Plant protection vehicle and method for realizing laser deinsectization thereof

Abstract

The invention provides a plant protection vehicle and a method for realizing laser deinsectization. The method comprises the following steps: acquiring crop images in a target crop area by using an image acquisition device; performing target pest recognition on the acquired crop image by using an upper computer, if the target pest is recognized, positioning the target pest to obtain positioning information of the target pest, and sending a pest killing control instruction to a steering engine based on the positioning information; and the steering engine adjusts the steering engine freedom degree platform according to the received deinsectization control instruction, and controls the laser head to emit laser to the target pests so as to realize laser deinsectization. According to the plant protection vehicle and the laser pest killing method, pest recognition and pest position positioning are integrated, the laser head located on the steering engine freedom degree platform is adjusted through the steering engine, accurate positioning of the target pests through laser is achieved, and therefore efficient pest control is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural pest control, and in particular to a plant protection vehicle and a method for achieving laser pest control therefor. Background Art

[0002] Current agricultural pest control methods generally rely on pesticide spraying, but this method presents numerous problems. For example, pesticides can cause environmental pollution, long-term use of the same pesticide can lead to pest resistance, and manual spraying is inefficient. Furthermore, existing laser insecticide control devices are mostly fixed in design; their position, shooting angle, and laser emission angle are fixed and cannot be moved or adjusted, resulting in a lack of mobility and precise positioning capabilities.

[0003] Therefore, the prior art needs to be further improved. Summary of the Invention

[0004] In view of the above-mentioned deficiencies in the prior art, the object of the present invention is to provide a plant protection vehicle and a method for achieving laser pest control, so as to improve the accuracy and reliability of pest removal.

[0005] In a first aspect, the present application discloses a plant protection vehicle for laser pest control, comprising: a bracket, at least one servo mounted on the bracket, at least one image acquisition device, and a host computer connected to the servo and the image acquisition device; a laser head is mounted on a servo freedom platform of the servo;

[0006] The image acquisition device is used to capture crop images of the target crop area;

[0007] The host computer is used to obtain the crop image, identify the crop image, determine whether it contains target pests, and send an insecticide control instruction to the steering engine if the target pests are identified;

[0008] The servo is used to adjust the servo freedom platform according to the pest control instruction, and control the laser head to emit laser to the target pests to achieve laser pest control.

[0009] Optionally, the image acquisition device is a camera, which is arranged on the top of the bracket and is provided with a narrow-band filter.

[0010] Optionally, the bracket is in an elongated strip structure, the camera is arranged in the middle of the bracket, and there are two laser heads, which are symmetrically arranged on both sides of the camera.

[0011] Optionally, the host computer stores a target object recognition model; the target object recognition model is used to receive the crop image and identify whether the crop image contains target pests; the target object recognition model is trained based on the yolov5 network model.

[0012] In a second aspect, the present application provides a method for laser pest control using a plant protection vehicle, which includes:

[0013] using an image acquisition device to acquire crop images within a target crop area;

[0014] The host computer uses the collected crop images to identify target pests. If the target pest is identified, the target pest is located to obtain the location information of the target pest, and the pest control command is sent to the servo based on the location information;

[0015] The servo adjusts the servo freedom platform according to the received pest control instruction, and controls the laser head to emit laser light to the target pests, so as to achieve laser pest control.

[0016] Optionally, the step of identifying target pests in the collected images includes:

[0017] The crop image is input into a trained target object recognition model, and the target pest recognition result is output; wherein the target object recognition model is trained based on the yolov5 network model.

