain a clustering result, wherein the clustering result comprises the following steps: selecting partial pixel information from a preset set to perform clustering analysis to obtain a plurality of clusters; and classifying the residual pixel information in the preset set based on the plurality of clusters to obtain a clustering result.
Optionally, classifying the remaining pixel information in the preset set based on a plurality of clusters includes: determining a classification label corresponding to each cluster; and determining the classification label to which the residual pixel information belongs to obtain a clustering result.
Optionally, the classifying the remaining pixel information in the preset set by the plurality of clusters to obtain a clustering result includes: calculating the similarity between each piece of pixel information in the residual pixel information and each piece of pixel information in the designated cluster to obtain a plurality of similarities, wherein the designated cluster is any one of the plurality of clusters; determining an average value of the plurality of similarities; and determining the cluster to which each pixel information in the residual pixel information belongs based on the average value to obtain a clustering result.
Optionally, the determining, by the average value, a cluster to which each pixel information in the remaining pixel information belongs to obtain a clustering result includes: comparing the similarity value range corresponding to the average value and the designated cluster; and determining a similarity value range to which the average value belongs, and taking a cluster corresponding to the determined value range as a cluster to which each piece of pixel information belongs, wherein the similarity value ranges corresponding to the clusters are continuous.
Optionally, the similarity value range is determined based on the similarity between each piece of pixel information in the remaining pixel information and the pixel information in each cluster.
Optionally, after determining the crop distribution information in the target area based on the clustering result, the method further includes: determining a reference leaf number of a single crop in a target area; counting the total leaf amount of all crops in the target area based on the indication information; determining a number of crops in the target area based on the total number of leaves and a reference number of leaves; a target work strategy for the target area is determined based on at least one of the crop quantity and the crop distribution information.
Optionally, the pixel information includes: information on relative distances between pixels, and information on pixel positions.
Optionally, acquiring image information of the target area includes: and receiving image information of the target area shot by the unmanned aerial vehicle.
According to an aspect of the embodiments of the present application, there is provided another method for acquiring crop distribution information, including: acquiring image information of a target area, wherein the image information is used for displaying 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 for indicating each pixel belonging to a target crop in the image information; carrying out clustering analysis on the effective pixel information to obtain a clustering result; and determining crop distribution information in the target area based on the clustering result.
According to another aspect of the embodiments of the present application, there is also provided an apparatus for acquiring crop distribution information, including: the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring image information of a target area, and the image information is used for displaying crop information in the target area; the analysis module is used for inputting the image information into the 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 for indicating whether the crop exists at each pixel position; the clustering module is used for carrying out clustering analysis on the pixel information to obtain a clustering result; and the first determining module is used for determining crop distribution information in the target area based on the clustering result.
According to another aspect of the present application, there is also provided a crop distribution information measuring system, including: the surveying and mapping unmanned machine is used for acquiring image information of a target area, wherein the image information is used for displaying crop information in the target area; the network side equipment is used for inputting the image information into the neural network model for analysis to obtain indicating information of each pixel position in the image information and pixel information corresponding to the pixel position where the crop exists, and the indicating information is used for indicating whether the crop exists at each pixel position; carrying out clustering analysis on the pixel information to obtain a clustering result; and determining crop distribution information in the target area based on the clustering result.
According to an aspect of the embodiments of the present application, there is also provided a non-volatile storage medium, where the storage medium includes a stored program, and when the program runs, a device in which the non-volatile storage medium is located is controlled to execute any method for acquiring crop distribution information.
According to an aspect of the embodiments of the present application, there is also provided a processor configured to execute a program stored in a storage medium, where the program executes any method for acquiring crop distribution information.
