Crop identification method, device, equipment and storage medium

Abstract

The present invention discloses a method, device, equipment and storage medium for identifying crops. The method includes: sending a collection instruction to a drone so that the drone collects high-precision images of a target area, and fusing the high-precision images with a preset planting map according to the location information of the drone; analyzing the high-precision image data corresponding to each planting area to determine the current crop state corresponding to each planting area; obtaining the current time, and determining the expected crop state according to the crop variety, sowing time and current time corresponding to each planting area; comparing the current crop state with the expected crop state to obtain a crop identification result, thereby determining the growth state of the crops in each planting area. By analyzing the high-precision images collected by the drone to determine the crop growth state corresponding to each planting area, manual identification with great subjectivity and limitations is avoided, and the accuracy of crop growth state identification is improved.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a crop recognition method, device, equipment and storage medium. Background Art

[0002] Traditionally, crop growth conditions are generally identified manually, that is, professional gardeners or technical experts are used to judge the growth conditions of crops. This identification method relies heavily on the knowledge and experience of gardeners or technical experts, and has great subjectivity and limitations, which can easily lead to inaccurate identification of crop growth conditions; and when faced with large areas of crop growth, the identification efficiency is low.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present invention is to provide a crop identification method, device, equipment and storage medium, aiming to solve the technical problem that the existing crop growth conditions are identified manually, and the manual identification method has great subjectivity and limitations.

[0005] To achieve the above object, the present invention provides a method for identifying crops, the method comprising the following steps:

[0006] Sending a collection instruction to a drone, so that the drone collects a high-precision image of a target area according to the collection instruction, wherein the drone includes an image collection device and a positioning device;

[0007] Receiving the high-precision image collected by the drone, fusing the high-precision image with a preset planting map according to the location information of the drone, and generating a current planting map, wherein the current planting map includes a number of planting areas, high-precision image data corresponding to each planting area, crop varieties, and sowing time;

[0008] Analyze the high-precision image data corresponding to each planting area to determine the current crop status corresponding to each planting area;

[0009] Obtaining the current time, and determining the expected crop status according to the crop variety and sowing time corresponding to each planting area and the current time;

[0010] Comparing the current crop state with the expected crop state to obtain a crop identification result;

[0011] The growth status of the crops in each planting area is determined according to the crop identification result.

[0012] Optionally, before sending the collection instruction to the drone, the method further includes:

[0013] Obtaining location information of the target area;

[0014] Dividing the target area into a number of planting areas;

[0015] Obtain the crop varieties and sowing times planted in each planting area;

[0016] A preset planting map is constructed according to the location information, the plurality of planting areas, the crop varieties and the sowing time.

[0017] Optionally, the obtaining of the current time and determining the expected crop state according to the crop variety and sowing time corresponding to each planting area and the current time include:

[0018] Obtaining the current time, and determining the growth time corresponding to each planting area according to the current time and the sowing time corresponding to each planting area;

[0019] According to the crop varieties and growth time corresponding to each planting area, the corresponding expected crop status is searched from the preset storage area.

[0020] Optionally, analyzing the high-precision image data corresponding to each planting area to determine the current crop status corresponding to each planting area includes:

[0021] Binarization processing is performed on the high-precision image data corresponding to each planting area to obtain a binary image;

[0022] Determine the density information of crops in each planting area according to the binary image;

[0023] Extracting color parameters of high-precision image data corresponding to each planting area, and determining the maturity information of crops in each planting area according to the color parameters;

[0024] Determine the height information of crops in each planting area according to the flight altitude of the drone when executing the acquisition instruction and the internal and external parameters of the image acquisition device;

[0025] The current state of crops corresponding to each planting area is determined according to the density information, the maturity information and the height information.

