Weed spraying method, device and equipment based on vehicle and storage medium

Abstract

The invention provides a weed spraying method, device and equipment based on a vehicle and a storage medium, and the method comprises the steps: determining the starting delay time of a nozzle corresponding to a camera based on the height of the camera relative to the horizontal ground and the inclination angle of the camera relative to the orthogonal plane of the horizontal ground; obtaining a current image collected by a camera; if at least one weed is detected from the current image by using a preset detection model, determining the coordinate of the weed in an image coordinate system, and determining the view distance between the weed and the view boundary of the camera close to the vehicle based on the coordinate of the weed in the image coordinate system; determining the continuous spraying time of the nozzle corresponding to the camera based on the maximum sprayable distance and the view distance of the nozzle corresponding to the camera; and based on the starting delay time of the nozzle corresponding to the camera and the continuous spraying time of the nozzle corresponding to the camera, controlling the nozzle corresponding to the camera to spray the weeds. The weed spraying precision and efficiency are improved, and resource waste is reduced.

Description

Technical Field

[0001] The present application relates to the field of vehicle spraying technology, and in particular to a vehicle-based weed spraying method, device, equipment and storage medium. Background Art

[0002] In the process of promoting agricultural modernization, precision agriculture technology has gradually become a key component of agricultural production. The core of precision agriculture technology is to carry out refined management of agricultural production with the help of information technology. Among them, weed detection and spraying technology, as an important application field of precision agriculture, has received extensive attention and in-depth research in recent years. Traditional weed spraying systems usually adopt carpet spraying mode or fixed spraying mode. Here, carpet spraying means that the nozzle sprays the entire farmland indiscriminately as the vehicle moves; fixed spraying mode means that the nozzle is triggered to spray at a predetermined time interval.

[0003] However, both the carpet spraying mode and the fixed spraying mode are difficult to achieve precise spraying. Not only can they not cope with the complex weed distribution environment, but they will also damage the healthy growth of crops and lead to higher costs. Therefore, how to spray weeds precisely has become an urgent problem to be solved. Summary of the invention

[0004] In view of this, the embodiments of the present application provide a vehicle-based weed spraying method, device, equipment and storage medium, which can accurately detect the location of weeds, realize adaptive adjustment of the spraying range, effectively improve the accuracy and efficiency of weed spraying, and reduce resource waste. At the same time, it ensures that the spraying of the vehicle has real-time responsiveness and accuracy while moving forward.

[0005] This application mainly includes the following aspects:

[0006] In a first aspect, an embodiment of the present application provides a vehicle-based weed spraying method, the spraying method comprising:

[0007] (A) for each camera, determining a start delay time of a nozzle corresponding to the camera based on a height of the camera relative to the horizontal ground and an inclination angle of the camera relative to an orthogonal plane of the horizontal ground;

[0008] (B) obtaining a current image captured by the camera;

[0009] (C) if at least one weed is detected from the current image using a preset detection model, determining, for each weed, a coordinate of the weed in the image coordinate system, and determining, based on the coordinate of the weed in the image coordinate system, a field of view distance between the weed and a boundary of the field of view of the camera close to the vehicle;

[0010] (D) determining a continuous spraying time of the nozzle corresponding to the camera based on a maximum spraying distance of the nozzle corresponding to the camera and the field of view distance;

[0011] (E) Based on the start-up delay time of the nozzle corresponding to the camera and the continuous spraying time of the nozzle corresponding to the camera, the nozzle corresponding to the camera is controlled to spray the weeds.

[0012] Furthermore, for each camera, based on the height of the camera relative to the horizontal ground and the inclination angle of the camera relative to the orthogonal plane of the horizontal ground, determining the opening delay time of the nozzle corresponding to the camera includes:

[0013] For each camera, based on the height of the camera relative to the horizontal ground and the inclination angle of the camera relative to the orthogonal plane of the horizontal ground, determine the blind spot length of the blind spot of the camera along the vehicle heading direction;

[0014] The quotient of the blind spot length and the current vehicle speed is determined as the opening delay time of the nozzle corresponding to the camera.