In the embodiment of the application, a mode that an unmanned aerial vehicle is in an ultra-low altitude state or image information of a target area is acquired through other equipment such as a ground robot is adopted, the image information is input into a neural network model to be analyzed, so that indication information of each pixel position in the image information and pixel information corresponding to the pixel position where a crop exists are obtained, the indication information is used for indicating whether the crop exists at each pixel position or not, and clustering analysis is performed on the pixel information to obtain a clustering result; and determining crop distribution information in the target area based on the clustering result. Because the acquired image information of the target area can be labeled based on a deep learning algorithm, the technical effect of acquiring crop distribution information in the target area by using shooting equipment such as an unmanned aerial vehicle can be realized, and the technical problems that the collected samples have more random factors and are time-consuming and labor-consuming due to artificial sampling statistics are solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1a is a schematic flow chart of a method for acquiring crop distribution information according to an embodiment of the present application;
FIG. 1b is a schematic diagram of an alternative labeling method according to an embodiment of the present application;
FIG. 1c is a schematic diagram of an alternative clustering method according to an embodiment of the present application;
FIG. 1d is a schematic diagram of an alternative split network architecture according to an embodiment of the present application;
fig. 2 is a schematic flow chart of another crop distribution information obtaining method according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an apparatus for acquiring crop distribution information according to an embodiment of the present application;
fig. 4 is a schematic diagram of a crop distribution information measuring system according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For better understanding of the above embodiments, technical terms referred to in the embodiments of the present application are briefly described as follows:
basic seedling: the individual crop is germinated from one seed and contains at least one main branch.
In accordance with an embodiment of the present application, there is provided a method for obtaining crop distribution information, where the steps illustrated in the flowchart of the drawings may be executed in a computer system, such as a set of computer executable instructions, and where a logical order is illustrated in the flowchart, in some cases, the steps illustrated or described may be executed in an order different than that illustrated or described herein.
Fig. 1a is a method for acquiring crop distribution information according to an embodiment of the present application, and as shown in fig. 1a, the method includes the following steps:
step S102, acquiring image information of a target area, wherein the image information is used for displaying crop information in the target area;
step S104, 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 for indicating whether the crop exists at each pixel position;
step S106, carrying out clustering analysis on the pixel information to obtain a clustering result;
and S108, determining crop distribution information in the target area based on the clustering result.
Specifically, in the method for acquiring crop distribution information, a mode that an unmanned aerial vehicle is in an ultra-low altitude state or other equipment such as a ground robot is used for acquiring image information of a target area, then the image information is input into a neural network model for analysis, so that indication information of each pixel position in the image information and pixel information corresponding to the pixel position where a crop exists are obtained, the indication information is used for indicating whether the crop exists in each pixel position, clustering analysis is performed on the pixel information, a clustering result is obtained, and further determination of the crop distribution information in the target area based on the clustering result is achieved.
For example, after the surveying and mapping unmanned aerial vehicle shoots the high-definition image, the leaves of each crop can be divided according to the high-definition image, then the number of the crops is calculated according to the leaf age of the current crop, as shown in fig. 1b, the wheat seedling of this type is considered to be a basic seedling, the wheat seedling and other basic seedlings can be tillered, that is, the basic seedling can be divided into a plurality of branches from one main branch, the wheat seedling will tillered when the fourth leaf grows, and the next management strategy can be guided by monitoring the number of the basic seedlings in a specific growth stage, for example, the number of the basic seedlings and the crop distribution information can be determined by the steps shown in fig. 1 a. Based on the crop distribution information, the condition of the basic seedlings can be determined, so that reasonable regulation and control management can be performed, and the purposes of increasing the yield and increasing the income can be finally achieved.
The manner of acquiring the image information is not limited to the above two manners, and may be acquired by other shooting devices, or may be acquired by combining a plurality of shooting devices.
Wherein, the crop information includes but is not limited to at least one of the following: type of crop, cultivation area, size of seedling, and morphology of leaves.
In order to solve the problem, in some embodiments of the present application, the pixel information indicating that a crop exists in the indicating information may be stored in a preset set; as shown in fig. 1c, when performing cluster analysis, selecting a part of pixel information from a preset set to perform cluster analysis, so as to obtain a plurality of clusters; and classifying the residual pixel information in the preset set based on the plurality of clusters to obtain a clustering result. Because only part of the pixel information is subjected to cluster analysis, the number of pixels participating in the cluster analysis is reduced, and the clustering efficiency is improved.