[0018] Optionally, the step of locating the target pests and obtaining the location information of the target pests includes:

[0019] Get the normalized position coordinates of the upper left and upper right corners of the target box output by the target recognition model;

[0020] Converting the normalized position coordinates of the upper left corner and the upper right corner of the target frame to obtain pixel coordinates of the upper left corner and the upper right corner of the target frame in the crop image;

[0021] When the laser head and the camera are on the same plane, the pixel coordinates of the upper left and upper right corners of the target frame are used as the positioning reference to calculate the plane coordinates of the upper left and upper right corners of the target pest in the Cartesian coordinate system;

[0022] Alternatively, when the laser head and the camera are in two planes, the pixel coordinates of the upper left and upper right corners of the target frame are used as the positioning reference, and the coordinates of the upper left and upper right corners of the target pest in the image coordinate system are mapped to the Cartesian coordinate system using the homography matrix to obtain the plane coordinates of the upper left and upper right corners of the target pest in the Cartesian coordinate system.

[0023] Optionally, the step of controlling the emission of laser light to the positioning information to kill target pests includes:

[0024] According to the coordinates of the upper left and upper right corners of the target frame, the horizontal swing angle of the laser head is calculated so that the emitted laser moves between the upper left and upper right corners of the target frame within the horizontal swing angle range, forming a linear coverage of the area within the target frame;

[0025] The calculation formula of the horizontal swing angle of the laser head is:

[0026]

[0027]

[0028] Among them, θ is the horizontal swing angle of the laser head when it swings to the coordinates of the upper left corner of the target frame, α is the horizontal swing angle of the laser head when it swings to the coordinates of the upper right corner of the target frame, and x is the horizontal swing angle of the laser head when it swings to the coordinates of the upper right corner of the target frame. left is the x coordinate of the upper left corner of the target box, Hy top is the y coordinate of the upper left corner of the target box, x right is the x coordinate of the upper right corner of the target box, Hy top The y coordinate of the upper right corner of the target box.

[0029] Optionally, the step of the servo adjusting the servo freedom platform according to the received pest control instruction to control the laser head to emit laser light to the target pests includes:

[0030] The servo adjusts the servo freedom platform through PWM pulse width, so that the laser head emits laser and swings horizontally between angles θ and α;

[0031] Among them, when the laser is placed at the upper left corner of the target box, the PWM pulse width is calculated as follows:

[0032]

[0033] When the laser is placed at the upper right corner of the target box, the PWM pulse width is calculated as follows:

[0034]

[0035] Optionally, before the step of locating the target pests and obtaining the location information of the target pests, the method further includes:

[0036] Calculate the correction term for the horizontal swing angle of the laser head based on the physical offset between the camera and the laser head when they are installed;

[0037] The horizontal swing angle of the laser head is corrected according to the calculated correction item.

[0038] Beneficial effects:

[0039] The present invention provides a plant protection vehicle and a method for laser pest control. The vehicle uses an image acquisition device to capture crop images within a target crop area. A host computer identifies target pests in the captured crop images. If a target pest is identified, the target pest is located, obtaining its location information. Based on this location information, a pest control command is sent to a servo. The servo adjusts the servo freedom platform based on the received pest control command, controlling the laser head to emit a laser beam toward the target pest, thereby achieving laser pest control. The plant protection vehicle and laser pest control method provided by the present invention achieve efficient pest control by integrating pest identification and pest location. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a schematic diagram of the three-dimensional structure of the plant protection vehicle provided by the present invention;

[0041] Figure 2 This is a front view of the plant protection vehicle provided by an embodiment of the present invention;

[0042] Figure 3 This is a front view of a plant protection vehicle provided by an embodiment of the present invention;

[0043] Figure 4 The figure is a flowchart of the steps of laser pest control according to the embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solutions and advantages of the present invention more clear and distinct, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to illustrate the present invention and are not intended to limit the present invention.

