Method and device for monitoring distribution condition of toxic weeds in grassland, and terminal equipment

Abstract

The invention provides a grassland toxic weed distribution condition monitoring method and device and terminal equipment, and is suitable for the technical field of image processing, and the method comprises the steps: obtaining first spectral image information and second spectral image information; according to a preset toxic weed sample information base and the first spectral image information, determining initial position information of toxic weeds in the first spectral image; calculating target position information of the toxic weeds in the first spectral image according to the initial position information of the toxic weeds in the first spectral image and a preset toxic weed band classification model; determining toxic weed position information of a second spectral image according to the toxic weed target position information of the first spectral image and the second spectral image information; and generating toxic weed position distribution information according to the toxic weed position information of the second spectral image, a preset toxic weed spectral image feature extraction model and a preset toxic weed position detection model. According to the invention, multiple spectral images are combined, so that the efficiency and accuracy of monitoring the toxic weed distribution condition are improved.

Description

Technical Field

[0001] The present application belongs to the field of image processing technology, and in particular relates to a method, device and terminal equipment for monitoring the distribution of poisonous weeds in grasslands. Background Art

[0002] Grassland ecosystem is one of the largest terrestrial ecosystems on Earth, and plays an important role in global ecological balance, soil and water conservation, and animal husbandry development. However, in recent years, grassland ecosystems have been severely degraded due to overgrazing, climate change, and the impact of human activities, with grassland area reduction, desertification intensification, and the spread of poisonous weeds. Poisonous weeds are not only toxic to livestock, causing livestock poisoning, weight loss, and even death, but also directly affect the meat and milk production of animal husbandry, threatening the economic benefits of herders. In addition, the spread and growth of poisonous weeds will further destroy the biodiversity and ecological balance of grasslands and accelerate grassland degradation. Therefore, the monitoring and control of poisonous weeds has become a key task for grassland protection and sustainable development of animal husbandry.

[0003] Poisonous weed monitoring has always been a major problem in grassland ecological protection and management. Traditional methods of poisonous weed monitoring mainly rely on manual ground surveys. Workers move dynamically on the grassland to collect data on poisonous weeds such as Leontopodiumnanum, Ajania tenuifolia, Aster hispidus, Saussureajaponica, Aconitum pendulum, and Ligularia virgaurea, and conduct follow-up investigations based on the collected data. In existing technologies, technicians can monitor the distribution of poisonous weeds on grasslands through remote sensing monitoring technology.

[0004] However, the method of staff walking around to investigate the distribution of poisonous weeds in a large grassland is time-consuming and labor-intensive, with extremely low efficiency, and it is difficult to fully reflect the actual distribution of poisonous weeds, and the accuracy of the detection of poisonous weeds cannot be guaranteed. Existing remote sensing monitoring technology has limitations in the spectral distinction between poisonous weeds and ordinary vegetation, especially in mixed backgrounds. The spectral overlap problem makes it difficult to accurately identify poisonous weeds, and there is a general lack of monitoring capabilities for the growth cycle and dynamic distribution changes of poisonous weeds. It is difficult to cope with grassland ecosystems with complex poisonous weed backgrounds and scattered distribution, resulting in poor monitoring of poisonous weeds and little room for improvement. Summary of the invention

[0005] In view of this, the embodiments of the present application provide a method, device and terminal device for monitoring the distribution status of poisonous weeds in grasslands, aiming to solve the problems existing in the prior art of long time consumption, small coverage, low efficiency in monitoring the distribution status of poisonous weeds, and inability to quickly and comprehensively monitor the distribution of poisonous weeds. At the same time, it solves the problems of the prior art of difficulty in tracking the dynamic distribution of poisonous weeds and redundant spectral bands, thereby improving the accuracy of monitoring poisonous weeds in grasslands.

[0006] A first aspect of an embodiment of the present application provides a method for monitoring the distribution of poisonous weeds in grasslands, comprising: Acquire a plurality of first spectral image information and a second spectral image information; Determine the initial position information of the poisonous weeds in the first spectral image according to the preset poisonous weed sample information library and the first spectral image information; Calculating target position information of poisonous weeds in the first spectral image according to the initial position information of poisonous weeds in the first spectral image and a plurality of preset poisonous weed band classification models; Determine the second spectral image poisonous weed position information according to the first spectral image poisonous weed target position information and the second spectral image information; The poisonous weed position distribution information is generated according to the poisonous weed position information of the second spectral image, a preset poisonous weed spectral image feature extraction model and a preset poisonous weed position detection model.

[0007] A second aspect of the embodiment of the present application provides a grassland poisonous weed distribution status monitoring device, comprising: A spectral image information acquisition module, used to acquire a plurality of first spectral image information and a second spectral image information; A first spectral image poisonous weed initial position information determination module, used to determine the first spectral image poisonous weed initial position information according to a preset poisonous weed sample information library and the first spectral image information; A first spectral image poisonous weed target position information calculation module, used to calculate the first spectral image poisonous weed target position information according to the first spectral image poisonous weed initial position information and a plurality of preset poisonous weed band classification models; A second spectral image poisonous weed position information determination module, configured to determine the second spectral image poisonous weed position information according to the first spectral image poisonous weed target position information and the second spectral image information; The poisonous weed location distribution information generating module is used to generate the poisonous weed location distribution information according to the second spectral image poisonous weed location information, a preset poisonous weed spectral image feature extraction model and a preset poisonous weed location detection model.

[0008] A third aspect of an embodiment of the present application provides a terminal device, which includes a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the steps of the grassland poisonous weed distribution status monitoring method as described in the first aspect above are implemented.

[0009] A fourth aspect of the embodiments of the present application provides a computer-readable storage medium, comprising: a computer program stored therein, which, when executed by a processor, implements the steps of the grassland poisonous weed distribution status monitoring method as described in the first aspect above.