Specifically, as shown in fig. 1d, the Image information Image is processed through an encoder and decoder convolutional neural network model, and segmentation and pixel embedding are respectively output, that is, indication information of each pixel position in the Image information is obtained, the segmentation is used as a mask for judging whether the current pixel position needs to be reserved, and pixel embedding is to change each pixel of the Image into higher-dimensional vector data and store the higher-dimensional vector data in a preset set; the clustering is to group part of data objects in a preset set into a plurality of clusters, and then classify the remaining pixel information in the preset set based on the plurality of clusters to obtain a clustering result. 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: a specimen image and a label for marking elemental seedlings in the specimen image.
The high-dimensional vector refers to a vector that is represented by R, G, B three components, and is represented by adding the relative distance between pixels and pixel position information.
As the number of the remaining pixels in the preset set is also large, in order to further reduce the calculation amount of the cluster analysis, in an alternative embodiment of the present application, the remaining pixels in the preset set may be classified in the following manner: determining a classification label corresponding to each cluster; and determining the classification label to which the residual pixel information belongs according to the classification label corresponding to each cluster to obtain a clustering result, so that the calculation amount of clustering analysis is further greatly reduced.
In some embodiments of the present application, determining a classification label to which the remaining pixel information belongs to obtain a clustering result includes: calculating the similarity between each piece of pixel information in the residual pixel information and each piece of pixel information in the designated cluster to obtain a plurality of similarities, wherein the designated cluster is any one of the plurality of clusters; determining an average value of the plurality of similarities; and determining the cluster to which each pixel information in the residual pixel information belongs based on the average value to obtain a clustering result.
When determining the cluster to which each pixel information belongs in the remaining pixel information based on the average value, the following may be implemented, but is not limited thereto: comparing the similarity value range corresponding to the average value and the designated cluster; and determining a similarity value range to which the average value belongs, and taking a cluster corresponding to the determined value range as a cluster to which each piece of pixel information belongs, wherein the similarity value ranges corresponding to the clusters are continuous.
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 in the previous cluster is equal to the minimum value of the value range in the next cluster in the value ranges of the two adjacent clusters.
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.
In addition, if the above scheme is adopted, the remaining pixel information still has pixels that are not classified, and at this time, a conventional classification algorithm may be adopted for classification, for example, a pixel point is selected from each cluster as a central pixel point, the euclidean distance between the central pixel point and the pixels that are not classified is calculated, and the cluster with the smallest euclidean distance between the central pixel point and the pixels that are not classified in each cluster is taken as the class or cluster to which the pixels that are not classified belong.
In some embodiments of the present application, after determining crop distribution information in the target area based on the clustering result, the method further includes: determining a reference leaf number of a single crop in a target area; counting the total leaf amount of all crops in the target area based on the indication information; determining a number of crops in the target area based on the total number of leaves and a reference number of leaves; a target work strategy for the target area is determined based on at least one of the number of crops and the crop distribution information.
Specifically, by taking wheat as an example, basic seedlings such as wheat can be tillered, namely, the basic seedlings can be divided into a plurality of branches and leaves from one main branch, the new tillers can be formed when the fourth leaves grow out, after the surveying and mapping unmanned aerial vehicle shoots high-definition images, the leaves of the single basic seedlings of wheat can be divided according to the high-definition images, the number of the leaves of a single crop is calculated, then indication information is combined to obtain the total amount of the leaves of the wheat in a target area, the next management strategy can be guided by monitoring the number of the basic seedlings in different growth stages, and for land blocks with few growing basic seedlings, tillering can be promoted by changing water quantity, fertilizer quantity, changing illumination time and the like, so that the purposes of increasing the amount of ears and increasing the harvest are achieved.
In a preferred embodiment of the present application, the pixel information includes: information on relative distances between pixels, and information on pixel positions.
In some embodiments of the present application, obtaining image information of a target area includes: receiving image information of a target area shot by an unmanned aerial vehicle, wherein an image information carrier can be a picture, a video image and the like; the image information includes the displayed crop information: the type of crop, the cultivation area, the size of the seedling, the morphology of the leaves, etc.
