A method and device for monitoring field moth pests, an electronic device and a storage medium

Abstract

The embodiment of the present specification discloses a kind of field moth pest monitoring method, device, electronic equipment and storage medium.The user recommendation method includes determining target pest species, and determining target trapping device;First control instruction is sent to target object, to indicate target object to place target trapping device in monitoring area;Every first preset time length passes, target space parameter of target trapping device is determined based on meteorological data, second control instruction is sent to target object, to indicate target object to adjust the current space parameter of target trapping device based on target space parameter.The embodiment of the present specification can automatically place target trapping device according to the target pest species needed to be monitored, and simultaneously, the space parameter of each target trapping device can also be continuously adjusted according to meteorological data, so that the accuracy of the obtained monitoring image data is high, meet the monitoring requirements of moth pest.

Description

Technical Field

[0001] This specification relates to pest monitoring technology in one or more embodiments, and more particularly to a method, device, electronic device and storage medium for monitoring field moth pests. Background Technology

[0002] Moth pests are a significant factor contributing to crop yield reduction. Field moth pest monitoring can be used to determine adult migration times, estimate pest population numbers, and assess population development progress. Traditional field moth pest monitoring methods involve manual surveys, light or pheromone trapping (insect monitoring lamps or instruments), and manual identification, counting, and reporting of results. These methods are highly specialized, time-consuming, labor-intensive, and lack real-time capabilities. While automated monitoring methods using photoelectric counting modules and machine vision modules have emerged in recent years, they struggle to adapt to changes in the complex field environment, resulting in poor data accuracy and failing to meet the monitoring requirements for moth pests. Summary of the Invention

[0003] To address the aforementioned problems, this specification describes one or more embodiments of a method, apparatus, electronic device, and storage medium for monitoring field moth pests.

[0004] According to the first aspect, a method for monitoring field moth pests is provided, including:

[0005] Identify the target pest species and determine the corresponding targeted trapping device for the target pest species;

[0006] Send a first control command to the target object to instruct the target object to place the target-trapping device in the monitoring area;

[0007] After each first preset time interval, the target spatial parameters of the target trapping device are determined based on meteorological data, and a second control command is sent to the target object to instruct the target object to adjust the current spatial parameters of the target trapping device based on the target spatial parameters.

[0008] Preferably, the step of determining the target pest species and the corresponding target trapping device includes:

[0009] Acquire monitoring targets, and determine the types of target pests based on the monitoring targets;

[0010] Determine the characteristics of the target pest corresponding to the target pest species, and determine the target trapping device based on the characteristics of the target pest.

[0011] Preferably, sending a first control command to the target object to instruct the target object to place the target-oriented trapping device in the monitoring area includes:

[0012] The initial number of the target trapping devices is determined based on the area of ​​the monitoring area, and the initial spatial parameters of the target trapping devices are obtained. The spatial parameters include the arrangement of the target trapping devices, the first distance between the target trapping devices and the field ridge, the second distance between the target trapping devices, and the height of the insect-attracting part.

[0013] A first control command is sent to the target object to instruct the target object to place the target-oriented trapping device in the monitoring area according to the initial quantity and initial spatial parameters.

[0014] Preferably, sending the first control command to the target object includes:

[0015] When a non-targeted trapping device is present in the monitoring area, the minimum distance between the targeted trapping device and the non-targeted trapping device is determined, and a first control command and a third control command are sent to the target object. The third control command is used to instruct the target object to adjust the third distance between any of the targeted trapping devices and the non-targeted trapping devices to be no less than the minimum distance.

[0016] Preferably, after each first preset time interval, the target spatial parameters of the target-oriented trapping device are determined based on meteorological data, and a second control command is sent to the target object to instruct the target object to adjust the current spatial parameters of the target-oriented trapping device based on the target spatial parameters, including:

[0017] After each first preset time period, the target spatial parameters of the target trapping device are determined based on meteorological data, and the target placement area and number of targets of the target trapping device are determined based on the characteristics of the monitoring area.

[0018] A second control command is sent to the target object to instruct the target object to adjust the current quantity and current spatial parameters of the target trapping device in the target placement area based on the target quantity and target spatial parameters.

[0019] Preferably, determining the target spatial parameters of the targeting trapping device based on meteorological data includes:

[0020] Obtain the meteorological data at the current moment, and query the parameter database corresponding to the target trapping device based on the meteorological data to obtain the target spatial parameters. The parameter database stores the mapping relationship between meteorological data and spatial parameters.