[0015] Furthermore, determining the field of view distance between the weed and the field of view boundary of the camera near the vehicle based on the coordinates of the weed in the image coordinate system includes:

[0016] Based on the camera intrinsic parameter matrix of the camera and the height of the camera relative to the horizontal ground, the coordinates of the weed in the image coordinate system are converted into coordinates in the camera coordinate system;

[0017] Based on the camera extrinsic parameter matrix of the camera, the coordinates of the weed in the camera coordinate system are converted into coordinates in the world coordinate system;

[0018] Based on the coordinates of the weed in the world coordinate system, a field of view distance between the weed and a field of view boundary of the camera close to the vehicle is determined.

[0019] Further, the determining of the continuous spraying time of the nozzle corresponding to the camera based on the maximum spraying distance of the nozzle corresponding to the camera and the field of view distance includes:

[0020] The product of the preset nozzle working time and the current vehicle speed is determined as the maximum spraying distance of the nozzle corresponding to the camera;

[0021] Determine whether the maximum spraying distance of the nozzle corresponding to the camera is greater than or equal to the field of view distance;

[0022] If the maximum spraying distance of the nozzle corresponding to the camera is greater than or equal to the field of view distance, the quotient of the field of view distance and the current vehicle speed is determined as the continuous spraying time of the nozzle corresponding to the camera;

[0023] If the maximum spraying distance of the nozzle corresponding to the camera is less than the field of view distance, return to step (B).

[0024] In a second aspect, an embodiment of the present application further provides a vehicle-based weed spraying device, the weed spraying device comprising:

[0025] An opening delay time determination module determines, for each camera, an opening delay time of a nozzle corresponding to the camera based on a height of the camera relative to the horizontal ground and an inclination angle of the camera relative to an orthogonal plane of the horizontal ground;

[0026] An image acquisition module obtains the current image captured by the camera;

[0027] a distance calculation module, which determines, for each weed, a coordinate of the weed in the image coordinate system if at least one weed is detected from the current image using a preset detection model, and determines, based on the coordinate of the weed in the image coordinate system, a field of view distance between the weed and a field of view boundary of the camera near the vehicle;

[0028] A continuous spraying time determination module, which determines the continuous spraying time of the nozzle corresponding to the camera based on the maximum sprayable distance of the nozzle corresponding to the camera and the field of view distance;

[0029] The control module controls the nozzle corresponding to the camera to spray the weeds based on the start delay time of the nozzle corresponding to the camera and the continuous spraying time of the nozzle corresponding to the camera.

[0030] Furthermore, the start-up delay time determination module is specifically used for:

[0031] For each camera, based on the height of the camera relative to the horizontal ground and the inclination angle of the camera relative to the orthogonal plane of the horizontal ground, determine the blind spot length of the blind spot of the camera along the vehicle heading direction;

[0032] The quotient of the blind spot length and the current vehicle speed is determined as the opening delay time of the nozzle corresponding to the camera.

[0033] Furthermore, when the distance calculation module is used to determine the visual distance between the weed and the visual field boundary of the camera near the vehicle based on the coordinates of the weed in the image coordinate system, it is also used to:

[0034] Based on the camera intrinsic parameter matrix of the camera and the height of the camera relative to the horizontal ground, the coordinates of the weed in the image coordinate system are converted into coordinates in the camera coordinate system;

[0035] Based on the camera extrinsic parameter matrix of the camera, the coordinates of the weed in the camera coordinate system are converted into coordinates in the world coordinate system;

[0036] Based on the coordinates of the weed in the world coordinate system, a field of view distance between the weed and a field of view boundary of the camera close to the vehicle is determined.

[0037] Furthermore, the continuous spraying time determination module is specifically used for:

[0038] The product of the preset nozzle working time and the current vehicle speed is determined as the maximum spraying distance of the nozzle corresponding to the camera;

[0039] Determine whether the maximum spraying distance of the nozzle corresponding to the camera is greater than or equal to the field of view distance;

[0040] If the maximum spraying distance of the nozzle corresponding to the camera is greater than or equal to the field of view distance, the quotient of the field of view distance and the current vehicle speed is determined as the continuous spraying time of the nozzle corresponding to the camera;

[0041] If the maximum spraying distance of the nozzle corresponding to the camera is smaller than the field of view distance, the image acquisition module is used.

