A control method, apparatus, device, and storage medium

Abstract

The present disclosure provides a control method, device, equipment and storage medium, the method comprises: acquiring a first farmland image containing weeds; determining the target position and attribute information of the weeds based on the first farmland image; determining the laser parameter of the laser weeding device according to the attribute information; controlling the laser weeding device to emit laser under the laser parameter to the target position. By using the method, the accurate position of the weeds and the attribute information of the weeds are obtained by processing the first farmland image, and the laser parameter of the laser weeding device is adjusted according to the attribute information of the weeds, so that the laser under the laser parameter can effectively remove the weeds, thereby realizing efficient and accurate weed removal operation.

Description

Technical Field

[0001] This disclosure relates to the field of image processing, and more particularly to a control method, apparatus, device, and storage medium. Background Technology

[0002] In agricultural production, weed management is crucial for maintaining healthy crop growth and yield. Commonly used weed control methods mainly include manual weeding and laser weeding. However, manual weeding is labor-intensive and inefficient. Laser weeding uses high-energy lasers to directly irradiate weeds, damaging and killing weed cells through heat to achieve the purpose of weed control. However, laser weeding has difficulty accurately distinguishing between crops and weeds, and can easily damage crops.

[0003] Therefore, how to efficiently and accurately remove weeds has become a technical problem that urgently needs to be solved. Summary of the Invention

[0004] This disclosure provides a control method, apparatus, device, and storage medium to at least solve the above-mentioned technical problems existing in the prior art.

[0005] According to a first aspect of this disclosure, a control method is provided, the method comprising:

[0006] Obtain an image of the first farmland containing weeds;

[0007] Based on the first farmland image, determine the target location and attribute information of the weeds;

[0008] The laser parameters of the laser weeding device are determined based on the attribute information.

[0009] The laser weeding device is controlled to emit laser light at the specified parameters toward the target location.

[0010] In one possible implementation, after controlling the laser weeding device to emit laser light at the specified laser parameters toward the target location, the method further includes:

[0011] Obtain the image of the second farmland;

[0012] Based on the first farmland image and the second farmland image, determine the success rate of weed removal;

[0013] Adjust the laser parameters of the laser weeding equipment based on the success rate of weed removal.

[0014] In one possible implementation, determining the target location and attribute information of the weeds based on the first farmland image includes:

[0015] The first farmland image is input into a pre-trained image recognition model to obtain images of each weed area contained in the first farmland image and information on the types of weeds.

[0016] Based on the position of the weeds in the first farmland map in each weed area image, the target location of the weeds in the farmland is determined;

[0017] The growth status information of the weeds is determined based on the images of each weed area, and the species information and the growth status information are used as the attribute information of the weeds.

[0018] In one possible implementation, determining the growth status information of the weeds based on the images of each weed area includes:

[0019] Extract the color and shape features of each weed area image;

[0020] The health status of the weed is determined based on the color characteristics, and the growth stage of the weed is determined based on the shape characteristics. The health status and the growth stage are used as growth status information.

[0021] In one possible implementation, determining the laser parameters of the laser weeding device based on the farmland environmental information and the attribute information includes:

[0022] The laser power and laser irradiation duration of the laser weeding device are determined based on the attribute information and used as laser parameters.

[0023] In one possible implementation, the attribute information includes the type, health status, and growth stage of the weeds;

[0024] The laser power of the laser weeding device is determined based on the attribute information using the following formula:

[0025] P = k × (delta_H × H + delta_S × S)

[0026] Where P represents the laser power, k is the coefficient corresponding to the type of weed, H represents the health status of the weed, S represents the growth stage of the weed, and delta_H and delta_S are sensitivity coefficients.

[0027] The laser irradiation duration of the laser weeding device is determined based on the attribute information using the following formula:

[0028] T = eta × sqrt(P) / rho

[0029] Where T represents the laser irradiation duration, eta is the time adjustment coefficient, sqrt(P) represents the square root of the laser power P, and rho represents the resistance coefficient.