[0026] Optionally, after determining the growth status of the crops in each planting area according to the crop identification result, the method further includes:

[0027] When it is determined according to the crop identification result that the growth state of the crops in the target planting area does not meet the preset requirements, determining the target position information of the target planting area;

[0028] Sending a target acquisition instruction to the drone according to the target position information, so that the drone flies at a preset altitude to collect close-range image data of the target planting area;

[0029] Determining characteristic information of crops in the target planting area according to the close-range image data;

[0030] Determine the nutritional deficiency elements corresponding to the crops in the target planting area based on the characteristic information.

[0031] Optionally, determining characteristic information of crops in the target planting area according to the close-range image data includes:

[0032] Extracting RGB color information of the close-range image data, and determining leaf color information of crops in the target planting area according to the RGB color information;

[0033] Determining leaf shape information of crops in the target planting area according to the close-range image data;

[0034] The leaf color information and the leaf shape information are used as characteristic information of crops in the target planting area.

[0035] Optionally, determining the nutritional deficiency elements corresponding to the crops in the target planting area according to the characteristic information includes:

[0036] Determining the corresponding performance symptoms of crops in the target planting area according to the characteristic information;

[0037] Find the corresponding nutritional deficiency elements based on the symptoms.

[0038] In addition, to achieve the above-mentioned purpose, the present invention further provides a crop identification device, the crop identification device comprising:

[0039] A collection module, used for sending a collection instruction to the drone, so that the drone collects a high-precision image of the target area according to the collection instruction, wherein the drone includes an image collection device and a positioning device;

[0040] A fusion module, used for receiving the high-precision image collected by the drone, fusing the high-precision image with a preset planting map according to the location information of the drone, and generating a current planting map, wherein the current planting map includes a number of planting areas, high-precision image data corresponding to each planting area, crop varieties, and sowing time;

[0041] An analysis module is used to analyze the high-precision image data corresponding to each planting area to determine the current crop status corresponding to each planting area;

[0042] A determination module is used to obtain the current time and determine the expected crop state according to the crop variety and sowing time corresponding to each planting area and the current time;

[0043] A comparison module, used for comparing the current crop state with the expected crop state to obtain a crop identification result;

[0044] The determination module is further used to determine the growth status of the crops in each planting area according to the crop identification result.

[0045] In addition, to achieve the above-mentioned purpose, the present invention also proposes a crop identification device, which includes: a memory, a processor, and a crop identification program stored in the memory and executable on the processor, and the crop identification program is configured to implement the steps of the crop identification method described above.

[0046] In addition, to achieve the above-mentioned purpose, the present invention further proposes a storage medium, on which a crop identification program is stored, and when the crop identification program is executed by a processor, the steps of the crop identification method described above are implemented.

[0047] The present invention sends a collection instruction to a drone so that the drone collects a high-precision image of a target area according to the collection instruction, wherein the drone includes an image collection device and a positioning device; receives the high-precision image collected by the drone, fuses the high-precision image with a preset planting map according to the location information of the drone, and generates a current planting map, wherein the current planting map includes a number of planting areas, high-precision image data corresponding to each planting area, crop varieties and sowing time; analyzes the high-precision image data corresponding to each planting area to determine the current crop state corresponding to each planting area; obtains the current time, and determines the expected crop state according to the crop variety, sowing time and current time corresponding to each planting area; compares the current crop state with the expected crop state to obtain a crop identification result; and determines the growth state of crops in each planting area according to the crop identification result. In the above manner, the high-precision image collected by the drone is fused with the preset planting map data, and the image data of each planting area is analyzed to determine the crop growth state corresponding to each planting area, thereby realizing automatic identification of the crop growth state, avoiding the use of manual identification with great subjectivity and limitations, and improving the accuracy of crop growth state identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a structural diagram of a crop identification device in a hardware operating environment involved in an embodiment of the present invention;

[0049] Figure 2 This is a schematic diagram of the process of the first embodiment of the crop identification method of the present invention;

[0050] Figure 3 This is a flow chart of a second embodiment of the crop identification method of the present invention;

[0051] Figure 4 It is a structural block diagram of the first embodiment of the crop identification device of the present invention.