[0010] Compared with the prior art, the embodiments of the present application have the following beneficial effects: the position of poisonous weeds in a local spectral image with high resolution is located by using a preset poisonous weed sample information library, and then the spectral information in the local spectral image is extracted to determine the position distribution of poisonous weeds in a global spectral image with low resolution, thereby combining the obtained multiple spectral images and automatically identifying the distribution of poisonous weeds in the global spectral image, so as to improve the efficiency, comprehensiveness and accuracy of monitoring the distribution of poisonous weeds. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0012] Figure 1 This is a schematic diagram of the implementation process of the method for monitoring the distribution of poisonous weeds in grasslands provided in Example 1 of the present application; Figure 2 This is a schematic diagram of the implementation process of the method for monitoring the distribution of poisonous weeds in grasslands provided in Example 2 of the present application; Figure 3 This is a schematic diagram of the implementation process of the method for monitoring the distribution of poisonous weeds in grasslands provided in Example 3 of the present application; Figure 4 This is a schematic diagram of the implementation process of the method for monitoring the distribution of poisonous weeds in grasslands provided in Example 4 of the present application; Figure 5 This is a schematic diagram of the implementation process of the method for monitoring the distribution of poisonous weeds in grasslands provided in Example 5 of the present application; Figure 6 This is a schematic diagram of the implementation process of the method for monitoring the distribution of poisonous weeds in grasslands provided in Example 6 of the present application; Figure 7 It is a schematic diagram of the structure of a grassland poisonous weed distribution monitoring device provided in an embodiment of the present application; Figure 8 It is a schematic diagram of a terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0013] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0014] In order to illustrate the technical solution described in this application, a specific embodiment is provided below for illustration.

[0015] Figure 1 The following is a flowchart of the method for monitoring the distribution of poisonous weeds in grasslands provided in Example 1 of the present application, which is described in detail as follows: Step S101: Acquire a plurality of first spectral image information and second spectral image information.

[0016] In this embodiment, the first spectral image information and the second spectral image information are used to represent two different spectral image information, wherein the first spectral image information can represent spectral image information with high resolution and reflecting the local situation of the grassland, that is, it has more spectral details but a small field of view, and the second spectral image information can represent spectral image information with low resolution and reflecting the overall situation of the grassland, that is, it has fewer spectral details but a large field of view. The spectral image information includes key parameters such as reflectivity and radiant brightness in each band. The first spectral image information can be a drone hyperspectral image, that is, it is obtained by dynamically shooting a drone on the grassland. It can be understood that although the drone hyperspectral image has high spatial resolution and rich spectral information, the drone's endurance is limited, and the shooting range is usually limited to a small area. Therefore, the first spectral image information obtained is a high-resolution local grassland image. The second spectral image information can be a satellite remote sensing image, that is, it is obtained by shooting with satellite remote sensing technology. It can be understood that satellite remote sensing has a wide coverage, but its spatial resolution and spectral resolution are low, and it is difficult to capture the detailed characteristics of small-scale poisonous weeds, especially scattered and mixed poisonous weeds.

[0017] Step S102: determining initial position information of poisonous weeds in the first spectral image according to a preset poisonous weed sample information database and the first spectral image information.

[0018] In this embodiment, the preset poisonous weed sample information library can be obtained by collecting high-quality samples of poisonous weeds through ground field surveys, recording their phenological information and summarizing them. Poisonous weeds have significant spectral feature differences in different bands (such as red edge, near infrared and short-wave infrared). These differences are mainly reflected in their reflectivity or absorption characteristics. Compared with ordinary vegetation, they form unique identification in the spectral curve. Combined with the poisonous weed sample information library, key band features can be extracted through band selection algorithms to distinguish poisonous weeds from ordinary vegetation backgrounds. Specifically, taking the alpine meadow with an altitude of 3500-4500m as an example, in the selected research area, a 1.0 m×1.0 m sample square frame is laid out, each sample square frame is numbered in sequence, and sample photos in the sample square frame are taken, and the GPS coordinates of the center position are recorded. The collected samples include common poisonous weed types in the area, such as dwarf fireweed, fine-leaved chrysanthemum, dog flower, wind chrysanthemum, iron hammer, yellow broom lily, etc., and record their phenological information (such as flowering period, growth peak period and degradation period). The sampling process needs to span different seasons to ensure that the database contains the spectral characteristics of poisonous weeds in different growth periods. It can be that the first spectral image information is first spliced, that is, multiple images reflecting the local situation of the grassland are spliced ​​to obtain a high-resolution global image that can reflect the overall situation of the grassland, and then according to the spectral characteristics of each poisonous weed in the preset poisonous weed sample information library, the position of the poisonous weeds in the spliced ​​global image is located and marked. The information obtained after marking is the initial position information of the poisonous weeds in the first spectral image, which is used for further screening in the future to obtain more accurate poisonous weed band information. The method of splicing the first spectral image information can be specifically that the first spectral image information is first preprocessed to eliminate noise, atmospheric correction and geometric correction, etc., to ensure the spectral image quality and data accuracy. The first spectral image information is stitched. Specifically, the pre-processed spectral image information is first calibrated for lens, black and white frame, atmosphere and reflectance in Spec View Version software. Then, in order to eliminate the influence of environmental noise and the instrument itself on the spectral data, the spectral data is smoothed by a smoothing method, and the bands affected by water vapor at the beginning and end are removed to obtain effective spectral band data. Finally, the corrected data is imported into the image processing software Hi Spectral Stitcher to stitch the spectral band data to obtain a complete hyperspectral image of the monitoring area, i.e., the first spectral stitched image information.

[0019] In this embodiment, it can be understood that since poisonous weeds have significant spectral feature differences in different bands (such as red edge, near infrared and short-wave infrared), the poisonous weed sample information library can be combined to screen the band features to distinguish poisonous weeds from ordinary vegetation, reduce spectral redundancy, and can also be used to improve the classification ability of the poisonous weed band classification model in the future.