In some embodiments of the present application, there is further provided a method for acquiring crop distribution information, as shown in fig. 2, the navigation method includes the following steps:
step S202, acquiring image information of a target area, wherein the image information is used for displaying crop information in the target area;
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 for indicating each pixel belonging to the target crop in the image information;
step S206, carrying out clustering analysis on the effective pixel information to obtain a clustering result;
and step S208, determining crop distribution information in the target area based on the clustering result.
Specifically, in the method for acquiring crop distribution information, image information of a target area is acquired by using an unmanned aerial vehicle in an ultra-low altitude environment or by using other equipment such as a ground robot, wherein the image information is used for displaying crop information in the target area, such as the type of a crop, a cultivation area, the size of a seedling, the shape of leaves, and the like, and then the image information is input to a neural network model for analysis to obtain effective pixel information in the image information, wherein the effective pixel information is used for indicating each pixel belonging to the target crop in the image information; the effective pixel information is subjected to clustering analysis to obtain a clustering result, so that the crop distribution information in the target area is determined based on the clustering result, and the technical problems of more random factors, time consumption and labor consumption of collected samples caused by artificial sampling statistics are solved.
In some embodiments of the present application, there is further provided an apparatus for acquiring crop distribution information, as shown in fig. 3, the apparatus for acquiring crop distribution information includes:
the acquiring module 30 is configured to acquire image information of a target area, where the image information is used to display crop information in the target area;
the analysis module 32 is configured to input the image information to the neural network model for analysis, so as to obtain indication information of each pixel position in the image information and pixel information corresponding to a pixel position where a crop exists, where the indication information is used for indicating whether a crop exists at each pixel position;
the clustering module 34 is configured to perform clustering analysis on the pixel information to obtain a clustering result;
and a first determining module 36 for determining crop distribution information in the target area based on the clustering result.
The acquisition module of the device for acquiring the crop distribution information acquires image information of a target area by adopting an unmanned aerial vehicle in an ultra-low altitude or other equipment such as a ground robot, wherein the image information is used for displaying the crop information in the target area; the analysis module is used for inputting the image information into the 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, and the indication information is used for indicating whether the crop exists at each pixel position; the clustering module is used for carrying out clustering analysis on the pixel information to obtain a clustering result; the first determining module is used for determining crop distribution information in the target area based on the clustering result, and the device solves the technical problems that more random factors exist in sample collection, and time and labor are consumed due to artificial sampling statistics.
For example, after the surveying and mapping unmanned aerial vehicle shoots a high-definition image, the leaves of each crop can be divided according to the high-definition image, then according to the leaf age of the current crop, the basic seedlings of wheat and the like can be tillered, that is, the basic seedlings of wheat can be divided into a plurality of branches from one main branch, the new tillering will be generated when the fourth leaf is generated, the next management strategy can be guided by monitoring the number of the basic seedlings at a specific growth stage, for example, the number of the basic seedlings and the crop distribution information can be determined through the steps shown in fig. 1 a. Based on the crop distribution information, the condition of the basic seedlings can be determined, so that reasonable regulation and control management can be performed, and the purposes of increasing yield and income can be finally achieved.
It should be noted that the manner of acquiring the image information is not limited to the above two manners, and may be acquired by other shooting devices, or may be acquired by combining multiple shooting devices;
wherein, the crop information includes but is not limited to at least one of the following: type of crop, cultivation area, size of seedling, and morphology of leaves.
In order to solve the problem, in some embodiments of the present application, the analysis module includes a storage sub-module, where the storage sub-module is configured to input the image information into the neural network model for analysis, and obtain indication information of each pixel position in the image information, where the storage sub-module is configured to: storing pixel information indicating that crops exist in the indicating information into a preset set; the clustering module comprises a clustering submodule, the clustering submodule is used for carrying out clustering analysis on the pixel information to obtain a clustering result, and the clustering module comprises: selecting partial pixel information from a preset set to perform clustering analysis to obtain a plurality of clusters; and classifying the residual pixel information in the preset set based on the plurality of clusters to obtain a clustering result. Because only part of the pixel information is subjected to clustering analysis, the number of pixels participating in the clustering analysis is reduced, and the clustering efficiency is improved.