[0052] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0053] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0054] Reference Figure 1 , Figure 1 The diagram is a structural diagram of a crop identification device in a hardware operating environment according to an embodiment of the present invention.

[0055] like Figure 1 As shown, the crop identification device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0056] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the crop identification device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0057] like Figure 1As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a crop identification program.

[0058] exist Figure 1 In the crop identification device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the crop identification device of the present invention can be set in the crop identification device, and the crop identification device calls the crop identification program stored in the memory 1005 through the processor 1001, and executes the crop identification method provided by the embodiment of the present invention.

[0059] The present invention provides a method for identifying crops. Figure 2 , Figure 2 Schematic diagram of the process of the first embodiment of the crop identification method of the present invention.

[0060] In this embodiment, the crop identification method includes the following steps:

[0061] Step S10: sending a collection instruction to the drone, so that the drone collects a high-precision image of the target area according to the collection instruction, wherein the drone includes an image collection device and a positioning device.

[0062] It can be understood that the executor of this embodiment is a crop identification device, which can be a processor, a computer, a server or a terminal device, or other devices with the same or similar functions, and this embodiment does not limit this.

[0063] It should be noted that the collection instruction includes scanning area information and altitude information. In a specific implementation, the storage area of ​​the crop identification device stores the location information of the target area to be scanned and the default altitude information. When the crop identification instruction input by the user is received, the collection instruction is sent to the drone according to the location information and the default altitude information of the target area.

[0064] It should be understood that the drone includes an image acquisition device, a positioning device, a flight device, and a communication device, wherein the communication device can be a wireless communication device for real-time communication with the crop identification device, or a wired communication device. After the drone acquires high-precision image data of the target area at a default height according to the acquisition instruction, the drone transmits the acquired high-precision image to the crop identification device when the user connects the drone to the crop identification device via a wire. The positioning device is used to locate the current position of the drone and send the current position to the flight device. The flight device is used to fly at a constant speed according to the default height and the position corresponding to the target area under the control of the acquisition instruction, and to make a position judgment based on the current position information acquired by the positioning device. The acquisition device is used to acquire high-precision images of a bird's-eye view during the flight of the drone, and the acquisition device is configured to acquire image data directly below.

[0065] Furthermore, before step S10, the method also includes: obtaining location information of the target area; dividing the target area into a number of planting areas; obtaining the crop varieties planted in each planting area and the sowing time; and constructing a preset planting map based on the location information, the several planting areas, the crop varieties and the sowing time.

[0066] It should be noted that before identifying the growth status of crops, the target area where crops are planted is calibrated in advance. In a specific implementation, an initial map of the target area to be scanned can be collected in advance by using a drone including a positioning device, so as to determine the location information of the target area, and store the location information of the target area in a preset storage area. The process of dividing the target area into several planting areas can be to divide the initial map into grids to obtain several planting areas. The process of dividing the target area into several planting areas can also be to divide the planting areas according to the variety of crops planted, and divide the target area according to the location information corresponding to the boundary line of the area where each crop variety is planted.

[0067] It should be understood that the crop varieties and sowing times are labeled by the user, the initial map framework is determined based on the location information and the division of the planting areas, and the corresponding crop varieties and sowing times are set in each planting area according to the labels set by the user, thereby constructing a preset planting map.

[0068] Step S20: Receive the high-precision image collected by the drone, merge the high-precision image with a preset planting map according to the location information of the drone, and generate a current planting map, wherein the current planting map includes several planting areas, high-precision image data corresponding to each planting area, crop varieties and sowing time.