[0020] Step S103, calculating the target position information of the poisonous weeds in the first spectral image according to the initial position information of the poisonous weeds in the first spectral image and a plurality of preset poisonous weed band classification models.

[0021] In this embodiment, the multiple preset poisonous weed band classification models can be support vector machine (SVM), random forest (RF), BP neural network and XGBoost, or other neural network models. Among them, the preset poisonous weed band classification model has been trained by the spectral features of poisonous weeds in the poisonous weed sample information library. In the training process of the poisonous weed band classification model, a suitable feature scaling method can be selected to improve the convergence speed and accuracy of the model. The initial position information of the poisonous weeds in the first spectral image can be subjected to band classification processing through the poisonous weed band classification model, and the initial position information of the poisonous weeds in the first spectral image is divided into poisonous weed position information and normal vegetation position information. The obtained poisonous weed position information is the first spectral image poisonous weed target position information. It can be understood that the position information in this embodiment is represented by the relative position of the spectral information in the image.

[0022] Step S104: determining the second spectral image poisonous weed position information according to the first spectral image poisonous weed target position information and the second spectral image information.

[0023] In this embodiment, the high-resolution global image obtained by splicing the first spectral image information is aligned with the second spectral image, so that the position of the poisonous weeds in the second spectral image is located and marked by the target position information of the poisonous weeds in the first spectral image. The marked poisonous weed position in the second spectral image, that is, the poisonous weed position information of the second spectral image, is used to characterize the relative position of the poisonous weed spectrum in the second spectral image.

[0024] Step S105, generating poisonous weed location distribution information according to the poisonous weed location information of the second spectral image, a preset poisonous weed spectral image feature extraction model, and a preset poisonous weed location detection model.

[0025] In this embodiment, the preset poisonous weed spectral image feature extraction model may be a Transformer model. The preset poisonous weed position detection model may be an LSTM model. The second spectral image poisonous weed position information may be first converted into a format recognizable by the neural network model, and then the spectral image features and the image time series features are extracted simultaneously by the preset poisonous weed spectral image feature extraction model, so that the spectral image features correspond to the image time series features, and then the image time series features are predicted and calculated by the poisonous weed position detection model, so as to obtain the poisonous weed position distribution information, which can be used to visualize the distribution of poisonous weeds on the grassland.

[0026] The method for monitoring the distribution of poisonous weeds in grasslands provided in the embodiment of the present application locates the position of poisonous weeds in a high-resolution local spectral image through a preset poisonous weed sample information library, and then extracts spectral information in the local spectral image to determine the position distribution of poisonous weeds in a global spectral image with a lower resolution, thereby combining the obtained multiple spectral images and automatically identifying the distribution of poisonous weeds in the global spectral image, so as to improve the efficiency, comprehensiveness and accuracy of monitoring the distribution of poisonous weeds.

[0027] Figure 2 The flowchart of the method for monitoring the distribution of poisonous weeds in grasslands provided in the second embodiment of the present application is shown. The difference between the method and the first embodiment is that the step S103 specifically includes: Step S201, dividing the first spectral image information into bands to obtain a plurality of initial poisonous weed detection band information.

[0028] In this embodiment, spectral curve data in the first spectral image information may be extracted, and the bands in the first spectral image information may be divided using a sub-interval band selection technique. The multiple spectral intervals obtained by the division, i.e., initial poisonous weed detection band information, are used to subsequently analyze and determine the distribution status of the poisonous weeds.

[0029] Step S202: performing band extraction on the first spectral image information according to the initial position information of the poisonous weeds in the first spectral image to obtain band information representing the poisonous weeds.

[0030] In this embodiment, the first spectral image information may be subjected to band extraction through the spectral data of the poisonous weeds reflected in the initial position information of the poisonous weeds in the first spectral image, that is, band data in the first spectral image information that can be used to indicate the location of the poisonous weeds, i.e., poisonous weed characterization band information, is determined.

[0031] Step S203, determining whether the band standard deviation of the initial poisonous weed detection band information and the poisonous weed characterization band information is less than a preset band standard deviation threshold; if so, proceeding to step S204; if not, not using the initial poisonous weed detection band information as the intermediate poisonous weed detection band information.

[0032] In this embodiment, the band standard deviation of the initial poisonous weed detection band information and the poisonous weed characterization band information is calculated to quantify the matching degree of the initial poisonous weed detection band information and the poisonous weed characterization band information, so as to determine whether the initial poisonous weed detection band information can be used as the band information characterizing the location of the poisonous weeds in the spectral image. The calculation formula of the band standard deviation of the initial poisonous weed detection band information and the poisonous weed characterization band information is as follows: (1) In the above formula (1), k Indicates the sample number, from 1 to n , n is the total number of samples, i Indicates the current band number. Indicates k Samples in the band i The reflectivity on Indicates band i The sample mean of .

[0033] When the band standard deviation of the initial poisonous weed detection band information and the poisonous weed characterization band information is less than the preset band standard deviation threshold, it means that the initial poisonous weed detection band information is highly likely to be the band reflection information of the poisonous weeds in the spectral image, and can be used as the intermediate poisonous weed detection band information for subsequent calculations. When the band standard deviation of the initial poisonous weed detection band information and the poisonous weed characterization band information is greater than or equal to the preset band standard deviation threshold, it means that the initial poisonous weed detection band information is highly likely not the band reflection information of the poisonous weeds in the spectral image, and cannot be used as the intermediate poisonous weed detection band information for subsequent calculations.

[0034] In this embodiment, the band standard deviations may also be arranged in descending order to screen out the main bands representing poisonous weeds.

[0035] Step S204: using the initial poisonous weed detection band information as intermediate poisonous weed detection band information.

[0036] In this embodiment, when the band standard deviation of the initial poisonous weed detection band information and the poisonous weed characterization band information is less than the preset band standard deviation threshold, it means that the initial poisonous weed detection band information is highly likely to be the band reflection information of the poisonous weeds in the spectral image, and can be used as the intermediate poisonous weed detection band information for subsequent calculations.

