Intelligent control method and system for multifunctional watering cart

Abstract

The invention discloses an intelligent control method and system for a multifunctional watering cart, and relates to the field of artificial intelligence. The method comprises the following steps: acquiring an image and a soil state of a green plant to be sprayed, wherein the soil state comprises a moisture bearing capacity, a maximum moisture bearing capacity and a moisture loss rate; image recognition is carried out on the to-be-sprayed green plants to obtain state information of the to-be-sprayed green plants, and the state information comprises types, growth stages and health indexes; based on the soil state and the state information of the green plants to be sprayed, a watering scheme is obtained through calculation, and the watering scheme comprises the watering amount and the watering angle; and sending the watering scheme to a control system, so that the control system controls the watering cart to execute the watering scheme. By implementing the technical scheme provided by the invention, the urban green plants in different growth states can be accurately and effectively watered, and the situation of excessive watering or insufficient watering is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of artificial intelligence, and specifically to an intelligent control method and system for a multifunctional sprinkler truck. Background Art

[0002] With the development of regional urbanization, living conditions have also been greatly improved. At present, by planting green plants in urban areas, it can not only purify a large amount of exhaust gas emitted in urban areas, but also beautify the urban environment; based on this, the maintenance of urban green plants has become an important part of urbanization development.

[0003] For the maintenance of urban green plants, in addition to selecting suitable varieties of green plants, it is also necessary to water the green plants regularly. Except for special circumstances, watering is usually done by a sprinkler truck, which adjusts the water output and angle of the water cannon during the watering process to water the green plants in the designated area. However, since many green plants are cyclical plants, the growth state of the plants varies with the change of seasons, and the current watering method is still to determine the amount of watering according to the fixed growth state of the green plants, which can easily cause problems such as excessive or insufficient watering, thereby shortening the life cycle of the green plants. Summary of the invention

[0004] In order to solve the problem of excessive or insufficient watering of green plants due to the single watering mode of a sprinkler truck, the present application provides an intelligent control method and system for a multifunctional sprinkler truck.

[0005] In a first aspect, the present application provides a multifunctional sprinkler truck intelligent control method, the method comprising: Acquire an image of the green plants to be sprayed and soil conditions, wherein the soil conditions include water bearing capacity, maximum water bearing capacity, and water loss rate; Performing image recognition on the green plants to be sprayed to obtain status information of the green plants to be sprayed, wherein the status information includes type, growth stage and health index; Based on the soil state and the state information of the green plants to be sprayed, a watering scheme is calculated, wherein the watering scheme includes a watering amount and a watering angle; The watering plan is sent to a control system so that the control system controls the watering truck to execute the watering plan.

[0006] In a second aspect, the present application provides a multifunctional sprinkler truck intelligent control system, the system comprising an acquisition module, a processing module and a sending module, wherein: The acquisition module is used to acquire the image of the green plants to be sprayed and the soil state, wherein the soil state includes the water bearing capacity, the maximum water bearing capacity and the water loss rate; The processing module is used to perform image recognition on the green plants to be sprayed to obtain status information of the green plants to be sprayed, wherein the status information includes type, growth stage and health index; Based on the soil state and the state information of the green plants to be sprayed, a watering scheme is calculated, wherein the watering scheme includes a watering amount and a watering angle; The sending module is used to send the watering plan to the control system so that the control system controls the sprinkler truck to execute the watering plan.

[0007] In one of the embodiments, a shooting route of the green plants to be sprayed is preset; When the water sprinkler truck drives to the starting point of the shooting route, the shooting is started, and when the water sprinkler truck drives to the end point of the shooting route, the shooting is stopped to generate a shooting video; Cutting the captured video to generate a plurality of pre-processed static images of the green plants to be sprayed; Inputting the plurality of pre-processed static images into an image feature recognition model to obtain high-precision regions corresponding to the plurality of pre-processed static images; The high-precision areas corresponding to the plurality of pre-processed static images are spliced ​​and combined and post-processed to generate the image of the green plant to be sprayed.