[0030] In one possible implementation, the method further includes:

[0031] Obtain farmland environmental information;

[0032] Determining the laser parameters of the laser weeding device based on the attribute information includes:

[0033] Based on the attribute information and the farmland environment information, the laser parameters of the laser weeding equipment are determined.

[0034] According to a second aspect of this disclosure, a control device is provided, the device comprising:

[0035] The image acquisition module is used to acquire an image of the first farmland containing weeds;

[0036] The information determination module is used to determine the target location and attribute information of the weeds based on the first farmland image;

[0037] The parameter determination module is used to determine the laser parameters of the laser weeding device based on the attribute information.

[0038] The control module is used to control the laser weeding device to emit laser light at the specified laser parameters toward the target location.

[0039] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0040] At least one processor; and

[0041] A memory communicatively connected to the at least one processor; wherein,

[0042] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the methods described in this disclosure.

[0043] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions for causing a computer to perform the methods described in this disclosure.

[0044] The control method, apparatus, device, and storage medium disclosed herein acquire a first farmland image containing weeds; based on the first farmland image, determine the target location and attribute information of the weeds; determine the laser parameters of a laser weeding device according to the attribute information; and control the laser weeding device to emit laser light at the target location according to the laser parameters. In other words, by processing the first farmland image, the accurate location and attribute information of the weeds are obtained, and the laser parameters of the laser weeding device are adjusted according to the weed attribute information, so that the laser light at the specified parameters can effectively remove the weeds, thereby achieving efficient and accurate weed removal.

[0045] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0046] The above and other objects, features, and advantages of this disclosure will become readily apparent from the following detailed description of exemplary embodiments, taken in conjunction with the accompanying drawings. Several embodiments of this disclosure are illustrated in the drawings by way of example and not limitation, in which:

[0047] In the accompanying drawings, the same or corresponding reference numerals indicate the same or corresponding parts.

[0048] Figure 1 A schematic diagram illustrating the implementation flow of the control method provided in an embodiment of this disclosure is shown;

[0049] Figure 2 This illustration shows a schematic diagram of an information determination process provided by an embodiment of the present disclosure;

[0050] Figure 3 A schematic diagram of a control device provided in an embodiment of this disclosure is shown;

[0051] Figure 4 A schematic diagram of the composition structure of an electronic device according to an embodiment of the present disclosure is shown. Detailed Implementation

[0052] To make the objectives, features, and advantages of this disclosure more apparent and understandable, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort are within the scope of protection of this disclosure.

[0053] Because existing weeding methods are inefficient and prone to damaging crops, this disclosure provides a control method, apparatus, device, and storage medium for efficient and accurate weed removal. The recommended method provided in this disclosure can be applied to electronic devices such as mobile phones, computers, and tablets.

[0054] The technical solutions of the embodiments of this disclosure will now be described with reference to the accompanying drawings.

[0055] Figure 1 A schematic diagram illustrating the implementation flow of the control method provided in this disclosure embodiment is shown, as follows: Figure 1 As shown, the method includes:

[0056] S101, Obtain the first farmland image containing weeds.

[0057] In this disclosure, the first farmland image can be an image captured using an image acquisition device of the farmland to be weeded. The first farmland image may include images of crops and weeds in the farmland to be weeded. The image acquisition device can be a high-resolution camera or a mobile phone with video recording capabilities, etc. In this disclosure, the image acquisition device can be mounted on a drone to capture images of the farmland to be weeded, or workers can directly capture images of the farmland to be weeded using the image acquisition device. In this disclosure, satellite cloud images of the farmland to be weeded can also be obtained as the first farmland image.

[0058] S102, Based on the first farmland image, determine the target location and attribute information of the weeds.

