Grain crop aphid forecasting system and method
By combining hardware data acquisition equipment with a back-end artificial intelligence algorithm library, the automation and accuracy of aphid monitoring and forecasting for grain crops have been achieved. This solves the problems of untimely and inaccurate monitoring and forecasting caused by manual intervention in existing technologies, and improves the safety and efficiency of grain production.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HANGZHOU MOSHANG CLOUD MEASUREMENT TECH CO LTD
- Filing Date
- 2023-06-21
- Publication Date
- 2026-04-17
AI Technical Summary
Existing aphid monitoring and forecasting systems for grain crops rely on manual intervention, resulting in low timeliness and accuracy of monitoring and forecasting. They also fail to achieve automatic identification and timely data collection, leading to reduced grain yields.
By combining hardware data acquisition equipment with a background artificial intelligence algorithm library, automated data acquisition and recognition are achieved through image segmentation, automatic adjustment of equipment height, and the installation of solar power supply components and wind direction rotation frame components.
It has improved the automation level of aphid monitoring and forecasting for grain crops, reduced labor costs, enhanced the timeliness and accuracy of monitoring and forecasting, reduced the frequency of equipment maintenance, and ensured the safety of grain production.
Smart Images
Figure CN121884102A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of intelligent monitoring and forecasting of agricultural pests, specifically to a system and method for monitoring and forecasting aphids in grain crops. Background Technology
[0002] Aphids, also known as oil lice, plant lice, or honeydew aphids, are one of the major pests of grain crops. They damage crops by piercing and sucking sap, affecting photosynthesis, nutrient absorption, and translocation. After the grain crop heads emerge, they concentrate their damage on the ear, causing empty grains and reducing the thousand-grain weight, resulting in yield loss. They occur in all wheat-growing regions worldwide. They primarily damage wheat and other gramineous crops and weeds. Nymphs and adults often congregate in large numbers on leaves, stems, and ears to suck sap. Initially, the affected areas appear as small yellow spots, which later develop into streaks, eventually leading to wilting, death, and the entire plant dying.
[0003] In existing technologies, the current monitoring and forecasting systems for aphids on grain crops typically involve manual field surveys to confirm insect population density and damage levels. Other methods involve placing sticky traps in the field to attract aphids, followed by manual collection and analysis in a laboratory. The entire monitoring and forecasting process requires specialized technicians to conduct field surveys or sampling, resulting in low timeliness and accuracy. Furthermore, the high labor costs of monitoring and forecasting, the inability to address data timeliness, and the susceptibility to errors in manual statistics all contribute to its drawbacks. The entire monitoring and forecasting process relies heavily on human intervention and, more importantly, the involvement of specialized technicians. Its low efficiency and the potential for untimely manual surveys can lead to damage, reduced crop yields, or even total crop failure.
[0004] In addition, other aphid monitoring systems for grain crops on the market use yellow sticky traps with cameras attached to them. These traps, which are the primary means of catching insects, require manual removal and replacement after 2-3 days once the traps are full of insects. This manual replacement is not possible, and the systems cannot replace manual monitoring of aphid damage. Furthermore, due to technical limitations, the aphid images captured are often unclear and do not meet the requirements for algorithmic recognition, resulting in untimely and inaccurate monitoring. This can lead to missed aphid infestation periods and reduced grain yields. Summary of the Invention
[0005] To overcome the technical problems existing in the prior art, this invention provides a grain crop aphid monitoring system and method. By setting up a background artificial intelligence algorithm library, the same image is processed in blocks, increasing the proportion of aphid areas in the same image, thus solving the problems of small insects, dense density, difficulty in target capture, and inability to automatically identify pest species. By setting up a frame component, the grain crop aphid monitoring system can rotate according to the set time and wind direction, solving the problem that the flight direction of pests changes due to sunlight, wind direction, etc., resulting in fewer pests being trapped. At the same time, the hardware data acquisition device can adjust the height of the sticky insect strip as the crop grows in the field, avoiding the situation where the sticky insect strip is blocked by the crop and cannot trap insects or requires manual adjustment on site. By setting up a solar power supply component, the hardware data acquisition device is given additional power, solving the problems of short use time and high power consumption, achieving ultra-long standby time, and improving the durability of the grain crop aphid monitoring system.