In order to further reduce the calculation amount of the cluster analysis, in an optional embodiment of the present application, the clustering submodule includes a first determining submodule and a second determining submodule, where the first determining submodule is configured to determine a classification label corresponding to each cluster; the second determining submodule is used for determining the classification label to which the residual pixel information belongs according to the classification label corresponding to each cluster to obtain a clustering result, so that the calculation amount of clustering analysis is further greatly reduced.
In some embodiments of the application, the clustering submodule further includes a first calculating submodule and a third determining submodule, and the fourth determining submodule, where the first calculating submodule is configured to calculate a similarity between each piece of pixel information in the remaining pixel information and each piece of pixel information in the designated cluster, so as to obtain a plurality of similarities, and the designated cluster is any one of the plurality of clusters; the third determining submodule is used for determining an average value of the plurality of similarities; and the fourth determining submodule is used for determining the cluster to which each pixel information belongs in the residual pixel information based on the average value to obtain a clustering result.
In a preferred embodiment of the present application, the fourth determining sub-module includes a fifth determining sub-module, and the fifth determining sub-module is configured to compare the average value with a similarity value range corresponding to the designated cluster; and determining a similarity value range to which the average value belongs, and taking a cluster corresponding to the determined value range as a cluster to which each piece of pixel information belongs, wherein the similarity value ranges corresponding to the clusters are continuous.
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 in the previous cluster is equal to the minimum value of the value range in the next cluster in the value ranges of the two adjacent clusters.
In some embodiments of the present application, in order to ensure that all remaining pixel information can be classified into corresponding clusters, the fifth determination sub-module similarity value range is determined based on similarities in the remaining pixel information and pixel information in each cluster.
The device also comprises a second determining module, a statistical module, a third determining module and a fourth determining module, wherein the second determining module is used for determining the reference leaf number of a single crop in the target area after the clustering result determines the crop distribution information in the target area; the counting module is used for counting the total leaf amount of all crops in the target area based on the indication information; the third determining module is used for determining the number of crops in the target area based on the total quantity of leaves and the reference quantity of leaves; the fourth determination module is used for determining a target operation strategy of the target area based on at least one of the number of the crops and the crop distribution information.
In a preferred embodiment of the present application, the pixel information includes: information on relative distances between pixels, and information on pixel positions.
In some embodiments of the application, the image information of the target area obtained by the obtaining module includes image information of the target area shot by the receiving unmanned aerial vehicle, wherein the image information carrier may be a picture, a video screen, or the like; the image information includes the displayed crop information: the type of crop, the cultivation area, the size of the seedling, the morphology of the leaves, etc.
According to some embodiments of the present application, there is also provided a measurement system of crop distribution information, as shown in fig. 4, the measurement system including:
the surveying and mapping unmanned aerial vehicle 40 is used for acquiring image information of the target area 10, wherein the image information is used for displaying crop information in the target area 10;
the network-side device 42 is configured to input the image information to the neural network model for analysis, so as to obtain indication information of each pixel position in the image information and pixel information corresponding to a pixel position where a crop exists, where the indication information is used to indicate whether a crop exists at each pixel position; carrying out clustering analysis on the pixel information to obtain a clustering result; crop distribution information in the target area 10 is determined based on the clustering result.
Specifically, the above-mentioned measurement system of crop distribution information, survey and drawing unmanned aerial vehicle for obtain the image information in target area, wherein, this image information is used for showing the crop information in the target area, and the crop information can be: the method comprises the steps that the type, cultivation area, seedling size and the like of crops are measured, shooting equipment on a surveying and mapping unmanned aerial vehicle sends information of the crops to network side equipment in an image mode, the network side equipment is used for inputting image information to a neural network model for analysis, indication information of each pixel position in the image information and pixel information corresponding to the pixel position where the crops exist are obtained, and the indication information is used for indicating whether the crops exist in each pixel position or not; carrying out clustering analysis on the pixel information to obtain a clustering result; based on the clustering result, the crop distribution information in the target area is determined, the measurement system can realize the unmanned aerial vehicle whole-course unmanned operation, and the collected sample has higher representativeness, thereby solving the problems that the collected sample has more random factors and consumes time and labor due to artificial sampling statistics in the prior art
In some embodiments of the present application, a non-volatile storage medium is further provided, where the storage medium includes a stored program, and when the program runs, the apparatus on which the storage medium is located is controlled to execute any method for acquiring crop distribution information.