[0008] In one embodiment, before inputting the plurality of pre-processed static images into the image feature recognition model to obtain the high-precision regions corresponding to the plurality of pre-processed static images, the method further includes: Acquire current environmental information, wherein the environmental information includes a plurality of image influencing factors, and the plurality of image influencing factors include light intensity, dust concentration, and wind speed; Subtracting the values ​​corresponding to the plurality of image impact factors from the corresponding optimal shooting values ​​to obtain difference results of the plurality of image impact factors; Determine a plurality of error image impact factors based on the difference results of the plurality of image impact factors; Based on the values ​​of the multiple error image influencing factors, the image feature recognition model is obtained by matching from a preset model library.

[0009] In one of the embodiments, a soil state acquisition range of the green plants to be sprayed is preset, and the soil state acquisition range is determined by a signal sending distance of a soil state monitoring device; When the watering truck enters the soil state acquisition range, the soil state is acquired from the soil state monitoring device.

[0010] In one of the embodiments, historical image data of the green plants to be sprayed is obtained; The historical image data and the current image of the green plants to be sprayed are input into a green plant detection model to obtain the status information of the green plants to be sprayed.

[0011] In one of the embodiments, according to the status information of the green plants to be sprayed, the effective water absorption depth of the green plants to be sprayed is queried from a preset green plant status information library; Calculating the water requirement of the soil state based on the effective water absorption depth of the green plants to be sprayed; Identifying the planting information of the green plants to be sprayed, wherein the planting information includes the planting area and the planting density; The watering amount and the watering angle of the green plants to be sprayed are determined according to the water demand of the soil state and the planting information of the green plants to be sprayed.

[0012] In one embodiment, the watering scheme is calculated based on the soil state and the state information of the green plants to be sprayed, and specifically includes: Determine the spraying water shape of the green plants to be sprayed according to the state information of the green plants to be sprayed, wherein the spraying water shape is any one of drop shape, column shape and mist shape; Generate the driving speed of the sprinkler truck based on the spraying water shape, watering amount and watering angle of the green plants to be sprayed; The spraying water state of the green plants to be sprayed is stored in the watering plan, and the driving speed of the sprinkler truck is sent to the voice broadcasting device in the cab to remind the sprinkler truck driver to control the speed of the sprinkler truck.

[0013] In a third aspect, the present application provides an electronic device comprising a processor, a memory, a user interface and a network interface, wherein the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes a method as described in any one of the first aspects.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, the method as described in any one of the first aspects is executed.

[0015] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. The growth status of urban green plants at different time points is different. Therefore, during the watering process of the sprinkler truck, the type, growth stage and health index of the green plants to be sprayed are first identified through the image of the green plants to be sprayed, so as to determine the current growth status of the green plants to be sprayed. Then, based on the growth status of the plants, the effective water absorption and water requirement of the green plants to be sprayed are queried. Then, by obtaining the current soil moisture carrying capacity, maximum moisture carrying capacity and moisture loss rate, the soil water requirement is calculated, and then the watering amount of the sprinkler truck is obtained. Finally, the spraying angle is determined in combination with the planting area and planting density of the green plants to be sprayed, so as to achieve accurate and effective watering of urban green plants in different growth states and reduce the occurrence of excessive or insufficient watering.

[0016] 2. In the process of acquiring images of green plants to be sprayed, the shooting conditions at different time points are affected by the environment, resulting in different optimal shooting angles of the images. Based on this, the shooting route of the green plants to be sprayed is first preset, and then the sprinkler truck takes pictures and generates shooting videos while driving along the shooting route. The shooting videos are then image cut to obtain pre-processed static images at multiple shooting angles, and then feature recognition is performed on multiple pre-processed static images to obtain high-precision areas of each pre-processed static image. Finally, multiple high-precision areas are spliced, combined, and post-processed to fuse the optimal shooting areas at different shooting angles, thereby improving the accuracy of subsequent image recognition.

