Crop identification method and device, and operation equipment control method

Abstract

The present application discloses a method and device for identifying crops, and a control method for operating equipment. The method includes: obtaining image data and digital surface model data of a plant protection area; determining first point cloud height information in the plant protection area based on the digital surface model data, the first point cloud height information including the height value of the point cloud in the plant protection area; determining second point cloud height information of the target crop based on the first point cloud height information; and identifying individual information of the target crop based on the image data and the second point cloud height information. The present application solves the technical problem that the distribution range of fruit trees is currently mapped using two-dimensional RGB images, and it is difficult to accurately identify each fruit tree due to the intersection of fruit trees.

Description

Technical Field

[0001] The present application relates to the field of plant protection, and more specifically, to a method and device for identifying crops, and a method for controlling operating equipment. Background Art

[0002] Currently, drone plant protection operations on fruit trees require manual mapping of the distribution range of fruit trees and the size of individual fruit trees, or the use of aerial survey high-definition RGB images for image segmentation and then identification of the location information of the fruit trees. However, manual mapping is time-consuming and costly, and simple RGB images are not very effective for densely grown orchards.

[0003] Figure 1 is a two-dimensional RGB image of a fruit tree. If only a two-dimensional RGB image is used to detect the fruit tree, the following will be obtained: Figure 2 As shown in the detection results, due to the intersection of the fruit trees, it is difficult to accurately identify each fruit tree using only two-dimensional images.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present application provide a method and device for identifying crops, and a control method for operating equipment, so as to at least solve the technical problem that the distribution range of fruit trees is currently mapped using two-dimensional RGB images, and it is difficult to accurately identify each fruit tree due to the intersection of fruit trees.

[0006] According to one aspect of an embodiment of the present application, a method for identifying crops is provided, including: acquiring image data and digital surface model data of a plant protection area; determining first point cloud height information in the plant protection area based on the digital surface model data, the first point cloud height information including a height value of a point cloud in the plant protection area; determining second point cloud height information of a target crop based on the first point cloud height information; and identifying individual information of the target crop based on the image data and the second point cloud height information.

[0007] Optionally, determining the second point cloud height information of the target crop based on the first point cloud height information includes: taking the area where the height value of the point cloud corresponding to the first point cloud height information gradually decreases from the middle to the surrounding areas as the area where the target crop is located; and taking the first point cloud height information corresponding to the area where the target crop is located as the second point cloud height information.

[0008] Optionally, determining the second point cloud height information of the target crop based on the first point cloud height information also includes: comparing the first point cloud height information with a preset height information range; and using the first point cloud height information that falls within the preset height information range as the second point cloud height information.

[0009] Optionally, individual information of the target crops is identified based on the image data and the second point cloud height information, including: inputting the image data and the second point cloud height information into a preset deep learning model for detection to obtain the position information and individual size information of each target crop, and the individual size information is used to characterize the outline size of the target crop when looking down.

[0010] Optionally, the above-mentioned image data includes a two-dimensional RGB image.

[0011] Optionally, after identifying the individual information of the target crops, the above method also includes: determining an operation route based on the location information of the target crops; determining a dosage of medicine to be sprayed on the target crops based on the individual size information of the target crops; and performing plant protection operations on the target crops based on the operation route and the dosage of the medicine to be sprayed.

[0012] Optionally, the method further includes: determining the position information of the target crop in a three-dimensional coordinate system corresponding to the digital surface model data according to the second point cloud height information of the target crop.

[0013] According to another aspect of an embodiment of the present application, a control method for operating equipment is also provided, including: acquiring image data and digital surface model data of a plant protection area; determining first point cloud height information in the plant protection area based on the digital surface model data, the first point cloud height information including the height value of the point cloud in the plant protection area; determining second point cloud height information of the target crop based on the first point cloud height information; identifying individual information of the target crop based on the image data and the second point cloud height information; and controlling the operating equipment to perform plant protection operations on the target crop based on the individual information of the target crop.

[0014] According to another aspect of an embodiment of the present application, a device for identifying crops is also provided, including: an acquisition module for acquiring image data and digital surface model data of a plant protection area; a first determination module for determining first point cloud height information in the plant protection area based on the digital surface model data, the first point cloud height information including the height value of the point cloud in the plant protection area; a second determination module for determining second point cloud height information of a target crop based on the first point cloud height information; and an identification module for identifying individual information of the target crop based on the image data and the second point cloud height information.