In some embodiments of the present application, a processor is further provided, and the processor is configured to execute a program stored in a storage medium, where the program executes any method for acquiring crop distribution information.
The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present application, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or a part of or all or part of the technical solution contributing to the prior art may be embodied in the form of a software product stored in a storage medium, and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present application and it should be noted that those skilled in the art can make several improvements and modifications without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.
Claims (14)
1. A method for acquiring crop distribution information is characterized by comprising the following steps:
acquiring image information of a target area, wherein the image information is used for displaying 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 for indicating whether the crop exists at each pixel position;
performing clustering analysis on the pixel information to obtain a clustering result;
determining crop distribution information in the target area based on the clustering result.
2. The method of claim 1,
inputting the image information into a neural network model for analysis to obtain indication information of each pixel position in the image information, wherein the indication information comprises: storing pixel information indicating that crops exist in the indicating information into a preset set;
performing cluster analysis on the pixel information to obtain a cluster result, including: selecting partial pixel information from the preset set to perform clustering analysis to obtain a plurality of clusters; and classifying the residual pixel information in the preset set based on the plurality of clusters to obtain the clustering result.
3. The method of claim 2, wherein classifying the remaining pixel information in the preset set based on the plurality of clusters comprises:
determining a classification label corresponding to each cluster;
and determining the classification label to which the residual pixel information belongs to obtain the clustering result.
4. The method of claim 3, wherein determining the classification label to which the remaining pixel information belongs to obtain the clustering result comprises:
calculating the similarity between each piece of pixel information in the residual pixel information and each piece of pixel information in an appointed cluster to obtain a plurality of similarities, wherein the appointed cluster is any one of the clusters;
determining an average of the plurality of similarities;
and determining a cluster to which each piece of pixel information in the residual pixel information belongs based on the average value, and determining a classification label to which each piece of pixel information in the residual pixel information belongs based on the determined cluster to obtain the clustering result.
5. The method according to claim 4, wherein determining a cluster to which each pixel information of the remaining pixel information belongs based on the average value to obtain the clustering result comprises:
comparing the similarity value range corresponding to the average value and the designated cluster; and determining a similarity value range to which the average value belongs, and taking a cluster corresponding to the determined value range as a cluster to which each piece of pixel information belongs, wherein the similarity value ranges corresponding to the clusters are continuous.
6. The method according to claim 5, wherein the similarity value range is determined based on a similarity between each of the remaining pixel information and the pixel information in each of the clusters.
7. The method of claim 2, wherein after determining crop distribution information in the target area based on the clustering result, the method further comprises:
determining a reference leaf count 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 a number of crops in the target area based on the total number of leaves and the reference number of leaves;
determining a target operating strategy for the target area based on at least one of the crop quantity and the crop distribution information.
8. The method of claim 1, wherein the pixel information comprises: information on relative distances between pixels, and information on pixel positions.
9. The method according to any one of claims 1 to 8, wherein acquiring image information of the target area comprises:
and receiving the image information of the target area shot by the unmanned aerial vehicle.
10. A method for acquiring crop distribution information is characterized by comprising the following steps:
acquiring image information of a target area, wherein the image information is used for displaying 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 for indicating each pixel belonging to a target crop in the image information;
carrying out clustering analysis on the effective pixel information to obtain a clustering result;
determining crop distribution information in the target area based on the clustering result.
11. A system for measuring crop distribution information, comprising:
the surveying and mapping unmanned aerial vehicle is used for acquiring image information of a target area, wherein the image information is used for displaying crop information in the target area;
the network side equipment is used for 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 for indicating whether the crop exists at each pixel position; performing clustering analysis on the pixel information to obtain a clustering result; determining crop distribution information in the target area based on the clustering result.