[0017] 3. The fragility of green plants varies in different growth states. For example, trees are less fragile, while flowers and plants are more fragile. Healthy plants are less fragile, while diseased plants are more fragile. Therefore, there are certain requirements for the shape of the sprinkler during the watering process, and the driving speeds corresponding to different sprinkler shapes are also different. Based on this, three sprinkler shapes are provided: columnar, drop-shaped, and mist-shaped. During the watering process, different sprinkler shapes are switched according to the growth state of the green plants to be sprayed. The corresponding driving speed is calculated in combination with the current sprinkler volume and sprinkler angle, thereby ensuring that the sprinkler volume requirements of the green plants to be sprayed are met, and the damage to the green plants to be sprayed during the watering process is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flow chart of a multifunctional sprinkler truck intelligent control method provided in an embodiment of the present application.

[0019] Figure 2 This is a watering route area distribution map provided in an embodiment of the present application.

[0020] Figure 3 This is a soil status signal receiving scenario diagram provided in an embodiment of the present application.

[0021] Figure 4 It is a structural schematic diagram of a multifunctional sprinkler truck intelligent control system provided in an embodiment of the present application.

[0022] Figure 5 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0023] Explanation of the reference numerals: 1. Acquisition module; 2. Processing module; 3. Sending module; 500. Electronic device; 501. Processor; 502. Communication bus; 503. User interface; 504. Network interface; 505. Memory. DETAILED DESCRIPTION

[0024] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0025] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0026] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0027] With the development of science and technology, the functions of sprinkler trucks have become diversified and intelligent. At present, multifunctional sprinkler trucks can not only clean and reduce dust on the road surface, but also water green plants on the roadside in urban areas. They are an important part of maintaining urban cleanliness and improving the city's image.

[0028] There are many kinds of green plants in the urban area, including trees and flowers. Although the plants planted in the urban area have strong adaptability, daily watering and maintenance work still needs to be carried out. Except for some special plants that are watered manually, most urban green plants are watered by sprinkler trucks. However, the current sprinkler trucks always determine the amount of water to be sprinkled according to the fixed growth state of the green plants when sprinkling water, and do not take into account the growth cycle of the green plants. For example, with the change of seasons, the green plants may be in a flowering state, and the demand for water at this time is greatly increased compared to the non-flowering state. Therefore, it will cause the sprinkler truck to have problems of excessive or insufficient watering during the sprinkling process.

[0029] In order to solve the above problems, the present application provides a multifunctional sprinkler intelligent control method, which is applied to a server, such as Figure 1 As shown, steps S101 to S104 are included, and the steps are as follows: S101, obtaining images of green plants to be sprayed and soil conditions, where the soil conditions include water bearing capacity, maximum water bearing capacity, and water loss rate.

[0030] In the above steps, the image of the green plants to be sprayed is obtained after the vehicle drives into the shooting area. A shooting device is installed in front of the sprinkler truck. When the sprinkler truck enters the shooting area, it shoots the green plant planting area to be watered, thereby obtaining the image of the green plants to be sprayed. It should be noted that the sprinkler truck needs to drive through 3 areas to complete the watering of the green plants to be watered, such as Figure 2 As shown, there are shooting area, information acquisition area and watering area respectively, wherein the shooting area is used to shoot images of green plants to be sprayed, the information acquisition area is used to obtain soil status and environmental data, and the watering area is used to water the planting area of ​​green plants to be sprayed.

[0031] In one possible implementation, when obtaining the soil state, the soil will change due to the influence of the environment, and this change is mainly reflected in the water loss rate. For example, both temperature and humidity will cause the loss of water in the soil, and this influence relationship is difficult to describe through intuitive quantitative standards. Therefore, it is impossible to accurately infer the soil water loss rate by measuring temperature or humidity alone. In order to solve this problem, the present application places multiple humidity sensors in the soil of the planting area where green plants are to be sprayed, and establishes a soil state monitoring device for receiving real-time humidity information uploaded by multiple humidity sensors, and converting the real-time humidity information into the current water loss rate and water carrying capacity of the soil. Since the maximum water carrying capacity of the soil generally does not change, no further measurement is required. At this time, a soil state acquisition range is preset, and the soil state acquisition range is determined by the signal sending distance of the soil state monitoring device, such as Figure 3As shown, the circular area is the signal transmission range generated by the signal transmission limit distance of the soil state monitoring device, and the circular area is located within the information acquisition area. When the sprinkler truck enters the soil state acquisition range, the current soil state of the area to be sprinkled is obtained from the soil state monitoring device. In this way, the accurate soil state is obtained, so as to facilitate the subsequent determination of the soil water demand and then calculate the accurate watering amount. In addition, this method has low requirements for signal transmission and does not need to consider the impact of the environment on the signal quality.