[0021] Preferably, the method further includes:

[0022] After a second preset time interval, a fourth control command is sent to the target object to control the target object to collect and upload images of the insect-attracting parts of the target trapping device;

[0023] The image of the insect-attracting part is analyzed to identify the target pest and count the target pest.

[0024] According to a second aspect, a field moth pest monitoring device is provided, the device comprising:

[0025] A determination module is used to determine the species of the target pest and the corresponding target trapping device for the species of the target pest.

[0026] The first sending module is used to send a first control command to the target object, instructing the target object to place the target-oriented trapping device in the monitoring area;

[0027] The second sending module is used to determine the target spatial parameters of the target trapping device based on meteorological data after a first preset time interval, and send a second control command to the target object to instruct the target object to adjust the current spatial parameters of the target trapping device based on the target spatial parameters.

[0028] According to a third aspect, an electronic device is provided, including a processor and a memory;

[0029] The processor is connected to the memory;

[0030] The memory is used to store executable program code;

[0031] The processor runs a program corresponding to the executable program code stored in the memory to perform the steps of the method provided as in the first aspect or any possible implementation thereof.

[0032] According to a fourth aspect, a computer-readable storage medium is provided having a computer program stored thereon, the computer-readable storage medium storing instructions that, when executed on a computer or processor, cause the computer or processor to perform the method provided as in the first aspect or any possible implementation thereof.

[0033] The methods and apparatus provided in the embodiments of this specification can automatically place targeted trapping devices according to the target pest species to be monitored. At the same time, they can continuously adjust the spatial parameters of each targeted trapping device according to meteorological data, so that the obtained monitoring image data is highly accurate and meets the monitoring requirements of moth pests. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 This is a flowchart of a field moth pest monitoring method in one embodiment of this specification.

[0036] Figure 2 This is a schematic diagram of the structure of a field moth pest monitoring device in one embodiment of this specification.

[0037] Figure 3 This is a schematic diagram of the structure of an electronic device in one embodiment of this specification. Detailed Implementation

[0038] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0039] In the following description, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance. The following description provides multiple embodiments of this application, which can be substituted or combined with each other. Therefore, this application can also be considered to include all possible combinations of the same and / or different embodiments described. Thus, if one embodiment includes features A, B, and C, and another embodiment includes features B and D, then this application should also be considered to include embodiments containing one or more other possible combinations of A, B, C, and D, even if such embodiments are not explicitly described in the following text.

[0040] The following description provides examples and does not limit the scope, applicability, or examples set forth in the claims. Changes may be made to the function and arrangement of the described elements without departing from the scope of this application. Various processes or components may be appropriately omitted, substituted, or added to the examples. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Furthermore, features described with respect to some examples may be combined into other examples.

[0041] See Figure 1 , Figure 1 This is a flowchart illustrating a method for monitoring field moth pests provided in an embodiment of this application. In this embodiment, the method includes:

[0042] S101. Determine the target pest species and determine the target trapping device corresponding to the target pest species.

[0043] The entity executing this application may be a cloud server.

[0044] In the embodiments described in this specification, the cloud server will first determine the target pest species to be monitored. Depending on the pest species, different pheromone traps will be used to trap the pests. Therefore, the cloud server will determine the target pheromone traps to be used for this pest monitoring based on the target pest species.

[0045] For example, a sex pheromone trap includes a lure containing a slow-release sex pheromone component, exhibiting species specificity and capable of attracting a single type of moth pest. Common shapes of sex pheromone traps include boat-shaped traps, cylindrical diamond-shaped entrance traps, and bell-shaped inverted funnel traps. Considering the impact of the trap's structure on the type and quantity of insects attracted—for example, noctuid moths require cylindrical diamond-shaped entrance traps, while pyralid moths require bell-shaped inverted funnel traps—insect samples can also be collected using sticky traps within the trapping area.

[0046] In one possible implementation, step S101 includes:

[0047] Acquire monitoring targets, and determine the types of target pests based on the monitoring targets;

[0048] Determine the characteristics of the target pest corresponding to the target pest species, and determine the target trapping device based on the characteristics of the target pest.

[0049] In the embodiments described in this specification, staff will set monitoring targets on the terminal according to the pests they need to monitor. The cloud server can determine the species of the target pest by acquiring the monitoring targets. Each pest species has corresponding pest characteristics (such as characteristics of noctuid moths, characteristics of pyralid moths, etc.) according to its species characteristics. The cloud server can then locate and determine the corresponding target trapping device based on the characteristics of the target pest.