[0045] Current agricultural pest control methods are generally divided into agricultural control, biological control, physical control, chemical control, and integrated control. Agricultural control involves adjusting the internal structure of the agricultural ecosystem, improving the crop growth environment, and enhancing the crop's own resistance, thereby reducing pests. Biological control uses biological factors such as natural enemies of pests and pathogenic microorganisms to control pest populations, which has the advantages of not polluting the environment or disrupting the ecological balance. Physical control uses physical factors such as light, heat, electricity, and radiation, or mechanical means, to control pests, which has the advantages of being simple to operate and pollution-free. Chemical control uses chemical pesticides to control pests, which has the advantages of rapid results and simple operation, but long-term use can lead to pest resistance and cause environmental pollution. Integrated control combines the above control methods to construct a pest control system.

[0046] Among the above methods, agricultural control and biological control are environmentally friendly but slow to take effect. Chemical control, although effective quickly, pollutes the environment, and the sprayed pesticides may also damage crops. Therefore, none of the above control methods can simultaneously meet the requirements of fast effect, environmental friendliness, high efficiency, and energy saving.

[0047] The prior art also discloses the use of trapping to attract pests to achieve the effect of pest control, but the pest control devices are mostly fixed and cannot be moved or positioned to locate the pests, and therefore lack the function of real-time pest identification and elimination.

[0048] To achieve rapid and environmentally friendly control of crop pests, this application provides a plant protection vehicle for laser pest control and a method for using the vehicle. The vehicle captures images of crops within a target crop area, identifies the crop images, determines whether the crop images contain target pests, and, if so, locates the target pests. Based on the located pest positions, the laser head is adjusted to align with the target pests, eliminating them. This embodiment's method combines image recognition with target positioning to achieve efficient and environmentally friendly pest control.

[0049] The following is a more detailed description of a laser pest control method and a plant protection vehicle for laser pest control disclosed in the present application in conjunction with the accompanying drawings.

[0050] In the first aspect, the present application discloses a plant protection vehicle for laser pest control, such as Figure 1 As shown, the system comprises a bracket 3, at least one servo 1 mounted on the bracket 3, at least one image acquisition device 4, and a host computer connected to both the servo and image acquisition devices. A laser head 2 is mounted on the servo's freedom platform. The bracket houses at least one servo and an image acquisition device, and the servo is equipped with a laser head. The laser head emits laser light. When the target pest is irradiated by the laser, the outer surface of the pest is rapidly carbonized, thereby eliminating the pest.

[0051] The image acquisition device 4 is used to capture crop images of the target crop area. The image acquisition device can be a high-definition camera, a smart phone, a sports camera, or other devices that can capture crop images of the target crop area.

[0052] To capture detailed information about objects within crop images, one specific implementation utilizes a 2-megapixel high-definition camera mounted on top of a crop protection vehicle. This camera captures the target crop area in real time at a frame rate of 30 fps. Furthermore, to mitigate visible light interference, an 850nm narrowband filter is added to the front of the camera to enhance the contrast of infrared reflection images, enabling more accurate identification of target objects within captured crop images.

[0053] The host computer is used to obtain the crop image and identify the crop image to determine whether it contains target pests. If the target pests are identified, the host computer sends an insect control instruction to the steering gear.

[0054] The image acquisition device is connected to a host computer. The host computer acquires crop images captured by the image acquisition device and identifies whether the target pests are present in the crop images. This step determines whether the crop images contain the target pests. The communication connection between the image acquisition device and the host computer in this step can be wireless or wired. Wireless communication can be achieved by transmitting crop images using Wi-Fi or Bluetooth, while wired communication can be achieved by connecting via wires.

[0055] The host computer identifies target pests, including aphids and other pests, from captured crop images. Specifically, the host computer includes a trained target object recognition module for identifying target pests in images. This module is used to identify target pests in crop images.

[0056] The servo 1 is used to adjust the servo freedom platform according to the pest control instruction, and control the laser head 2 to emit laser light to the target pests to achieve laser pest control.

[0057] A servo is a high-precision actuator that can quickly and accurately rotate to a specified angle and maintain stability based on input signals, such as PWM (Pulse Width Modulation). It combines a motor, a reduction gear set, a position sensor, and a control circuit, achieving angular positioning through a feedback mechanism. In this embodiment, the servo is used to adjust the angle of the laser head, aligning it with the target pest, thereby achieving rapid elimination.