[0069] It should be noted that the location information can be longitude and latitude information. The high-precision image is fused with the preset planting map based on the corresponding longitude and latitude information when the drone collects image data. When performing map fusion, the high-precision image collected by the drone is corrected according to the internal and external parameters of the acquisition device installed on the drone. The central image of multiple frames of high-precision images, the corresponding longitude and latitude when collecting data, and the longitude and latitude corresponding to the preset planting map are used as a benchmark to fuse the high-precision image with the preset planting map to obtain the current planting map. The current planting map includes the planting areas corresponding to the preset planting map and the crop varieties and sowing times corresponding to each planting area. The high-precision image is matched with each planting area to obtain high-precision image data corresponding to each planting area.

[0070] Step S30: Analyze the high-precision image data corresponding to each planting area to determine the current crop status corresponding to each planting area.

[0071] Specifically, the step S30 includes: binarizing the high-precision image data corresponding to each planting area to obtain a binary image; determining the density information of crops in each planting area based on the binary image; extracting the color parameters of the high-precision image data corresponding to each planting area, and determining the maturity information of the crops in each planting area based on the color parameters; determining the height information of the crops in each planting area based on the flight altitude when the UAV executes the collection instruction and the internal and external parameters of the image collection device; determining the current crop status corresponding to each planting area based on the density information, the maturity information and the height information.

[0072] It can be understood that the binarization process can be to calculate the average pixel value of the pixels, set the pixel values ​​greater than the average pixel value to 255, and set the pixel values ​​less than or equal to the average pixel value to 0. The density information of crops is determined according to the distribution position and number of pixel points with a pixel value of 255 in the binary image. In a specific implementation, clustering is performed on the binary images corresponding to each planting area, and the number of clusters is set according to a preset number. The preset number can be determined according to the median in the density information. For example, the normal number of crops growing in the planting area is 10, and the preset number is set to 10. After clustering according to the preset number, the number of pixel points with a pixel value of 255 in each class is determined. When the pixel points with a pixel value of 255 in each class exceed the preset value, it is determined that the crops in the planting area are dense; when the pixel points with a pixel value of 255 in each class do not exceed the preset value, it is determined that the crops in the planting area are sparse; in the preset number of classes, some have more pixel points with a pixel value of 255, while some have fewer pixel points with a pixel value of 255, and it is determined that the crops in the planting area are relatively sparse.

[0073] It should be noted that the color parameters can be RGB color values. The maturity of crops in each planting area is determined based on the RGB color values. The maturity parameters corresponding to each crop variety are pre-stored, such as leaf color, bud color, flower color, and fruit color, etc. The RGB color values ​​collected in the high-precision image are compared with the maturity parameters corresponding to the crop variety to determine the maturity information of crops in each planting area.

[0074] It should be understood that the preset storage area stores the number of frames collected by the drone when the drone is traveling at a constant speed when no crops are planted in each planting area. The ratio of the current planting area size to the unplanted area size is determined based on the number of frames collected by the drone's current collection device. The height information of the crops is determined based on the flight altitude, internal and external parameters, and the range ratio.

[0075] It should be noted that the density information, maturity information and height information of each planting area are stored in a pre-set format to generate the current crop status. The pre-set format can be a key-value format for subsequent search and call.

[0076] Step S40: Acquire the current time, and determine the expected crop status according to the crop variety and sowing time corresponding to each planting area and the current time.

[0077] It can be understood that the growth cycle corresponding to each crop variety is determined in advance based on the user's input information, and sample data corresponding to each growth cycle is collected and stored in a preset storage area as the expected crop state, so that the corresponding expected crop state can be found from the preset storage area when identifying the crop growth state.

[0078] Specifically, the step S40 includes: obtaining the current time, determining the growth time corresponding to each planting area according to the current time and the sowing time corresponding to each planting area; searching for the corresponding expected crop state from a preset storage area according to the crop variety and growth time corresponding to each planting area.

[0079] It can be understood that the expected crop state stored in the preset storage area corresponds to the crop variety and the growth time range. After determining the growth time based on the current time and the sowing time, the growth time range to which the growth time belongs is determined, and the expected crop state corresponding to the growth time range of the crop variety is searched from the preset storage area. The expected crop state can be the height, color, whether it blooms and bears fruit, etc. corresponding to the crop at this growth stage (growth time).