[0032] In a possible implementation, the acquisition of the image of the green plant to be sprayed is often carried out by fixed-point shooting. However, this method is easily affected by the environment, resulting in low quality of the captured image. For example, too strong or too weak light intensity will cause unclear features in the image, too high dust concentration will cause low visibility and affect the clarity of the photo, and high wind speed will cause static objects to be in motion and cause image ghosting. In addition, a single shooting angle can easily cause misjudgment between similar plants. Therefore, in order to improve the accuracy of the acquired image of the green plant to be sprayed, a shooting route is preset. The shooting route is located in the shooting area. When the sprinkler truck drives to the starting point of the shooting route, shooting starts. When the sprinkler truck drives to the end point of the shooting route, shooting stops, and a shooting route is generated. At this time, the captured video is cut to obtain pre-processed static images at multiple shooting angles. Then, the multiple pre-processed static images are input into the image feature recognition model to obtain high-precision areas in each pre-processed static image. The high-precision area can be understood as the feature area of ​​the same plant at different shooting angles. Then, the high-precision areas corresponding to the multiple pre-processed static images are spliced ​​and combined. Post-processing, specifically, uses three-dimensional model stitching technology to stitch the characteristic areas of the green plants to be sprayed at multiple angles into a three-dimensional model of the green plants to be sprayed, and then post-processes the three-dimensional model of the green plants to be sprayed to generate a two-dimensional picture of the green plants to be sprayed. At this time, the picture of the green plants to be sprayed is used as the image for subsequent processing, wherein the picture of the green plants to be sprayed integrates the key features of the green plants to be sprayed at multiple angles, reduces the influence of the environment on a single shooting angle, and greatly reduces the possibility of misjudgment between similar plants under the influence of multiple key features, which provides effective support for the subsequent identification of the status information of the green plants to be sprayed, thereby improving the accuracy of the acquired images to be sprayed.

[0033] In a possible implementation, the image feature recognition model is a neural network model trained using a large number of images of green plants to be sprayed, but the general image feature recognition model is difficult to deal with the errors caused by various influencing factors in the environment, resulting in low robustness. Based on this, for different environmental information, a variety of different types of image feature recognition models are trained, and the various types of image feature recognition models have different focuses when dealing with various influencing factors, and then are classified and stored in a preset model library, wherein each image feature recognition model is provided with applicable intervals corresponding to a variety of influencing factors. When identifying the high-precision area of ​​the preprocessed static image, the current environmental information is first obtained, and the environmental information includes a plurality of image influencing factors, which may be light intensity, dust concentration, and wind speed. Then, the numerical values ​​corresponding to each of the various image factors are subtracted from the corresponding optimal shooting values, thereby obtaining the difference results of the plurality of image influencing factors, which reflects the degree of influence on the image quality in the current environment. The larger the difference result, the heavier the degree of influence, and the lower the quality of the captured image; the smaller the difference result, the lighter the degree of influence, and the higher the quality of the captured image. Then, it is determined whether the difference results of multiple image influencing factors are within the corresponding error range. If not, it is determined to be an error image influencing factor. If so, it is determined to be a normal image influencing factor. Finally, the numerical values ​​corresponding to one or more error image influencing factors are matched with the preset model library to obtain the image recognition model of the green plants to be sprayed. Among them, by analyzing the environmental information, multiple error image influencing factors with a greater degree of influence are obtained, and then the image feature recognition model suitable for processing the current multiple error image influencing factors is matched from the preset model library. Since the image feature recognition model has high robustness under the influence of multiple error image influencing factors, it can not only improve the accuracy of image feature recognition, but also speed up the image feature recognition.