[0058] Specifically, the servo is equipped with a micromotor, a reduction gear set, a position sensor, and a control circuit. The servo receives PWM pulses from an external controller. The control circuit converts the pulse width into a target angle. The position sensor detects the current angle and compares it with the target value to generate an error signal. The control circuit adjusts the direction and magnitude of the motor current based on the error, driving the gear set to rotate until the error approaches zero. Once the target angle is reached, the motor stops driving, and the gear set locks to maintain the position.

[0059] The value-preserving vehicle disclosed in this embodiment is positioned within a target crop area, and an image acquisition device (e.g., a camera) mounted on a bracket captures images of the crops within the target crop area in real time. A host computer connected to the image acquisition device acquires the crop images captured by the image acquisition device and uses its internal target object recognition module to identify the crop images, determining whether the crop images contain target pests. If so, the host computer locates the target pests within the crop images and sends pest control commands to the servo based on the target pests' location coordinates. The servo adjusts the current angle of the laser head based on the target rotation angle value contained in the pest control command, so that the laser head is aligned with the target pests after adjustment.

[0060] Combine Figure 2 and Figure 3 As shown, to facilitate precise positioning of target pests, this embodiment utilizes a long, rectangular bracket with the camera positioned in the middle. Two servos and two laser heads are mounted on each servo, with the laser heads mounted symmetrically on either side of the camera. To enable the lasers emitted by the laser heads to be rotated and positioned over a wider area, servos are installed near the edges of the bracket at both ends, expanding the scanning area of the two laser heads.

[0061] In order to ensure that the laser emitted by the laser head can be more accurately positioned on the target pest, the laser head and camera are arranged on the same plane, and the emission direction and shooting direction are the same.

[0062] Furthermore, a target object recognition model is stored on the host computer; the target object recognition model is used to receive the crop image and identify whether the crop image contains target pests; the target object recognition model is trained based on the yolov5 network model.

[0063] This example uses a trained object recognition model to identify target pests in crop images. The model's network structure is based on the YOLOv5 network model and is trained using a large number of target pest image samples. In this example, the YOLOv5 classification model was trained using a self-collected dataset of over 10,000 images, achieving recognition accuracy exceeding 96%. The output target bounding box coordinates are based on the image size.

[0064] When the target object recognition model outputs the target frame where the target pest is located, the coordinates corresponding to the target frame are converted to the Cartesian coordinate system. Based on the plane coordinates of the target pest in the Cartesian coordinate system, the servo degree of freedom platform is controlled to adjust the rotation angle of the laser head and position the laser head on the straight line where the target pest is located, thereby eliminating the target pest.

[0065] Multiple plant protection vehicles provided by the present invention can be set in the target crop area, or only one plant protection vehicle can be set. For ease of use, a set of wheels can be installed on the support of the plant protection vehicle to achieve walking in the target crop area, facilitating the elimination of pests in the entire target crop area.

[0066] The plant protection vehicle disclosed in this embodiment has a simple structure and is easy to manufacture. It uses deep learning to identify target pests and utilizes a servo to locate the laser head, thereby achieving intelligent laser pest control. This not only overcomes the limitations of existing pest control devices, which are immobile and consume a lot of energy, but also utilizes lasers to effectively and environmentally friendlyly eliminate insects. Therefore, the plant protection vehicle provided in this embodiment has high promotional value, as it uses lasers to effectively and effectively eliminate insects, and can be used in real time.

[0067] In the second aspect, the present application provides a method for laser pest control using a plant protection vehicle, such as Figure 4 Shown, including:

[0068] Step S1: using an image acquisition device to acquire crop images within a target crop area.

[0069] In this step, a high-definition camera is used to shoot the target crop area in real time or at a fixed time to obtain crop images within the target crop area.