[0080] Step S50: Compare the current crop state with the expected crop state to obtain a crop identification result.

[0081] It should be noted that the maturity information and height information of each planting area are compared with the pre-stored expected crop status to determine whether the maturity information and height information of each planting area meet the preset requirements. The crop identification results include sparse crop growth, current maturity information inconsistent with expected maturity information, and height inconsistent with expected height.

[0082] Step S60: determining the growth status of the crops in each planting area according to the crop identification result.

[0083] It is understandable that whether the crops have problems such as low survival rate, slow growth or short growth can be determined based on the crop identification results.

[0084] In this embodiment, a collection instruction is sent to a drone so that the drone collects a high-precision image of the target area according to the collection instruction, wherein the drone includes an image collection device and a positioning device; the high-precision image collected by the drone is received, and the high-precision image is merged with a preset planting map according to the location information of the drone to generate a current planting map, wherein the current planting map includes several planting areas, high-precision image data corresponding to each planting area, crop varieties and sowing time; the high-precision image data corresponding to each planting area is analyzed to determine the current crop state corresponding to each planting area; the current time is obtained, and the expected crop state is determined according to the crop variety, sowing time and current time corresponding to each planting area; the current crop state is compared with the expected crop state to obtain a crop identification result; and the growth state of the crops in each planting area is determined according to the crop identification result. In the above manner, the high-precision image collected by the drone is merged with the preset planting map data, and the image data of each planting area is analyzed to determine the crop growth state corresponding to each planting area, so as to realize automatic identification of the crop growth state, avoid the use of manual identification with great subjectivity and limitations, and improve the accuracy of crop growth state identification.

[0085] refer to Figure 3 , Figure 3 FIG. 4 is a flow chart of a second embodiment of a method for identifying crops according to the present invention.

[0086] Based on the first embodiment, the crop identification method of this embodiment further includes, after step S60:

[0087] Step S601: when it is determined according to the crop identification result that the growth state of the crops in the target planting area does not meet the preset requirements, the target position information of the target planting area is determined.

[0088] It is understandable that when crops in a certain planting area are sparse or grow slowly or are short, it is determined that the growth status of the crops in the planting area does not meet the preset requirements, and the location information of the planting area is determined based on the current planting map.

[0089] Step S602: sending a target acquisition instruction to the drone according to the target position information, so that the drone flies at a preset altitude to acquire close-range image data of the target planting area.

[0090] It should be understood that the preset height is determined based on the height information of the crops in the target planting area. Specifically, the height of the crops in the target planting area can be added to the preset redundant height to obtain the preset height. According to the preset height and the target position information, the target collection instruction is sent to the UAV to control the UAV to fly at a constant speed at the preset height to collect close-range image data of the target planting area.

[0091] Step S603: determining characteristic information of crops in the target planting area according to the close-range image data.

[0092] Specifically, the step S603 includes: extracting the RGB color information of the close-range image data, and determining the leaf color information of the crops in the target planting area based on the RGB color information; determining the leaf shape information of the crops in the target planting area based on the close-range image data; and using the leaf color information and the leaf shape information as characteristic information of the crops in the target planting area.

[0093] It should be noted that determining the leaf color information of crops in the target planting area is to determine whether the crops have problems with yellowing leaves, leaf spots, and leaf withering, and determining the leaf shape information of crops in the target planting area is to determine whether the crops have problems with leaf withering and leaf rot.

[0094] Step S604: Determine the nutritional deficiency elements corresponding to the crops in the target planting area according to the characteristic information.

[0095] Specifically, the step S604 includes: determining the corresponding performance symptoms of the crops in the target planting area according to the characteristic information; and searching for the corresponding nutritional deficiency elements according to the performance symptoms.