[0034] S102, performing image recognition on the green plants to be sprayed to obtain status information of the green plants to be sprayed, where the status information includes type, growth stage and health index.

[0035] In the above steps, when identifying the status information of the green plants to be sprayed, in order to improve the recognition accuracy; by obtaining the historical image data of the green plants to be sprayed, and then inputting the historical image data of the green plants to be sprayed and the currently captured image into the green plant detection model, the status information of the green plants to be sprayed is obtained. In the recognition process of the green plant detection model, the historical image data is first compared with the current image to obtain the difference features between the two, and then the difference features are identified and processed to obtain the status information to be corrected; then the status information of the historical image data is obtained, and the status information corresponding to the difference features in the historical image data is replaced with the status information to be corrected to obtain the current status information of the green plants to be sprayed. In this process, since there is no need to identify all the image features of the current image of the green plants to be sprayed, the adverse effects of noise in the image on the green plant detection model are reduced, thereby improving the recognition accuracy of the status information of the green plants to be sprayed.

[0036] S103, based on the soil state and the state information of the green plants to be sprayed, a watering plan is calculated, and the watering plan includes a watering amount and a watering angle.

[0037] S104: Send the watering plan to the control system so that the control system controls the sprinkler truck to execute the watering plan.

[0038] In the above steps, firstly, according to the status information of the green plants to be sprayed, the current effective water absorption depth of the green plants to be sprayed is queried from the preset green plant status information database. The effective water absorption depth can be understood as the extension depth of the roots of the green plants to be sprayed in the soil during the growth process. In actual situations, after the sprinkler truck has finished spraying water, the water will penetrate from the soil surface to the deep soil layer, and the water on the soil surface is more likely to evaporate, resulting in a phenomenon in which the effective water carrying capacity from the deep soil layer to the soil surface layer decreases. Therefore, this application needs to take this phenomenon into account when calculating the soil water requirement, so the following calculation formula is used to calculate the soil water requirement: S= G; Where S is the soil water requirement, is the maximum moisture carrying capacity of the soil at depth h, is the effective water carrying capacity of the soil at depth h at any time t, G is the water loss, and D is the effective water absorption depth.

[0039] In the above formula, the actual water bearing and penetration characteristics of water at different depths are taken into account, so as to integrate the effective water bearing capacity of the soil at different depths, so as to more accurately calculate the soil water demand. Specifically: In this calculation formula, the maximum water bearing capacity of the soil at depth h is fixed and known, but the effective water bearing capacity of the soil at depth h is There is uncertainty, and it is impossible to know before the sprinkler truck sprays water The exact value of can only be reasonably estimated based on the existing data. Therefore, the soil permeability coefficient K(h) is introduced. K(h) is a function related to soil texture and structure, reflecting the difficulty of water penetration in the soil at depth h. As time goes by, the continuous penetration of water in the soil causes the water carrying capacity at different depths to change. When the water carrying capacity C(h) before the soil change is known, C(h) at the soil depth h becomes , and then based on Darcy's law, generate the flow equation of water in the depth direction:

[0040] Darcy's law is a law that describes the linear relationship between the seepage velocity and the water bearing capacity gradient in the soil. In the above formula, the left side of the equation represents the rate of change of the water bearing capacity C at the depth h over time, that is, it reflects how the water bearing capacity in the soil changes over time at a certain depth; the right side of the equation represents the rate of change of the water bearing capacity gradient in the depth direction, where

[0041] It represents the gradient of water bearing capacity in the depth direction. In addition, the direction of water flow in the soil is from the place where the water bearing capacity gradient is large to the place where the gradient is small, that is, the left and right sides of the equation are negatively correlated.

[0042] The above flow equation directly and indirectly describes the influence of the water penetration effect in the soil on the water carrying capacity at each soil depth from two aspects: the rate of change of the water carrying capacity C over time and the rate of change of the water carrying capacity gradient in the depth direction. Finally, according to the boundary conditions of the rate of change of the water carrying capacity C over time and the boundary conditions of the rate of change of the water carrying capacity gradient in the depth direction (i.e., D=0 and D=h), the above flow equation is solved to obtain the effective water carrying capacity at any time t at the depth h. .