[0070] Step S2: Use the host computer to identify target pests in the collected crop images. If the target pests are identified, the target pests are located to obtain the location information of the target pests, and an insecticide control instruction is sent to the steering engine based on the location information.

[0071] The host computer identifies target pests in the crop image and determines whether there are target pests in the crop image. If any target pest is identified, the position of the target pest in the image is located, and then an insect control instruction for the target pest is sent to the servo according to the location information of the target pest.

[0072] In detail, the step of identifying target pests in the collected images includes:

[0073] The crop image is input into a trained target object recognition model, and the target pest recognition result is output; wherein the target object recognition model is trained based on the yolov5 network model.

[0074] The object recognition model processes the crop image and outputs the target pest identification result, which is a target box containing the target pest's location information and a confidence score. The target box is a rectangular bounding box that marks the target pest's location and range.

[0075] When training the object recognition model, the model input image size was 640×640, and the training parameters were: an initial learning rate of 0.01, an SGD optimizer, and 100 training epochs. The final test set accuracy was 96.3%. After training, the object recognition model outputs the target bounding box in the format of normalized center coordinates and width and height (x_center, y_center, w, h), with a confidence threshold of 0.7.

[0076] Furthermore, the step of locating the target pests and obtaining the location information of the target pests includes:

[0077] Step S21: Obtain the normalized position coordinates of the upper left corner and the upper right corner of the target box output by the target recognition model.

[0078] Step S22 : converting the normalized position coordinates of the upper left corner and the upper right corner of the target frame to obtain the pixel coordinates of the upper left corner and the upper right corner of the target frame in the crop image.

[0079] Since the coordinate data corresponding to the target box output by the object recognition model is normalized coordinates (relative to the feature map or input image size), this step requires converting the coordinate data corresponding to the target box to pixel coordinates. The conversion method is: multiply the normalized position coordinates by the scaling factor of the feature map to the original image to obtain the actual pixel coordinates. For example: if the feature map size is (13,13) and the input image size is (416,416), the normalized coordinates need to be multiplied by 416 / 13 = 32 to convert to pixel coordinates.

[0080] The target box annotation format is normalized center coordinates and width and height (x_center, y_center, w, h), which need to be converted to actual pixel coordinates in the entire image. The following is the conversion method for the upper left corner coordinates and the upper right corner coordinates:

[0081] Assume that the image size is (width, height), the YOLO annotation value is (x_center, y_center, w, h), and the value range of the annotation value is [0, 1].

[0082] Coordinates of the upper left corner:

[0083]

[0084] Coordinates of the upper right corner:

[0085]

[0086] For example, if the image size is 800×600 and YOLO outputs (0.5, 0.5, 0.3, 0.4), the upper left corner is (280, 180) and the upper right corner is (520, 180).

[0087] Step S23: When the laser head and the camera are in the same plane, the pixel coordinates of the upper left corner and the upper right corner of the target frame are used as positioning references to calculate the plane coordinates of the upper left corner and the upper right corner of the target pest in the Cartesian coordinate system.

[0088] Alternatively, when the laser head and the camera are in two planes, the pixel coordinates of the upper left and upper right corners of the target frame are used as the positioning reference, and the coordinates of the upper left and upper right corners of the target pest in the image coordinate system are mapped to the Cartesian coordinate system using the homography matrix to obtain the plane coordinates of the upper left and upper right corners of the target pest in the Cartesian coordinate system.

[0089] If the laser head and the camera are on the same plane, the upper left and upper right corners of the target frame in the Cartesian coordinate system can be directly obtained without coordinate system conversion.

[0090] If the laser head and the camera are not on the same plane, the pixel coordinates in the image coordinate system need to be converted to plane coordinates in the Cartesian coordinate system through the homography matrix, so that the laser head can locate the coordinate position.