[0042] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and the machine-readable instructions are executed by the processor to execute the steps of the vehicle-based weed spraying method described in the first aspect or any possible implementation manner of the first aspect.

[0043] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of vehicle-based weed spraying as described in the first aspect or any possible implementation of the first aspect are executed.

[0044] The embodiments of the present application provide a vehicle-based weed spraying method, device, equipment and storage medium, which collect images in real time through a camera, use a preset detection model to identify weeds and determine the position of weeds in the image coordinate system, calculate the opening delay time of the nozzle in combination with the camera height and tilt angle, and determine the continuous spraying time according to the distance between the weeds and the boundary of the camera field of view and the maximum sprayable distance of the nozzle, and finally control the nozzle to spray weeds accurately within an appropriate time and range.

[0045] In this way, the present application can accurately detect the location of weeds and realize adaptive adjustment of the spraying range, effectively improving the accuracy and efficiency of weed spraying and reducing resource waste. At the same time, it ensures that the spraying of the vehicle has real-time responsiveness and accuracy while moving forward.

[0046] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 One of the flow charts of a vehicle-based weed spraying method provided in an embodiment of the present application is shown;

[0049] Figure 2 A second flow chart of a vehicle-based weed spraying method provided in an embodiment of the present application is shown;

[0050] Figure 3 An example diagram showing the position of a camera and weeds provided in an embodiment of the present application is shown;

[0051] Figure 4 A third flowchart of a vehicle-based weed spraying method provided in an embodiment of the present application is shown;

[0052] Figure 5 A fourth flowchart of a vehicle-based weed spraying method provided in an embodiment of the present application is shown;

[0053] Figure 6 A schematic structural diagram of a vehicle-based weed spraying device provided in an embodiment of the present application is shown;

[0054] Figure 7 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0055] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art, under the guidance of the content of the present application, can add one or more other operations to the flowchart, or remove one or more operations from the flowchart.

[0056] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0057] The following methods, devices, electronic devices, or computer-readable storage media of the embodiments of the present application can be applied to any scenario where vehicle weed spraying is required. The embodiments of the present application are not limited to specific application scenarios. Any solution using the vehicle-based weed spraying method and device provided by the embodiments of the present application is within the protection scope of the present application.

[0058] It is worth noting that in the process of promoting agricultural modernization, precision agriculture technology has gradually become a key component of agricultural production. The core essence of precision agriculture technology is to carry out refined management of agricultural production with the help of information technology. Among them, weed detection and spraying technology, as an important application field of precision agriculture, has received extensive attention and in-depth research in recent years. Traditional weed spraying systems usually adopt carpet spraying mode or fixed spraying mode. Here, carpet spraying means that the nozzle sprays the entire farmland indiscriminately as the vehicle moves; fixed spraying mode means that the nozzle triggers the spraying operation at a predetermined time interval. However, both carpet spraying mode and fixed spraying mode are difficult to achieve precise spraying. Not only can they not cope with complex weed distribution environments, but they will also damage the healthy growth of crops and also lead to higher cost investment. Therefore, how to spray weeds accurately has become an urgent problem to be solved.

[0059] In view of the above problems, the embodiments of the present application propose a vehicle-based weed spraying method, device, equipment and storage medium, which can accurately detect the location of weeds and realize adaptive adjustment of the spraying range, effectively improving the accuracy and efficiency of weed spraying and reducing resource waste. At the same time, it ensures that the spraying of the vehicle has real-time responsiveness and accuracy while moving forward.

[0060] To facilitate the understanding of the present application, the technical solution provided by the present application is described in detail below in conjunction with specific embodiments.

[0061] See also Figure 1 , Figure 1 This is one of the flow charts of a vehicle-based weed spraying method provided in an embodiment of the present application.

[0062] Corn, soybeans and other grains are important food crops, and weeds are one of the main problems in corn and soybean cultivation. Weeds compete with crops for soil moisture, nutrients and sunlight, reducing crop yields, resulting in lower crop yields and increased difficulty in harvesting. In addition, weeds may become hosts for pests and diseases, further harming crop growth.