[0043] In summary, Darcy's law is used to calculate the effective water carrying capacity of the soil at any depth at any time, and then the effective carrying capacity at each depth is integrated to obtain the overall water demand of the soil. This scheme more accurately considers the penetration effect and actual distribution of water in the soil, thereby more accurately calculating the water demand of the soil.

[0044] Finally, the planting area and planting density of the green plants to be sprayed are combined to determine the watering angle and amount, so as to achieve accurate and effective watering of urban green plants in different growth states and reduce the occurrence of excessive or insufficient watering.

[0045] In one possible implementation, the fragility of the green plants to be sprayed varies due to their types, growth stages, and health indexes, for example, trees and flowers, flowering stages and growth stages, sick green plants and healthy green plants. Based on this, green plants with different status information also have different watering methods, and the wrong watering method can easily cause the green plants to be damaged by strong water flow impact. Therefore, in the process of watering the green plants to be sprayed, it is also necessary to determine at least one spraying water shape of the green plants to be sprayed according to the status information of the green plants to be sprayed. The spraying water shape includes droplet, columnar, and mist. Among them, the columnar shape is suitable for green plants with low fragility; the droplet shape is suitable for green plants with high fragility; and the mist shape is suitable for green plants with extremely high fragility. In addition, since different spraying water shapes have differences in watering efficiency, when the green plants to be sprayed can choose two or more watering methods, the watering method with high watering efficiency is preferred. For example, if the green plants to be sprayed can choose droplet watering or mist watering, then the droplet watering with high watering efficiency is selected as the current watering method. In addition, as the watering method changes, the amount of water per unit area of ​​the planting area also changes. Based on this, by changing the driving speed of the sprinkler truck, the amount of water per unit area of ​​the planting area can be effectively controlled to ensure that the amount of water meets the demand. Based on the spraying water shape, watering amount and watering angle of the green plants to be sprayed, generating the driving speed of the sprinkler truck is a common technical means used by technicians in this field, which will not be elaborated here. Finally, the spraying water shape of the green plants to be sprayed is stored in the sprinkler plan to adjust the current default spraying water shape; in addition, the driving speed of the sprinkler truck needs to be sent to the voice broadcast device in the cab or the on-board display screen to remind the sprinkler truck driver to control the driving speed of the sprinkler truck.

[0046] The present application also provides a multifunctional sprinkler intelligent control system, such as Figure 4 As shown, the system includes an acquisition module 1, a processing module 2 and a sending module 3, wherein: Acquisition module 1, used to acquire images of green plants to be sprayed and soil conditions, where the soil conditions include water bearing capacity, maximum water bearing capacity and water loss rate; Processing module 2 is used to perform image recognition on the green plants to be sprayed, and obtain the status information of the green plants to be sprayed, including the type, growth stage and health index; based on the soil state and the status information of the green plants to be sprayed, a watering plan is calculated, and the watering plan includes the watering amount and the watering angle; The sending module 3 is used to send the watering plan to the control system so that the control system controls the sprinkler truck to execute the watering plan.

[0047] In a possible implementation, a shooting route of the green plants to be sprayed is preset; When the water sprinkler truck reaches the starting point of the shooting route, the shooting starts, and when the water sprinkler truck reaches the end point of the shooting route, the shooting stops, and a shooting video is generated; Cut and process the video footage to generate multiple pre-processed static images of the green plants to be sprayed; Inputting a plurality of pre-processed static images into an image feature recognition model to obtain high-precision regions corresponding to the plurality of pre-processed static images; The high-precision areas corresponding to the various pre-processed static images are spliced ​​and combined and post-processed to generate images of the green plants to be sprayed.

[0048] In a possible implementation, before inputting the plurality of pre-processed static images into the image feature recognition model to obtain the high-precision regions corresponding to the plurality of pre-processed static images, the method further includes: Acquire current environmental information, which includes multiple image influencing factors, including light intensity, dust concentration, and wind speed; Subtracting the values ​​corresponding to the multiple image influencing factors from the corresponding optimal shooting values ​​to obtain the difference results of the multiple image influencing factors; Determine multiple error image impact factors based on the difference results of multiple image impact factors; Based on the values ​​of multiple error image influencing factors, an image feature recognition model is obtained by matching from a preset model library.