[0091] Specifically, the laser head is located at the top left corner of the image (origin (0,0)), and the target frame and the laser head are on the same horizontal line. The specific steps are as follows:

[0092] Coordinate system conversion:

[0093] Image coordinate system: The upper left corner is the origin (0,0), the x-axis is to the right, and the y-axis is downward.

[0094] Cartesian coordinate system: the y-axis needs to be reversed (upward is positive), and the upper right corner of the target frame is the coordinate point of the target pest (x left ,y top ), converted to (x left ,Hy top ), where H is the image height.

[0095] Step S3: The servo adjusts the servo freedom platform according to the received pest control instruction, and controls the laser head to emit laser light to the target pests, so as to achieve laser pest control.

[0096] In this step, the servo receives the insecticide control command from the host computer, parses the insecticide control command to extract the target rotation angle of the servo freedom platform, and controls the rotation of the servo freedom platform to achieve the horizontal swing angle of the laser head.

[0097] The pest control instruction is generated based on the plane coordinates of the target pest positioning, which includes the target rotation angle of the servo freedom platform. The pest control instruction also includes: when the servo freedom platform rotates to the target rotation angle, the laser head is triggered to emit laser to eliminate the target pest.

[0098] Furthermore, the step of controlling the emission of laser to the positioning information to kill target pests includes:

[0099] According to the coordinates of the upper left and upper right corners of the target frame, the horizontal swing angle of the laser head is calculated so that the emitted laser moves between the upper left and upper right corners of the target frame within the horizontal swing angle range, forming a linear coverage of the area within the target frame;

[0100] The calculation formula of the horizontal swing angle of the laser head is:

[0101]

[0102]

[0103] Among them, θ is the horizontal swing angle of the laser head when it swings to the coordinates of the upper left corner of the target frame, α is the horizontal swing angle of the laser head when it swings to the coordinates of the upper right corner of the target frame, and x is the horizontal swing angle of the laser head when it swings to the coordinates of the upper right corner of the target frame. left is the x coordinate of the upper left corner of the target box, Hy top is the y coordinate of the upper left corner of the target box, x right is the x coordinate of the upper right corner of the target box, Hy top The y coordinate of the upper right corner of the target box.

[0104] In specific implementation, for the upper left corner of the target frame, the horizontal swing angle θ of the laser head is:

[0105]

[0106] x left : x coordinate of the target point (pixels)

[0107] Hy top : converted y coordinate (pixels)

[0108] The upper right corner of the target frame is the coordinate point of the target pest (x right ,y top ), the transformed coordinates are (x right ,Hy top ), where H is the image height.

[0109] For the upper right corner of the target point target frame, the horizontal swing angle α of the laser head is:

[0110]

[0111] x right : The x-coordinate of the target point (pixels).

[0112] Hy top : The converted y coordinate (pixels).

[0113] Assuming the image height H = 600, the coordinates of the upper left corner are (280, 180). After the coordinate system transformation, it is converted to (280, 420). Then the horizontal swing angle θ of the laser head is:

[0114]

[0115] Once the laser head's horizontal swing angle range is calculated, the servo's freedom of movement platform oscillates back and forth between θ and α at a frequency of 10Hz based on the PWM value, creating a linear coverage of the laser focus within the target frame. The laser power is set to no less than 2W (wavelength 980nm) and a pulse frequency of 1kHz to ensure instantaneous carbonization of the pest's skin.

[0116] Specifically, the step of adjusting the servo freedom platform according to the received pest control instruction to control the laser head to emit laser light to the target pests includes:

[0117] The servo adjusts the servo freedom platform through PWM pulse width, so that the laser head emits laser and swings horizontally between angles θ and α;

[0118] Among them, when the laser is placed at the upper left corner of the target box, the PWM pulse width is calculated as follows:

[0119]

[0120] When the laser is placed at the upper right corner of the target box, the PWM pulse width is calculated as follows:

[0121]

[0122] In this step, an angle control instruction of the servo freedom platform is generated according to the located coordinate information. The servo controls the adjustment angle of the servo freedom platform through the PWM pulse width. After the adjustment is completed, the upper computer controls the laser head to emit laser to eliminate the target pests. In a specific embodiment, the control parameters of the method for adjusting the servo freedom platform include: PWM period parameters, PWM pulse width corresponding to the upper left corner point of the laser positioning target frame, and PWM pulse width corresponding to the laser positioning at the upper right corner point of the target frame.