[0015] According to another aspect of an embodiment of the present application, a plant protection system is also provided, including: a surveying and mapping device, used to collect image data and digital surface model data of a plant protection area, and send the image data and the digital surface model data to a server; a server, used to determine first point cloud height information of the plant protection area based on the digital surface model data, wherein the first point cloud height information includes a height value of the point cloud in the plant protection area; determine second point cloud height information of a target crop based on the first point cloud height information; identify individual information of the target crop based on the image data and the second point cloud height information; and an operating device, communicating with the server, for performing plant protection operations on the target crop.

[0016] According to another aspect of an embodiment of the present application, a storage medium is further provided, the storage medium including a stored program, wherein when the program is executed, the device where the storage medium is located is controlled to execute the above crop identification method.

[0017] According to another aspect of an embodiment of the present application, a processor is further provided, and the processor is used to run a program, wherein the above crop identification method is executed when the program is run.

[0018] In an embodiment of the present application, the method of acquiring image data and digital surface model data of a plant protection area; determining first point cloud height information in the plant protection area based on the digital surface model data, the first point cloud height information including the height value of the point cloud in the plant protection area; determining second point cloud height information of a target crop based on the first point cloud height information; and identifying individual information of the target crop based on the image data and the second point cloud height information is adopted. The height information of the target crop in the plant protection area is determined by using the digital surface model data of the plant protection area, and then the individual information of each crop in the plant protection area is accurately identified in combination with the two-dimensional RGB image data of the plant protection area, thereby achieving the technical effect of accurately mapping the distribution information of each fruit tree in the plant protection area, improving the degree of automation of plant protection operations in orchards, and reducing the complexity of plant protection operations in orchards, thereby solving the technical problem that the distribution range of fruit trees is currently mapped using two-dimensional RGB images, and it is difficult to accurately identify each fruit tree due to the intersection of fruit trees. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] 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:

[0020] Figure 1 is a schematic diagram of an RGB image of a fruit tree according to an embodiment of the present application;

[0021] Figure 2 It is a schematic diagram of the distribution of fruit trees obtained by detecting fruit trees based on RGB images;

[0022] Figure 3 is a flow chart of a method for identifying crops according to an embodiment of the present application;

[0023] Figure 4 It is a schematic diagram of two-dimensional visualization of digital surface model data of a fruit tree according to an embodiment of the present application;

[0024] Figure 5 is a flow chart of a control method of an operating equipment according to an embodiment of the present application;

[0025] Figure 6 is a structural diagram of a crop identification device according to an embodiment of the present application;

[0026] Figure 7 It is a structural diagram of a plant protection system according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] 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.

[0028] 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.

[0029] According to an embodiment of the present application, an embodiment of a control method for working equipment 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.

[0030] Figure 3is a flow chart of a crop identification method according to an embodiment of the present application. Figure 3 As shown, the method comprises the following steps:

[0031] Step S302, acquiring image data and digital surface model data of the plant protection area.

[0032] According to an optional embodiment of the present application, the image data includes a two-dimensional RGB image. The RGB color model is a color standard in the industry, which obtains various colors by changing the three color channels of red, green and blue and superimposing them.

[0033] In an optional embodiment of the present application, the RGB image of the above-mentioned plant protection area can be captured and collected using a high-definition camera installed on a surveying and mapping drone.

[0034] A digital surface model refers to a ground elevation model that includes the heights of buildings, bridges, and trees on the surface. It is used to express the undulations of the ground in the most realistic way and can be widely used in various industries. For example, in forest areas, it can be used to detect the growth of forests.

[0035] Step S304: determining first point cloud height information in the plant protection area according to the digital surface model data, wherein the first point cloud height information includes a height value of the point cloud in the plant protection area.

[0036] Step S306, determining second point cloud height information of the target crop according to the first point cloud height information.

[0037] The acquired digital surface model data includes the height information of various crops. Different crops have different height information. Therefore, it is necessary to first acquire the digital surface model data of the plant protection area to determine the height information of the target crops in the plant protection area. It should be noted that the target crops mentioned here refer to fruit trees.

[0038] In an optional embodiment of the present application, taking an orchard as an example, the fruit trees in the orchard are intertwined, and each fruit tree cannot be accurately identified using only a two-dimensional RGB image. Therefore, it is necessary to use the digital surface model data of the orchard to determine the height of each fruit tree, and then use the height of the fruit trees to distinguish the fruit trees.