[0096] It should be understood that whether the crops have symptoms such as leaf yellowing, leaf spots, leaf wilting and leaf rot is determined based on the leaf color information and leaf shape information of the crops. For example, when the number of leaf yellowing feature points in the leaf color information exceeds a preset proportion, it is determined whether the crops have symptoms of leaf yellowing.

[0097] It should be noted that the preset storage area stores nutrient deficiency elements and corresponding symptoms. For example, when crops are iron deficient, the plants will show symptoms such as dwarfing, yellowing, and chlorosis. The symptoms of the crops are compared with the symptoms corresponding to the nutrient deficiency elements one by one, so as to find the nutrient deficiency elements corresponding to the symptoms.

[0098] It should be understood that after step S60, the method further includes: obtaining the historical growth status of crops in each planting area, generating a growth curve chart based on the historical growth status, and scoring the seeds planted in each planting area based on the generated growth curve chart.

[0099] This embodiment determines the target location information of the target planting area when it is determined according to the crop recognition result that the growth status of the crops in the target planting area does not meet the preset requirements; sends a target acquisition instruction to the drone according to the target location information, so that the drone flies at a preset height and collects close-range image data of the target planting area; determines the characteristic information of the crops in the target planting area according to the close-range image data; and determines the nutritional deficiency elements corresponding to the crops in the target planting area according to the characteristic information. Through the above method, after determining the growth status of the crops corresponding to each planting area, the drone is controlled again to collect close-range image data, and the growth status of the crops is analyzed more carefully according to the close-range image data to determine the nutritional elements missing from the crops, so as to provide a reference basis for improving the growth status of the crops, realize automatic identification of the growth status of the crops, avoid the use of manual identification with great subjectivity and limitations, and improve the accuracy of identifying the growth status of the crops.

[0100] In addition, an embodiment of the present invention further provides a storage medium, on which a crop identification program is stored. When the crop identification program is executed by a processor, the steps of the crop identification method described above are implemented.

[0101] Reference Figure 4 , Figure 4 It is a structural block diagram of the first embodiment of the crop identification device of the present invention.

[0102] like Figure 4 As shown, the crop identification device proposed in the embodiment of the present invention includes:

[0103] The acquisition module 10 is used to send an acquisition instruction to the drone, so that the drone acquires a high-precision image of the target area according to the acquisition instruction, wherein the drone includes an image acquisition device and a positioning device.

[0104] The fusion module 20 is used to receive the high-precision image collected by the drone, fuse the high-precision image with a preset planting map according to the location information of the drone, and generate a current planting map, wherein the current planting map includes several planting areas, high-precision image data corresponding to each planting area, crop varieties and sowing time.

[0105] The analysis module 30 is used to analyze the high-precision image data corresponding to each planting area to determine the current crop status corresponding to each planting area.

[0106] The determination module 40 is used to obtain the current time and determine the expected crop status according to the crop variety and sowing time corresponding to each planting area and the current time.

[0107] The comparison module 50 is used to compare the current crop state with the expected crop state to obtain a crop identification result.

[0108] The determination module 40 is further configured to determine the growth status of the crops in each planting area according to the crop identification result.

[0109] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0110] In this embodiment, a collection instruction is sent to a drone so that the drone collects a high-precision image of the target area according to the collection instruction, wherein the drone includes an image collection device and a positioning device; the high-precision image collected by the drone is received, and the high-precision image is merged with a preset planting map according to the location information of the drone to generate a current planting map, wherein the current planting map includes several planting areas, high-precision image data corresponding to each planting area, crop varieties and sowing time; the high-precision image data corresponding to each planting area is analyzed to determine the current crop state corresponding to each planting area; the current time is obtained, and the expected crop state is determined according to the crop variety, sowing time and current time corresponding to each planting area; the current crop state is compared with the expected crop state to obtain a crop identification result; and the growth state of the crops in each planting area is determined according to the crop identification result. In the above manner, the high-precision image collected by the drone is merged with the preset planting map data, and the image data of each planting area is analyzed to determine the crop growth state corresponding to each planting area, so as to realize automatic identification of the crop growth state, avoid the use of manual identification with great subjectivity and limitations, and improve the accuracy of crop growth state identification.