[0123] In a specific embodiment, the PWM pulse width period is fixed, for example, the PWM period is fixed at 20 ms (50 Hz), the pulse width range is 0.5 ms (0°) to 2.5 ms (180°), and the mapping is linear.

[0124] The calculation formula for the PWM pulse width corresponding to positioning the laser at the upper left corner of the target box is:

[0125]

[0126] The calculation formula for the PWM pulse width corresponding to positioning the laser at the upper right corner of the target box is:

[0127]

[0128] The calculation formula for converting the laser positioning at the upper left or upper right corner of the target box into a PWM value (assuming the PWM resolution is 12 bits, ranging from 0 to 4095) is:

[0129]

[0130] Specifically, the host computer outputs the PWM value that controls the servo.

[0131] Furthermore, in order to achieve more accurate positioning of the target pests, before the step of positioning the target pests and obtaining positioning information of the target pests, the method further includes:

[0132] According to the physical offset between the camera and the laser head when they are installed, a correction term for the horizontal swing angle of the laser head is calculated; and according to the calculated correction term, the horizontal swing angle of the laser head is corrected.

[0133] Since the camera and laser head will have physical offset during installation, in order to overcome the positioning deviation caused by the physical offset, a correction term is calculated in this step to correct the physical offset, thereby improving the accuracy of positioning.

[0134] In specific implementation, the calculation principle of coordinate offset compensation is:

[0135] There is a physical offset between the camera and the laser head (Δx = 5cm, Δy = 10cm). After measuring with a calibration plate, a correction term is added to the angle calculation:

[0136]

[0137] Where H is the height of the image, y is the located y coordinate, and x is the located x coordinate.

[0138] The present invention provides a plant protection vehicle and a method for laser pest control. The vehicle uses an image acquisition device to capture crop images within a target crop area. A host computer identifies target pests in the captured crop images. If a target pest is identified, the target pest is located, obtaining its location information. Based on this location information, a pest control command is sent to a servo. The servo adjusts the servo freedom platform based on the received pest control command, controlling the laser head to emit a laser beam toward the target pest, thereby achieving laser pest control. The plant protection vehicle and laser pest control method provided by the present invention achieve efficient pest control by integrating pest identification and pest location.

[0139] The present invention achieves precise killing of farmland pests through high-precision target detection, rapid coordinate conversion and dynamic laser control. It has the characteristics of high efficiency, environmental protection and low power consumption, and is suitable for large-scale smart agricultural scenarios.

[0140] Other embodiments of the present invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. The present invention is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the invention being indicated by the following claims.

[0141] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0142] It is understandable that the above embodiments are exemplary and should not be construed as limiting the present application. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A plant protection vehicle for laser pest control, characterized in that: include: A bracket, at least one steering gear provided on the bracket, at least one image acquisition device, and a host computer connected to the steering gear and the image acquisition device; A laser head is provided on the steering freedom platform of the steering gear; The image acquisition device is used to capture crop images of the target crop area; The host computer is used to obtain the crop image, identify the crop image, determine whether it contains target pests, and send an insecticide control instruction to the steering engine if the target pests are identified; The servo is used to adjust the servo freedom platform according to the pest control instruction, and control the laser head to emit laser to the target pests to achieve laser pest control.

2. The plant protection vehicle for laser pest control according to claim 1, characterized in that: The image acquisition device is a camera, which is arranged on the top of the bracket and is provided with a narrow-band filter.