[0059] In this disclosure, plants in a first farmland image can be identified and classified to obtain the types of weeds in the farmland to be weeded. After identifying the weeds in the first farmland image, the position of the weeds in the first farmland image can be determined by edge detection or object localization algorithms. Then, based on the transformation relationship between the image coordinate system and the coordinate system of the real-world object position, and the position of the weeds in the first farmland image, the true position coordinates of the weeds in the first farmland image are determined, and the true position is used as the target position of the weeds. The transformation relationship between the image coordinate system and the coordinate system of the real-world object position can be determined based on the intrinsic and extrinsic parameters of the image acquisition device and the geometric relationship between the farmland to be weeded and the image acquisition device.

[0060] The attributes of weeds include, but are not limited to, their size, shape, and color.

[0061] S103, determine the laser parameters of the laser weeding device based on the attribute information.

[0062] In this disclosure, laser parameters are parameters that can affect the weeding effect, energy consumption, and / or efficiency of laser weeding equipment. Laser parameters may include at least one of the following: laser power, laser wavelength, laser focus, and laser irradiation duration. Specifically, laser power refers to the energy output by the laser beam of the laser weeding equipment; the higher the laser power, the more significant the destructive effect on weeds. Laser wavelength refers to the wavelength of the laser beam output by the laser weeding equipment; different wavelengths can achieve different destructive effects on vegetation. For example, green lasers can directly destroy the cellular structure of weeds, while infrared lasers can destroy weeds by heating or evaporating plant tissue. Laser focus refers to the degree of focusing of the laser beam of the laser weeding equipment; the degree of focusing can affect the energy density and depth of action of the laser beam. Laser irradiation duration refers to the duration for which the laser beam of the laser weeding equipment irradiates the weeds. In this disclosure, the laser irradiation duration can be reasonably controlled based on the properties of the weeds to achieve better weeding effects while ensuring the safety of weeding.

[0063] S104, control the laser weeding device to emit laser light at the specified laser parameters toward the target location.

[0064] In this disclosure, a laser weeding device can be controlled to emit laser light towards a target location where weeds are located. The parameters of the emitted laser light are determined based on the attribute information of the weeds. By using laser light with the specified parameters to precisely irradiate the weeds, the accuracy of weeding is improved while reducing the impact of the laser on other plants in the environment.

[0065] This method involves acquiring an image of a first farmland containing weeds; determining the target location and attribute information of the weeds based on the image; determining the laser parameters of a laser weeding device based on the attribute information; and controlling the laser weeding device to emit laser light at the target location according to the specified parameters. In other words, by processing the first farmland image, the precise location and attribute information of the weeds are obtained, and the laser parameters of the laser weeding device are adjusted according to the weed attribute information, ensuring that the laser light at the specified parameters can effectively remove the weeds, thus achieving efficient and accurate weed removal.

[0066] In one possible implementation, Figure 2 This illustration shows a schematic diagram of an information determination process provided by an embodiment of the present disclosure, such as... Figure 2 As shown, determining the target location and attribute information of the weeds based on the first farmland image includes:

[0067] S201, input the first farmland image into a pre-trained image recognition model to obtain images of each weed area contained in the first farmland image and information on the types of weeds.

[0068] In this disclosure, the image recognition model is obtained by pre-training a convolutional neural network to be trained based on multiple sample images and their corresponding labeling information. The sample images are images containing weeds, and the labeling information for each sample image includes the weed region and the type of weed.

[0069] The image recognition model identifies the weed area image in the first farmland image, extracts the features of the weed area image, and then determines the similarity between the image features of the weed area and the features of known different types of weeds. The weed type corresponding to the highest similarity is determined as the weed species information, thereby outputting the weed area image and the weed species information.

[0070] S202, determine the target location of the weeds in the farmland based on the location of the weeds in the first farmland map in each weed area image.

[0071] In this disclosure, the position coordinates of weeds in each weed area image can be mapped to the coordinate system of the object in the real world based on the transformation relationship between the image coordinate system and the coordinate system of the object in the real world. The resulting mapped coordinates are used as the target position of the weeds in the farmland.

