Strawberry planting monitoring system and method based on Internet of Things technology

Abstract

The invention, which relates to the technical field of strawberry planting, discloses a strawberry planting monitoring system based on the Internet of Things technology, comprising a data acquisition module, a transmission module, an audio analysis module, a compound analysis module, an image analysis and evaluation module and an interaction module. The data acquisition module comprises a sound acquisition unit, a biochemical acquisition unit and an image acquisition unit, and the sound acquisition unit is used for acquiring audio data of insect activity in the strawberry garden. The invention further discloses a strawberry planting monitoring method based on the Internet of Things technology. According to the method, the dynamic change of the pest activity in the strawberry garden can be tracked in real time, whether the pest threat is intensified, maintained or relieved is accurately judged according to different trends, continuous increase, no obvious change or reduction of the concentration change, continuous pest information is provided for planters, management measures are taken in time, the influence of pests on strawberries is reduced, and the yield of the strawberries is improved. The strawberry planting quality is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of strawberry planting, and in particular to a strawberry planting monitoring system and method based on Internet of Things technology. Background Art

[0002] With the continuous growth of the global population and the increasing demand for high-quality agricultural products, agricultural production is facing huge challenges and opportunities. The traditional strawberry planting method relies heavily on the experience and manual operation of the growers. This model has many limitations and it is difficult to achieve refined management of large-scale planting areas. It is impossible to know the strawberry pest control in the first time, resulting in unstable yield and quality of strawberries caused by pests, which is difficult to meet the growing market demand. In the traditional strawberry planting pest monitoring method, although manual inspection can intuitively observe some surface phenomena of strawberry plants, such as leaf color and morphological changes, fruit development and insect infestation, this method is inefficient and difficult to cover large areas of planting areas. It is easily affected by subjective factors, resulting in inaccurate and incomplete monitoring results. At the same time, manual inspection has a time lag and cannot timely detect small changes in environmental parameters and early signs of pests and diseases. In this regard, we propose a strawberry planting monitoring system and method based on Internet of Things technology. Summary of the invention

[0003] In order to solve the above technical problems, a strawberry planting monitoring system and method based on Internet of Things technology are provided. This technical solution solves the problem that the results of the above manual inspections are not accurate and comprehensive enough to detect the early signs of pests and diseases.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is: a strawberry planting monitoring system based on Internet of Things technology, including: a data acquisition module, a transmission module, an audio analysis module, a compound analysis module, an image analysis and evaluation module and an interaction module; The data acquisition module includes a sound acquisition unit, a biochemical acquisition unit and an image acquisition unit. The sound acquisition unit is used to collect audio data of pest activities in the strawberry garden. The biochemical acquisition unit is used to collect concentration data of volatile organic compounds released by strawberry plants in the strawberry garden. The image acquisition unit continuously obtains image data of strawberry growth. The transmission module pre-processes and integrates the collected data and uploads them to the audio analysis module, compound analysis module and image analysis and evaluation module for subsequent analysis; The audio analysis module obtains audio data of pests in the strawberry garden based on the Internet of Things, compares the collected audio data with the audio data, and determines whether they are consistent. If they are consistent, it is determined that there is a pest threat in the strawberry garden and the degree of harm is analyzed. If they are inconsistent, it is determined that there is no pest threat in the strawberry garden. The compound analysis module monitors and determines the changes in concentration values ​​based on regularly collected data. If the concentration continues to increase, it is judged that the pest threat in the strawberry garden is serious. If the concentration does not increase significantly, it is judged that the pest threat in the strawberry garden is mild. If the concentration decreases, the pest threat in the strawberry garden is reduced. Different treatment measures are taken according to different degrees of damage. The image analysis and evaluation module obtains strawberry growth image data, extracts features from the image, obtains images regularly for analysis, evaluates the growth status of the strawberry, and determines the growth of the strawberry; The interactive module displays the results of monitoring and analysis for personnel to interact with the system.

[0005] Preferably, the sound collection unit is arranged at a key position in the strawberry garden, and data is collected based on a sound sensor to capture the subtle sounds emitted by strawberry pests, and the audio data is continuously recorded at a specific sampling frequency; the biochemical collection unit is distributed near the strawberry plants and is equipped with a biochemical sensor. When pests attack strawberries, the strawberry plants produce a series of stress responses, release specific volatile organic compounds, spread in the air, and are collected by the biochemical sensor; the image collection unit is located above the strawberry garden, and the strawberry plants are photographed based on a camera at fixed time intervals to obtain image data of strawberry growth.

[0006] Preferably, the transmission module preprocessing includes denoising the audio data and converting it into a format, monitoring and filling abnormal values ​​for compound concentration data, and compressing and graying the image data; integrating the different acquired data and uploading them separately.

[0007] Preferably, the audio analysis module receives audio data from the Internet of Things transmission module, uses short-time Fourier transform to convert the audio signal from the time domain to the frequency domain, obtains the spectral characteristics of the audio, obtains the pest audio feature database based on the Internet, and records the typical audio features of each pest respectively; compares the features of the audio data collected and preprocessed from the strawberry garden with the pest audio feature data, and calculates the similarity between the collected audio and the audio of each type of pest in the database; establishes a similarity threshold, and during the comparison process, when the calculated similarity exceeds the threshold, it is judged that there is a pest threat in the strawberry garden and enters the hazard degree analysis stage; when it is less than the threshold, it is judged that there is no pest threat in the strawberry garden and continuous monitoring is performed.