3. The plant protection vehicle for laser pest control according to claim 2, characterized in that: The bracket is in an elongated strip structure, the camera is arranged in the middle of the bracket, and there are two laser heads, which are symmetrically arranged on both sides of the camera.

4. The plant protection vehicle for laser pest control according to claim 1, characterized in that: The host computer stores a target object recognition model; the target object recognition model is used to receive the crop image and identify whether the crop image contains target pests; the target object recognition model is trained based on the yolov5 network model.

5. A method for laser pest control using the plant protection vehicle according to any one of claims 1 to 4, characterized in that: include: using an image acquisition device to acquire crop images within a target crop area; The host computer uses the collected crop images to identify target pests. If the target pest is identified, the target pest is located to obtain the location information of the target pest, and the pest control command is sent to the servo based on the location information; The servo adjusts the servo freedom platform according to the received pest control instruction, and controls the laser head to emit laser light to the target pests, so as to achieve laser pest control.

6. The laser insecticide method according to claim 5, characterized in that: The step of identifying target pests on the collected images includes: The crop image is input into a trained target object recognition model, and the target pest recognition result is output; wherein the target object recognition model is trained based on the yolov5 network model.

7. The laser insecticide method according to claim 6, characterized in that: The step of locating the target pests and obtaining the location information of the target pests includes: Get the normalized position coordinates of the upper left and upper right corners of the target box output by the target recognition model; Converting the normalized position coordinates of the upper left corner and the upper right corner of the target frame to obtain pixel coordinates of the upper left corner and the upper right corner of the target frame in the crop image; When the laser head and the camera are on the same plane, the pixel coordinates of the upper left and upper right corners of the target frame are used as the positioning reference to calculate the plane coordinates of the upper left and upper right corners of the target pest in the Cartesian coordinate system; Alternatively, when the laser head and the camera are in two planes, the pixel coordinates of the upper left and upper right corners of the target frame are used as the positioning reference, and the coordinates of the upper left and upper right corners of the target pest in the image coordinate system are mapped to the Cartesian coordinate system using the homography matrix to obtain the plane coordinates of the upper left and upper right corners of the target pest in the Cartesian coordinate system.

8. The laser insecticide method according to claim 7, characterized in that: The step of controlling the emission of laser light to the positioning information to kill target pests includes: According to the coordinates of the upper left and upper right corners of the target frame, the horizontal swing angle of the laser head is calculated so that the emitted laser moves between the upper left and upper right corners of the target frame within the horizontal swing angle range, forming a linear coverage of the area within the target frame; The calculation formula for the horizontal swing angle of the laser head is: Among them, θ is the horizontal swing angle of the laser head when it swings to the coordinates of the upper left corner of the target frame, α is the horizontal swing angle of the laser head when it swings to the coordinates of the upper right corner of the target frame, and x is the horizontal swing angle of the laser head when it swings to the coordinates of the upper right corner of the target frame. left is the x coordinate of the upper left corner of the target box, Hy top is the y coordinate of the upper left corner of the target box, x right is the x coordinate of the upper right corner of the target box, Hy top The y coordinate of the upper right corner of the target box.

9. The laser insecticide method according to claim 8, characterized in that: The step of the servo adjusting the servo freedom platform according to the received pest control command to control the laser head to emit laser light to the target pests includes: The servo adjusts the servo freedom platform through PWM pulse width, so that the laser head emits laser and swings horizontally between angles θ and α; Among them, when the laser is placed at the upper left corner of the target box, the PWM pulse width is calculated as follows: When the laser is placed at the upper right corner of the target box, the PWM pulse width is calculated as follows:

10. The laser insecticide method according to claim 8, characterized in that: Before the step of locating the target pests and obtaining the location information of the target pests, the method further includes: Calculate the correction term for the horizontal swing angle of the laser head based on the physical offset between the camera and the laser head when they are installed; The horizontal swing angle of the laser head is corrected according to the calculated correction item.

Images