[0039] Step S308 , identifying individual information of the target crop based on the image data and the second point cloud height information.

[0040] As mentioned above, since the fruit trees in the orchard are intertwined, it is impossible to accurately identify each fruit tree using only two-dimensional RGB images. However, after determining the height of each fruit tree using the digital surface model data of the orchard, combined with the two-dimensional RGB images of the fruit trees, the information of each fruit tree in the orchard can be accurately identified.

[0041] Figure 4 is a schematic diagram of two-dimensional visualization of digital surface model data of a fruit tree according to an embodiment of the present application, such as Figure 4 As shown, the digital surface model data of the fruit trees is visualized in two dimensions. The fruit trees that are difficult to distinguish on two-dimensional RGB become very easy to distinguish after being mapped to the height information, and the distribution information of each fruit tree can be obtained.

[0042] Through the above steps, the height information of the target crops in the plant protection area is determined by using the digital surface model data of the plant protection area, and then the individual information of each target crop in the plant protection area is accurately identified in combination with the two-dimensional RGB image data of the plant protection area, thereby achieving the technical effect of accurately mapping the distribution information of each fruit tree in the plant protection area, improving the degree of automation of orchard plant protection operations, and reducing the complexity of orchard plant protection operations.

[0043] In an optional embodiment of the present application, step S306 can be implemented by the following method: taking the area where the height value of the point cloud corresponding to the first point cloud height information gradually decreases from the middle to the surrounding areas as the area where the target crop is located; taking the first point cloud height information corresponding to the area where the target crop is located as the second point cloud height information.

[0044] The crown of a fruit tree is generally high in the middle and low in the surrounding areas. Therefore, when identifying fruit trees, the area where the point cloud height value corresponding to the point cloud height information gradually decreases from the middle to the surrounding areas is used as the planting area of ​​the fruit tree. The point cloud height information corresponding to this area is also the point cloud height information of the fruit tree, that is, the second point cloud height information mentioned above.

[0045] In an optional embodiment of the present application, step S306 can also be implemented by the following method: comparing the first point cloud height information with the preset height information range respectively; and taking the first point cloud height information falling within the preset height information range as the second point cloud height information.

[0046] There may be a variety of crops distributed in the plant protection area, and different crops have different heights. For example, it is necessary to map the distribution range of fruit trees in the plant protection area. The height information of various crops is obtained through the digital surface model data of the orchard. If the height information of the fruit trees is obtained, it is necessary to further compare the obtained height information of the various crops with the height range of fruit trees pre-stored in the database to determine which height information is the height information of the fruit trees that need to be mapped.

[0047] In an optional embodiment of the present application, step S308 can be implemented by the following method: input the image data and the second height information into a preset deep learning model for detection to obtain the position information and individual size information of each target crop, and the individual size information is used to characterize the outline size of the target crop when looking down.

[0048] According to an optional embodiment of the present application, after obtaining the height information of the fruit trees, the height information of the fruit trees and the RGB image of the fruit trees are used as the depth channel and the RGB channel as the input of the machine learning model, and are input into the pre-trained machine learning model for segmentation and detection. The location information and individual size information of each fruit tree are obtained. It should be noted that the individual size information here refers to the size of the crown outline when looking down at the fruit trees. The above method can greatly improve the robustness and accuracy of the machine learning model.

[0049] In an optional embodiment of the present application, before using a machine learning model to identify the location information and individual size information of the target crops, it is necessary to obtain a training data set, wherein the training data set includes: image data of the plant protection area, point cloud height information of the target crops, and the location information and individual size information of the target crops; based on the training data set, the trained machine learning model is generated.

[0050] In another optional embodiment of the present application, after executing step S308, it is also necessary to determine the operation route according to the location information of the target crop; determine the dosage of the sprayed medicine for the target crop according to the individual size information of the target crop; and perform plant protection operations on the target crop according to the operation route and the dosage of the sprayed medicine. The route of the plant protection drone can be formulated according to the distribution information of the fruit tree; and the dosage of the pesticide sprayed when performing plant protection operations on the fruit tree can be determined according to the size of the fruit tree's crown.

[0051] Through this method, the location distribution information of fruit trees is used to plan the route of plant protection operations in advance, and the dosage of pesticides sprayed on fruit trees during plant protection operations is determined according to the individual size of the fruit trees. This can not only improve the efficiency of plant protection operations, but also save resources.