[0072] In this disclosure, the first farmland image can be divided according to the actual farmland plots, and the first farmland image can be matched with the actual farmland plots. Then, the positions of each weed area image in the first farmland image can be obtained as the corresponding positions of the actual farmland plots, which can be used as the target positions of the weeds in the farmland.

[0073] S203, determine the growth status information of the weeds based on the images of each weed area, and use the species information and the growth status information as the attribute information of the weeds.

[0074] In this disclosure, the growth status information of weeds may include the health status of the weeds and / or the growth stage of the weeds.

[0075] In one possible implementation, determining the growth status information of the weeds based on the images of each weed area may include steps A1-A2:

[0076] Step A1: Extract the color and shape features of each weed area image.

[0077] In this disclosure, color and shape features of each weed area image can be extracted using an image feature extraction model, or computer vision techniques can be used to extract color and shape features of each weed area image. The shape features of the weed area image may include at least one of weed edge features, weed texture features, and weed shape.

[0078] Step A2: Determine the health status of the weeds based on the color characteristics, and determine the growth stage of the weeds based on the shape characteristics, using the health status and the growth stage as growth status information.

[0079] The color of weeds can reflect their health. For example, healthy weeds are usually a bright green, while unhealthy weeds may have yellow or brown spots.

[0080] In this disclosure, the health status of plants can be pre-classified, for example, into good condition, pest and disease condition, and reproductive condition. A good condition refers to a plant in a normal growth state with healthy morphology; a pest and disease condition refers to a plant suffering from disease or pest infestation, manifested by symptoms such as yellowing or spotted leaves; and a reproductive condition refers to a plant in the process of developing reproductive organs. In this disclosure, the health status of weeds determined based on color characteristics is one of these three states: good condition, pest and disease condition, or reproductive condition.

[0081] In this disclosure, the health status of weeds determined based on color characteristics can also be termed a weed health index. The health index is a quantitative measure of weed health; a higher health index indicates better weed health. Specifically, the weed health index can be determined using the following formula:

[0082] H = (alpha × color_features) / M

[0083] Where H represents the health index, M represents the number of color features, color_features represents the extracted color features, and alpha represents the weight of each color feature. color_features typically includes RGB (red, green, blue) values, and may also include HSV (hue, saturation, lightness) and / or Lab color space values. The alpha weight is determined in advance based on the degree of influence of different color features on the plant's health status.

[0084] In this disclosure, the growth stage of a plant can include the seedling stage, the growth stage, or the mature stage. The stage of a weed—whether it is a seedling, a growth stage, or a mature stage—can be determined by analyzing characteristics such as the size, shape, or number of leaves.

[0085] In this disclosure, the growth stage of a weed determined based on its shape characteristics can also be termed a weed growth stage index. The growth stage index is a quantitative measure of the weed's growth stage; a higher index value indicates a more mature growth stage. Specifically, the weed growth stage index can be determined using the following formula:

[0086] S = beta × shape_features + gamma

[0087] Where S is the growth stage index, shape_features represents shape features, beta represents the weighting coefficient of the shape features, and gamma represents the bias parameter. shape_features can include at least one of the features of weeds such as area, perimeter, and number of leaves, and gamma can be used to adjust the baseline of the growth stage index to ensure that the growth stage index varies within a reasonable range.

[0088] Determining the health status and growth stage of weeds can help determine the appropriate laser irradiation intensity and duration to achieve efficient, accurate, and safe weed control.

[0089] In one possible implementation, determining the laser parameters of the laser weeding device based on the farmland environmental information and the attribute information may include: determining the laser power and laser irradiation duration of the laser weeding device as laser parameters based on the attribute information. The attribute information includes the type, health status, and growth stage of the weeds; in this disclosure, the laser power of the laser weeding device can be determined based on the attribute information using the following formula:

[0090] P = k × (delta_H × H + delta_S × S)

[0091] Where P represents the laser power, k is the coefficient corresponding to the type of weed, H represents the health status of the weed, S represents the growth stage of the weed, and delta_H and delta_S are sensitivity coefficients.