[0049] In a possible implementation, a soil state acquisition range of the green plants to be sprayed is preset, and the soil state acquisition range is determined by a signal transmission distance of the soil state monitoring device; When the sprinkler truck enters the soil state acquisition range, the soil state is acquired from the soil state monitoring device.

[0050] In a possible implementation, historical image data of green plants to be sprayed is obtained; The historical image data and the current image of the green plants to be sprayed are input into the green plant detection model to obtain the status information of the green plants to be sprayed.

[0051] In a possible implementation, according to the status information of the green plants to be sprayed, the effective water absorption depth of the green plants to be sprayed is queried from a preset green plant status information library; Calculate the water requirement of the soil state based on the effective water absorption depth of the green plants to be sprayed; Identify the planting information of the green plants to be sprayed, including the planting area and planting density; According to the water demand of the soil state and the planting information of the green plants to be sprayed, the watering amount and angle of the green plants to be sprayed are determined.

[0052] In a possible implementation, a watering plan is calculated based on the soil state and the state information of the green plants to be sprayed, which specifically includes: Determine the spraying water shape of the green plants to be sprayed according to the state information of the green plants to be sprayed, and the spraying water shape is any one of drop shape, column shape and mist shape; Generate the driving speed of the sprinkler truck based on the spraying water shape, watering amount and watering angle of the green plants to be sprayed; The spraying water state of the green plants to be sprayed is stored in the watering plan, and the driving speed of the sprinkler truck is sent to the voice broadcast device in the cab to remind the sprinkler truck driver to control the speed of the sprinkler truck.

[0053] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0054] The present application also discloses an electronic device. Figure 5 , Figure 5 The electronic device 500 may include: at least one processor 501 , at least one network interface 504 , a user interface 503 , a memory 505 , and at least one communication bus 502 .

[0055] The communication bus 502 is used to realize the connection and communication between these components.

[0056] The user interface 503 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 503 may also include a standard wired interface and a wireless interface.

[0057] The network interface 504 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0058] Among them, the processor 501 may include one or more processing cores. The processor 501 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 505, and calling data stored in the memory 505. Optionally, the processor 501 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 501 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 501, and it can be implemented separately through a chip.

[0059] Among them, the memory 505 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 505 includes a non-transitory computer-readable storage medium. The memory 505 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 505 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 505 may also be optionally at least one storage device located away from the aforementioned processor 501. Refer to Figure 5 , as a computer storage medium, the memory 505 may include an operating system, a network communication module, a user interface module, and an application program of a multifunctional sprinkler truck intelligent control method.

[0060] exist Figure 5In the electronic device 500 shown, the user interface 503 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 501 can be used to call the application program stored in the memory 505 for a multifunctional sprinkler truck intelligent control method. When executed by one or more processors 501, the electronic device 500 executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0061] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0062] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0063] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0064] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0065] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0066] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0067] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A multifunctional sprinkler intelligent control method, characterized in that: The method comprises: Acquire an image of the green plants to be sprayed and soil conditions, wherein the soil conditions include water bearing capacity, maximum water bearing capacity, and water loss rate; Performing image recognition on the green plants to be sprayed to obtain status information of the green plants to be sprayed, wherein the status information includes type, growth stage and health index; Based on the soil state and the state information of the green plants to be sprayed, a watering scheme is calculated, wherein the watering scheme includes a watering amount and a watering angle; The watering plan is sent to a control system so that the control system controls the watering truck to execute the watering plan.