[0063] With the development of smart agricultural technology, intelligent spraying systems based on machine vision and automatic control have gradually become a research hotspot. For example, John Deere's See&Spray system integrates computer vision technology to enable the machine to identify weeds and crops and apply herbicides only to weeds. The system installs a camera on the spray boom to capture ground images in real time, uses a deep learning detection model to detect crops and weeds in the image, and combines GPS remote sensing and other technologies to achieve trigger control of sprinkler spraying. However, this solution is costly, has high requirements for the working environment, and does not consider the impact of factors such as vehicle running speed, weed density, and trigger delay in actual use, which reduces the spraying accuracy to a certain extent.

[0064] In the embodiment of the present application, the front of the vehicle is provided with a plurality of nozzles on the same horizontal straight line; at least one camera is provided above the plurality of nozzles; and the horizontal field of view of each camera covers the spraying range of at least one nozzle. As an example, it is assumed that the front of the vehicle is provided with a spray bar, which is placed horizontally on the front of the vehicle, and there are 12 nozzles on the spray bar, which spray perpendicularly to the ground, and a camera is provided above the midpoint of the straight line where two adjacent nozzles are located, and for each camera, the horizontal field of view of the camera covers the spraying range of the two nozzles.

[0065] like Figure 1 As shown in , the vehicle-based weed spraying method provided in the embodiment of the present application comprises the following steps:

[0066] Step S101, for each camera, based on the height of the camera relative to the horizontal ground and the inclination angle of the camera relative to the orthogonal plane of the horizontal ground, determine the opening delay time of the nozzle corresponding to the camera.

[0067] Here, the height of the camera relative to the horizontal ground is detected by a depth sensor installed on the vehicle. The height of the camera relative to the horizontal ground obtained by the depth sensor can dynamically adjust the relative height of the camera and the nozzle to ensure that the nozzle can spray accurately under various height conditions. Among them, the inclination angle of the camera relative to the orthogonal plane of the horizontal ground is the installation angle of the camera.

[0068] Combine the following Figure 2 To illustrate how to determine the opening delay time of the nozzle corresponding to each camera based on the height of the camera relative to the horizontal ground and the inclination angle of the camera relative to the orthogonal plane of the horizontal ground.

[0069] Here, the start delay time of the nozzle corresponding to the camera is the time required to wait from the moment when the presence of weeds is detected to the time when the nozzle actually starts spraying.

[0070] See also Figure 2 , Figure 2 This is a second flow chart of a vehicle-based weed spraying method provided in an embodiment of the present application.

[0071] like Figure 2 As shown, regarding step S101, in specific implementation, as an example, the following steps may be included:

[0072] Step S1011, for each camera, based on the height of the camera relative to the horizontal ground and the inclination angle of the camera relative to the orthogonal plane of the horizontal ground, determine the blind spot length of the camera along the vehicle heading direction.

[0073] Here, if Figure 3 As shown in , as an example, H is the height of the camera relative to the horizontal ground, θ is the installation angle of the camera, and r blind The length of the blind spot of the camera along the vehicle's direction is as follows: Figure 3 It can be seen that the blind spot length of the camera blind spot along the vehicle's direction can be calculated by formula (1).

[0074]

[0075] Step S1012: The quotient of the blind spot length and the current vehicle speed is determined as the opening delay time of the nozzle corresponding to the camera.

[0076] Here, if Figure 3As shown in , as an example, the opening delay time of the nozzle corresponding to the camera can be calculated by formula (2).

[0077]

[0078] Among them, t delay is the opening delay time of the nozzle corresponding to the camera, V car is the current vehicle speed.

[0079] See again Figure 1 , step S102, obtaining the current image captured by the camera.

[0080] Step S103: if at least one weed is detected from the current image using the preset detection model, then for each weed, the coordinates of the weed in the image coordinate system are determined, and based on the coordinates of the weed in the image coordinate system, the field of view distance between the weed and the field of view boundary of the camera close to the vehicle is determined.

[0081] Here, the prediction detection model is an intelligent algorithm model trained with a large amount of image data. Its function is to analyze and process the current image collected by the camera and identify the presence of weeds in the image.

[0082] If no weeds are detected from the current image using the preset detection model, the process returns to step S102 .

[0083] Combine the following Figure 4 To illustrate how to determine the field of view distance between the weed and the field of view boundary of the camera close to the vehicle based on the coordinates of the weed in the image coordinate system.