[0092] In this disclosure, the laser irradiation duration of the laser weeding device can be determined based on the attribute information using the following formula:

[0093] T = eta × sqrt(P) / rho

[0094] Where T represents the laser irradiation duration, eta is the time adjustment coefficient, sqrt(P) represents the square root of the laser power P, and rho represents the resistance coefficient.

[0095] The coefficient *k* corresponding to the weed species reflects the differences in sensitivity of different weeds to laser irradiation. For example, some weeds with thicker leaves require higher laser power to remove. *delta_H* and *delta_S* are sensitivity coefficients; *delta_H* represents the influence of weed health status on laser power requirements, and *delta_S* represents the influence of weed growth stage on laser power requirements. These sensitivity coefficients reflect the importance of weed health status and growth stage in determining the appropriate laser power. For example, unhealthy weeds or those in the early stages of growth may require lower laser power for removal. The resistance coefficient *rho* reflects the tolerance of different weeds to laser irradiation.

[0096] In this disclosure, by determining the health status and growth stage of the weeds, the actual situation of the weeds can be understood. This allows for precise control of the laser power and laser irradiation duration of the laser weeding equipment based on the actual situation of the weeds, thereby achieving the best weeding effect under different conditions and minimizing damage to the plants around the weeds.

[0097] In this disclosure, a laser weeding device can be controlled to emit a laser beam with a power equal to the laser power at the target location of each weed, and the laser irradiation duration can be continuously maintained. Before controlling the laser weeding device to emit the laser, it is necessary to determine the emission angle Δθ between the current position of the laser emitting device and the target location, and to adjust the laser focal length according to the distance D between the current position of the laser emitting device and the target location to ensure that the laser can be precisely focused on the weed. Specifically, the emission angle Δθ can be determined using the following formula:

[0098] Δθ = atan2(Y_target - Y_laser, X_target - X_laser)

[0099] Where Δθ represents the emission angle Δθ, atan2 is a mathematical function that calculates the angle between the line connecting two points and the positive x-axis, X_target and Y_target represent the x-coordinate and y-coordinate of the target position, respectively, and X_laser and Y_laser represent the x-coordinate and y-coordinate of the current position of the laser emitting device, respectively.

[0100] The laser focal length F can be determined using the following formula:

[0101] F = D / tan(Φ)

[0102] Where F represents the laser focal length, D represents the straight-line distance from the current position of the laser emitter of the laser weeding equipment to the target position, and Φ represents the laser divergence angle, that is, the angle at which the laser diverges from the emission point.

[0103] After determining the emission angle and laser focal length, the laser weeding equipment can be controlled. The emission angle of the laser weeding equipment is adjusted to Δθ, the laser focal length is adjusted to F, the power is set to the laser power, and the irradiation time is set to the laser irradiation time. The laser beam is then emitted to the weeds at the target location to precisely irradiate each weed.

[0104] This disclosure ensures the high efficiency and safety of laser weed control by precisely locating and irradiating weeds, while also reducing damage to non-weed plants and improving the accuracy of weed control.

[0105] In one possible implementation, after controlling the laser weeding device to emit laser light at the specified laser parameters toward the target location, the method further includes steps B1-B2:

[0106] Step B1: Obtain the image of the second farmland.

[0107] In this disclosure, after the laser weeding device irradiates the weeds in the farmland to be weeded with laser light, an image acquisition device can be used to continue acquiring images of the farmland to be weeded, which are then used as a second farmland image. The second farmland image is used to analyze the effect of laser weeding. The second farmland image and the first farmland image are images of the same size acquired by the image acquisition device at the same location and angle, but at different times, of the same farmland to be weeded.

[0108] Step B2: Based on the first farmland image and the second farmland image, determine the success rate of weed removal.