12. An apparatus for acquiring crop distribution information, comprising:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring image information of a target area, and the image information is used for displaying crop information in the target area;
the analysis module is used for 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 for indicating whether the crop exists at each pixel position;
the clustering module is used for carrying out clustering analysis on the pixel information to obtain a clustering result;
a first determining module, configured to determine crop distribution information in the target area based on the clustering result.
13. A non-volatile storage medium, characterized in that the storage medium includes a stored program, and when the program runs, the apparatus on which the storage medium is located is controlled to execute the method for acquiring crop distribution information according to any one of claims 1 to 10.
14. A processor, characterized in that the processor is configured to run a program stored in a storage medium, wherein the program is configured to execute the method for acquiring crop distribution information according to any one of claims 1 to 10 when running.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911319115.6A CN113011221A (en) | 2019-12-19 | 2019-12-19 | Crop distribution information acquisition method and device and measurement system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911319115.6A CN113011221A (en) | 2019-12-19 | 2019-12-19 | Crop distribution information acquisition method and device and measurement system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113011221A true CN113011221A (en) | 2021-06-22 |
Family
ID=76381282
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911319115.6A Pending CN113011221A (en) | 2019-12-19 | 2019-12-19 | Crop distribution information acquisition method and device and measurement system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113011221A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113988701A (en) * | 2021-11-15 | 2022-01-28 | 广州极飞科技股份有限公司 | Terrain analysis method and device and electronic equipment |
| CN114375711A (en) * | 2021-12-27 | 2022-04-22 | 广州极飞科技股份有限公司 | Polar coordinate type crop processing device, crop processing equipment and crop processing method |
| CN114489045A (en) * | 2021-12-27 | 2022-05-13 | 广州极飞科技股份有限公司 | Operation control method, module, equipment and storage medium |
| CN116882612A (en) * | 2023-09-08 | 2023-10-13 | 安徽农业大学 | Intelligent agricultural machinery path planning method and device based on remote sensing image and deep learning |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170161560A1 (en) * | 2014-11-24 | 2017-06-08 | Prospera Technologies, Ltd. | System and method for harvest yield prediction |
| CN108564102A (en) * | 2018-01-04 | 2018-09-21 | 百度在线网络技术（北京）有限公司 | Image clustering evaluation of result method and apparatus |
| CN108765429A (en) * | 2018-05-18 | 2018-11-06 | 深圳智达机械技术有限公司 | A kind of image segmentation system based on clustering |
| CN109445457A (en) * | 2018-10-18 | 2019-03-08 | 广州极飞科技有限公司 | Determination method, the control method and device of unmanned vehicle of distributed intelligence |
| CN109800781A (en) * | 2018-12-07 | 2019-05-24 | 北京奇艺世纪科技有限公司 | A kind of image processing method, device and computer readable storage medium |
| CN109886094A (en) * | 2019-01-08 | 2019-06-14 | 中国农业大学 | A kind of crop growth of cereal crop seedlings seedling gesture capturing analysis method and device |
| US20190228225A1 (en) * | 2018-01-23 | 2019-07-25 | X Development Llc | Crop boundary detection in images |
-
2019
- 2019-12-19 CN CN201911319115.6A patent/CN113011221A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170161560A1 (en) * | 2014-11-24 | 2017-06-08 | Prospera Technologies, Ltd. | System and method for harvest yield prediction |
| CN108564102A (en) * | 2018-01-04 | 2018-09-21 | 百度在线网络技术（北京）有限公司 | Image clustering evaluation of result method and apparatus |
| US20190228225A1 (en) * | 2018-01-23 | 2019-07-25 | X Development Llc | Crop boundary detection in images |
| CN108765429A (en) * | 2018-05-18 | 2018-11-06 | 深圳智达机械技术有限公司 | A kind of image segmentation system based on clustering |