[0050] S102. Send a first control command to the target object to instruct the target object to place the target-oriented trapping device in the monitoring area.

[0051] In the embodiments described in this specification, the target object can be an AGV (Automated Guided Vehicle) or an intelligent robot capable of moving in a field environment. After the cloud server identifies the target trapping device, it sends a first control command to the target object. Upon receiving the first control command, the target object can grasp the target trapping device and place it within the designated monitoring area. The monitoring area is a pre-defined area used to monitor specific moth pests in a fixed field (or a plant protection department's observation nursery), providing data for comprehensive monitoring.

[0052] For example, the target object can travel to the area corresponding to the targeted trapping device in a fixed field. Based on the identification sensors installed on each trapping device, its specific location is determined. The identification sensors then identify the gripping part of the trapping device, and the object uses its robotic arm and gripping components to grasp the identified gripping part, thus completing the capture of the trapping device. Next, based on its current location and the monitoring area, it can plan a route. After arriving at the monitoring area according to the route, the object uses the height and orientation identification sensors to confirm that the trapping device has been placed. Once this is confirmed, the object releases the gripping part, completing the placement of the trapping device. The identification sensors can be infrared sensors, photoelectric sensors, etc. The route planning can be any existing AI path planning method that can be implemented, and will not be detailed here.

[0053] In one possible implementation, step S102 includes:

[0054] The initial number of the target trapping devices is determined based on the area of ​​the monitoring area, and the initial spatial parameters of the target trapping devices are obtained. The spatial parameters include the arrangement of the target trapping devices, the first distance between the target trapping devices and the field ridge, the second distance between the target trapping devices, and the height of the insect-attracting part.

[0055] A first control command is sent to the target object to instruct the target object to place the target-oriented trapping device in the monitoring area according to the initial quantity and initial spatial parameters.

[0056] In the embodiments described in this specification, to diversify the acquired data, reduce misjudgments, and improve monitoring accuracy, the cloud server can control the placement of multiple targeted traps within the monitoring area. To ensure the actual effectiveness of each targeted trap, the position and distribution of the traps need to be adjusted. Specifically, given a defined type of targeted trap, the database pre-sets a mapping relationship between the number of traps and the monitoring area based on experience. The cloud server determines the initial number of targeted traps based on the area of ​​the monitoring region. Furthermore, given a defined type of targeted trap, its corresponding initial spatial parameters—such as the distance between the trap and the field ridge, the distance between the traps, and the height of the trapping point—can be pre-set based on human experience. The target object is placed within the monitoring area according to the initial number and initial spatial parameters. The initial placement position of the first targeted trap can be at the edge or center of the area. The specific method for adjusting the height of the insect-attracting part can be that the target trapping device is equipped with an electrically controlled telescopic component. When the target object grasps the target trapping device, it can send telescopic parameters to the controller of the telescopic component through the transmission of electrical signals, and then the telescopic component responds to the telescopic parameters and extends to the specified height.

[0057] In one possible implementation, sending the first control command to the target object includes:

[0058] When a non-targeted trapping device is present in the monitoring area, the minimum distance between the targeted trapping device and the non-targeted trapping device is determined, and a first control command and a third control command are sent to the target object. The third control command is used to instruct the target object to adjust the third distance between any of the targeted trapping devices and the non-targeted trapping devices to be no less than the minimum distance.

[0059] In the embodiments of this specification, multiple sex pheromone traps can be set up in the monitoring area at the same time to attract various field moth pests. To avoid interference between different sex pheromone traps, the traps need to be reasonably spaced and arranged. Specifically, the database can also pre-set the minimum distance between various types of sex pheromone traps based on human experience. Simultaneously with sending the first control command, the cloud server also sends a third control command to instruct the target object to correct the position of the target sex pheromone trap, ensuring that the third distance between the target and non-target traps is not less than the minimum distance.

[0060] S103. After each first preset time interval, the target spatial parameters of the target trapping device are determined based on meteorological data, and a second control command is sent to the target object to instruct the target object to adjust the current spatial parameters of the target trapping device based on the target spatial parameters.