[0037] Step S205 , obtaining the first spectral image poisonous weed target position information according to the intermediate poisonous weed detection band information and a plurality of preset poisonous weed band classification models.

[0038] In this embodiment, the preset poisonous weed band classification model can be a support vector machine (SVM), a random forest (RF), a BP neural network and XGBoost, or other neural network models. The intermediate poisonous weed detection band information can be used as input data of the poisonous weed band classification model, the poisonous weed band information and the normal vegetation band information can be used as output data of the poisonous weed band classification model, and the poisonous weed band information in the output data can be used as the first spectral image poisonous weed target position information to represent the poisonous weed position information in the first spectral image information.

[0039] The method for monitoring the distribution of poisonous weeds in grasslands provided in the embodiment of the present application divides the bands of the first spectral image information, and screens the divided band information once according to the initially determined poisonous weed location information, matches the band information after the primary screening with the poisonous weed characterization band information to perform a secondary screening on the band information, and then screens the band information a third time using a preset poisonous weed band classification model, thereby ensuring the screening accuracy of the band information used to characterize the location of the poisonous weeds in the first spectral image, and ensuring the accuracy and effectiveness of automatic monitoring of the distribution of poisonous weeds on the grassland.

[0040] Figure 3 The flowchart of the implementation of the method for monitoring the distribution of poisonous weeds in grasslands provided in the third embodiment of the present application is shown. The difference between the method and the second embodiment is that the step S205 specifically includes: Step S301, calculating the band correlation and band distance of a plurality of the intermediate poisonous weed detection band information.

[0041] In this embodiment, the band correlation may be calculated to perform correlation analysis on the initially screened intermediate poisonous weed detection band information. The band correlation calculation method may be: (2) In the above formula (2), x jk Indicates k Samples in the band j The reflectivity on Indicates band j The sample mean of . In each subinterval, the correlation coefficient Measure the correlation between bands i and j; You can combine six bands into a group and calculate the Jeffreys-Matusita (JM) distance of the noxious weed spectrum corresponding to each group of bands. Select JM distance JM (I,j) For band combinations greater than or equal to 1.8, the selected bands are further verified, and the calculation formula is as follows: (3) In the above formula (3), m i and m j Respectively represent bands i and j The mean of S i and S j is the covariance matrix of the band. Step S302: screening the intermediate poisonous weed detection band information according to the band correlation and the band distance to obtain a plurality of poisonous weed detection band combination information.

[0042] In this embodiment, the correlation coefficient not higher than 0.3 can be used as a screening criterion to determine a representative band, and the JM distance is calculated based on the representative band to select the JM distance. JM (I,j) The band combination greater than or equal to 1.8 is used as the band combination information for poisonous weed detection to ensure that the selected band has the best resolution ability.

[0043] Step S303: calculating classification accuracy evaluation indicators of multiple poisonous weed band classification models according to the poisonous weed detection band combination information and multiple preset poisonous weed band classification models.

[0044] In this embodiment, the poisonous weed detection band combination information can be used as the input data of the poisonous weed band classification model to calculate the classification accuracy evaluation index of the poisonous weed band classification model. The classification accuracy evaluation index includes the overall classification accuracy (OA), the average classification accuracy (AA) and the Kappa coefficient, which are used to verify the effectiveness and reliability of the model in wide-area poisonous weed monitoring. The calculation formulas of the overall classification accuracy (OA), the average classification accuracy (AA) and the Kappa coefficient are as follows: (4) In the above formula (4), C Indicates the number of samples correctly classified in each category, T i represents the number of samples correctly classified in each category, and N represents the total number of samples.

[0045] (5) In the above formula (5), p i Indicates category i classification accuracy.

[0046] (6) In the above formula (6), p o Indicates the total classification accuracy of the category OA , p i represents the expected classification accuracy, a i Indicates category i The number of real samples, b i Indicates that the model predicts the category i The number of .

[0047] Step S304: screening a plurality of preset poisonous weed band classification models according to the classification accuracy evaluation index to obtain a target poisonous weed band classification model.

[0048] In this embodiment, the best poisonous weed band classification model in the classification accuracy evaluation index can be selected as the target poisonous weed band classification model, that is, the poisonous weed band classification model with the highest overall classification accuracy (OA), average classification accuracy (AA) and Kappa coefficient is selected as the target poisonous weed band classification model, which can be used to obtain a small-scale weed distribution map generated based on the UAV hyperspectral image through inversion in the subsequent process.

[0049] Step S305: Obtain the target location information of the poisonous weeds in the first spectral image according to the poisonous weed detection band combination information and the target poisonous weed band classification model.

[0050] In this embodiment, the poisonous weed detection band combination information can be used as input information of the target poisonous weed band classification model. The target poisonous weed band classification model will automatically distinguish the poisonous weed band information from the normal vegetation band information, so as to determine whether the target position is a poisonous weed. Based on the target poisonous weed classification model, the first spectral image information is inverted to output the position information of all poisonous weeds in the first spectral image, that is, the first spectral image poisonous weed target position information.

[0051] The method for monitoring the distribution of poisonous weeds in grasslands provided in the embodiment of the present application ensures the accuracy and reliability of determining the characteristic bands of poisonous weeds by calculating the band correlation and band distance of the bands corresponding to the poisonous weeds, and reduces the amount of input data of the poisonous weed position detection model in subsequent calculations to reduce model redundancy. The performance of multiple poisonous weed band classification models is evaluated by calculating the classification accuracy evaluation index, so as to screen out the poisonous weed band classification model with the best classification calculation effect, which is used to accurately locate the location of the poisonous weeds in the first spectral image, thereby improving the accuracy and effectiveness of identifying the poisonous weeds.