[0084] See also Figure 4 , Figure 4 This is a third flow chart of a vehicle-based weed spraying method provided in an embodiment of the present application.

[0085] like Figure 4 As shown, regarding the step S103 of determining the field of view distance between the weed and the field of view boundary of the camera near the vehicle based on the coordinates of the weed in the image coordinate system, in specific implementation, as an example, the following steps may be included:

[0086] Step S1031 : based on the camera intrinsic parameter matrix of the camera and the height of the camera relative to the horizontal ground, the coordinates of the weeds in the image coordinate system are converted into coordinates in the camera coordinate system.

[0087] Here, as an example, the coordinates of the weed in the camera coordinate system can be calculated by (3).

[0088]

[0089] Among them, X c is the X-axis coordinate of the weed in the camera coordinate system, Y c is the Y-axis coordinate of the weed in the camera coordinate system, Z c is the Z-axis coordinate of the weed in the camera coordinate system, K is the camera internal parameter matrix of the camera, u is the X-axis coordinate of the weed in the image coordinate system, and v is the Y-axis coordinate of the weed in the image coordinate system. c Equal to the height of the camera relative to the horizontal ground.

[0090] Step S1032: based on the camera extrinsic parameter matrix of the camera, convert the coordinates of the weeds in the camera coordinate system into coordinates in the world coordinate system.

[0091] Here, as an example, the coordinates of the weed in the world coordinate system can be calculated by (4).

[0092]

[0093] Among them, X w is the X-axis coordinate of the weed in the world coordinate system, Y w is the Y-axis coordinate of the weed in the world coordinate system, Z w is the Z-axis coordinate of the weed in the world coordinate system, and T is the camera extrinsic parameter matrix of the camera.

[0094] Step S1033: determining the field of view distance between the weed and the field of view boundary of the camera close to the vehicle based on the coordinates of the weed in the world coordinate system.

[0095] See again Figure 1 , step S104, determining the continuous spraying time of the nozzle corresponding to the camera based on the maximum spraying distance of the nozzle corresponding to the camera and the field of view distance.

[0096] Here, the maximum spraying distance of the nozzle corresponding to the camera is the distance the nozzle moves within the preset nozzle working time; wherein the preset nozzle working time is the longest time allowed for the working process from the start of the spraying operation to the stop of the spraying operation. The continuous spraying time of the nozzle corresponding to the camera is the duration from the nozzle being turned on to being turned off.

[0097] Combine the following Figure 5 To illustrate how to determine the continuous spraying time of the nozzle corresponding to the camera based on the maximum spraying distance of the nozzle corresponding to the camera and the field of view distance.

[0098] See also Figure 5 , Figure 5 This is a fourth flow chart of a vehicle-based weed spraying method provided in an embodiment of the present application.

[0099] like Figure 5 As shown, regarding step S104, in specific implementation, as an example, the following steps may be included:

[0100] Step S1041, determining the product of the preset nozzle working time and the current vehicle speed as the maximum spraying distance of the nozzle corresponding to the camera.

[0101] Here, as an example, assuming that the preset nozzle working time is 5 seconds and the current vehicle speed is 1 meter per second, the maximum spraying distance of the nozzle corresponding to the camera is 5 meters.

[0102] Step S1042, determining whether the maximum spraying distance of the nozzle corresponding to the camera is greater than or equal to the field of view distance.

[0103] Here, the purpose of comparing the maximum spraying distance of the nozzle corresponding to the camera with the field of view distance between the weeds and the field of view boundary of the camera near the vehicle is to ensure that after the nozzle is turned on, there is enough time to spray the pesticide or herbicide evenly on the weeds, while avoiding waste and environmental pollution caused by excessive spraying.

[0104] Step S1043: If the maximum spraying distance of the nozzle corresponding to the camera is greater than or equal to the field of view distance, the quotient of the field of view distance and the current vehicle speed is determined as the continuous spraying time of the nozzle corresponding to the camera.

[0105] Here, as an example, the continuous spraying time of the nozzle corresponding to the camera can be calculated by (5).