[0061] In the embodiments described in this specification, the activity location and height of moth pests will change accordingly under conditions of strong winds, rainfall, or changes in wind direction. To more accurately trap target pests, the specific location / distribution / height of the target trapping device should be adjusted based on changes in meteorological data. Therefore, every first preset time interval (e.g., 24 hours), the cloud server acquires the current meteorological data and determines the most suitable spatial parameters, i.e., target spatial parameters, based on historical meteorological data and current field vegetation information. Then, the cloud server sends a second control command to the target object, instructing it to adjust the current spatial parameters of the target trapping device according to the target spatial parameters after the target object grasps the device; that is, to adjust the first distance, second distance, and height of the insect-attracting part of the target trapping device. This allows for adjustments to the setting of the target trapping device based on the activity range of the target pests under different meteorological data, improving the accuracy of the target trapping device in trapping target pests. The meteorological data may include nighttime wind force, wind direction, rainfall factor, temperature, humidity, etc.

[0062] In one possible implementation, step S103 includes:

[0063] After each first preset time period, the target spatial parameters of the target trapping device are determined based on meteorological data, and the target placement area and number of targets of the target trapping device are determined based on the characteristics of the monitoring area.

[0064] A second control command is sent to the target object to instruct the target object to adjust the current quantity and current spatial parameters of the target trapping device in the target placement area based on the target quantity and target spatial parameters.

[0065] In the embodiments described in this specification, considering that not all locations within the monitoring area are suitable for preventing targeted trapping devices due to varying actual conditions, the cloud server, in addition to determining the target spatial parameters of the targeted trapping device based on meteorological data, also obtains the monitoring area characteristics based on map data and the region's planting data. This allows the cloud server to determine the actual placement area of ​​the targeted trapping device, i.e., the target placement area, and the number of targets within that area. Thus, the second control command generated by the cloud server can instruct the target object to adjust the actual state of the targeted trapping device within the target placement area according to the target quantity and target spatial parameters, further ensuring the accuracy of pest monitoring. The monitoring area characteristics may include crop planting structure, such as crop variety, layout, and planting period, as well as surrounding terrain and topography.

[0066] In one possible implementation, determining the target spatial parameters of the targeting trapping device based on meteorological data includes:

[0067] Obtain the meteorological data at the current moment, and query the parameter database corresponding to the target trapping device based on the meteorological data to obtain the target spatial parameters. The parameter database stores the mapping relationship between meteorological data and spatial parameters.

[0068] In the embodiments described in this specification, a parameter database is pre-set. This database contains a mapping relationship between meteorological data and spatial parameters based on historical data showing the activity patterns of moth pests under different meteorological conditions. After obtaining the current meteorological data, the cloud server inputs the meteorological data into the parameter database for querying and calculation, thereby obtaining the target spatial parameters.

[0069] Specifically, the mapping relationship can be determined by setting corresponding spatial parameters for each type of meteorological data after determining the spatial distribution of moth pests corresponding to each type of meteorological data, combined with human experience; or it can be determined by training a CNN neural network based on historical data and using the mapping function of the neural network as the mapping relationship.

[0070] In one possible implementation, the method further includes:

[0071] After a second preset time interval, a fourth control command is sent to the target object to control the target object to collect and upload images of the insect-attracting parts of the target trapping device;

[0072] The image of the insect-attracting part is analyzed to identify the target pest and count the target pest.

[0073] In the embodiments described in this specification, after a second preset time interval, the cloud server sends a fourth control command to the target object to control the target object to capture images of the insect-attracting parts of the target trap using its own camera equipment. The target object uploads the captured images to the cloud server, which then performs image recognition on the images of the insect-attracting parts to identify the target pests in the images, determine the number of target pests, and determine the reproductive period of each target pest based on the different images. The second preset time interval can be the same as the first preset time interval, allowing the target object to capture images each time it adjusts the target trap, or it can be different from the first preset time interval, staggering the time for spatial position adjustment and image acquisition. Furthermore, in some relatively stable environments, the target object may not need to adjust the spatial parameters every first preset time interval, but it can still complete image acquisition according to the fourth control command generated every second preset time interval, and vice versa.

[0074] In addition, the image data corresponding to the collected images of the insect-attracting sites can be supplemented with additional information, such as the type of target bait, placement time, placement location, crop name, and growth stage information. This allows staff to integrate various information to calculate the dynamic information of target occurrence at a specific time, display the peak moth period for a certain time frame, infer the larval emergence period (damage period), predict and recommend the appropriate control period.

[0075] The specific process for analyzing and identifying images of the insect-attracting sites can be as follows:

[0076] Step 1, Image Generation and Brightness Preprocessing:

[0077] Use Java's ImageIO to extract images from the database and perform various processing on the raw images received from the cloud server, including backing up the raw images, generating compressed images, data augmentation, and image preprocessing.

[0078] The original image, in JPG format, is used for high-resolution display, generating compressed images, model training, and plotting the results.