[0052] Figure 4 The flowchart of the method for monitoring the distribution of poisonous weeds in grassland provided by the fourth embodiment of the present application is shown. The difference between the method and the first embodiment is that the step S104 specifically includes: Step S401, registering the target position information of poisonous weeds in the first spectral image and the second spectral image, and determining the initial position information of poisonous weeds in the second spectral image according to the target position information of poisonous weeds in the first spectral image.

[0053] In this embodiment, the second spectral image information may be first declouded through the QA60 band, retaining images with less than 30% cloud cover, and then performing atmospheric correction and geometric correction on the image to ensure the quality of the image, and then applying an image synthesis strategy to synthesize multiple satellite images of the same phenological period into a cloudless synthetic image to increase the coverage of image data of the key growth period of poisonous weeds. In the registration process, specifically, the local, multi-phenological period poisonous weed invasion degree distribution map of the first spectral splicing image information may be resampled by the nearest neighbor interpolation method to achieve the same spatial resolution as the second spectral image information. The second spectral image information may be a Sentinel-2 satellite image, and then, the local, multi-phenological period poisonous weed invasion degree distribution map of the resampled first spectral splicing image information is used as a reference benchmark, and the second spectral image information is geometrically registered by the first-order polynomial method, and the ground control point (GCP) is used for correction during registration to ensure that the correction error is controlled within one pixel, thereby achieving accurate spatial alignment.

[0054] In this embodiment, it can be understood that what is directly registered with the second spectral image information may be the classification result obtained by classifying the first spectral image information, rather than all the information in the first spectral stitching image information, so as to reduce the amount of calculation and computational complexity while determining the location information of the poisonous weeds in the second spectral image information.

[0055] Step S402: masking the initial position information of poisonous weeds in the second spectral image according to preset poisonous weed mask pixel information to determine the position information of poisonous weeds in the second spectral image.

[0056] In this embodiment, the preset poisonous weed mask pixel information can be compiled based on the poisonous weed sample information in the poisonous weed sample information database and the normal vegetation information collected in the daily grassland monitoring work, or it can be compiled based on the classification result obtained by the first spectral image information classification model. The mask processing can be to perform mask processing on the poisonous weed pixels and non-poisonous weed pixels in the poisonous weed position information of the second spectral image respectively, and then count the number of poisonous weed and non-poisonous weed pixels falling into each second spectral image pixel window, and calculate the proportion of these pixels to the total number of second spectral image pixel windows, so as to obtain the distribution characteristics of poisonous weeds and non-poisonous weeds on the second spectral image pixel scale, which can be represented by the second spectral image poisonous weed position information. The distribution characteristics will be used as sample label data for subsequent model classification, and can be used for the training of the poisonous weed monitoring model.

[0057] The method for monitoring the distribution of poisonous weeds in grasslands provided in the embodiment of the present application performs registration processing on a high-resolution spectral image and a low-resolution global image, so as to determine the position data of poisonous weeds in a low-resolution global image through the poisonous weed position information in the high-resolution spectral image. The poisonous weed position data can be used to train a poisonous weed position detection model. The trained poisonous weed position detection model can be used to automatically identify the poisonous weed position distribution information in the global image, thereby realizing automatic, rapid and accurate monitoring of the distribution of poisonous weeds through the global image, and helping the staff to disinfect the poisonous weeds in a timely manner.

[0058] Figure 5 The flowchart of the implementation of the method for monitoring the distribution of poisonous weeds in grasslands provided in the fifth embodiment of the present application is shown. The difference between the method and the first embodiment is that the step S105 specifically includes: Step S501: convert the format of the poisonous weed position information of the second spectral image to obtain the poisonous weed spectral image tensor information.

[0059] In this embodiment, the second spectral image poisonous weed position information may be formatted into a multi-dimensional array in the form of [ N , T , C , H , W ], where N represents the number of samples, T is the time step, C is the number of spectral bands, H and W are the height and width of the image block respectively. Then, the two-spectral image poisonous weed location information is patch segmented, and the two-spectral image poisonous weed location information is divided into 3D patches of equal size. Each patch is subjected to preliminary feature transformation through linear projection to form the poisonous weed spectral image tensor information.

[0060] Step S502: Based on a preset poisonous weed spectral image feature extraction model, the tensor information of the poisonous weed spectral image is subjected to spatiotemporal feature extraction to obtain a plurality of poisonous weed distribution time feature information and a plurality of poisonous weed distribution space feature information.

[0061] In this embodiment, the preset poisonous weed spectral image feature extraction model can be a Transformer model. The temporal and spatial features of the poisonous weed spectral image tensor information are extracted through the Transformer model, and the temporal features and spatial features can be extracted respectively through the convolution layer and the time encoder. Specifically, the feature extraction of each patch can be performed through the convolution layer. The convolution layer can adopt a 3×3 kernel size and a step size of 1 to capture the local features of the image. Then, the data of each time step is input into the time encoder. The time encoder uses a multi-head attention mechanism to capture the relationship between different time steps. The extracted time step information is used as the temporal feature information of the poisonous weed distribution, and the extracted spatial information is used as the spatial feature information of the poisonous weed distribution.

[0062] Step S503: performing position coding processing on the time characteristic information of the poisonous weed distribution to obtain time series information of the poisonous weed distribution.

[0063] In this embodiment, each time step data enters the encoder after position encoding to retain the order of the time series. The time series information output by the time encoder can be expressed as time series information of the poisonous weed distribution, which is used to enable the poisonous weed position detection model to understand the changing trend of the poisonous weeds in the time dimension and the association between adjacent time steps.

[0064] Step S504: alternately concatenate the time series information of the poisonous weed distribution and the spatial feature information of the poisonous weed distribution to obtain a fused feature tensor of the poisonous weed distribution.