[0106]

[0107] Among them, t spray is the continuous spraying time of the nozzle corresponding to the camera, d max is the maximum sprayable distance of the nozzle. As an example, assuming that the maximum sprayable distance of the nozzle is 5 meters, the field of view distance between the weeds and the field of view boundary of the camera close to the vehicle is 3 meters, and the current vehicle speed is 5 meters / second, since the maximum sprayable distance of 5 meters is greater than the field of view distance of 3 meters, the continuous spraying time of the nozzle is 3m÷5m / s=0.6 seconds. If the maximum sprayable distance of the nozzle corresponding to the camera is greater than or equal to the field of view distance, the time when the weeds start to be sprayed can be calculated by (6).

[0108]

[0109] Among them, t start This is the time when weeds start to be sprayed.

[0110] Step S1044: if the maximum spraying distance of the nozzle corresponding to the camera is less than the field of view distance, return to step S102.

[0111] Here, if the maximum spraying distance of the nozzle corresponding to the camera is less than the field of view distance, the nozzle corresponding to the camera will not be turned on, and the continuous spraying time of the nozzle corresponding to the camera is 0.

[0112] See again Figure 1 , step S105, based on the opening delay time of the nozzle corresponding to the camera and the continuous spraying time of the nozzle corresponding to the camera, control the nozzle corresponding to the camera to spray the weeds.

[0113] Here, as an example, assuming that the opening delay time of the nozzle corresponding to the camera is 5 seconds, and the continuous spraying time of the nozzle corresponding to the camera is 0.6 seconds, the nozzle corresponding to the camera is turned on at 5 seconds, and is turned off after being turned on for 0.6 seconds.

[0114] The embodiment of the present application provides a vehicle-based weed spraying method, through which the weed position can be accurately detected, and the spraying range can be adaptively adjusted, which effectively improves the accuracy and efficiency of weed spraying and reduces resource waste. At the same time, it ensures that the vehicle sprays with real-time responsiveness and accuracy while moving forward.

[0115] Based on the same application concept, the embodiments of the present application also provide a vehicle-based weed spraying device corresponding to the vehicle-based weed spraying method provided in the above embodiments. Since the principle of solving the problem by the device in the embodiments of the present application is similar to that of the vehicle-based weed spraying method in the above embodiments of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0116] See also Figure 6 , Figure 6 A schematic structural diagram of a vehicle-based weed spraying device provided in an embodiment of the present application.

[0117] like Figure 6 As shown in FIG. 1 , the vehicle-based weed spraying device 210 provided in the embodiment of the present application includes:

[0118] The opening delay time determination module 211 determines, for each camera, the opening delay time of the nozzle corresponding to the camera based on the height of the camera relative to the horizontal ground and the inclination angle of the camera relative to the orthogonal plane of the horizontal ground;

[0119] The image acquisition module 212 acquires the current image acquired by the camera;

[0120] The distance calculation module 213 determines, for each weed, the coordinates of the weed in the image coordinate system if at least one weed is detected from the current image using the preset detection model, and determines, based on the coordinates of the weed in the image coordinate system, the field of view distance between the weed and the field of view boundary of the camera near the vehicle;

[0121] A continuous spraying time determination module 214 determines the continuous spraying time of the nozzle corresponding to the camera based on the maximum sprayable distance of the nozzle corresponding to the camera and the field of view distance;

[0122] The control module 215 controls the nozzle corresponding to the camera to spray the weeds based on the start delay time of the nozzle corresponding to the camera and the continuous spraying time of the nozzle corresponding to the camera.

[0123] Furthermore, the start-up delay time determination module 211 is specifically used for:

[0124] For each camera, based on the height of the camera relative to the horizontal ground and the inclination angle of the camera relative to the orthogonal plane of the horizontal ground, determine the blind spot length of the blind spot of the camera along the vehicle heading direction;

[0125] The quotient of the blind spot length and the current vehicle speed is determined as the opening delay time of the nozzle corresponding to the camera.