[0006] To achieve the aforementioned objective, the present invention is implemented through the following technical solution: A grain crop aphid monitoring and forecasting system includes a hardware data acquisition device for collecting grain crop aphid data, a background artificial intelligence algorithm library for identifying and distinguishing grain crop aphids, a data knowledge base for associating with pest models, and a front-end display interface for display. The hardware data acquisition device includes a solar power supply component for power supply, an image acquisition component for data acquisition, a wireless transmission component for data transmission, a capture component for capturing aphids on grain crops, and a support frame component.
[0007] Preferably, the solar power supply component is located on top of the hardware data acquisition device and includes a solar panel and a battery power supply component built into the solar panel. The solar panel is equipped with a temperature protection switch.
[0008] Preferably, the trapping assembly includes an insect-sticking tape assembly and an insect inlet. The insect-sticking tape assembly includes a color board and an insect-sticking tape. An insect-attracting lamp tube is provided above the insect inlet. The insect inlet is V-shaped and has mesh plates on both sides to prevent large insects from flying in.
[0009] Preferably, the color plate is made of color-changing glass or an LED backlight panel, and the sticky insect tape is provided with a lure or food attractant.
[0010] Preferably, the frame assembly includes a base, on which a bearing and a motor are mounted. Gears and racks are respectively mounted on both sides of the frame assembly. The motor is used to drive the sticky insect tape assembly and the frame assembly to move up and down. An optical coupler sensor is mounted on the transmission shaft of the motor.
[0011] Preferably, the sticky insect tape assembly further includes two paper rolls, the sticky insect tape is wound out of the sticky insect area of the insect inlet along the bearing path of one of the paper rolls and then wound out through the camera area of the image acquisition and shooting component until the position of the other paper roll.
[0012] Preferably, the image acquisition and shooting component includes a movable camera and a fill light.
[0013] This invention also provides a method for a pest forecasting system for grain crops, comprising the following steps: Step S1: Collect aphid data on grain crops using hardware data acquisition equipment; Step S2: Transmit the aphid data of grain crops collected in step S1 to the background artificial intelligence algorithm library through a wireless transmission component; Step S3: The background artificial intelligence algorithm library identifies and distinguishes the aphid data of grain crops transmitted in step S2. Step S4: The front-end display interface displays the results obtained from identifying and distinguishing the aphid data of grain crops in step S3.
[0014] Preferably, in step S1, the motor is controlled by a program to rotate the camera and capture images of aphids on grain crops. In step S3, the density of aphids per unit area in the captured images of aquatic crops is evaluated through a local client or a remote server. When the density is lower than a set value, the motor is reversed to flip the tape back out for reuse. The captured images of aphids are stitched together into a large image by a background algorithm for user observation and confirmation; or each image is used separately according to the shooting order, and the background automatically names and arranges them for user review and confirmation.