[0052] In some optional embodiments of the present application, the above-mentioned crop identification method also includes determining the position information of the target crop in the three-dimensional coordinate system corresponding to the digital surface model data based on the second point cloud height information of the target crop.

[0053] As mentioned above, the location distribution information and individual size information of crops are determined by combining the digital surface model data of the plant protection area with the RGB image data of the plant protection area. The height information of crops can also be directly determined by using the digital surface model data of the plant protection area, and then the crops can be identified in the three-dimensional space corresponding to the digital surface model data of the plant protection area.

[0054] Through the above method, after the mapping drone takes the high-definition image, the position and individual size of the fruit trees can be directly detected based on the high-definition image and digital surface model data, and then directly used for plant protection operations, which can improve the degree of automation of plant protection operations and reduce the complexity of orchard operations.

[0055] Figure 5 is a flow chart of a control method for an operating device according to an embodiment of the present application, such as Figure 5 As shown, the method comprises the following steps:

[0056] Step S502: acquiring image data and digital surface model data of the plant protection area.

[0057] Step S504: determining first point cloud height information in the plant protection area according to the digital surface model data, wherein the first point cloud height information includes a height value of the point cloud in the plant protection area.

[0058] Step S506, determining second point cloud height information of the target crop according to the first point cloud height information.

[0059] Step S508 , identifying individual information of the target crop based on the image data and the second point cloud height information.

[0060] According to an optional embodiment of the present application, identifying the individual information of the target crop in step S508 refers to identifying the location information and individual size information of the target crop.

[0061] Step S510, controlling the operation equipment to perform plant protection operations on the target crops according to the individual information of the target crops.

[0062] Optionally, after identifying the individual information of the target crop, the operation route is determined according to the location information of the target crop; the dosage of the spraying drug on the target crop is determined according to the individual size information of the target crop. The operation equipment performs plant protection operations on the target crop according to the determined operation route and the dosage of the spraying drug.

[0063] It should be noted that Figure 5 The preferred implementation of the illustrated embodiment can be found in Figure 3 The relevant description of the illustrated embodiment will not be repeated here.

[0064] Figure 6is a structural diagram of a crop identification device according to an embodiment of the present application, such as Figure 6 As shown, the device comprises:

[0065] The acquisition module 60 is used to acquire image data and digital surface model data of the plant protection area.

[0066] According to an optional embodiment of the present application, the image data includes a two-dimensional RGB image. The RGB color model is a color standard in the industry, which obtains various colors by changing the three color channels of red, green and blue and superimposing them.

[0067] In an optional embodiment of the present application, the RGB image of the above-mentioned plant protection area can be captured and collected using a high-definition camera installed on a surveying and mapping drone.

[0068] A digital surface model (DSM) is a ground elevation model that includes the heights of buildings, bridges, and trees. A digital surface model is the most realistic representation of ground undulations and can be widely used in various industries. For example, in forest areas, it can be used to detect forest growth.

[0069] The first determination module 62 is used to determine first point cloud height information in the plant protection area according to the digital surface model data, where the first point cloud height information includes a height value of a point cloud in the plant protection area.

[0070] The second determination module 64 is used to determine second point cloud height information of the target crop according to the first point cloud height information.

[0071] The acquired digital surface model data includes the height information of various crops. Different crops have different height information. Therefore, it is necessary to first acquire the digital surface model data of the plant protection area to determine the height information of the target crops in the plant protection area. It should be noted that the target crops mentioned here refer to fruit trees.

[0072] The identification module 66 is used to identify individual information of the target crop according to the image data and the second point cloud height information.

[0073] Through the above-mentioned device, the height information of the target crops in the plant protection area is determined by utilizing the digital surface model data of the plant protection area, and then the individual information of each target crop in the plant protection area is accurately identified in combination with the two-dimensional RGB image data of the plant protection area, thereby achieving the technical effect of accurately mapping the distribution information of each fruit tree in the plant protection area, improving the degree of automation of plant protection operations in the orchard, and reducing the complexity of plant protection operations in the orchard.

[0074] It should be noted that Figure 6The preferred implementation of the illustrated embodiment can be found in Figure 3 The relevant description of the illustrated embodiment will not be repeated here.