[0126] Furthermore, when the distance calculation module 213 is used to determine the visual distance between the weed and the visual field boundary of the camera near the vehicle based on the coordinates of the weed in the image coordinate system, it is also used to:

[0127] Based on the camera intrinsic parameter matrix of the camera and the height of the camera relative to the horizontal ground, the coordinates of the weed in the image coordinate system are converted into coordinates in the camera coordinate system;

[0128] Based on the camera extrinsic parameter matrix of the camera, the coordinates of the weed in the camera coordinate system are converted into coordinates in the world coordinate system;

[0129] Based on the coordinates of the weed in the world coordinate system, a field of view distance between the weed and a field of view boundary of the camera close to the vehicle is determined.

[0130] Furthermore, the continuous spraying time determination module 214 is specifically used for:

[0131] The product of the preset nozzle working time and the current vehicle speed is determined as the maximum spraying distance of the nozzle corresponding to the camera;

[0132] Determine whether the maximum spraying distance of the nozzle corresponding to the camera is greater than or equal to the field of view distance;

[0133] If the maximum spraying distance of the nozzle corresponding to the camera is greater than or equal to the field of view distance, the quotient of the field of view distance and the current vehicle speed is determined as the continuous spraying time of the nozzle corresponding to the camera;

[0134] If the maximum spraying distance of the nozzle corresponding to the camera is smaller than the field of view distance, the image acquisition module 212 is used.

[0135] The embodiment of the present application provides a vehicle-based weed spraying device, through which the weed position can be accurately detected, and the spraying range can be adaptively adjusted, which effectively improves the accuracy and efficiency of weed spraying and reduces resource waste. At the same time, it ensures that the spraying of the vehicle has real-time responsiveness and accuracy while moving forward.

[0136] See also Figure 7 , Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0137] like Figure 7 As shown in , the electronic device 300 includes a processor 310 , a memory 320 and a bus 330 .

[0138] The memory 320 stores machine-readable instructions executable by the processor 310. When the electronic device 300 is running, the processor 310 communicates with the memory 320 via the bus 330. When the machine-readable instructions are executed by the processor 310, the above-mentioned Figure 1 , Figure 2 , Figure 4 and Figure 5 The specific implementation of the steps of the vehicle-based weed spraying method in the method embodiment shown can be found in the method embodiment, and will not be repeated here.

[0139] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the computer program can execute the above-mentioned Figure 1 , Figure 2 , Figure 4 and Figure 5 The specific implementation of the steps of the vehicle-based weed spraying method in the method embodiment shown can be found in the method embodiment, and will not be repeated here.

[0140] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0141] 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.

[0142] 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.

[0143] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0144] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A vehicle-based weed spraying method, characterized in that: The front of the vehicle is provided with a plurality of nozzles on the same horizontal line; at least one camera is provided above the plurality of nozzles; the horizontal field of view of each camera covers the spraying range of at least one nozzle; the spraying method comprises: (A) for each camera, determining a start delay time of a nozzle corresponding to the camera based on a height of the camera relative to the horizontal ground and an inclination angle of the camera relative to an orthogonal plane of the horizontal ground; (B) obtaining a current image captured by the camera; (C) if at least one weed is detected from the current image using a preset detection model, determining, for each weed, a coordinate of the weed in the image coordinate system, and determining, based on the coordinate of the weed in the image coordinate system, a field of view distance between the weed and a boundary of the field of view of the camera close to the vehicle; (D) determining a continuous spraying time of the nozzle corresponding to the camera based on a maximum spraying distance of the nozzle corresponding to the camera and the field of view distance; (E) Based on the start-up delay time of the nozzle corresponding to the camera and the continuous spraying time of the nozzle corresponding to the camera, the nozzle corresponding to the camera is controlled to spray the weeds.

2. The spraying method according to claim 1, characterized in that: The method of determining, for each camera, a start delay time of a nozzle corresponding to the camera based on a height of the camera relative to the horizontal ground and an inclination angle of the camera relative to an orthogonal plane of the horizontal ground, comprises: For each camera, based on the height of the camera relative to the horizontal ground and the inclination angle of the camera relative to the orthogonal plane of the horizontal ground, determine the blind spot length of the blind spot of the camera along the vehicle heading direction; The quotient of the blind spot length and the current vehicle speed is determined as the opening delay time of the nozzle corresponding to the camera.