[0079] Compressed images, in JPG format, are used for displaying small images on user systems to speed up image transmission.

[0080] The corresponding path of the above image on the cloud server will be saved to the database.

[0081] Data augmentation is primarily used to expand the dataset, preparing it for subsequent model training and improving the model's robustness. It mainly employs image flipping and rotation, noise addition, and other noise enhancement techniques.

[0082] The data-augmented images are stored on the image dataset server and used for subsequent model training.

[0083] Step 2, Image Preprocessing - Adaptive Brightness Adjustment and Local Highlight Reduction:

[0084] Use Python's OpenCV to extract images from a database and preprocess the images.

[0085] Images of pheromone traps suffer from complex backgrounds, uneven brightness, and localized highlights due to variations in the adhesive on the traps and lighting conditions.

[0086] To address the issue of uneven brightness, an image preprocessing method based on linear transformation was employed to obtain an image with uniform background brightness. Specifically, an adaptive brightness adjustment algorithm was used to analyze the image histogram. The histogram of RGB in the RGB three-channel image was calculated, and the image was converted from the RGB color space to the HSI color space. Histogram equalization was then performed on the brightness channel in the HSI color space, followed by conversion back to the RGB color space. Histogram equalization provides initial correction to the image brightness, reducing overexposure. Finally, the image brightness was adjusted, including the following steps:

[0087] (1) First, obtain the brightness of the image according to the following formula.

[0088] Brightness=0.299×R+0.587×G+0.114×B

[0089] Where R, G, and B are the pixel values ​​of the Red, Green, and Blue channels of the image, respectively, and Brightness is the calculated image brightness.

[0090] (2) After obtaining the image brightness, the original image f is linearly transformed by formula (2) to generate a new image g.

[0091] g(i,j)=goal_Brightness / Brightness×f(i,j)

[0092] In the formula, i,j represent the corresponding positions of pixels in the image, f(i,j) is the RGB pixel value of image f at position (i,j), and g(i,j) is the RGB pixel value of image g at position (i,j). goal_Brightness is the target brightness, ranging from [0,255]. To calculate the goal_Brightness value, this embodiment sets goal_Brightness within the range of [150, 200] and performs multiple tests. The best result is achieved when goal_Brightness=180, ensuring the overall brightness of all images is the same.

[0093] To address the issue of localized highlights, a grayscale image is first generated. Experiments show that areas with pixel values ​​above 220 are highlight regions, which can be filtered out using a binarized mask. Traditional methods for filling highlight regions involve filling with white or the most frequently occurring color in the image. However, due to complex backgrounds, determining the correct color is often difficult, resulting in an unnatural-looking image that hinders subsequent model recognition. This algorithm employs a block-based color selection strategy, dividing the R, G, and B channels into blocks. For each channel, the original pixel value range is 0-255. The initial block size is set to `blocksize` (usually a factor of 256). After several trials, a `blocksize` of 16 yielded the best results. This divides the pixel value range into 16 equal parts, with each block corresponding to a continuous segment of color values. Therefore, the initial selection of fill colors is reduced from 255*255*255 colors to 16*16*16 blocks, better encompassing colors visible to the naked eye. Although the background is complex, causing certain colors to appear more frequently than the main color, the overall background color is similar because it's the same color panel. While the colors are different, they all tend to fall within a certain color block. Therefore, we only need to calculate the frequency of each color block in the image; the color block with the highest frequency is the color block kmax needed for filling. After obtaining the color blocks, we need to determine the specific fill color. The method continues the block-based color selection strategy: within the area where color block kmax is located, the color block with the highest frequency is selected, and so on, continuously reducing the blocksize until it reaches 1. When the blocksize is 1, the color value represented by the most frequent color block is used as the fill color value for that channel. Using the block-based color selection strategy quickly determines the background color range, reduces the influence of background interference, and ensures that the final selected color conforms to the overall trend, resulting in a more reasonable generated image.

[0094] The corresponding path of the above image on the cloud server will be saved to the database.

[0095] The de-highlighted image will be transmitted to the Django framework via HTTP. The Django framework will then call the model to recognize the de-highlighted image. The image will be compressed proportionally to meet the size requirements of the model input, and the remaining space in the width and height will be either left blank or processed using the SPP algorithm.