[0065] In this embodiment, the extracted spatial features are recorded as Vs and the temporal features are recorded as Vt. First, Vs and Vt are divided into several feature vectors. For each feature vector, elements can be alternately selected from Vs and Vt for fusion. Specifically, the i-th feature is extracted from Vs and placed at the 2i+1 position of the fusion vector; the i-th feature is extracted from Vt and placed at the 2i position, and the fused global spatiotemporal feature tensor is output. X g , which can be expressed as a fused feature tensor of poisonous weed distribution. After the alternating fusion process, the spatial and temporal features are evenly distributed in the new feature vector, ensuring that the feature quantities can be evenly alternating in the spatial and temporal dimensions. Through this fusion strategy, in subsequent calculations, the poisonous weed location detection model can retain and utilize information from space and time, making the output feature vector more representative and balanced. Therefore, the use of this alternating fusion strategy ensures that the spatial features and temporal features are evenly alternating in the fused feature vector, which helps the poisonous weed location detection model to better extract the distribution characteristics of poisonous weeds, so as to achieve a more stable and accurate classification effect.

[0066] Step S505: Based on a preset poisonous weed location detection model, the poisonous weed distribution fusion feature tensor is analyzed and calculated to generate poisonous weed location distribution information.

[0067] In this embodiment, the preset poisonous weed location detection model can be an LSTM model. The time information in the poisonous weed distribution fusion feature tensor can be extracted, and the time information is used as the input data of the LSTM model. The LSTM captures the long-term and short-term dependencies between time steps through its memory unit and gating mechanism, and generates the poisonous weed location distribution information as output data. Specifically, a multi-layer LSTM structure can be used to extract deep time series features.

[0068] The grassland poisonous weed distribution status monitoring method provided by the embodiment of the present application extracts the spectral features of poisonous weeds in the poisonous weed position information of the second spectral image through the poisonous weed spectral image feature extraction model, and alternately fuses the extracted time features and spatial features to make the output feature vector more representative and balanced, ensuring that the time features and spatial features are evenly alternated in the fused feature vector, which helps the poisonous weed position detection model to better extract the distribution characteristics of poisonous weeds within the global field of view, and achieve a more stable and accurate classification effect, thereby improving the recognition accuracy and comprehensiveness of monitoring of poisonous weeds over a wide area, and helping staff to timely and accurately understand the distribution status of poisonous weeds, so as to take measures to control the spread of poisonous weeds.

[0069] Figure 6 The flowchart of the implementation of the method for monitoring the distribution of poisonous weeds in grassland provided by the sixth embodiment of the present application is shown. The difference between the sixth embodiment and the fifth embodiment is that the step S505 specifically includes: Step S601, performing inverse residual calculation on the poisonous weed distribution fusion feature tensor to obtain a poisonous weed distribution optimization feature tensor.

[0070] In this embodiment, the inverse residual calculation can be performed on the poisonous weed distribution fusion feature tensor through the inverse residual module in the LSTM model, and the calculation result is used as the poisonous weed distribution optimization feature tensor to improve the parameter efficiency of the model. The fusion feature is optimized through the inverse residual module, and the consistency of the feature dimension is ensured, and the feature expression ability in the poisonous weed position detection model is enhanced in subsequent calculations.

[0071] Step S602: performing time series extraction on the optimized feature tensor of the poisonous weed distribution to obtain a time series feature tensor of the poisonous weed distribution.

[0072] In this embodiment, the time series classification module in the LSTM model can be used to further enhance the extraction of time series information. The extracted feature information can be represented as a time series feature tensor of the poisonous weed distribution, which is used as input data for subsequent analysis and calculation of the poisonous weed location detection model.

[0073] Step S603, based on a preset poisonous weed location detection model, feature mapping processing and nonlinear transformation are performed on the poisonous weed distribution time series feature tensor to obtain poisonous weed location distribution time series information corresponding to each poisonous weed distribution spatial feature information.

[0074] In this embodiment, the preset poisonous weed location detection model can be an LSTM model. It can be that the poisonous weed distribution time series feature tensor is subjected to feature mapping through a fully connected layer, and the mapped feature tensor is subjected to nonlinear transformation through an activation function, so as to obtain the poisonous weed location distribution time sequence information corresponding to each poisonous weed distribution space feature information, which can be used to characterize the time point at which the poisonous weed feature bands may appear at the relative position of each band in the spectral image, and can also be used to characterize the poisonous weed distribution space in the time dimension in the spectral image, so as to evaluate the spread of poisonous weeds. Among them, the activation function can be a Softmax function.

[0075] Step S604: generating poisonous weed location distribution information according to the poisonous weed distribution spatial characteristic information and the poisonous weed location distribution time sequence information.

[0076] In this embodiment, the time sequence information of the location distribution of the poisonous weeds and the spatial characteristic information of the distribution of the poisonous weeds may be spliced ​​to obtain the spatiotemporal distribution for characterizing the poisonous weeds, thereby generating the location distribution information of the poisonous weeds.

[0077] The grassland poisonous weed distribution status monitoring method provided in the embodiment of the present application performs reverse residual calculation on the poisonous weed distribution fusion feature, reduces the feature value while retaining important features, so as to reduce the calculation complexity, and analyzes and processes the time features in the poisonous weed distribution fusion feature through a poisonous weed position detection model, so as to calculate the poisonous weed position distribution time sequence information corresponding to each poisonous weed distribution spatial feature information, and generate the spatiotemporal distribution status information of the poisonous weeds, so as to realize rapid, accurate and comprehensive monitoring of the spread of poisonous weeds in a wide area of ​​grassland, and comprehensively improve the effectiveness, efficiency and accuracy of monitoring of poisonous weeds.

[0078] Corresponding to the method of the above embodiment, Figure 7 The structural block diagram of the grassland poisonous weed distribution status monitoring device provided in the embodiment of the present application is shown. For the convenience of explanation, only the part related to the embodiment of the present application is shown. Figure 7The exemplary grassland poisonous weed distribution status monitoring device may be an execution body of the grassland poisonous weed distribution status monitoring method provided in the aforementioned first embodiment.