[0109] In this disclosure, preprocessing is performed on a first farmland image and a second farmland image, including noise removal, contrast adjustment, and brightness adjustment, to obtain preprocessed first and second farmland images. Then, color and shape features are extracted from the preprocessed first and second farmland images, respectively, and weed and non-weed regions are determined based on these features. The differences in weed regions between the preprocessed first and second farmland images are then compared to calculate the weed removal success rate. Specifically, a first proportion of the image occupied by the weed region in the preprocessed first farmland image and a second proportion of the image occupied by the weed region in the preprocessed second farmland image can be calculated. The absolute value of the difference between the second and first proportions can be used as the weed removal success rate.

[0110] In this disclosure, the success rate of weed removal can also be determined using the following formula:

[0111] E = 1 - (phi × U / T_total)

[0112] Where E represents the success rate of weed removal, U represents the number of weeds that were not successfully removed in the second farmland image, which may include weeds that were irradiated by the laser but not completely eliminated during the weeding process and weeds that were not covered by the laser irradiation, T_total represents the total number of plants in the second farmland image, and phi is the evaluation coefficient. phi is used to adjust the calculation of E to reflect the changes in weeding effect under different conditions. For example, for weeding operations under unfavorable environmental conditions, the value of phi can be adjusted to reflect the impact of external environmental factors on the weeding effect.

[0113] Step B3: Adjust the laser parameters of the laser weeding device based on the weed removal success rate.

[0114] In this disclosure, laser parameters such as laser power, laser irradiation time, moving speed and moving path of the laser weeding device can be adjusted according to the success rate of weed removal, so as to improve weeding efficiency and reduce the number of weeds missed by the laser.

[0115] In this disclosure, by monitoring the success rate of weed removal, the laser parameters of the laser weeding equipment can be adjusted in a timely manner to optimize the laser weeding equipment. This allows the laser weeding equipment to continuously improve the accuracy and efficiency of weed removal, enhances its adaptability to the agricultural environment and weed conditions, and makes agricultural management more efficient, environmentally friendly, and sustainable.

[0116] In one possible implementation, the control method may further include step C1:

[0117] Step C1: Obtain farmland environmental information.

[0118] The step of determining the laser parameters of the laser weeding device based on the attribute information may include: determining the laser parameters of the laser weeding device based on the attribute information and the farmland environment information.

[0119] This disclosure describes the real-time monitoring of farmland environmental information in the field to be weeded using environmental monitoring equipment. This farmland environmental information may include at least one of the following: light intensity, light direction, soil color and reflectivity, and air humidity. Soil color and reflectivity affect the propagation mode of the laser; light intensity and light direction may affect the laser's effectiveness; and air humidity affects the plant's water content and its absorption rate of the laser, with wetter plants potentially requiring higher laser power.

[0120] In this disclosure, laser parameters are determined by attribute information and farmland environment information, which can improve the environmental adaptability of laser weeding equipment and further improve the weeding accuracy and efficiency of laser weeding equipment.

[0121] Based on the same inventive concept, and according to the control method provided in the above embodiments of this disclosure, another embodiment of this disclosure also provides a control device, the structural schematic diagram of which is shown below. Figure 3 As shown, it specifically includes:

[0122] Image acquisition module 301 is used to acquire an image of a first farmland containing weeds;

[0123] The information determination module 302 is used to determine the target location and attribute information of the weeds based on the first farmland image;

[0124] Parameter determination module 303 is used to determine the laser parameters of the laser weeding device based on the attribute information;

[0125] The control module 304 is used to control the laser weeding device to emit laser light at the specified laser parameters toward the target location.

[0126] This device acquires an image of a first farmland containing weeds; based on the image, it determines the target location and attribute information of the weeds; it determines the laser parameters of the laser weeding device according to the attribute information; and it controls the laser weeding device to emit laser light at the target location according to the specified parameters. In other words, by processing the first farmland image, the accurate location and attribute information of the weeds are obtained, and the laser parameters of the laser weeding device are adjusted according to the weed attribute information, so that the laser light at the specified parameters can effectively remove the weeds, thus achieving efficient and accurate weed removal.