[0015] Preferably, in step S1, aphids on grain crops are captured by a capture component, and image data of aphids on grain crops are captured by an image acquisition and shooting component. When collecting and photographing pests, the rotation of the motor drives the film to rotate, and the rotation distance is controlled by the program to ensure that all the insects are photographed and collected, preventing missed shots. The solar power supply component is used for power supply, and the motor transmission shaft is equipped with an optocoupler sensor that can accurately detect the travel distance of the adhesive tape of the sticky insect tape, and work with the control system to complete the data collection. For sticky insect tape, roll it up to the shooting area. The shooting background can be changed to a white background or white fill light as needed. The bottom backlight plus the fill light system on the camera form a complete top and bottom fill light system, which is used to capture the detailed features of the insect more clearly. This provides clear feature images for the subsequent AI artificial intelligence algorithm to identify and distinguish, thereby improving the accuracy and precision of the algorithm. The camera moves left and right under program control. The camera and the tape's motor work together to capture images of different parts of the sticky insect tape, increasing the effective pixels of the target body per unit area and reducing the pixel requirements of the camera. The AI camera in the image acquisition and shooting component accurately identifies and calculates, controls the extension and retraction of the bracket motor, and automatically adjusts the installation height of the equipment. It can automatically follow and adjust the height of the equipment according to the growth height of the crops. In step S2, the on-site data status of the hardware data acquisition device can be obtained anytime and anywhere through the built-in wireless transmission component of the hardware data acquisition device. In step S3, based on the uploaded data and combined with artificial intelligence algorithms, the types and quantities of pests are accurately identified and calculated. The big data model in the background is used to replace manual methods to make correct prevention and control guidance measures. For the aphid images of grain crops obtained after shooting, the aphid recognition model on the server side adopts a convolutional neural network model to divide the same image into blocks, thereby increasing the proportion of aphid areas in the same image.
[0016] Compared with the prior art, the present invention has the following beneficial effects: By setting up an insect-sticking tape assembly, which includes a color board, an insect-sticking tape, and a paper roll, the need to frequently replace the insect-sticking tape is avoided: with the old product, when the insect-sticking tape was full of insects, it needed to be manually removed and replaced with a new one after 2-3 days.
[0017] By setting up a fill light, the problem of unclear data in photos caused by weather conditions affecting brightness and the camera being exposed to strong light and weather outside was solved.
[0018] The server-side aphid identification model for grain crops uses a convolutional neural network model to divide the same image into blocks, increasing the proportion of aphid areas in the same image. This solves the problems of small insects, dense density, difficulty in target capture, and inability to automatically identify pest species.
[0019] By incorporating bearings, motors, and gears and racks on both sides of the frame assembly, the aphid monitoring system for grain crops rotates according to the set time and wind direction. This solves the problem that the flight direction of pests changes due to sunlight, wind direction, etc., resulting in fewer pests being trapped. At the same time, the hardware data acquisition equipment can adjust the height of the sticky insect tape as the crop grows in the field, avoiding situations where the sticky insect tape is blocked by crops and fails to trap insects, or where manual adjustment of the height is required on-site.
[0020] By setting up color swatches and light tubes, it is possible to use different color bands to attract different pests according to environmental needs, thus avoiding the need for manual on-site replacement of the color bands of the sticky insect tapes.
[0021] By setting up a grid board, large moths and tiny pests can be prevented from getting stuck together on the sticky insect tape. This would prevent the large insects from blocking the tiny pests, making it impossible to capture the target when taking pictures and resulting in inaccurate data.
[0022] By setting up temperature sensors, a temperature curve can be displayed within the grain crop aphid monitoring system, allowing for remote acquisition of on-site temperatures.
[0023] By installing solar power components, the power supply to the hardware data acquisition equipment is increased, solving the problems of short usage periods and high power consumption of the hardware data acquisition equipment, achieving ultra-long standby time, and improving the durability of the aphid monitoring system for grain crops. Attached Figure Description
[0024] Figure 1 This is a schematic diagram of the overall structure of a hardware data acquisition device according to an embodiment of the present invention; Figure 2 This is a partial structural cross-sectional view of a hardware data acquisition device according to an embodiment of the present invention. Detailed Implementation
[0025] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.
[0026] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.
[0027] 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 invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.
[0028] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection, an electrical connection, or a connection that allows communication between the components; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise explicitly limited. Those skilled in the art can understand the specific meaning of these terms in this invention according to the specific circumstances.
[0029] Please see Figures 1-2 This is a first embodiment of the grain crop aphid monitoring and forecasting system and method of the present invention. In this embodiment, it includes a hardware data acquisition device for collecting grain crop aphid data, a background artificial intelligence algorithm library for identifying and distinguishing grain crop aphids, a data knowledge base for associating with pest models, and a front-end display interface for display. The hardware data acquisition device includes a solar power supply component 1 for power supply, an image acquisition component for data acquisition, a wireless transmission component for data transmission, a capture component 3 for capturing aphids on grain crops, and a support frame component 2.