[0079] Reference Figure 7 The grassland poisonous weed distribution monitoring device comprises: The spectral image information acquisition module 710 is used to acquire a plurality of first spectral image information and a second spectral image information; A first spectral image poisonous weed initial position information determination module 720, configured to determine the first spectral image poisonous weed initial position information according to a preset poisonous weed sample information library and the first spectral image information; The first spectral image poisonous weed target position information calculation module 730 is used to calculate the first spectral image poisonous weed target position information according to the first spectral image poisonous weed initial position information and a plurality of preset poisonous weed band classification models; A second spectral image poisonous weed position information determining module 740 is used to determine the second spectral image poisonous weed position information according to the first spectral image poisonous weed target position information and the second spectral image information; The poisonous weed location distribution information generating module 750 is used to generate poisonous weed location distribution information according to the second spectral image poisonous weed location information, a preset poisonous weed spectral image feature extraction model and a preset poisonous weed location detection model.

[0080] The process of each module in the grassland poisonous weed distribution status monitoring device provided in the embodiment of the present application realizing its own function can be specifically referred to the aforementioned Figure 1 The description of the first embodiment is not repeated here.

[0081] The second spectrum image poisonous weed location information determination module 740 includes: A first spectrum stitching image information generating unit, configured to stitch a plurality of the first spectrum image information to generate first spectrum stitching image information; A second spectral image poisonous weed initial position information determining unit, configured to perform registration processing on the first spectral splicing image information and the second spectral image information, and determine the second spectral image poisonous weed initial position information according to the first spectral image poisonous weed target position information; The second spectral image poisonous weed position information determining unit is used to perform mask processing on the initial position information of the poisonous weeds in the second spectral image according to preset poisonous weed mask pixel information to determine the second spectral image poisonous weed position information.

[0082] The process of each unit in the second spectral image poisonous weed location information determination module 740 provided in the embodiment of the present application realizing its own function can be specifically referred to the aforementioned Figure 4The description of the fourth embodiment is not repeated here.

[0083] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0084] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0085] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0086] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0087] In addition, in the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish descriptions, and cannot be understood as indicating or suggesting relative importance. It should also be understood that although the terms "first", "second", etc. are used to describe various elements in some embodiments of the present application in the text, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, the first table can be named as the second table, and similarly, the second table can be named as the first table without departing from the scope of the various described embodiments. The first table and the second table are both tables, but they are not the same table.

[0088] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0089] The grassland poisonous weed distribution status monitoring method provided in the embodiment of the present application can be applied to terminal devices such as mobile phones, tablet computers, wearable devices, vehicle-mounted devices, augmented reality (AR) / virtual reality (VR) devices, laptops, ultra-mobile personal computers (UMPC), netbooks, personal digital assistants (PDA), etc. The embodiment of the present application does not impose any restrictions on the specific type of terminal devices.

[0090] For example, the terminal device can be a station (STAION, ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a vehicle networking terminal, a computer, a laptop computer, a handheld communication device, a handheld computing device, a satellite wireless device, a wireless modem card, a TV set top box (STB), a customer premises equipment (CPE) and / or other devices for communicating on a wireless system and a next-generation communication system, such as a mobile terminal in a 5G network or a mobile terminal in a future evolved Public Land Mobile Network (PLMN) network, etc.

[0091] As an example but not limitation, when the terminal device is a wearable device, the wearable device can also be a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not just hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are fully functional, large in size, and can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0092] Figure 8 Schematic diagram of the structure of a terminal device provided by an embodiment of the present application. Figure 8 As shown, the terminal device 8 of this embodiment includes: at least one processor 80 ( Figure 8 Only one is shown in the figure), a memory 81, wherein the memory 81 stores a computer program 82 that can be run on the processor 80. When the processor 80 executes the computer program 82, the steps in each of the above-mentioned grassland poisonous weed distribution status monitoring method embodiments are implemented, such as Figure 1 Alternatively, when the processor 80 executes the computer program 82, the functions of each module / unit in the above-mentioned device embodiments are realized, for example, Figure 7 Functions of modules 710 to 750 are shown.

[0093] The terminal device 8 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal device may include, but is not limited to, a processor 80 and a memory 81. Those skilled in the art will appreciate that Figure 8 It is only an example of the terminal device 8 and does not constitute a limitation of the terminal device 8. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device may also include an input sending device, a network access device, a bus, etc.

[0094] The processor 80 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0095] In some embodiments, the memory 81 may be an internal storage unit of the terminal device 8, such as a hard disk or memory of the terminal device 8. The memory 81 may also be an external storage device of the terminal device 8, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device 8. Further, the memory 81 may also include both an internal storage unit and an external storage device of the terminal device 8. The memory 81 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory 81 may also be used to temporarily store data that has been sent or is to be sent.

[0096] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0097] An embodiment of the present application also provides a terminal device, which includes at least one memory, at least one processor, and a computer program stored in the at least one memory and executable on the at least one processor, wherein when the processor executes the computer program, the terminal device implements the steps in any of the above-mentioned method embodiments.

[0098] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0099] An embodiment of the present application provides a computer program product. When the computer program product runs on a terminal device, the terminal device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0100] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0101] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0102] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0103] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0104] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for monitoring the distribution of poisonous weeds in grasslands, characterized in that: include: Acquire a plurality of first spectral image information and second spectral image information; Determining initial position information of poisonous weeds in the first spectral image according to a preset poisonous weed sample information database and the first spectral image information; Calculating target position information of poisonous weeds in the first spectral image according to the initial position information of poisonous weeds in the first spectral image and a plurality of preset poisonous weed band classification models; determining the poisonous weed position information of the second spectral image according to the target position information of the poisonous weeds in the first spectral image and the second spectral image information; The poisonous weed position distribution information is generated according to the poisonous weed position information of the second spectral image, a preset poisonous weed spectral image feature extraction model, and a preset poisonous weed position detection model.