[0127] In one possible embodiment, the device further includes:

[0128] The parameter adjustment module (not shown in the figure) is used to acquire a second farmland image; determine the weed removal success rate based on the first farmland image and the second farmland image; and adjust the laser parameters of the laser weeding device according to the weed removal success rate.

[0129] In one possible implementation, the information determination module 302 is specifically used to input the first farmland image into a pre-trained image recognition model to obtain images of various weed areas contained in the first farmland image and information on the types of weeds; determine the target location of the weeds in the farmland based on the location of the weeds in the first farmland image in each weed area image; determine the growth status information of the weeds based on each weed area image, and use the type information and the growth status information as attribute information of the weeds.

[0130] In one possible implementation, the information determination module 302 is specifically used to extract color features and shape features from the images of each weed area; determine the health status of the weeds based on the color features; and determine the growth stage of the weeds based on the shape features, using the health status and the growth stage as growth status information.

[0131] In one embodiment, the parameter determination module 303 is specifically used to determine the laser power and laser irradiation duration of the laser weeding device as laser parameters based on the attribute information.

[0132] In one embodiment, the attribute information includes the type, health status, and growth stage of the weeds; the parameter determination module 303 is specifically used to determine the laser power of the laser weeding device based on the attribute information using the following formula:

[0133] P = k × (delta_H × H + delta_S × S)

[0134] Where P represents the laser power, k is the coefficient corresponding to the type of weed, H represents the health status of the weed, S represents the growth stage of the weed, and delta_H and delta_S are sensitivity coefficients.

[0135] The parameter determination module 303 is specifically used to determine the laser irradiation duration of the laser weeding device based on the attribute information using the following formula:

[0136] T = eta × sqrt(P) / rho

[0137] Where T represents the laser irradiation duration, eta is the time adjustment coefficient, sqrt(P) represents the square root of the laser power P, and rho represents the resistance coefficient.

[0138] In one possible embodiment, the device further includes:

[0139] The environmental information acquisition module (not shown in the figure) is used to acquire farmland environmental information;

[0140] The parameter determination module 303 is specifically used to determine the laser parameters of the laser weeding device based on the attribute information and the farmland environment information.

[0141] According to embodiments of this disclosure, this disclosure also provides an electronic device and a readable storage medium.

[0142] Figure 4A schematic block diagram of an example electronic device 400 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0143] like Figure 4 As shown, device 400 includes a computing unit 401, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 402 or a computer program loaded from storage unit 408 into random access memory (RAM) 403. RAM 403 may also store various programs and data required for the operation of device 400. The computing unit 401, ROM 402, and RAM 403 are interconnected via bus 404. Input / output (I / O) interface 405 is also connected to bus 404.

[0144] Multiple components in device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of monitors, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0145] The computing unit 401 can be a variety of general-purpose and / or special-purpose processing development components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as control methods. For example, in some embodiments, the control method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the control method described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform control methods by any other suitable means (e.g., by means of firmware).

[0146] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, the at least one input device, and the at least one output device.

[0147] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0148] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0149] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0150] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0151] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0152] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0153] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means two or more, unless otherwise explicitly specified.

[0154] The above description is merely a specific embodiment of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