[0030] In this embodiment, the solar power supply component 1 is located on top of the hardware data acquisition device, and includes a solar panel and a battery power supply component built into the solar panel. The solar panel is equipped with a temperature protection switch.
[0031] In this embodiment, the trapping component 3 includes an insect sticky tape 32 component and an insect inlet. The insect sticky tape 32 component includes a color board and an insect sticky tape 32. An insect lamp is provided above the insect inlet for attracting insects. The insect inlet is V-shaped and has mesh plates 31 on both sides for preventing large insects from flying in.
[0032] In this embodiment, the color plate is made of color-changing glass or an LED backlight panel, and the sticky insect tape 32 is provided with a lure or food attractant.
[0033] In this embodiment, the frame assembly 2 includes a base 21, on which a bearing and a motor are provided. Gears and racks are respectively provided on both sides of the frame assembly 2. The motor is used to drive the sticky insect tape 32 assembly and the frame assembly 2 to move up and down. An optical coupler sensor is provided on the transmission shaft of the motor.
[0034] In this embodiment, the sticky insect tape 32 assembly further includes two paper rolls. The sticky insect tape 32 is wound around the sticky insect area of the insect inlet along the bearing path of one of the paper rolls and then wound around the image acquisition and shooting area of the image acquisition and shooting assembly until it reaches the position of the other paper roll.
[0035] In this embodiment, the image acquisition and shooting component includes a movable camera and a fill light.
[0036] A method for a pest forecasting system for grain crops includes the following steps: Step S1: Collect aphid data on grain crops using hardware data acquisition equipment; Step S2: Transmit the aphid data of grain crops collected in step S1 to the background artificial intelligence algorithm library through a wireless transmission component; Step S3: The background artificial intelligence algorithm library identifies and distinguishes the aphid data of grain crops transmitted in step S2. Step S4: The front-end display interface displays the results obtained from identifying and distinguishing the aphid data of grain crops in step S3.
[0037] In this embodiment, in step S1, the motor is controlled by the program to drive the camera to rotate and capture images of aphids on grain crops. In step S3, the density of aphids per unit area in the captured images of aquatic crops is evaluated through a local client or a remote server. When the density is lower than a set value, the motor is reversed to flip the tape back out for reuse. The captured images of aphids are stitched together into a large image by a background algorithm for user observation and confirmation; or each image is used separately according to the shooting order, and the background automatically names and arranges them for user review and confirmation.
[0038] In this embodiment, in step S1, the aphids of grain crops are captured by the capture component 3 and the image data of the aphids of grain crops are captured by the image acquisition and shooting component. When collecting and photographing pests, the rotation of the motor drives the film to rotate, and the rotation distance is controlled by the program to ensure that all the insects are photographed and collected, preventing missed shots. The solar power supply component 1 is used for power supply, and an optical coupler sensor is installed at the position of the motor transmission shaft to accurately detect the travel distance of the adhesive tape 32 of the sticky insect tape, and complete the data collection in conjunction with the control system. For the sticky insect tape 32, roll it up to the shooting area. The shooting background can be changed to a white background or white fill light as needed. The bottom backlight plus the fill light system on the camera form a complete top and bottom fill light system, which is used to capture the detailed features of the insect more clearly. This provides clear feature images for the subsequent AI artificial intelligence algorithm to identify and distinguish, and improves the accuracy and precision of the algorithm. The camera moves left and right under program control. The camera and the tape's motor work together to capture images of different parts of the sticky insect tape, increasing the effective pixels of the target body per unit area and reducing the pixel requirements of the camera. The AI camera in the image acquisition and shooting component accurately identifies and calculates, controls the extension and retraction of the bracket motor, and automatically adjusts the installation height of the equipment. It can automatically follow and adjust the height of the equipment according to the growth height of the crops. In step S2, the on-site data status of the hardware data acquisition device can be obtained anytime and anywhere through the built-in wireless transmission component of the hardware data acquisition device. In step S3, based on the uploaded data and combined with artificial intelligence algorithms, the types and quantities of pests are accurately identified and calculated. The big data model in the background is used to replace manual methods to make correct prevention and control guidance measures. For the aphid images of grain crops obtained after shooting, the aphid recognition model on the server side adopts a convolutional neural network model to divide the same image into blocks, thereby increasing the proportion of aphid areas in the same image.