2. The method according to claim 1, characterized in that: The step of obtaining the image of the green plants to be sprayed and the soil state specifically includes: Preset the shooting route of the green plants to be sprayed; When the water sprinkler truck drives to the starting point of the shooting route, the shooting is started, and when the water sprinkler truck drives to the end point of the shooting route, the shooting is stopped to generate a shooting video; Cutting the captured video to generate a plurality of pre-processed static images of the green plants to be sprayed; Inputting the plurality of pre-processed static images into an image feature recognition model to obtain high-precision regions corresponding to the plurality of pre-processed static images; The high-precision areas corresponding to the plurality of pre-processed static images are spliced ​​and combined and post-processed to generate the image of the green plant to be sprayed.

3. The method according to claim 2, further comprising, before inputting the plurality of pre-processed static images into the image feature recognition model to obtain the high-precision regions corresponding to the plurality of pre-processed static images respectively: Acquire current environmental information, wherein the environmental information includes a plurality of image influencing factors, and the plurality of image influencing factors include light intensity, dust concentration, and wind speed; Subtracting the values ​​corresponding to each of the plurality of image impact factors from the corresponding optimal shooting values ​​to obtain difference results of the plurality of image impact factors; Determine a plurality of error image impact factors based on the difference results of the plurality of image impact factors; Based on the values ​​of the multiple error image influencing factors, the image feature recognition model is obtained by matching from a preset model library.

4. The method according to claim 1, characterized in that The step of obtaining the image of the green plants to be sprayed and the soil state specifically includes: Presetting the soil state acquisition range of the green plants to be sprayed, the soil state acquisition range is determined by the signal sending distance of the soil state monitoring device; When the watering truck enters the soil state acquisition range, the soil state is acquired from the soil state monitoring device.

5. The method according to claim 1, characterized in that The performing image recognition on the green plants to be sprayed to obtain status information of the green plants to be sprayed specifically includes: Acquire historical image data of the green plants to be sprayed; The historical image data and the current image of the green plants to be sprayed are input into a green plant detection model to obtain the status information of the green plants to be sprayed.

6. The method according to claim 1, characterized in that The calculating of the watering scheme based on the soil state and the state information of the green plants to be sprayed specifically includes: According to the status information of the green plants to be sprayed, querying the effective water absorption depth of the green plants to be sprayed from a preset green plant status information database; Calculating the water requirement of the soil state based on the effective water absorption depth of the green plants to be sprayed; Identifying the planting information of the green plants to be sprayed, wherein the planting information includes the planting area and the planting density; The watering amount and the watering angle of the green plants to be sprayed are determined according to the water demand of the soil state and the planting information of the green plants to be sprayed.

7. The method according to claim 1, characterized in that The calculating of the watering scheme based on the soil state and the state information of the green plants to be sprayed specifically includes: Determine the spraying water shape of the green plants to be sprayed according to the state information of the green plants to be sprayed, wherein the spraying water shape is any one of drop shape, column shape and mist shape; Generate the driving speed of the sprinkler truck based on the spraying water shape, watering amount and watering angle of the green plants to be sprayed; The spraying water state of the green plants to be sprayed is stored in the watering plan, and the driving speed of the sprinkler truck is sent to the voice broadcasting device in the cab to remind the sprinkler truck driver to control the speed of the sprinkler truck.

8. A multifunctional sprinkler truck intelligent control system, characterized in that: The system comprises an acquisition module (1), a processing module (2) and a sending module (3), wherein: The acquisition module (1) is used to acquire images of green plants to be sprayed and soil conditions, wherein the soil conditions include water bearing capacity, maximum water bearing capacity and water loss rate; The processing module (2) is used to perform image recognition on the green plants to be sprayed to obtain status information of the green plants to be sprayed, wherein the status information includes type, growth stage and health index; Based on the soil state and the state information of the green plants to be sprayed, a watering scheme is calculated, wherein the watering scheme includes a watering amount and a watering angle; The sending module (3) is used to send the watering plan to the control system so that the control system controls the watering truck to execute the watering plan.

9. An electronic device, characterized in that: The electronic device (500) comprises a processor (501), a memory (505), a user interface (503) and a network interface (504), wherein the memory (505) is used to store instructions, the user interface (503) and the network interface (504) are used to communicate with other devices, and the processor (501) is used to execute the instructions stored in the memory (505) so that the electronic device (500) executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is performed.

Images