1. A control method characterized by, The method comprises: acquiring a first farmland image containing weeds; determining target positions and attribute information of the weeds based on the first farmland image; determining laser parameters of a laser weeding device according to the attribute information; controlling the laser weeding device to emit laser under the laser parameters to the target positions; determining laser parameters of a laser weeding device according to farmland environment information and the attribute information, comprising: determining laser power and laser irradiation duration of the laser weeding device as the laser parameters according to the attribute information; the attribute information comprises the species, health status and growth stage of the weeds; determining the laser power of the laser weeding device according to the attribute information by using the following formula: P = k (delta_H H + delta_S S) wherein P represents the laser power, k is a coefficient corresponding to the species of the weeds, H represents the health status of the weeds, S represents the growth stage of the weeds, and delta_H and delta_S are sensitivity coefficients; determining the laser irradiation duration of the laser weeding device according to the attribute information by using the following formula: T = eta sqrt(P) / rho wherein T represents the laser irradiation duration, eta is a time adjustment coefficient, sqrt(P) represents the square root of the laser power P, and rho represents a resistance coefficient; after the control of the laser weeding device to emit laser under the laser parameters to the target positions, the method further comprises: acquiring a second farmland image; determining a weed removal success rate based on the first farmland image and the second farmland image; adjusting the laser parameters of the laser weeding device according to the weed removal success rate; the second farmland image and the first farmland image are images of the same size collected by an image collection device at the same position, the same angle and different times for the same farmland to be weeded; calculating a first proportion of a weed area in the preprocessed first farmland image and a second proportion of a weed area in the preprocessed second farmland image, calculating the absolute value of the difference between the second proportion and the first proportion, and taking the ratio of the absolute value to the first proportion as the weed removal success rate; the determination of the target positions and the attribute information of the weeds based on the first farmland image comprises: inputting the first farmland image into a pre-trained image recognition model to obtain each weed area image contained in the first farmland image and the species information of the weeds; determining the target positions of the weeds in the farmland according to the positions of the weeds in the first farmland image in each weed area image; determining the growth state information of the weeds according to each weed area image, and taking the species information and the growth state information as the attribute information of the weeds.

2. The method of claim 1, wherein, the determination of the growth state information of the weeds according to each weed area image comprises: extracting color features and shape features of each weed area image; determining the health status of the weeds according to the color features, and determining the growth stage of the weeds according to the shape features, and taking the health status and the growth stage as the growth state information.

3. The method of claim 1, wherein, the method further comprises: acquiring farmland environment information; the determination of the laser parameters of the laser weeding device according to the attribute information comprises: Determine laser parameters of the laser weeding device based on the attribute information and the farmland environment information.

4. A control device for implementing the method of any one of claims 1-3, characterized in that, The device comprises: An image acquisition module configured to acquire a first farmland image containing weeds; An information determination module configured to determine target positions and attribute information of the weeds based on the first farmland image; A parameter determination module configured to determine laser parameters of the laser weeding device according to the attribute information; A control module configured to control the laser weeding device to emit laser at the laser parameters to the target positions; The parameter determination module is further configured to determine laser power and laser irradiation duration of the laser weeding device as the laser parameters according to the attribute information; The attribute information comprises the species, health status and growth stage of the weeds; The laser power of the laser weeding device is determined according to the attribute information by using the following formula: P = k (delta_H H + delta_S S) wherein P represents the laser power, k is a coefficient corresponding to the species of the weeds, H represents the health status of the weeds, S represents the growth stage of the weeds, and delta_H and delta_S are sensitivity coefficients; The laser irradiation duration of the laser weeding device is determined according to the attribute information by using the following formula: T = eta sqrt(P) / rho wherein T represents the laser irradiation duration, eta is a time adjustment coefficient, sqrt(P) represents the square root of the laser power P, and rho represents a resistance coefficient; The control device is further configured to, after the control of the laser weeding device to emit laser at the laser parameters to the target positions, the method further comprises: acquiring a second farmland image; determining a weed removal success rate based on the first farmland image and the second farmland image; and adjusting the laser parameters of the laser weeding device according to the weed removal success rate; The information determination module is further configured to: input the first farmland image into a pre-trained image recognition model to obtain weed region images contained in the first farmland image and species information of the weeds; determine target positions of the weeds in the farmland according to positions of the weeds in the first farmland image in the weed region images; and determine growth state information of the weeds according to the weed region images, and take the species information and the growth state information as attribute information of the weeds.

5. An electronic device, comprising: Comprise: At least one processor; And A memory in communication connection with the at least one processor; wherein The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method of any one of claims 1-3.

6. A non-transitory computer-readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to execute the method of any one of claims 1-3. The computer instructions are used to enable the computer to execute the method of any one of claims 1-3.

Images