[0075] Figure 7 is a structural diagram of a plant protection system according to an embodiment of the present application, such as Figure 6 As shown, the system includes: surveying and mapping equipment 70, server 72 and operation equipment 74, wherein:

[0076] Surveying and mapping equipment 70, used to collect image data and digital surface model data of the plant protection area, and send the image data and digital surface model M data to the server 72;

[0077] Optionally, the surveying and mapping equipment may be a surveying and mapping drone, and a high-definition camera is installed on the surveying and mapping drone to collect high-definition images of the plant protection area, thereby obtaining a two-dimensional RGB image of the plant protection area. A three-dimensional imager is installed on the surveying and mapping drone to obtain digital surface model data of the plant protection area. The surveying and mapping drone is provided with a communication module to send the collected image data and GSM data to the server 72.

[0078] Server 72 is used to determine the first point cloud height information in the plant protection area based on the digital surface model data, the first point cloud height information includes the height value of the point cloud in the plant protection area; determine the second point cloud height information of the target crop based on the first point cloud height information; and identify the individual information of the target crop based on the image data and the second point cloud height information.

[0079] The operation equipment 74 communicates with the server 72 and is used to perform plant protection operations on target crops.

[0080] According to an optional embodiment of the present application, after identifying the individual information of the target crop, the server 72 determines the operation route of the operation according to the location information of the target crop; and determines the dosage of the spraying drug on the target crop according to the individual size information of the target crop. The operation equipment 74 performs plant protection operations on the target crop according to the operation route and the dosage of the spraying drug.

[0081] Optionally, the operating equipment 74 includes but is not limited to unmanned equipment such as plant protection drones.

[0082] It should be noted that Figure 7 The preferred implementation of the illustrated embodiment can be found in Figure 3 The relevant description of the illustrated embodiment will not be repeated here.

[0083] An embodiment of the present application further provides a storage medium, which includes a stored program, wherein when the program is executed, the device where the storage medium is located is controlled to execute the above crop identification method or operation equipment control method.

[0084] The storage medium is used to store a program that performs the following functions: obtaining image data and digital surface model data of the plant protection area; determining the first point cloud height information of the plant protection area based on the digital surface model data, the first point cloud height information including the height value of the point cloud in the plant protection area; determining the second point cloud height information of the target crop based on the first point cloud height information; identifying the individual information of the target crop based on the image data and the second point cloud height information. Or

[0085] Acquire image data and digital surface model data of the plant protection area; determine first point cloud height information of the plant protection area based on the digital surface model data, the first point cloud height information including the height value of the point cloud in the plant protection area; determine second point cloud height information of the target crop based on the first point cloud height information; identify individual information of the target crop based on the image data and the second point cloud height information; control the operation equipment to perform plant protection operation on the target crop based on the individual information of the target crop.

[0086] The embodiment of the present application further provides a processor, which is used to run a program, wherein the program executes the above crop identification method or operation equipment control method when running.

[0087] The processor is used to run a program that performs the following functions: obtain image data and digital surface model data of the plant protection area; determine the first point cloud height information of the plant protection area based on the digital surface model data, the first point cloud height information includes the height value of the point cloud in the plant protection area; determine the second point cloud height information of the target crop based on the first point cloud height information; identify the individual information of the target crop based on the image data and the second point cloud height information. Or

[0088] Acquire image data and digital surface model data of the plant protection area; determine first point cloud height information of the plant protection area based on the digital surface model data, the first point cloud height information including the height value of the point cloud in the plant protection area; determine second point cloud height information of the target crop based on the first point cloud height information; identify individual information of the target crop based on the image data and the second point cloud height information; control the operation equipment to perform plant protection operation on the target crop based on the individual information of the target crop.

[0089] 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.

[0090] 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.

[0091] 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. For example, 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.

[0092] 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.

[0093] 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.

[0094] 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, a server or a 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.

[0095] The above is only a preferred implementation 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 identifying crops, characterized in that: include: Obtain image data and digital surface model data of the plant protection area; Determine first point cloud height information in the plant protection area according to the digital surface model data, wherein the first point cloud height information includes a height value of a point cloud in the plant protection area; Determining the second point cloud height information of the target crop according to the first point cloud height information includes: taking the area where the height value of the point cloud corresponding to the first point cloud height information gradually decreases from the middle to the surrounding as the area where the target crop is located, and taking the first point cloud height information corresponding to the area where the target crop is located as the second point cloud height information; or, respectively comparing the first point cloud height information with a preset height information range, and taking the first point cloud height information falling within the preset height information range as the second point cloud height information; Identify the individual information of the target crops based on the image data and the second point cloud height information, including: inputting the image data and the second point cloud height information into a preset deep learning model for detection to obtain the position information and individual size information of each target crop, wherein the individual size information is used to characterize the outline size of the target crop when looking down.