[0039] In this embodiment, the monitoring and reporting system of the present invention consists of three main parts: a hardware data acquisition terminal and a background artificial intelligence algorithm library, a data knowledge base related to pest models, and a front-end display interface. In this embodiment, the hardware acquisition terminal consists of a solar power supply system, a camera system, and a wireless transmission and capture system. The solar power system is located at the top of the hardware, and the battery power system is built into the solar panel. It has an internal temperature protection switch that controls the equipment to work or go into sleep mode according to the ambient temperature. It only works during the grain production season and shuts down and goes into sleep mode at other times to protect the life of the equipment components and prevent damage to the components due to low temperature. The solar power system is installed above the crop canopy and its height can be adjusted manually or automatically by a motor as the crops grow, ensuring that the solar panels are not covered by the crops and that the equipment is charged. The solar panels can also be adjusted by a motor to follow the direction of sunlight, always ensuring that the equipment is charged at its most efficient. The trapping system consists of sticky boards that attract aphids by their color attraction. The aphids stick to the adhesive on the surface of the boards and, once a certain number or time condition is reached, the boards are driven by a motor to rotate under the imaging system for data capture. Trapping sticky traps can be made of yellow or other specific colored background boards, with a certain viscosity of adhesive applied to their surface according to the habits of aphids to trap the pests; the sticky traps can also be transparent, with different colored boards placed behind them so that the background color of the trap can be changed as needed to trap different insects.
[0040] When the sticky insect tape 32 is transparent, the color-attracting backplate inside can be made in different colors as needed. Currently, yellow and blue are commonly used. One side is yellow, and when it needs to be replaced, it can be pulled out, flipped over, and inserted tightly against the tape for easy color replacement. The color plate is made of sheet metal, with different colors of paint sprayed on both sides. It can also be sprayed with red and blue or red and yellow stripes as needed to avoid accidentally killing natural enemy insects. The backplate can also be made of other materials such as plastic. The color of the color board can also be other color-changing glass or LED backlight. Through program control, it can change to the required color and pattern in different seasons and for different targets. The equipment can automatically and remotely control the replacement, eliminating the need for manual on-site replacement, reducing usage and maintenance costs, and improving monitoring efficiency. You can also place lures or food attractants on the sticky insect tape 32, and add light attraction to attract pests for capture; it can be a single trapping method or a combination of other trapping methods to increase trapping efficiency; When collecting and photographing pests, the rotation of the motor drives the film to rotate, and the rotation distance is controlled by the program to ensure that all the insects are photographed and collected, preventing missed shots. An optocoupler sensor is installed at the position of the motor drive shaft, which can accurately detect the conveyor belt travel distance and, in conjunction with the control system, complete the data acquisition. For the transparent sticky insect tape 32, roll it up to the shooting area. The shooting background can be changed to a white background or a white fill light system as needed. The bottom backlight plus the fill light system on the camera form a complete top and bottom fill light system, which can more clearly capture the detailed features of the insects. This provides clear feature images for the later AI artificial intelligence algorithm to identify and distinguish them, improving the accuracy and precision of the algorithm. The captured images can be used to assess the insect density per unit area via a local client or a remote server. When the density is lower than the set value, the motor can be reversed to flip the tape out for reuse, reducing tape loss, increasing utilization, and lowering equipment usage and maintenance costs. The camera is mounted on a mobile platform and can be moved left and right by a program. When the shooting range is large, the camera and the tape's motor can work together to capture images of different parts of the tape, increasing the effective pixels of the target object per unit area, reducing the pixel requirements of the camera, thereby reducing the cost of the shooting equipment, which is conducive to reducing equipment costs and promoting its widespread application. The captured images can be stitched together into a single large image using a backend algorithm for easy viewing and confirmation by the user; alternatively, they can be used as individual images, automatically named and arranged in the order they were captured for easy review and confirmation by the user. The equipment is equipped with a camera that can take pictures of crops in the field, automatically identify the crop's growing season and growth model, and accurately calculate the crop's growing season, such as the seedling stage, flowering stage, fruiting stage, and maturity stage, through the background artificial intelligence algorithm. According to the crop growth model, it provides corresponding decision-making services and technical guidance for fertilization, watering, and pesticide application at different growth stages. Meteorological sensors can also be installed on the device to form a crop disease and pest occurrence and development model, which can be combined with crop growth models and collected crop model and pest images. Based on the crop's growth height, the AI camera can accurately identify and calculate, control the extension and retraction of the support motor, and automatically adjust the equipment's installation height. The equipment height can be automatically adjusted according to the crop's growth height to ensure accurate trapping, shooting, and monitoring, reducing the frequency of manual maintenance and achieving automation to replace human labor. With the machine's built-in wireless network module, it can obtain on-site data anytime and anywhere. Based on the uploaded data and combined with artificial intelligence algorithms, it can accurately identify and calculate the types and quantities of pests. Using the big data model in the background, it can replace manual methods to make correct prevention and control policy guidance measures, thus serving to increase crop yields and ensure harvests. After the images are captured, the aphid recognition model on the server side uses a convolutional neural network model. In order to reduce the false negative rate, the images are divided into blocks so that the aphid area occupies a larger proportion of a single image. In order to improve the recognition accuracy, attention mechanisms or modules that can extract more accurate image feature parameters are added to the model.
[0041] In this embodiment, two paper rolls are installed. One roll is wrapped with clean, transparent sticky insect paper containing mucus. Following the bearing path of the paper roll, a V-shaped insect-inlet area is created, and a flat area is created after passing the top camera assembly, continuing to the other paper roll. After taking a picture, a motor rotates the shaft, rolling the photographed sticky insect paper into the other paper roll. One roll of clean sticky insect paper can be used for one month, greatly reducing manual operation. This solves the problem of needing to manually replace the sticky insect tape 32 on-site every 2-3 days, by adding an automatic replacement system for the sticky insect tape 32, reducing the frequency of manual replacement.
[0042] A camera and supplementary light that can move left and right are installed above the flat surface of the sticky insect roll. The system is set to a 100x100mm field of view. The sticky insect roll, which traps pests, is moved back and forth by a motor and pauses in the field of view, waiting for the camera to move left and right. After each module has taken a picture, the sticky insect roll is wound onto the roll. This solves the problems of small insects, their dense density, difficulty in target acquisition, inability to automatically identify pest species, and the problem of unclear data due to weather conditions affecting the brightness of the pictures. Automatic picture taking is added, automatically taking pictures of small insects in modules, narrowing the field of view, and increasing the pixel count, making the collected pictures of small insects clearer and more intuitive. Furthermore, the camera component is modular, combined with the 32 components of the sticky insect roll and housed internally, with supplementary lighting, making it unaffected by weather conditions.
[0043] The machine consists of three parts: a solar panel, an upper sticky insect assembly and a frame assembly, and a base. A bearing and motor are installed on the base. The motor drives the sticky insect assembly and the frame assembly. The system rotates according to the set time and wind direction to trap more insects. This solves the problem that the flight direction of pests changes over time due to factors such as sunlight and wind, resulting in fewer pests being trapped. The addition of a bearing and motor mechanism, along with a wind control device, allows the upper part of the machine to rotate. Based on sunlight and wind conditions, the system automatically selects the appropriate direction to trap pests.
[0044] At the sticky insect roll, several different wavelengths of light are installed above the V-shaped insect-attracting opening. The system is set to the pests to be trapped, and the corresponding wavelength of light is selected. Insects entering from both sides of the V-shape are attracted by the pulsating light through the transparent sticky insect strip 32 and become stuck to it. This solves the problem of having to manually change the color wavelength of the sticky insect strip 32 on-site if needed, as different wavelengths attract different pests depending on environmental requirements. By adding different wavelengths of light inside the sticky insect roll, the system can select the corresponding light wavelength for the relevant pest, attracting pests through the transparent sticky insect roll.
[0045] Gear racks are installed on both sides of the overall frame component 2, and a motor is installed on the top. The motor drives the racks to make the sticky insect tape 32 component move up and down automatically. The bottom area of the insect inlet of the sticky insect component is equipped with an infrared sensor, which senses the height of the crop and sends the information to the system to automatically adjust to the appropriate height.
[0046] To address the issues where machines placed in fields cannot adjust the height of the sticky insect tape 32 as the crops grow, causing it to be obstructed by the crops and thus unable to trap insects, or requiring manual adjustment on-site, an electric up-and-down moving hinge device is added. An infrared device is installed in the insect inlet area of the sticky insect tape 32 to sense the height of the crops and automatically adjust the height of the moving sticky insect component accordingly.
[0047] Two 3mm mesh plates 31 are installed at the V-shaped insect inlet of the sticky insect tape 32 assembly to prevent large insects from flying in and getting stuck on the tape. This solves the problem of large moths and small pests getting stuck on the sticky insect tape 32 together, which would cause the large insects to block the small pests, making it impossible to capture the target during photography and resulting in inaccurate data. By adding smaller mesh holes, the size of the insect inlet is changed, allowing only small insects to fly in, thereby trapping small pests.
[0048] In this embodiment, the hardware data acquisition device is installed at the edge of the field requiring monitoring. It uses one or more combinations of color-baited traps, sex pheromones, food attractants, or light attractants to lure aphids or other small insects in the grain crop field. Once a set time or threshold is reached, the device activates a photographic system to capture images of the captured pests. These images, along with other relevant data, are uploaded to a backend server via a wireless communication module. The backend artificial intelligence algorithm identifies and classifies the pests, directly displaying the species and quantity of aphids requiring monitoring on a web interface. This provides data support for decision-making by national plant protection monitoring departments and related support departments. Based on the backend database and the artificial intelligence database, it provides prevention and control recommendations and strategies, safeguarding national food production security. Through structural design, hardware design, and server algorithm improvements and iterations, the device solves the problem of how to achieve on-site collection and remote monitoring and processing of aphid data using intelligent equipment. Furthermore, by combining biological growth models and algorithms, it provides prevention and control recommendations for identified pests, thereby ensuring safe and increased yields for grain crops.
[0049] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.
Claims
1. A system for forecasting aphids on grain crops, characterized in that it comprises: This includes hardware data acquisition equipment for collecting data on aphids in food crops, a back-end artificial intelligence algorithm library for identifying and distinguishing aphids in food crops, a data knowledge base for associating with pest models, and a front-end display interface for presentation. The hardware data acquisition device includes a solar power supply component for power supply, an image acquisition component for data acquisition, a wireless transmission component for data transmission, a capture component for capturing aphids on grain crops, and a support frame component.
2. The system according to claim 1, wherein: The solar power supply component is located on top of the hardware data acquisition device and includes a solar panel and a battery power supply component built into the solar panel. The solar panel is equipped with a temperature protection switch.
3. The aphid monitoring and forecasting system for grain crops according to claim 2, characterized in that: The trapping assembly includes an insect-sticking tape assembly and an insect inlet. The insect-sticking tape assembly includes a color board and an insect-sticking tape. An insect-attracting lamp tube is provided above the insect inlet. The insect inlet is V-shaped and has mesh plates on both sides to prevent large insects from flying in.