[0096] Step 3, Detection Model:

[0097] The detection of fall armyworms is achieved through a convolutional model network based on YOLO-SFD. Due to the presence of numerous impurities in sticky insect images, different insects may be adhered together. Furthermore, the specificity of sex pheromones may lead to the presence of similar non-target pests. To improve the detection accuracy of fall armyworms and reduce false detections of similar non-target pests, this solution proposes an image detection model, YOLO-SFD, based on YOLOX. This model consists of a feature extraction module and a decoupling head module. After image preprocessing, multi-scale features are extracted using CSPDarknet, and then the image passes through a new attention mechanism module, Channel and Space Transformer (CST), formed by fusing CBAM and Transformer. This enhances key information in the input feature map. To preserve global features, CST employs image fusion methods from Transformer. The multi-scale image output from CSPDarknet is first input into CST, passing through channel attention and spatial attention mechanisms to generate enhanced feature maps. Feature maps are then fused using the Add&Norm structure in Transformer to generate the final feature map, which is then fused again using the Add&Norm structure to generate the output feature map. CST amplifies key information at the image channel and spatial levels, while preserving all information of the input features. CST implements channel attention and spatial attention mechanisms.

[0098] Step 4: The final YOLO-SFD recognition result is the position information of each target in the image, specifically in the format (target's horizontal coordinate position in the image, target's vertical coordinate position in the image, target's width, target's height). The algorithm server on the cloud server returns this position information and the corresponding target information to the web server.

[0099] Step 5: Based on the information returned by the algorithm server, the original image is plotted as a result image. The target location is outlined in the original image, and different targets are marked with different colors. The number of different targets can be displayed in the upper right corner of the image. A compressed image is also generated from the result image. The paths of the result image and the corresponding compressed image in the server are stored in the database, and the board status is determined using a new and old board verification algorithm. The compressed image of the acquired image and the corresponding compressed image result image are loaded into the interface for display through parallel loading.

[0100] The board status determination involves comparing two images to determine if the later image represents a new board relative to the earlier one. Specifically, this is done by processing the positional information in the corresponding result image. The positional information in both images is known; each target consists of four data points in the format: the target's x-coordinate, y-coordinate, width, and height. First, it's determined whether the targets in the two images overlap and whether they represent the same pest. If these conditions are met, the Intersection over Union (IOU) value is calculated. If the IOU > 0.5, it's considered a matched target. After calculating all targets, the number of matched targets is counted. If this number is greater than 2 / 3 of the number in the previous image, it's considered an old board, and the number of non-overlapping targets in the new image is calculated during data analysis. Otherwise, it's a new board, and all targets are considered newly added during data analysis.

[0101] The following will be combined with the appendix Figure 2 This application provides a detailed description of the field moth pest monitoring device provided in its embodiments. It should be noted that the appendix... Figure 2 The field moth pest monitoring device shown is used to perform the functions described in this application. Figure 1 The methods shown in the embodiments are for illustrative purposes only, illustrating the parts relevant to the embodiments of this application. For specific technical details not disclosed, please refer to this application. Figure 1 The example shown.

[0102] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of a field moth pest monitoring device provided in an embodiment of this application. Figure 2 As shown, the device includes:

[0103] The determination module 201 is used to determine the species of the target pest and the target trapping device corresponding to the species of the target pest.

[0104] The first sending module 202 is used to send a first control command to the target object, instructing the target object to place the target trapping device in the monitoring area;

[0105] The second sending module 203 is used to determine the target spatial parameters of the target trapping device based on meteorological data after a first preset time interval, and send a second control command to the target object to instruct the target object to adjust the current spatial parameters of the target trapping device based on the target spatial parameters.

[0106] In one possible implementation, the determining module 201 is specifically used for:

[0107] Acquire monitoring targets, and determine the types of target pests based on the monitoring targets;

[0108] Determine the characteristics of the target pest corresponding to the target pest species, and determine the target trapping device based on the characteristics of the target pest.

[0109] In one possible implementation, the first sending module 202 is specifically used for:

[0110] The initial number of the target trapping devices is determined based on the area of ​​the monitoring area, and the initial spatial parameters of the target trapping devices are obtained. The spatial parameters include the arrangement of the target trapping devices, the first distance between the target trapping devices and the field ridge, the second distance between the target trapping devices, and the height of the insect-attracting part.

[0111] A first control command is sent to the target object to instruct the target object to place the target-oriented trapping device in the monitoring area according to the initial quantity and initial spatial parameters.

[0112] In one possible implementation, the first sending module 202 is further configured to:

[0113] When a non-targeted trapping device is present in the monitoring area, the minimum distance between the targeted trapping device and the non-targeted trapping device is determined, and a first control command and a third control command are sent to the target object. The third control command is used to instruct the target object to adjust the third distance between any of the targeted trapping devices and the non-targeted trapping devices to be no less than the minimum distance.