| CN109445457A (en) * | 2018-10-18 | 2019-03-08 | 广州极飞科技有限公司 | Determination method, the control method and device of unmanned vehicle of distributed intelligence |
| CN109800781A (en) * | 2018-12-07 | 2019-05-24 | 北京奇艺世纪科技有限公司 | A kind of image processing method, device and computer readable storage medium |
| CN109886094A (en) * | 2019-01-08 | 2019-06-14 | 中国农业大学 | A kind of crop growth of cereal crop seedlings seedling gesture capturing analysis method and device |
Non-Patent Citations (2)
| Title |
|---|
| M. SCHIRRMANN ET AL.: "Estimating wheat biomass by combining image clustering with crop height", 《COMPUTERS AND ELECTRONICS IN AGRICULTURE》, vol. 121, 31 December 2016 (2016-12-31), pages 374 * |
| 陈道颖 等: "一种基于航空可见光图像的烟草数量统计方法", 湖北农业科学, vol. 56, no. 7, 10 April 2017 (2017-04-10), pages 1348 - 1350 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113988701A (en) * | 2021-11-15 | 2022-01-28 | 广州极飞科技股份有限公司 | Terrain analysis method and device and electronic equipment |
| CN114375711A (en) * | 2021-12-27 | 2022-04-22 | 广州极飞科技股份有限公司 | Polar coordinate type crop processing device, crop processing equipment and crop processing method |
| CN114489045A (en) * | 2021-12-27 | 2022-05-13 | 广州极飞科技股份有限公司 | Operation control method, module, equipment and storage medium |
| CN116882612A (en) * | 2023-09-08 | 2023-10-13 | 安徽农业大学 | Intelligent agricultural machinery path planning method and device based on remote sensing image and deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sun et al. | Three-dimensional photogrammetric mapping of cotton bolls in situ based on point cloud segmentation and clustering | |
| Iqbal et al. | Gray level co-occurrence matrix (GLCM) texture based crop classification using low altitude remote sensing platforms | |
| CN108647652B (en) | Cotton development period automatic identification method based on image classification and target detection | |
| Zhu et al. | In-field automatic observation of wheat heading stage using computer vision | |
| CN113011221A (en) | Crop distribution information acquisition method and device and measurement system | |
| Yu et al. | Automatic image-based detection technology for two critical growth stages of maize: Emergence and three-leaf stage | |
| Li et al. | In-field cotton detection via region-based semantic image segmentation | |
| CN109583301B (en) | Method and device for predicting optimal external planting conditions in crop growth process | |
| Zhou et al. | Strawberry maturity classification from UAV and near-ground imaging using deep learning | |
| CN109886094A (en) | A kind of crop growth of cereal crop seedlings seedling gesture capturing analysis method and device | |
| CN102542560B (en) | Method for automatically detecting density of rice after transplantation | |
| Selvi et al. | Weed detection in agricultural fields using deep learning process | |
| CN114818909A (en) | Weed detection method and device based on crop growth characteristics | |
| CN115620151A (en) | Method and device for identifying phenological period, electronic equipment and storage medium | |
| Mortensen et al. | The oil radish growth dataset for semantic segmentation and yield estimation | |
| CN108537164B (en) | Method and device for monitoring germination rate of dibbling and sowing based on unmanned aerial vehicle remote sensing | |
| Guo et al. | Panicle Ratio Network: streamlining rice panicle measurement by deep learning with ultra-high-definition aerial images in the field | |
| CN110689022A (en) | Leaf matching-based image extraction method for each crop | |
| Zhang et al. | Automatic counting of lettuce using an improved YOLOv5s with multiple lightweight strategies | |
| CN107437262B (en) | Crop planting area early warning method and system | |
| CN117197595A (en) | Fruit tree growth period identification method, device and management platform based on edge calculation | |
| CN115314851A (en) | Agricultural information management platform based on big data platform | |
| Shuai et al. | Image segmentation of field rape based on template matching and K-means clustering | |
| CN113486773A (en) | Cotton plant growth period identification method, system, storage medium and equipment | |
| Jahan et al. | Using images from a handheld camera to detect wheat bacterial leaf streak disease severities |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |