Plant cultivation method, apparatus and system
By analyzing plant height using an aerial field inspection platform and a neural network model, areas were divided and fertilization plans were formulated, solving the problem of excessive differences in plant height in unmanned farms and achieving normal growth of plant populations and high-yield harvesting.
Patent Information
- Application Number
- PCT/CN2024/075546
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-09-20
- Filing Date
- 2024-02-02
- Publication Date
- 2025-11-20
AI Technical Summary
In unmanned farms, excessive differences in plant height make it difficult for large harvesters to harvest normally, affecting the overall yield of the plant population.
By acquiring plant images through an aerial field inspection platform, analyzing plant height curves and planting information using a neural network model, dividing height zones, and developing targeted fertilization plans, including aerial fertilization by drones and ground fertilization by drip irrigation systems, the height difference of the plant population is controlled within a reasonable range.
Effectively controlling the height difference of plant groups ensures normal harvesting by large harvesters, increases the overall yield of plant groups, and realizes a virtuous cycle of plant cultivation in unmanned farms.
Smart Images
Figure CN2024075546_20112025_PF_FP_ABST
Abstract
Description
Method, device and system for plant cultivation
[0001] The present application claims priority to the Chinese patent application No. 202311213783.7, filed on September 20, 2023, and entitled "Method, device and system for plant cultivation", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD
[0002] The present application relates to the field of agricultural intelligent control, and more particularly, to a method, device and system for plant cultivation. BACKGROUND
[0003] With the advancement of agricultural automation, informatization and intelligentization technologies, unmanned farms are playing an increasingly important role. And with the gradual maturity of the related technologies of unmanned farms, the planting scale of unmanned farms is also gradually expanding.
[0004] Based on the agricultural experience, if the heights of the field crops are uneven, it will be difficult for large harvesters to harvest normally, and it will also lead to uneven distribution of the growth state of the plant population, thereby affecting the overall yield of the plant population. Therefore, it is crucial to reasonably control the growth height of the field crops in the unmanned farm, and it also faces great challenges.
[0005] In view of this, a method for plant cultivation applied to unmanned farms is urgently needed to be developed.
[0006] SUMMARY
[0007] The present application provides a method, device and system for plant cultivation, which can determine whether the height difference of the plant population is reasonable in the scenario of the unmanned farm, and determine and implement the cultivation scheme for the plant population of different heights in the case of unreasonable determination result.
[0008] In a first aspect, a method for plant cultivation is provided, and is applied to unmanned farms. The method comprises: performing a first cultivation operation on a first plant population planted in a first area, the first cultivation operation comprising: obtaining a first image by an aerial field inspection platform, and inputting the first image into a first model to output a first height surface and first planting information, wherein the aerial field inspection platform comprises a drone or a tethered balloon, the first image comprises the first plant population, and the first planting information comprises a plant variety and a planting density of the first plant population; determining a first reference height according to the first height surface, the first reference height being a mode of a first height set, the first height set comprising height values corresponding to a plurality of points constituting the first height surface; inputting the first reference height, the first height surface, and the first planting information into a second model to output a first deviation value, wherein the first deviation value is used to represent an expected value of a first height range of the first plant population, and the second model is configured with a first standard table comprising a first correspondence relationship among the first height surface, the first planting information, and the first deviation value; in a case where the first height range is greater than the first deviation value, dividing the first height surface into a plurality of height regions in a vertical direction according to the first deviation value to obtain a second height surface of each height region; inputting the first planting information and the second height surface of each height region into a third model to output a first cultivation scheme, the first cultivation scheme being used to control the first height range to be within the first deviation value, and the first cultivation scheme comprising a fertilization scheme corresponding to the first plant population in each height region, the fertilization scheme comprising a fertilization mode and a planned cultivation duration, and the fertilization mode comprising an aerial fertilization mode based on a drone and / or a ground fertilization mode based on a drip irrigation system; and after the planned cultivation duration, re-executing the first cultivation operation.
[0009] For example, the first image can be a photo image, a video image, a multispectral image, an ultrasonic image, or a laser point cloud image.
[0010] For example, in a case where the first height range is greater than the first deviation value, the height difference of the plant population is unreasonable, so a cultivation scheme for the plant population at different heights is determined and implemented.
[0011] For example, the first model can be a pre-trained neural network model. After the first image is input into the first model, the first model can extract a plurality of vertices of the first plant population in the first image, connect the plurality of vertices, and thus form the first height surface, and output the first height surface. In addition, the first model can also extract plant features of the first plant population in the first image and corresponding semantic information, so as to determine and output the planting density of the first plant population and the plant variety of the first plant, that is, to determine and output the first planting information.
[0012] For example, the second model can be a pre-trained neural network model, which is trained based on the first standard table. The first standard table can be determined based on historical cultivation experience, which includes expert guidance information for different plant varieties, different planting densities, and different reference heights of plants. The guidance information can be a height deviation value of the plant population for the planting scenario.
[0013] For example, the third model can be a pre-trained expert model. The model performs a plurality of iteration cycles of calculation based on the input first planting information and the second height curve of each height region, and finally solves a convergence result. The convergence result can be used to indicate the corresponding cultivation scheme.
[0014] For example, after the first cultivation operation is re-executed, if it is determined that the first height range is less than or equal to the first deviation value, the corresponding first cultivation scheme does not need to be further generated, and a preset general cultivation scheme can be adopted. The general cultivation scheme can be a cultivation scheme determined at the beginning of planting. As can be seen, the first cultivation scheme proposed in the embodiment of the application is a response measure taken for abnormal plant growth conditions to restore the plant growth state to normal. If it is determined that the first height range is still greater than the first deviation value, the subsequent operation is continued until the first height range is less than or equal to the first deviation value.
[0015] Based on the above technical solution, the unmanned farm can effectively control the height of the plant population in the specified area, so that their height and height range are within a reasonable deviation value, so that the large harvester can normally harvest the plant population, and the plant population can grow normally, which helps to increase the overall yield of the plant population. And periodically repeat the cultivation operation, according to the new condition of plant growth, formulate a new cultivation scheme, realize the benign internal circulation of the unmanned farm plant cultivation.
[0016] In combination with the first aspect, in some implementations of the first aspect, according to the first cultivation scheme, a first prescription map is generated, which is used to represent the amount of fertilizer required for spraying in each height region for the first plant population.
[0017] Based on the above technical solution, the cultivation scheme is quantified in the form of a prescription map, so that the unmanned farm automatic equipment can better implement the cultivation scheme.
[0018] In some implementations of the first aspect, when the application mode comprises an unmanned aerial vehicle (UAV)-based aerial fertilization mode, first control information is determined according to the first prescription map and the range of the first area, the first control information comprising a starting point position of the UAV, a spraying height, a flight speed at the time of spraying, a plurality of waypoints to be reached in sequence, and a required amount of fertilizer to be sprayed in each segment of a flight path; and the first control information is sent to the UAV.
[0019] Based on the above technical solution, the flight points, the amount of fertilizer, and other control quantities of the UAV can be determined based on the determined cultivation scheme, and the UAV is instructed to perform the corresponding cultivation work through the control information, so as to control the growth rate of the plant population in the specified sub-area, and further to control the height of the plant population in the entire area and make the height range within the expected deviation.
[0020] In some implementations of the first aspect, a valve area set corresponding to a dynamic wheel irrigation area of a drip irrigation system is determined according to the first prescription map and the range of the first area; second control information is determined according to the drip irrigation pipe network capacity of the drip irrigation system, pump parameters, and historical full-network pressure distribution, the second control information comprising a control quantity for each valve in the valve area set and a corresponding fertilizer concentration, so that the drip irrigation system performs wheel irrigation work with a high-to-low fertilizer concentration; and the second control information is sent to the drip irrigation system.
[0021] Based on the above technical solution, the control quantity of the valve set of the drip irrigation system can be determined based on the determined cultivation scheme, and the drip irrigation system is instructed to perform the corresponding cultivation work through the control information, so as to control the growth rate of the plant population in the specified sub-area, and further to control the height of the plant population in the entire area and make the height range within the expected deviation.
[0022] In a second aspect, a plant cultivation system is provided, which is applied to an unmanned farm, and comprises:
[0023] A total control center is configured to instruct the system to perform a first cultivation operation on a first plant population planted in a first area, and the total control center comprises:
[0024] An aerial field inspection platform is configured to obtain a first image comprising the first plant population, and the aerial field inspection platform comprises a UAV or a tethered balloon;
[0025] A digital image processing device is configured to input the first image into a first model and output a first height surface and first planting information, the first planting information comprising a plant variety and a planting density of the first plant population;
[0026] The data processing device is configured to determine a first reference height based on the first height curve, the first reference height being a mode of a first height set, the first height set including height values corresponding to the plurality of points forming the first height curve; input the first reference height, the first height curve, and the first planting information into a second model, and output a first deviation value, the first deviation value representing an expected value of a first height range of the first plant population, the second model being configured with a first standard table including a first correspondence relationship among the first height curve, the first planting information, and the first deviation value; and in a case where the first height range is greater than the first deviation value, divide the first height curve into a plurality of height regions according to the first deviation value, to obtain a second height curve of each height region.
[0027] The expert system is configured to input the first planting information and the second height curve of each height region into a third model, and output a first cultivation scheme, the first cultivation scheme being used in a case where the first height range is within the first deviation value, the first cultivation scheme including a fertilization scheme corresponding to the first plant population in each height region, the fertilization scheme including a fertilization mode and a planned cultivation duration, and the fertilization mode including an aerial fertilization mode based on a UAV and / or a ground fertilization mode based on a drip irrigation system.
[0028] The total control center is further configured to re-execute the first cultivation operation after the planned cultivation duration.
[0029] With reference to the second aspect, in some implementations of the second aspect, the expert system is further configured to:
[0030] generate a first prescription map based on the first cultivation scheme, the first prescription map representing a required amount of fertilizer to be sprayed for the first plant population in each height region.
[0031] With reference to the second aspect, in some implementations of the second aspect, the system further includes:
[0032] The remote control device is configured to, in a case where the fertilization mode includes the aerial fertilization mode based on the UAV, determine first control information based on the first prescription map and a range of the first region, the first control information including a starting point position of the UAV, a spraying height, a flight speed at the time of spraying, a plurality of waypoints to be reached in sequence, and a required amount of fertilizer to be sprayed in each flight path; and send the first control information to the UAV.
[0033] With reference to the second aspect, in some implementations of the second aspect, the remote control device is further configured to:
[0034] According to the first prescription map and the range of the first area, a valve area set corresponding to a dynamic wheel irrigation area of the drip irrigation system is determined; according to the drip irrigation pipe network capacity of the drip irrigation system, the water pump parameters and the historical full-network pressure distribution, second control information is determined, the second control information including a control amount and a corresponding fertilizer concentration for each valve in the valve area set, so that the drip irrigation system performs wheel irrigation work with high fertilizer concentration first and low fertilizer concentration later; and the second control information is sent to the drip irrigation system.
[0035] In a third aspect, a device for plant cultivation is provided, including a processor and a memory, wherein the processor and the memory are connected, the memory is configured to store program code, and the processor is configured to invoke the program code to execute any one of the methods in the possible implementation manners of the method design of the first aspect.
[0036] In a fourth aspect, a chip system is provided, which is applied to an electronic device; the chip system includes one or more interface circuits and one or more processors; the interface circuit and the processor are interconnected through a circuit; the interface circuit is configured to echo a signal from a memory of the electronic device and send the signal to the processor, the signal including computer instructions stored in the memory; when the processor executes the computer instructions, the electronic device executes any one of the methods in the possible implementation manners of the method design of the first aspect.
[0037] In a fifth aspect, a computer readable storage medium is provided, which stores a computer program or instructions for implementing any one of the methods in the possible implementation manners of the method design of the first aspect.
[0038] In a sixth aspect, a computer program product is provided, including a computer program or instructions, which, when executed on a computer, causes the computer to execute any one of the methods in the possible implementation manners of the method design of the first aspect. BRIEF DESCRIPTION OF DRAWINGS
[0039] FIG. 1 is a schematic block diagram of a system 100 for plant cultivation according to an embodiment of the present application.
[0040] FIG. 2 is a schematic block diagram of a method for plant cultivation according to an embodiment of the present application.
[0041] FIG. 3 is a schematic diagram of dividing a height area according to an embodiment of the present application.
[0042] FIG. 4 is a schematic block diagram of a method for implementing a fertilization scheme according to an embodiment of the present application.
[0043] FIG. 5 is a schematic block diagram of another method for implementing a fertilization scheme according to an embodiment of the present application.
[0044] FIG. 6 is a schematic block diagram of another system for plant cultivation 600 according to embodiments of the present application. DETAILED DESCRIPTION
[0045] In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" herein is a description of the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can mean that A exists alone, A and B exist together, and B exists alone. In the present application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or the like means any combination of the items, including any combination of single item or multiple items. For example, at least one of a, b, or c can mean a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.
[0046] In the embodiments of the present application, the prefix words such as "first", "second" are used only to distinguish different description objects, and have no limiting effect on the position, order, priority, quantity or content of the described objects. The use of ordinal words such as ordinal words in the embodiments of the present application does not limit the described objects, and the description of the described objects should be seen in the context of the claims or embodiments, and should not be construed as redundant limitations because of the use of such prefix words.
[0047] The technical solutions in the embodiments of the present application will be described below with reference to the drawings.
[0048] An unmanned farm refers to a kind of all-weather, all-process, and all-space unmanned production and operation mode in which all farm production and management tasks are completed through remote control of farm facilities, equipment, and machinery or autonomous decision and autonomous operation of intelligent equipment and robots by using new generation information technologies such as Internet of Things, big data, artificial intelligence, 5th generation (5G) communication system, and robot technology without human entering the farm.
[0049] In the process of plant cultivation, it is crucial to control the height difference between plants in the field. Because large harvesters have high requirements for the height consistency of the harvested objects, in addition, if the height difference between plants is too large, the shorter plants will not receive sufficient light, which will cause the growth conditions of the shorter plants and the normally growing plants to be too different, and thus will affect the overall yield of the plant population.
[0050] In view of this, the embodiments of the present application propose a plant cultivation method, device and system, which are applied to unmanned farms to obtain the growth height of a plant population planted in a specified area, analyze the growth height, generate a cultivation strategy for the plant population in the area, and instruct relevant equipment to execute the strategy.
[0051] FIG. 1 is a schematic block diagram of a plant cultivation system 100 according to an embodiment of the present application.
[0052] In some possible embodiments, the system 100 described above includes a collection device 110, a data processing device 120, an intelligent decision device 130 and an automated device 140. These devices can be connected through a wireless network to realize data interaction between the devices.
[0053] The collection device 110 is mainly used to collect relevant data of the plant population and transmit the data to the data processing device 120 and the intelligent decision device 130. The collection device 110 includes a monocular camera, a binocular camera, a aerial unmanned aerial vehicle or a millimeter wave radar, etc.
[0054] The data processing device 120 is mainly used to process and analyze the relevant data of the plant population received from the collection device 110, determine the growth condition of the plant population, such as the height range of the plant population, the plant height surface information of the plant population, etc., and transmit the processing result to the decision device 130.
[0055] In some possible embodiments, the data processing device 120 described above can include a neural network model dedicated to digital image processing, and based on the neural network model, the extraction and analysis of image features are realized, and the analysis result is used to represent the growth condition of the plant population.
[0056] The decision device 130 is mainly used to generate a cultivation scheme for the current plant population based on the received data, and transmit the cultivation scheme to the automated device 140.
[0057] In some possible embodiments, the decision device 130 includes a neural network model dedicated to decision making, and stores a crop cultivation experience library, which saves corresponding plant cultivation schemes under different planting scenarios.
[0058] The automated device 140 is mainly used to perform specified cultivation work, such as aerial fertilizer spraying and ground fertilization, based on the received cultivation scheme. The automated device 140 includes agricultural machinery endowed with specified functions, such as agricultural unmanned aerial vehicles, irrigation systems, etc.
[0059] Based on the system 100 described above, the embodiments of the present application propose a plant cultivation method.
[0060] FIG. 2 is a schematic block diagram of a method for cultivating provided by an embodiment of the present application. The method can be applied to an unmanned farm.
[0061] It should be understood that the unmanned farm is configured with automated equipment for cultivating plants.
[0062] S210: performing a first cultivating operation on a first plant population planted in a first area.
[0063] The flow of the first cultivating operation is as follows:
[0064] S211: obtaining a first image by an aerial field inspection platform, inputting the first image into a first model, and outputting a first height surface and first planting information.
[0065] The aerial field inspection platform includes a drone or a tethered balloon, the first image includes the first plant population, and the first planting information includes plant varieties and planting density of the first plant population.
[0066] In some possible embodiments, the first image can be a photo image or a video image, or the first image can also be a multispectral image, an ultrasonic image, or a laser point cloud image including visible light, NDVI, and the like.
[0067] It should be understood that the plant height refers to the distance between the root neck of the plant and the top of the plant, where the top refers to the top of the main stem of the plant.
[0068] In some possible embodiments, the first model can be a pre-trained neural network model. After the first image is input into the first model, the first model can extract a plurality of vertices of the first plant population in the first image, connect the plurality of vertices, and thus form the first height surface, and output the first height surface. In addition, the first model can also extract plant features and corresponding semantic information of the first plant population in the first image, so as to determine and output the planting density of the first plant population and the plant varieties of the first plant, that is, to determine and output the first planting information.
[0069] In some possible embodiments, the heights of the plurality of first plants can be obtained by the acquisition device 110 in the system 100.
[0070] S212: determining a first reference height according to the first height surface.
[0071] The first reference height is the mode of a first height set, and the first height set includes height values corresponding to a plurality of points forming the first height surface.
[0072] It should be understood that the first reference height described above can be used to represent an expected height that the first plant population should reach under normal growth conditions.
[0073] S213: input the first reference height, the first height curve, and the first planting information into a second model, and output a first deviation value.
[0074] The first deviation value is used to represent an expected value of a first height range of the first plant population, and the first height range is used to represent a height difference between the tallest plant and the shortest plant in the first plant population. The second model is configured with a first standard table including a first correspondence relationship between the first height curve, the first planting information, and the first deviation value.
[0075] In some possible embodiments, the second model described above can be a pre-trained neural network model, and the second model is trained based on the first standard table described above. The first standard table can be determined by historical cultivation experience, and the historical cultivation experience includes cultivation guidance information provided by an expert for different plant varieties, different planting densities, and different reference heights of plants in a planting scenario. The cultivation guidance information can be a height deviation value of a plant population in the planting scenario.
[0076] S214: in a case where the first height range is greater than the first deviation value, the first height curve is divided into a plurality of height regions according to the first deviation value, to obtain a second height curve of each height region.
[0077] FIG. 3 is a schematic diagram of dividing height regions according to an embodiment of the present application.
[0078] In some possible embodiments, the interval length corresponding to the height region can be equal to the first deviation value, that is, as shown in the example of FIG. 3, or can be a multiple of the first deviation value. The multiple can be an integer multiple or a non-integer multiple compared with the first deviation value.
[0079] As shown in FIG. 3, the first height curve is divided into three second height curves in three height regions, that is, the second height curve in each height region corresponds to a part of the first height curve. The dividing surface of the three height regions is a plane perpendicular to the direction of gravity, that is, a cross section used to divide the first height curve.
[0080] In some possible embodiments, in a case where the first height range is less than or equal to the first deviation value, it indicates that the growth state of the first plant population is good, and no special cultivation plan needs to be taken for the first plant population. After a preset first time length, the above S210 can be re-executed. Therefore, the plant cultivation method proposed in the embodiments of the present application is a long-term and repetitive method. Based on the scheme, the growth state of the plant population can be observed regularly, and whether the growth state of the plant population is good can be compared and found in a timely manner.
[0081] S215: input the first planting information and the second height surface of each height region into a third model, and output a first cultivation scheme.
[0082] The first cultivation scheme is used to control the first height range to be within the first deviation value, and the first cultivation scheme includes a corresponding fertilization scheme of the first plant population in each height region. The fertilization scheme includes a fertilization mode and a planned cultivation time length, and the fertilization mode includes an unmanned aerial vehicle-based aerial fertilization mode and / or a drip irrigation system-based ground fertilization mode.
[0083] In some possible embodiments, the third model can be a pre-trained expert model. Based on the input first planting information and the second height surface of each height region, the model performs a plurality of iteration cycles of calculation, and finally calculates a convergence result. The convergence result can be used to indicate the corresponding cultivation scheme.
[0084] It should be understood that, in a case where the boundary line of the height region is determined, the height information of the boundary line of the height region is also determined. The height information can be extracted by the third model and used as a basis for determining the first cultivation scheme.
[0085] In addition, the boundary line of the height region also implies that the height region corresponds to a lateral range region of the first region, and the corresponding first plant population in the lateral range region can be determined. Similarly, the information can also be extracted by the third model and used as a basis for determining the first cultivation scheme.
[0086] In some possible embodiments, referring to FIG. 3, in the cultivation scenario, the first height surface is divided into three height regions. For the convenience of description, the three height regions are sequentially recorded as a first height region, a second height region and a third height region in order from low to high.
[0087] When the first reference height falls into the second height region, it can be indicated that the first plant has a good growth state and a reasonable plant height, and the first plant with a height in the first height region has a poor growth state and a too low plant height, and the first plant with a height in the third height region has a poor growth state and a too high plant height. Therefore, in the first cultivation scheme, for the first plant population corresponding to the first height region, the amount of fertilizer applied needs to be appropriately increased to make the height of the first plant reach the standard height interval; for the first plant population corresponding to the second height region, the amount of fertilizer applied does not need to be adjusted to make the first plant maintain the current growth state and grow normally; and for the first plant population corresponding to the third height region, the amount of fertilizer applied needs to be appropriately reduced, or a growth inhibitor corresponding to the crop variety needs to be appropriately applied to make the height of the first plant return to the standard height interval.
[0088] When the first reference height falls into the first height region, based on the same principle, in the first cultivation scheme, the amount of fertilizer applied does not need to be adjusted for the first height region; the amount of fertilizer applied needs to be reduced for the second height region; and the amount of fertilizer applied needs to be further reduced for the third height region.
[0089] When the first reference height falls into the third height region, based on the same principle, in the first cultivation scheme, the amount of fertilizer applied does not need to be adjusted for the third height region; the amount of fertilizer applied needs to be increased for the second height region; and the amount of fertilizer applied needs to be further increased for the first height region.
[0090] It should be understood that when the first height curve is divided into N height regions, the above scheme is also applicable.
[0091] So far, the first cultivation operation proposed in S210 is completed, and the output of the first cultivation scheme is the completion symbol.
[0092] S220: Re-execute the first cultivation operation after a planned cultivation duration.
[0093] In some possible embodiments, after re-executing the first cultivation operation, if it is determined that the first height range is less than or equal to the first deviation value, a corresponding first cultivation scheme does not need to be further generated, and a preset ordinary cultivation scheme can be adopted, which can be a cultivation scheme determined at the beginning of planting. It can be seen that the first cultivation scheme proposed in the embodiments of the present application is a response measure taken for abnormal plant growth conditions to restore the normal plant growth state; if it is determined that the first height range is still greater than the first deviation value, subsequent operations are continuously performed until the first height range is less than or equal to the first deviation value.
[0094] Based on the above technical scheme, the unmanned farm can effectively control the height of the plant population in the specified area, so that the height and height range of the plant population are within a reasonable deviation value, so that the large harvester can normally harvest the plant population, and the plant population can grow normally, which helps to increase the overall yield of the plant population. And periodically repeat the cultivation operation, according to the new condition of plant growth, formulate a new cultivation scheme, realize the benign internal circulation of the plant cultivation of the unmanned farm.
[0095] In some possible embodiments, after determining the first cultivation scheme, it is also necessary to determine how to control the corresponding automated equipment, such as unmanned aerial vehicles or drip irrigation systems, etc. The specific operation is as follows:
[0096] According to the above first cultivation scheme, a first prescription map is generated, which is used to represent the amount of fertilizer required for spraying for each first plant population in the height area.
[0097] Figure 4 is a schematic block diagram of a method for implementing a fertilization scheme according to an embodiment of the present application.
[0098] In some possible embodiments, when the above scheme application method is an unmanned aerial vehicle-based aerial fertilizer application method, the following operations can be performed:
[0099] S410: Determine the first control information according to the first prescription map and the range of the first area.
[0100] The first control information includes the starting point position of the unmanned aerial vehicle, the spraying height, the flight speed at the time of spraying, the plurality of waypoints reached in turn, and the amount of fertilizer required to be sprayed in each flight path.
[0101] In some possible embodiments, since the first height surface is divided into a plurality of height areas, the first area is also correspondingly divided into a plurality of first sub-areas, and correspondingly, the first plant population of each first sub-area also corresponds to a different height area. Therefore, the amount of fertilizer to be sprayed by the unmanned aerial vehicle is different when passing over different first sub-areas, for example, for the first sub-area where the first plant population is located in a lower height area, the unmanned aerial vehicle needs to spray more fertilizer; for the first sub-area where the first plant population is located in a higher height area, the unmanned aerial vehicle needs to spray less fertilizer.
[0102] S420: Send the first control information to the unmanned aerial vehicle.
[0103] Based on the above technical scheme, the control amount such as the waypoint and the amount of fertilizer of the unmanned aerial vehicle can be determined based on the determined cultivation scheme, and the unmanned aerial vehicle is instructed to perform the corresponding cultivation work through the control information, the growth rate of the plant population in the specified sub-area is controlled, and the height of the plant population in the entire area is controlled, and the height range is within the expected deviation.
[0104] FIG. 5 is a schematic block diagram of another method for implementing a fertilization scheme according to an embodiment of the present application.
[0105] In some possible embodiments, when the above-mentioned scheme is a ground fertilization scheme based on a drip irrigation system, the following operations can be performed:
[0106] S510: According to the first prescription map and the range of the first area, determine a valve area set corresponding to a dynamic wheel irrigation area of the drip irrigation system.
[0107] It should be understood that the irrigation function of the drip irrigation system is controlled by a plurality of valves, and these valves constitute a valve area. Since the deployment scale of the drip irrigation system is usually large, the above-mentioned first area is usually a partial range covered by the drip irrigation system, and therefore the valve area corresponding to the partial drip irrigation system deployed for the first area constitutes the above-mentioned valve area set.
[0108] S520: Determine the second control information according to the drip irrigation pipe network capacity of the drip irrigation system, the water pump parameters and the historical full-network pressure distribution.
[0109] The second control information includes a control amount for each valve in the above-mentioned valve area set and a corresponding fertilizer concentration, so that the drip irrigation system performs wheel irrigation work with a fertilizer concentration that is high first and then low.
[0110] It should be understood that the control amount of the valve can be a control amount of a valve opening degree, so as to control the fertilizer amount mixed with the water pipe per unit time, and further control the fertilizer concentration.
[0111] In some possible embodiments, the above-mentioned historical full-network pressure distribution can be a full-network pressure distribution detected at the last time.
[0112] In some possible embodiments, similar to the above-mentioned aerial fertilizer spraying method based on a drone, for a first sub-area with a lower height area of the first plant population, the opening control amount of the corresponding valve of the drip irrigation system is larger, and the corresponding fertilizer concentration is also larger; for a first sub-area with a higher height area of the first plant population, the opening control amount of the corresponding valve of the drip irrigation system is smaller, and the corresponding fertilizer concentration is also smaller.
[0113] S530: Send the second control information to the above-mentioned drip irrigation system.
[0114] Based on the above-mentioned technical scheme, the control amount for the valve set of the drip irrigation system can be determined based on the determined cultivation scheme, and the drip irrigation system is instructed to perform the corresponding cultivation work through the control information, so as to control the growth speed of the plant population in the specified sub-area, and further control the height of the plant population in the entire area, and make the height range within the expected deviation.
[0115] In some possible embodiments, the first cultivation scheme can also combine the unmanned aerial vehicle-based aerial fertilization method and the drip irrigation system-based ground fertilization method.
[0116] In some possible embodiments, when a part of the valves of the drip irrigation system fails, the drip irrigation system determines a first abnormal area range, which is a part of the first area that cannot be covered by the irrigation range of the drip irrigation system. Then, the drip irrigation system can send the first prescription map and the first abnormal area range to the unmanned aerial vehicle, so that the unmanned aerial vehicle completes the cultivation work for the abnormal area instead of the drip irrigation system. Meanwhile, the drip irrigation system can also send first abnormal information to the command center of the unmanned farm, where the first abnormal information is used to indicate that a part of the valves of the drip irrigation system fails, so that the on-duty personnel of the command center can take timely repair measures.
[0117] Similarly, when the unmanned aerial vehicle deviates, the unmanned aerial vehicle determines a second abnormal area range, which is a part of the first area that cannot be covered by the current flight path of the unmanned aerial vehicle, and then the unmanned aerial vehicle can send the first prescription map and the second abnormal area range to the drip irrigation system, so that the drip irrigation system completes the cultivation work for the abnormal area instead of the unmanned aerial vehicle. Meanwhile, the unmanned aerial vehicle can also send second abnormal information to the command center of the unmanned farm, where the second abnormal information is used to indicate that the unmanned aerial vehicle deviates, so that the on-duty personnel of the command center can take timely repair measures.
[0118] In some possible embodiments, when the drip irrigation system and the unmanned aerial vehicle cannot cooperate with each other to complete the cultivation scheme, the drip irrigation system or the unmanned aerial vehicle can send alarm information to the command center, where the alarm information is used to indicate that the current application method cannot complete the current cultivation scheme, so that the on-duty personnel of the command center can contact relevant personnel to troubleshoot the drip irrigation system and the unmanned aerial vehicle, and if no fault is found, introduce corresponding automatic equipment to implement the cultivation scheme.
[0119] Based on the technical scheme, the unmanned aerial vehicle and the drip irrigation system are communicatively connected, and when a fault occurs in one of the devices during the execution of the cultivation scheme, the other device can be instructed to assist in completing the cultivation scheme, which increases the robustness of the scheme and helps to avoid downtime caused by device failure.
[0120] In addition, the embodiments of the present application also provide a system for implementing any one of the above methods. FIG. 6 is a schematic block diagram of another system 600 for plant cultivation provided by the embodiments of the present application. The system can be applied to an unmanned farm. As shown in FIG. 6, the system 600 includes:
[0121] The total control center 610 is configured to instruct the system to perform a first cultivation operation on a first plant population planted in a first area, and the total control center 610 comprises:
[0122] An aerial field inspection platform 611 is configured to obtain a first image comprising the first plant population, and the aerial field inspection platform comprises a drone or a tethered balloon;
[0123] A digital image processing device 612 is configured to input the first image into a first model, and output a first height surface and first planting information, wherein the first planting information comprises a plant variety and a planting density of the first plant population;
[0124] A data processing device 613 is configured to determine a first reference height according to the first height surface, wherein the first reference height is a mode of a first height set comprising height values corresponding to a plurality of points constituting the first height surface; and input the first reference height, the first height surface and the first planting information into a second model, and output a first deviation value, wherein the first deviation value is used to represent an expected value of a first height range of the first plant population, and the second model is configured with a first standard table comprising a first corresponding relationship among the first height surface, the first planting information and the first deviation value; and in a case where the first height range is greater than the first deviation value, divide the first height surface into a plurality of height regions in a longitudinal direction according to the first deviation value to obtain a second height surface of each height region;
[0125] An expert system 614 is configured to input the first planting information and the second height surface of each height region into a third model, and output a first cultivation scheme, wherein the first cultivation scheme is used when the first height range is within the first deviation value, and the first cultivation scheme comprises a fertilization scheme corresponding to the first plant population in each height region, and the fertilization scheme comprises a fertilization mode and a planned cultivation duration, and the fertilization mode comprises an aerial fertilization mode based on a drone and / or a ground fertilization mode based on a drip irrigation system;
[0126] The total control center 610 is further configured to re-perform the first cultivation operation after the planned cultivation duration.
[0127] In some possible embodiments, the expert system 614 is further configured to generate a first prescription map according to the first cultivation scheme, wherein the first prescription map is used to represent a required amount of spraying fertilizer for the first plant population in each height region.
[0128] In some possible embodiments, the system 600 further comprises:
[0129] The remote control device 620 is configured to determine first control information according to the first prescription map and the range of the first area, when the application mode includes the unmanned aerial vehicle-based aerial fertilizer spraying mode, the first control information including a starting point position of the unmanned aerial vehicle, a spraying height, a flight speed during spraying, a plurality of flight points to be reached in sequence, and a required amount of fertilizer to be sprayed in each flight path; and send the first control information to the unmanned aerial vehicle.
[0130] In some possible embodiments, the remote control device 620 is further configured to determine a valve area set corresponding to a dynamic wheel irrigation area of the drip irrigation system according to the first prescription map and the range of the first area; determine second control information according to a drip irrigation pipe network capacity of the drip irrigation system, a water pump parameter, and a historical full-network pressure distribution, the second control information including a control amount and a corresponding fertilizer concentration for each valve in the valve area set, so that the drip irrigation system performs wheel irrigation work with a high-to-low fertilizer concentration; and send the second control information to the drip irrigation system.
[0131] Based on the system, the height of the plant population in the specified area can be effectively controlled to be within a reasonable deviation, so that the large harvester can normally harvest the plant population, and the plant population can grow normally, which helps to increase the overall yield of the plant population. The cultivation operation is periodically repeated, a new cultivation scheme is formulated according to the new growth condition of the plants, and a benign internal circulation of plant cultivation in the unmanned farm is realized.
[0132] Those skilled in the art can understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.
[0133] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the system, device and unit described above can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.
[0134] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. For example, the described device embodiments are merely schematic. The division of the units is merely logical function division. There can be another division manner for the 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. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.
[0135] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.
[0136] In addition, each functional unit in the various embodiments of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.
[0137] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application can be embodied in the form of a software product, and the computer software product is stored in a storage medium, and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory, a magnetic disk or an optical disk, and various program codes that can be stored in the medium.
[0138] The above is merely a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.
Claims
1. A method of plant cultivation, characterized by, The method is applied to an unmanned farm, and comprises the following steps: a first cultivation operation is performed on a first plant population planted in a first area, the first cultivation operation comprising: a first image is obtained by an aerial field inspection platform, and the first image is input into a first model to output a first height surface and first planting information, the aerial field inspection platform comprising a drone or a tethered balloon, the first image comprising the first plant population, and the first planting information comprising plant varieties and planting density of the first plant population; a first reference height is determined according to the first height surface, the first reference height being a mode of a first height set, the first height set comprising height values corresponding to a plurality of points constituting the first height surface; the first reference height, the first height surface and the first planting information are input into a second model to output a first deviation value, the first deviation value being used to represent an expected value of a first height range of the first plant population, the second model being configured with a first standard table, the first standard table comprising a first corresponding relationship between the first height surface, the first planting information and the first deviation value; in a case where the first height range is greater than the first deviation value, the first height surface is divided into a plurality of height regions in a longitudinal direction according to the first deviation value to obtain a second height surface of each height region; the first planting information and the second height surface of each height region are input into a third model to output a first cultivation scheme, the first cultivation scheme being used to control the first height range to be within the first deviation value, the first cultivation scheme comprising a fertilization scheme corresponding to the first plant population in each height region, the fertilization scheme comprising a fertilization mode and a planned cultivation duration, and the fertilization mode comprising an aerial fertilization mode based on a drone and / or a ground fertilization mode based on a drip irrigation system; after the planned cultivation duration, the first cultivation operation is re-executed.
2. The method of claim 1, wherein, The method further comprises: a first prescription map is generated according to the first cultivation scheme, the first prescription map being used to represent a required amount of fertilizer to be sprayed for the first plant population in each height region.
3. The method of claim 2, wherein, in a case where the fertilization mode comprises the aerial fertilization mode based on the drone, the method further comprises: first control information is determined according to the first prescription map and a range of the first area, the first control information comprising a starting point position, a spraying height, a flight speed at the time of spraying, a plurality of waypoints to be reached in sequence and an amount of fertilizer required to be sprayed in each flight path of the drone; the first control information is sent to the drone.
4. The method according to claim 2 or 3, characterized in that, in a case where the fertilization mode comprises the ground fertilization mode based on the drip irrigation system, the method further comprises: a valve area set corresponding to a dynamic wheel irrigation area of the drip irrigation system is determined according to the first prescription map and a range of the first area; Determine second control information according to the drip irrigation pipe network capacity, pump parameters and historical full-network pressure distribution of the drip irrigation system, the second control information including a control amount and a corresponding fertilizer concentration for each valve in the valve zone set, so that the drip irrigation system performs a rotation irrigation work with high fertilizer concentration first and low fertilizer concentration later; Send the second control information to the drip irrigation system.
5. A system for plant cultivation, characterized by, The system is applied to unmanned farms and includes: A general control center for instructing the system to perform a first cultivation operation on a first plant population planted in a first area, the general control center including: An aerial field inspection platform for obtaining a first image including the first plant population, the aerial field inspection platform including a drone or a tethered balloon; A digital image processing device for inputting the first image into a first model and outputting a first height surface and first planting information including plant varieties and planting densities of the first plant population; A data processing device for determining a first reference height according to the first height surface, the first reference height being a mode of a first height set including height values corresponding to multiple points constituting the first height surface, and for inputting the first reference height, the first height surface and the first planting information into a second model and outputting a first deviation value for representing an expected value of a first height range of the first plant population, the second model being configured with a first standard table including a first correspondence relationship between the first height surface, the first planting information and the first deviation value, and for dividing the first height surface into multiple height regions to obtain second height surfaces of the height regions according to the first deviation value in a case where the first height range is greater than the first deviation value; An expert system for inputting the first planting information and the second height surfaces of the height regions into a third model and outputting a first cultivation scheme for controlling the first height range within the first deviation value, the first cultivation scheme including a fertilization scheme corresponding to the first plant population in each height region, the fertilization scheme including a fertilization mode and a planned cultivation duration, the fertilization mode including an aerial fertilization mode based on a drone and / or a ground fertilization mode based on a drip irrigation system; The general control center is further configured to re-perform the first cultivation operation after the planned cultivation duration.
6. A device for plant cultivation, characterized in that, A device including a processor and a memory, wherein the processor and the memory are connected, wherein the memory is configured to store program code, and the processor is configured to call the program code to execute the method according to any one of claims 1 to 4.
7. A chip system, characterized by The chip system is applied to an electronic device; the chip system comprises one or more interface circuits and one or more processors; the interface circuits and the processors are interconnected through lines; the interface circuits are used for receiving signals from a memory of the electronic device and sending the signals to the processors, the signals comprising computer instructions stored in the memory; when the processors execute the computer instructions, the electronic device executes the method as claimed in any one of claims 1 to 4.
8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method as claimed in any one of claims 1 to 4.
9. A computer program product, characterised in that, The computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method as claimed in any one of claims 1 to 4. The computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method as claimed in any one of claims 1 to 4.