[0114] In one possible implementation, the second sending module 203 is specifically used for:

[0115] After each first preset time period, the target spatial parameters of the target trapping device are determined based on meteorological data, and the target placement area and number of targets of the target trapping device are determined based on the characteristics of the monitoring area.

[0116] A second control command is sent to the target object to instruct the target object to adjust the current quantity and current spatial parameters of the target trapping device in the target placement area based on the target quantity and target spatial parameters.

[0117] In one possible implementation, the second sending module 203 is further configured to:

[0118] Obtain the meteorological data at the current moment, and query the parameter database corresponding to the target trapping device based on the meteorological data to obtain the target spatial parameters. The parameter database stores the mapping relationship between meteorological data and spatial parameters.

[0119] In one possible implementation, the device further includes:

[0120] The third sending module is used to send a fourth control command to the target object every second preset time interval, so as to control the target object to collect and upload images of the insect-attracting parts of the target trapping device;

[0121] The analysis module is used to analyze the image of the insect-attracting part, identify the target pest, and count the target pest.

[0122] Those skilled in the art will clearly understand that the technical solutions of the embodiments of this application can be implemented by means of software and / or hardware. In this specification, "unit" and "module" refer to software and / or hardware that can independently complete or cooperate with other components to complete a specific function, wherein the hardware may be, for example, a field-programmable gate array (FPGA), an integrated circuit (IC), etc.

[0123] Each processing unit and / or module in the embodiments of this application can be implemented by an analog circuit that implements the functions described in the embodiments of this application, or by software that executes the functions described in the embodiments of this application.

[0124] See Figure 3 It shows a schematic diagram of the structure of an electronic device according to an embodiment of this application, which can be used to implement... Figure 1 The method in the illustrated embodiment. (As shown) Figure 3 As shown, the electronic device 300 may include: at least one central processing unit 301, at least one network interface 304, user interface 303, memory 305, and at least one communication bus 302.

[0125] The communication bus 302 is used to enable communication between these components.

[0126] The user interface 303 may include a display screen and a camera. Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0127] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0128] The central processing unit 301 may include one or more processing cores. The central processing unit 301 connects to various parts within the electronic device 300 using various interfaces and lines. It executes various functions of the terminal 300 and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling data stored in the memory 305. Optionally, the central processing unit 301 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The central processing unit 301 may integrate one or more of the following: a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also be implemented as a separate chip without being integrated into the central processing unit 301.

[0129] The memory 305 may include random access memory (RAM) or read-only memory. Optionally, the memory 305 may include a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 305 may also be at least one storage device located remotely from the aforementioned central processing unit 301. Figure 3 As shown, the memory 305, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and program instructions.

[0130] exist Figure 3In the illustrated electronic device 300, the user interface 303 is mainly used to provide an input interface for the user and to acquire user input data; while the central processing unit 301 can be used to call the field moth pest monitoring application stored in the memory 305 and specifically perform the following operations:

[0131] Identify the target pest species and determine the corresponding targeted trapping device for the target pest species;

[0132] Send a first control command to the target object to instruct the target object to place the target-trapping device in the monitoring area;

[0133] After each first preset time interval, the target spatial parameters of the target trapping device are determined based on meteorological data, and a second control command is sent to the target object to instruct the target object to adjust the current spatial parameters of the target trapping device based on the target spatial parameters.

[0134] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method. The computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, microdrives, as well as magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic cards or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0135] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0136] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0137] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0138] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0139] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0140] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0141] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0142] The foregoing description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Those skilled in the art will readily conceive of embodiments of this disclosure upon considering the specification and practicing the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described herein. The specification and embodiments are to be considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. A method for monitoring field moth pests, characterized in that, The method includes: Identify the target pest species and determine the corresponding targeted trapping device for the target pest species; Send a first control command to the target object to instruct the target object to place the target-trapping device in the monitoring area; After a first preset time interval, the target spatial parameters of the target trapping device are determined based on meteorological data, and a second control command is sent to the target object to instruct the target object to adjust the current spatial parameters of the target trapping device based on the target spatial parameters. The spatial parameters include the arrangement of the target trapping devices, the first distance between the target trapping devices and the field ridge, the second distance between the target trapping devices, and the height of the insect-attracting part. The meteorological data includes nighttime wind force, wind direction, rainfall factor, temperature, and humidity. After a second preset time interval, a fourth control command is sent to the target object to control the target object to collect and upload images of the insect-attracting parts of the target trapping device; The image of the insect-attracting part is analyzed to identify the target pest and count the target pests. The state of the board is determined by the new and old board verification algorithm. The board state determination process is as follows: the horizontal coordinate position of the target in the image, the vertical coordinate position of the target in the image, the width of the target, and the height of the target are used as a target. It is determined whether the identified targets in the two images overlap and whether they are the same pest. The identified targets with an IOU > 0.5 are recorded as a matching target. When the number of matching targets is greater than 2 / 3 of the number in the previous image, it is determined to be the old version. During data analysis, the number of non-overlapping targets in the new image is calculated. Otherwise, it is the new board. During data analysis, all targets are newly added targets.