[0111] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0112] In addition, for technical details not fully described in this embodiment, reference can be made to the crop identification method provided in any embodiment of the present invention, and will not be repeated here.

[0113] In one embodiment, the acquisition module 10 is also used to obtain the location information of the target area, divide the target area into several planting areas, obtain the crop varieties planted in each planting area and the sowing time, and construct a preset planting map based on the location information, the several planting areas, the crop varieties and the sowing time.

[0114] In one embodiment, the determination module 40 is also used to obtain the current time, determine the growth time corresponding to each planting area according to the current time and the sowing time corresponding to each planting area, and search the corresponding expected crop state from a preset storage area according to the crop variety and growth time corresponding to each planting area.

[0115] In one embodiment, the analysis module 30 is also used to binarize the high-precision image data corresponding to each planting area to obtain a binary image, determine the density information of crops in each planting area based on the binary image, extract the color parameters of the high-precision image data corresponding to each planting area, determine the maturity information of the crops in each planting area based on the color parameters, determine the height information of the crops in each planting area based on the flight altitude of the UAV when executing the collection instruction and the internal and external parameters of the image collection device, and determine the current crop status corresponding to each planting area based on the density information, the maturity information and the height information.

[0116] In one embodiment, the crop identification device further includes a nutrition deficiency analysis module;

[0117] The nutrient deficiency analysis module is used to determine the target position information of the target planting area when it is determined according to the crop identification result that the growth status of the crops in the target planting area does not meet the preset requirements, send a target acquisition instruction to the drone according to the target position information, so that the drone flies at a preset altitude to collect close-range image data of the target planting area, determine the characteristic information of the crops in the target planting area according to the close-range image data, and determine the nutrient deficiency elements corresponding to the crops in the target planting area according to the characteristic information.

[0118] In one embodiment, the nutrient deficiency analysis module is also used to extract RGB color information of the close-range image data, determine leaf color information of crops in the target planting area based on the RGB color information, determine leaf shape information of crops in the target planting area based on the close-range image data, and use the leaf color information and the leaf shape information as characteristic information of crops in the target planting area.

[0119] In one embodiment, the nutrient deficiency analysis module is further used to determine the corresponding symptoms of crops in the target planting area according to the characteristic information, and to search for corresponding nutrient deficiency elements according to the symptoms.

[0120] In addition, it should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0121] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0122] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0123] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for identifying crops, characterized in that: The crop identification method comprises: Sending a collection instruction to a drone, so that the drone collects a high-precision image of a target area according to the collection instruction, wherein the drone includes an image collection device and a positioning device; Receiving the high-precision image collected by the drone, fusing the high-precision image with a preset planting map according to the location information of the drone, and generating a current planting map, wherein the current planting map includes a number of planting areas, high-precision image data corresponding to each planting area, crop varieties, and sowing time; Analyze the high-precision image data corresponding to each planting area to determine the current crop status corresponding to each planting area; The analyzing of the high-precision image data corresponding to each planting area to determine the current crop status corresponding to each planting area includes: Binarization processing is performed on the high-precision image data corresponding to each planting area to obtain a binary image; Determine the density information of crops in each planting area according to the binary image; Extracting color parameters of high-precision image data corresponding to each planting area, and determining the maturity information of crops in each planting area according to the color parameters; Determine the height information of crops in each planting area according to the flight altitude of the drone when executing the acquisition instruction and the internal and external parameters of the image acquisition device; Determine the current crop status corresponding to each planting area according to the density information, the maturity information and the height information; Obtaining the current time, and determining the expected crop status according to the crop variety and sowing time corresponding to each planting area and the current time; Comparing the current crop state with the expected crop state to obtain crop identification results, the crop identification results including: sparse crop growth, current maturity information not matching expected maturity information, and height not matching expected height; The growth status of the crops in each planting area is determined according to the crop identification results.