3. The spraying method according to claim 1, characterized in that: The determining, based on the coordinates of the weeds in the image coordinate system, the field of view distance between the weeds and the field of view boundary of the camera near the vehicle includes: Based on the camera intrinsic parameter matrix of the camera and the height of the camera relative to the horizontal ground, the coordinates of the weed in the image coordinate system are converted into coordinates in the camera coordinate system; Based on the camera extrinsic parameter matrix of the camera, the coordinates of the weed in the camera coordinate system are converted into coordinates in the world coordinate system; Based on the coordinates of the weed in the world coordinate system, a field of view distance between the weed and a field of view boundary of the camera close to the vehicle is determined.

4. The spraying method according to claim 1, characterized in that: The determining the continuous spraying time of the nozzle corresponding to the camera based on the maximum sprayable distance of the nozzle corresponding to the camera and the field of view distance includes: The product of the preset nozzle working time and the current vehicle speed is determined as the maximum spraying distance of the nozzle corresponding to the camera; Determine whether the maximum spraying distance of the nozzle corresponding to the camera is greater than or equal to the field of view distance; If the maximum spraying distance of the nozzle corresponding to the camera is greater than or equal to the field of view distance, the quotient of the field of view distance and the current vehicle speed is determined as the continuous spraying time of the nozzle corresponding to the camera; If the maximum spraying distance of the nozzle corresponding to the camera is less than the field of view distance, return to step (B).

5. A vehicle-based weed spraying device, characterized in that: The weed spraying device comprises: An opening delay time determination module determines, for each camera, an opening delay time of a nozzle corresponding to the camera based on a height of the camera relative to the horizontal ground and an inclination angle of the camera relative to an orthogonal plane of the horizontal ground; An image acquisition module obtains the current image captured by the camera; a distance calculation module, which determines, for each weed, a coordinate of the weed in the image coordinate system if at least one weed is detected from the current image using a preset detection model, and determines, based on the coordinate of the weed in the image coordinate system, a field of view distance between the weed and a field of view boundary of the camera near the vehicle; A continuous spraying time determination module, which determines the continuous spraying time of the nozzle corresponding to the camera based on the maximum sprayable distance of the nozzle corresponding to the camera and the field of view distance; The control module controls the nozzle corresponding to the camera to spray the weeds based on the start delay time of the nozzle corresponding to the camera and the continuous spraying time of the nozzle corresponding to the camera.

6. The spraying device according to claim 5, characterized in that The start-up delay time determination module is specifically used for: For each camera, based on the height of the camera relative to the horizontal ground and the inclination angle of the camera relative to the orthogonal plane of the horizontal ground, determine the blind spot length of the blind spot of the camera along the vehicle heading direction; The quotient of the blind spot length and the current vehicle speed is determined as the opening delay time of the nozzle corresponding to the camera.

7. The spraying device according to claim 5, characterized in that The distance calculation module, when used to determine the visual field distance between the weed and the visual field boundary of the camera near the vehicle based on the coordinates of the weed in the image coordinate system, is further used to: Based on the camera intrinsic parameter matrix of the camera and the height of the camera relative to the horizontal ground, the coordinates of the weed in the image coordinate system are converted into coordinates in the camera coordinate system; Based on the camera extrinsic parameter matrix of the camera, the coordinates of the weed in the camera coordinate system are converted into coordinates in the world coordinate system; Based on the coordinates of the weed in the world coordinate system, a field of view distance between the weed and a field of view boundary of the camera close to the vehicle is determined.

8. The spraying device according to claim 5, characterized in that The continuous spraying time determination module is specifically used for: The product of the preset nozzle working time and the current vehicle speed is determined as the maximum spraying distance of the nozzle corresponding to the camera; Determine whether the maximum spraying distance of the nozzle corresponding to the camera is greater than or equal to the field of view distance; If the maximum spraying distance of the nozzle corresponding to the camera is greater than or equal to the field of view distance, the quotient of the field of view distance and the current vehicle speed is determined as the continuous spraying time of the nozzle corresponding to the camera; If the maximum spraying distance of the nozzle corresponding to the camera is smaller than the field of view distance, the image acquisition module is used.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate with each other through the bus, and the machine-readable instructions are executed by the processor to execute the steps of the vehicle-based weed spraying method as described in any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that: The computer readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the vehicle-based weed spraying method according to any one of claims 1 to 4 are performed.

Images