2. The method for monitoring the distribution of poisonous weeds in grasslands according to claim 1, wherein: The step of obtaining target location information of poisonous weeds in the first spectral image based on the initial location information of poisonous weeds in the first spectral image and a plurality of preset poisonous weed band classification models specifically includes: Dividing the first spectral image information into bands to obtain a plurality of initial poisonous weed detection band information; performing band extraction on the first spectral image information according to the initial position information of the poisonous weeds in the first spectral image to obtain band information representing the poisonous weeds; When the band standard deviation of the initial poisonous weed detection band information and the poisonous weed characterization band information is less than a preset band standard deviation threshold, the initial poisonous weed detection band information is used as the intermediate poisonous weed detection band information; The target position information of poisonous weeds in the first spectral image is obtained according to the intermediate poisonous weed detection band information and a plurality of preset poisonous weed band classification models.

3. The method for monitoring the distribution of poisonous weeds in grasslands according to claim 2, wherein: The step of obtaining the target location information of poisonous weeds in the first spectral image based on the intermediate poisonous weed detection band information and a plurality of preset poisonous weed band classification models specifically includes: Calculating the band correlation and band distance of the plurality of intermediate poisonous weed detection band information; filtering the intermediate poisonous weed detection band information according to the band correlation and the band distance to obtain a plurality of poisonous weed detection band combination information; Calculating classification accuracy evaluation indicators of multiple poisonous weed band classification models based on the poisonous weed detection band combination information and multiple preset poisonous weed band classification models; screening a plurality of preset poisonous weed band classification models according to the classification accuracy evaluation index to obtain a target poisonous weed band classification model; The target position information of poisonous weeds in the first spectral image is obtained according to the poisonous weed detection band combination information and the target poisonous weed band classification model.

4. The method for monitoring the distribution of poisonous weeds in grasslands according to claim 1, wherein: The step of determining the poisonous weed position information of the second spectral image based on the poisonous weed target position information of the first spectral image and the second spectral image information specifically includes: performing registration processing on the target position information of poisonous weeds in the first spectral image and the second spectral image information, and determining the initial position information of poisonous weeds in the second spectral image according to the target position information of poisonous weeds in the first spectral image; According to the preset poisonous weed mask pixel information, mask processing is performed on the initial position information of the poisonous weeds in the second spectral image to determine the position information of the poisonous weeds in the second spectral image.

5. The method for monitoring the distribution of poisonous weeds in grasslands according to claim 1, wherein: The step of generating the poisonous weed location distribution information based on the poisonous weed location information of the second spectral image, a preset poisonous weed spectral image feature extraction model, and a preset poisonous weed location detection model specifically includes: performing format conversion on the second spectral image of poisonous weed position information to obtain spectral image tensor information of the poisonous weed; Based on a preset poisonous weed spectral image feature extraction model, performing spatiotemporal feature extraction on the poisonous weed spectral image tensor information to obtain a plurality of poisonous weed distribution time feature information and a plurality of poisonous weed distribution space feature information; performing position coding processing on the time characteristic information of the poisonous weed distribution to obtain time series information of the poisonous weed distribution; Alternately splicing the poisonous weed distribution time series information and the poisonous weed distribution spatial feature information to obtain a poisonous weed distribution fusion feature tensor; Based on a preset poisonous weed location detection model, the poisonous weed distribution fusion feature tensor is analyzed and calculated to generate poisonous weed location distribution information.

6. The method for monitoring the distribution of noxious weeds in grasslands according to claim 5, wherein: The step of analyzing and calculating the poisonous weed distribution fusion feature tensor based on a preset poisonous weed location detection model to generate poisonous weed location distribution information specifically includes: Performing inverse residual calculation on the poisonous weed distribution fusion feature tensor to obtain a poisonous weed distribution optimized feature tensor; Performing time series extraction on the optimized feature tensor of the poisonous weed distribution to obtain a time series feature tensor of the poisonous weed distribution; Based on a preset poisonous weed location detection model, feature mapping processing and nonlinear transformation are performed on the poisonous weed distribution time series feature tensor to obtain poisonous weed location distribution time series information corresponding to each poisonous weed distribution spatial feature information; The poisonous weed position distribution information is generated according to the poisonous weed distribution spatial characteristic information and the poisonous weed position distribution time sequence information.

7. A device for monitoring the distribution of poisonous weeds in grasslands, characterized in that: include: A spectral image information acquisition module, configured to acquire a plurality of first spectral image information and a second spectral image information; A first spectral image poisonous weed initial position information determination module, configured to determine the first spectral image poisonous weed initial position information based on a preset poisonous weed sample information library and the first spectral image information; A first spectral image poisonous weed target position information calculation module, configured to calculate the first spectral image poisonous weed target position information based on the first spectral image poisonous weed initial position information and a plurality of preset poisonous weed band classification models; a second spectral image poisonous weed position information determining module, configured to determine the second spectral image poisonous weed position information based on the first spectral image poisonous weed target position information and the second spectral image information; The poisonous weed location distribution information generating module is configured to generate poisonous weed location distribution information based on the poisonous weed location information of the second spectral image, a preset poisonous weed spectral image feature extraction model, and a preset poisonous weed location detection model.

8. The grassland poisonous weed distribution monitoring device according to claim 7, characterized in that: The second spectral image poisonous weed location information determination module includes: a first spectral stitching image information generating unit, configured to stitch together a plurality of the first spectral image information to generate first spectral stitching image information; a second spectral image poisonous weed initial position information determining unit, configured to perform registration processing on the first spectral stitching image information and the second spectral image information, and determine the second spectral image poisonous weed initial position information based on the first spectral image poisonous weed target position information; The second spectral image poisonous weed position information determining unit is used to perform mask processing on the initial position information of poisonous weeds in the second spectral image according to preset poisonous weed mask pixel information, filter non-poisonous weed areas, and determine the second spectral image poisonous weed position information.

9. A terminal device, characterized in that: The terminal device includes a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images