2. The crop identification method according to claim 1, characterized in that: Before sending the collection instruction to the drone, the method further includes: Obtaining location information of the target area; Dividing the target area into a number of planting areas; Obtain the crop varieties and sowing times planted in each planting area; A preset planting map is constructed according to the location information, the plurality of planting areas, the crop varieties and the sowing time.

3. The crop identification method according to claim 1, characterized in that: The obtaining of the current time and determining the expected crop state according to the crop variety and sowing time corresponding to each planting area and the current time include: Obtaining the current time, and determining the growth time corresponding to each planting area according to the current time and the sowing time corresponding to each planting area; According to the crop varieties and growth time corresponding to each planting area, the corresponding expected crop status is searched from the preset storage area.

4. The crop identification method according to claim 1, characterized in that: After determining the growth status of the crops in each planting area according to the crop identification result, the method further includes: When it is determined according to the crop identification result that the growth state of the crops in the target planting area does not meet the preset requirements, determining the target position information of the target planting area; Sending a target acquisition instruction to the drone according to the target position information, so that the drone flies at a preset altitude to collect close-range image data of the target planting area; Determining characteristic information of crops in the target planting area according to the close-range image data; Determine the nutritional deficiency elements corresponding to the crops in the target planting area based on the characteristic information.

5. The crop identification method according to claim 4, characterized in that: Determining the characteristic information of the crops in the target planting area according to the close-range image data includes: Extracting RGB color information of the close-range image data, and determining leaf color information of crops in the target planting area according to the RGB color information; Determining leaf shape information of crops in the target planting area according to the close-range image data; The leaf color information and the leaf shape information are used as characteristic information of crops in the target planting area.

6. The crop identification method according to claim 4, characterized in that: Determining the nutritional deficiency elements corresponding to the crops in the target planting area according to the characteristic information includes: Determining the corresponding performance symptoms of crops in the target planting area according to the characteristic information; Find the corresponding nutritional deficiency elements based on the symptoms.

7. A crop identification device, characterized in that: The crop identification device comprises: A collection module, used for sending a collection instruction to the drone, so that the drone collects a high-precision image of the target area according to the collection instruction, wherein the drone includes an image collection device and a positioning device; A fusion module, used for receiving the high-precision image collected by the drone, fusing the high-precision image with a preset planting map according to the location information of the drone, and generating a current planting map, wherein the current planting map includes a number of planting areas, high-precision image data corresponding to each planting area, crop varieties, and sowing time; An analysis module is used to analyze the high-precision image data corresponding to each planting area to determine the current crop status of each planting area; the analysis of the high-precision image data corresponding to each planting area to determine the current crop status of each planting area includes: binarizing the high-precision image data corresponding to each planting area to obtain a binarized image; determining the density information of the crops in each planting area according to the binarized image; extracting the color parameters of the high-precision image data corresponding to each planting area, and determining the maturity information of the crops in each planting area according to the color parameters; determining the height information of the crops in each planting area according to the flight altitude of the UAV when executing the collection instruction and the internal and external parameters of the image collection device; determining the current crop status of each planting area according to the density information, the maturity information and the height information; A determination module is used to obtain the current time and determine the expected crop state according to the crop variety and sowing time corresponding to each planting area and the current time; A comparison module, used for comparing the current crop state with the expected crop state to obtain a crop identification result, wherein the crop identification result includes: sparse crop growth, current maturity information does not match the expected maturity information, and height does not match the expected height; The determination module is further used to determine the growth status of the crops in each planting area according to the crop identification result.

8. A crop identification device, characterized in that: The device comprises: a memory, a processor, and a crop identification program stored in the memory and executable on the processor, wherein the crop identification program is configured to implement the crop identification method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores a crop identification program, and when the crop identification program is executed by the processor, the crop identification method according to any one of claims 1 to 6 is implemented.

Images