2. The method according to claim 1, characterized in that The image data includes a two-dimensional RGB image.

3. The method according to claim 1, characterized in that After identifying the individual information of the target crop, the method further includes: Determining an operation route of the operation according to the location information of the target crop; Determining the dosage of the drug to be sprayed on the target crops according to the individual size information of the target crops; Plant protection operations are performed on the target crops according to the operation route and the dosage of the spraying medicine.

4. The method according to claim 1, characterized in that: The method further comprises: The position information of the target crop is determined in the three-dimensional coordinate system corresponding to the digital surface model data according to the second point cloud height information of the target crop.

5. A method for controlling an operating device, characterized in that: include: Obtain image data and digital surface model data of the plant protection area; Determine first point cloud height information in the plant protection area according to the digital surface model data, wherein the first point cloud height information includes a height value of a point cloud in the plant protection area; Determining the second point cloud height information of the target crop according to the first point cloud height information includes: taking the area where the height value of the point cloud corresponding to the first point cloud height information gradually decreases from the middle to the surrounding as the area where the target crop is located, and taking the first point cloud height information corresponding to the area where the target crop is located as the second point cloud height information; or, respectively comparing the first point cloud height information with a preset height information range, and taking the first point cloud height information falling within the preset height information range as the second point cloud height information; Identifying individual information of the target crop based on the image data and the second point cloud height information, including: inputting the image data and the second point cloud height information into a preset deep learning model for detection, obtaining position information and individual size information of each target crop, wherein the individual size information is used to characterize the outline size of the target crop when looking down; The operation equipment is controlled according to the individual information of the target crops to perform plant protection operations on the target crops.

6. A crop identification device, characterized in that: include: An acquisition module is used to acquire image data and digital surface model data of the plant protection area; A first determination module is used to determine first point cloud height information in the plant protection area according to the digital surface model data, wherein the first point cloud height information includes a height value of a point cloud in the plant protection area; The second determination module is used to determine the second point cloud height information of the target crop according to the first point cloud height information, including: taking the area where the height value of the point cloud corresponding to the first point cloud height information gradually decreases from the middle to the surrounding as the area where the target crop is located, and taking the first point cloud height information corresponding to the area where the target crop is located as the second point cloud height information; or, respectively comparing the first point cloud height information with a preset height information range, and taking the first point cloud height information falling within the preset height information range as the second point cloud height information; An identification module is used to identify the individual information of the target crop based on the image data and the second point cloud height information, including: inputting the image data and the second point cloud height information into a preset deep learning model for detection to obtain the position information and individual size information of each target crop, wherein the individual size information is used to characterize the outline size of the target crop when looking down.

7. A plant protection system, characterized in that: include: Surveying and mapping equipment, used for collecting image data and digital surface model data of the plant protection area, and sending the image data and the digital surface model data to the server; The server is used to determine first point cloud height information in the plant protection area according to the digital surface model data, wherein the first point cloud height information includes a height value of a point cloud in the plant protection area; It is also used to determine the second point cloud height information of the target crop based on the first point cloud height information, including: taking the area where the height value of the point cloud corresponding to the first point cloud height information gradually decreases from the middle to the surroundings as the area where the target crop is located, and taking the first point cloud height information corresponding to the area where the target crop is located as the second point cloud height information; or, respectively comparing the first point cloud height information with the preset height information range, and taking the first point cloud height information falling within the preset height information range as the second point cloud height information; It is also used to identify the individual information of the target crop based on the image data and the second point cloud height information, including: inputting the image data and the second point cloud height information into a preset deep learning model for detection, and obtaining the position information and individual size information of each of the target crops, and the individual size information is used to characterize the outline size when looking down at the target crop; The operation equipment communicates with the server and is used for performing plant protection operations on the target crops.

8. A 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 crop identification method according to any one of claims 1 to 4.

9. A processor, characterized in that: The processor is used to run a program, wherein the program executes the crop identification method according to any one of claims 1 to 4 when running.

Images