2. The method according to claim 1, characterized in that, The step of determining the target pest species and the corresponding target trapping device includes: Acquire monitoring targets, and determine the types of target pests based on the monitoring targets; Determine the characteristics of the target pest corresponding to the target pest species, and determine the target trapping device based on the characteristics of the target pest.

3. The method according to claim 1, characterized in that, Sending a first control command to the target object to instruct the target object to place the target-trapping device in the monitoring area includes: The initial number of the target trapping devices is determined based on the area of ​​the monitoring region, and the initial spatial parameters of the target trapping devices are obtained. A first control command is sent to the target object to instruct the target object to place the target-oriented trapping device in the monitoring area according to the initial quantity and initial spatial parameters.

4. The method according to claim 1, characterized in that, Sending the first control command to the target object includes: When a non-targeted trapping device is present in the monitoring area, the minimum distance between the targeted trapping device and the non-targeted trapping device is determined, and a first control command and a third control command are sent to the target object. The third control command is used to instruct the target object to adjust the third distance between any of the targeted trapping devices and the non-targeted trapping devices to be no less than the minimum distance.

5. The method according to claim 1, characterized in that, After each first preset time interval, the target spatial parameters of the target-oriented trapping device are determined based on meteorological data, and a second control command is sent to the target object to instruct the target object to adjust the current spatial parameters of the target-oriented trapping device based on the target spatial parameters, including: After each first preset time period, the target spatial parameters of the target trapping device are determined based on meteorological data, and the target placement area and number of targets of the target trapping device are determined based on the characteristics of the monitoring area. A second control command is sent to the target object to instruct the target object to adjust the current quantity and current spatial parameters of the target trapping device in the target placement area based on the target quantity and target spatial parameters.

6. The method according to claim 5, characterized in that, The determination of the target spatial parameters of the target trapping device based on meteorological data includes: Obtain the meteorological data at the current moment, and query the parameter database corresponding to the target trapping device based on the meteorological data to obtain the target spatial parameters. The parameter database stores the mapping relationship between meteorological data and spatial parameters.

7. A field moth pest monitoring device, comprising: A determination module is used to determine the species of the target pest and the corresponding target trapping device for the species of the target pest. The first sending module is used to send a first control command to the target object, instructing the target object to place the target-oriented trapping device in the monitoring area; The second sending module is used to determine the target spatial parameters of the target trapping device based on meteorological data after a first preset time interval, and send a second control command to the target object to instruct the target object to adjust the current spatial parameters of the target trapping device based on the target spatial parameters. The spatial parameters include the arrangement of the target trapping devices, the first distance between the target trapping devices and the field ridge, the second distance between the target trapping devices, and the height of the insect-attracting part. The meteorological data includes the wind force, wind direction, rainfall factor, temperature, and humidity at night. The third sending module is used to send a fourth control command to the target object every second preset time interval, so as to control the target object to collect and upload images of the insect-attracting parts of the target trapping device; The parsing module is used to parse the image of the insect-attracting part, identify the target pests, and count the target pests. The image of the insect-attracting part is used to determine the state of the board through a new and old board verification algorithm. The board state determination process is as follows: taking the horizontal coordinate position of the target in the image, the vertical coordinate position of the target in the image, the width of the target, and the height of the target as a target, it is determined whether the identified targets in the two images overlap and whether they are the same pests. The identified targets with an IOU > 0.5 are recorded as a matching target. When the number of matching targets is greater than 2 / 3 of the number in the previous image, it is determined to be the old version. During data analysis, the number of non-overlapping targets in the new image is calculated. Otherwise, it is the new board, and all targets are newly added targets during data analysis.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, the computer-readable storage medium storing instructions that, when executed on a computer or processor, cause the computer or processor to perform the steps of the method as claimed in any one of claims 1-6.

Images