4. The aphid monitoring and forecasting system for grain crops according to claim 3, characterized in that: The color plate is made of color-changing glass or an LED backlight panel, and the sticky insect tape is equipped with a lure or food attractant.
5. The aphid monitoring and forecasting system for grain crops according to claim 4, characterized in that: The frame assembly includes a base, on which a bearing and a motor are mounted. Gears and racks are mounted on both sides of the frame assembly. The motor is used to drive the sticky insect tape assembly and the frame assembly to move up and down. An optical coupler sensor is mounted on the transmission shaft of the motor.
6. The aphid monitoring system for grain crops according to claim 3, characterized in that: The sticky insect tape assembly also includes two paper rolls. The sticky insect tape is wound around the sticky insect area of the insect inlet along the bearing path of one of the paper rolls and then wound around the image acquisition and shooting area of the image acquisition and shooting assembly until it reaches the position of the other paper roll.
7. The aphid monitoring system for grain crops according to claim 1, characterized in that: The image acquisition and shooting components include a movable camera and a fill light.
8. A method for a grain crop aphid monitoring system according to any one of claims 1-7, characterized in that, Includes the following steps: Step S1: Collect aphid data on grain crops using hardware data acquisition equipment; Step S2: Transmit the aphid data of grain crops collected in step S1 to the background artificial intelligence algorithm library through a wireless transmission component; Step S3: The background artificial intelligence algorithm library identifies and distinguishes the aphid data of grain crops transmitted in step S2. Step S4: The front-end display interface displays the results obtained from identifying and distinguishing the aphid data of grain crops in step S3.
9. The method for monitoring and forecasting aphids in grain crops according to claim 8, characterized in that: In step S1, the motor is controlled by the program to drive the camera to rotate and capture images of aphids on grain crops. In step S3, the density of aphids per unit area in the captured images of aquatic crops is evaluated through a local client or a remote server. When the density is lower than a set value, the motor is reversed to flip the tape back out for reuse. The captured images of aphids are stitched together into a large image by a background algorithm for user observation and confirmation; or each image is used separately according to the shooting order, and the background automatically names and arranges them for user review and confirmation.
10. The method of the aphid monitoring system for grain crops according to claim 9, characterized in that: In step S1, aphids on grain crops are captured by the capture component, and image data of aphids on grain crops are captured by the image acquisition and shooting component. When collecting and photographing pests, the rotation of the motor drives the film to rotate, and the rotation distance is controlled by the program to ensure that all the insects are photographed and collected, preventing missed shots. The solar power supply component is used for power supply, and the motor transmission shaft is equipped with an optocoupler sensor that can accurately detect the travel distance of the adhesive tape of the sticky insect tape, and work with the control system to complete the data collection. For sticky insect tape, roll it up to the shooting area. The shooting background can be changed to a white background or white fill light as needed. The bottom backlight plus the fill light system on the camera form a complete top and bottom fill light system, which is used to capture the detailed features of the insect more clearly. This provides clear feature images for the later AI artificial intelligence algorithm to identify and distinguish, improving the accuracy and precision of the algorithm. The camera moves left and right under program control. The camera and the tape's motor work together to capture images of different parts of the sticky insect tape, increasing the effective pixels of the target body per unit area and reducing the pixel requirements of the camera. The AI camera in the image acquisition and shooting component accurately identifies and calculates, controls the extension and retraction of the bracket motor, and automatically adjusts the installation height of the equipment. It can automatically follow and adjust the height of the equipment according to the growth height of the crops. In step S2, the on-site data status of the hardware data acquisition device can be obtained anytime and anywhere through the built-in wireless transmission component of the hardware data acquisition device. In step S3, based on the uploaded data and combined with artificial intelligence algorithms, the types and quantities of pests are accurately identified and calculated. The big data model in the background is used to replace manual methods to make correct prevention and control guidance measures. For the aphid images of grain crops obtained after shooting, the aphid recognition model on the server side adopts a convolutional neural network model to divide the same image into blocks, thereby increasing the proportion of aphid areas in the same image.