[0008] Preferably, the similarity calculation is performed by assuming that the feature vector of the collected audio data after feature extraction is A=(a1, a2, ... a n ), the feature vector of a pest audio in the database is B=(b1,b2,……b n ), calculate the Euclidean distance between the two, the calculation formula is: Where d(A, B) is the Euclidean distance between the feature vector after feature extraction and the feature vector of a pest audio in the database, and the similarity between the two is calculated by the Euclidean distance value; The similarity calculation formula is: Among them, S (A, B) is the similarity value between the two, n is the number of selected audio features, and the calculated S (A, B) value is compared with the similarity threshold for judgment.

[0009] Preferably, the compound analysis module arranges the received volatile organic compound concentration data in chronological order to construct time series data, takes the acquisition time as the horizontal coordinate and the corresponding compound concentration value as the vertical coordinate, draws a curve of concentration change over time, and calculates the concentration difference between adjacent time points, E=C(t)-C(t-1), where C(t) is the compound concentration collected at the current time t, t is time, E is the concentration change value, C(t-1) is the concentration collected before time t-1, calculates the concentration change rate, sets the initial calculated concentration value to E1, and the concentration value after the time is E2. The concentration change rate calculation formula is: R={(E1-E2) / E2}*100% Where R is the calculated concentration change rate, and the strawberry garden pest situation is judged by analyzing the concentration change rate.

[0010] Preferably, a concentration change threshold is set. Based on the experimental data and the actual monitoring data of the strawberry garden, different concentration change thresholds are set to distinguish the degree of pest threat. When the concentration change rate at multiple consecutive time points is greater than the concentration change threshold, it is judged that the concentration continues to increase, that is, the pest threat in the strawberry garden is serious; when the concentration change rate continues to fluctuate around the threshold and there is no obvious upward trend overall, it is judged that the concentration has not increased significantly, that is, the pest threat is mild; if the concentration change rate is continuously lower than the concentration change threshold, it is judged that the concentration has decreased, that is, the pest threat is reduced.

[0011] Preferably, the image analysis and evaluation module obtains the captured images and extracts features. Based on the image analysis technology, the image analysis module pays attention to the size, shape, color, maturity and whether there is deformity or damage of the strawberry fruit. By comparing the changes in the morphology, leaves and fruit characteristics of the strawberry plants at different time points, a dynamic change curve and an evaluation model of the strawberry growth state are constructed. It is found that the height of the strawberry plants grows slowly, the leaf color gradually fades and a small number of lesions appear in a certain period of time, and the fruit is sluggish and the maturity is uneven. The characteristic change information is comprehensively combined with the environmental data and the past planting experience data to evaluate the current growth state of the strawberry and judge the growth of the strawberry. If all the characteristic indicators are in line with or better than the normal standard range of the variety of strawberry at the corresponding growth stage, it is judged that the strawberry is growing well; otherwise, if there are multiple characteristic indicators that deviate from the normal range and show an unfavorable change trend, it is judged that the strawberry is growing poorly.

[0012] Preferably, the interactive module displays the results obtained through monitoring and analysis in an all-round and multi-level manner. The interactive module uses visualization technology to convert the data into intuitive and easy-to-understand charts for display, and provides detailed data reporting functions.

[0013] The strawberry planting monitoring method based on the Internet of Things technology includes the following steps: S1, collecting audio data of pest activities in the strawberry garden, concentration data of volatile organic compounds released by pests in the strawberry garden, and image data of strawberry growth through a data acquisition module; S2. Preprocess and integrate the collected data and upload them to the audio analysis module, compound analysis module and image analysis and evaluation module for subsequent analysis; S3. Obtain frequency data of insect pests in the strawberry garden through the Internet of Things, compare the collected audio data with the frequency data, and determine whether they are consistent. If they are consistent, it is determined that there is an insect pest threat in the strawberry garden and the degree of harm is analyzed. If they are inconsistent, it is determined that there is no insect pest threat in the strawberry garden and the strawberry garden is continuously monitored. S4. Continuously monitor and judge the changes in the concentration of volatile organic compounds released by strawberry plants. If the concentration continues to increase, it is judged that the pest threat in the strawberry garden is serious. If the concentration does not increase significantly, it is judged that the pest threat in the strawberry garden is mild. If the concentration decreases, the pest threat in the strawberry garden is reduced; take different treatment measures according to different degrees of harm; S5. Obtain strawberry growth image data, extract features from the image, regularly obtain images for analysis, evaluate the growth status of the strawberries, determine the growth of the strawberries, further analyze the reasons leading to poor growth, and make targeted treatments.

[0014] Compared with the prior art, the present invention has the following beneficial effects: The present invention acquires an audio database in real time through the Internet of Things, and after comparing the sound signals generated by the pest activities with the database, it can promptly discover pests in the early stages when the number of pests is small and the harm has not yet been obviously manifested. It can track the dynamic changes of pest activities in the strawberry garden in real time, and accurately judge whether the pest threat is intensifying, maintaining or alleviating according to the different trends of concentration changes, such as continuous increase, no obvious change or decrease. It provides growers with continuous pest information, enables them to take management measures in time, reduce the impact of pests on strawberries, and improve the quality of strawberry cultivation. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is the framework diagram of the monitoring system of the present invention; Figure 2 The present invention is a flow chart of the monitoring steps. DETAILED DESCRIPTION

[0016] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0017] Reference Figure 1 and Figure 2 As shown, the strawberry planting monitoring system based on the Internet of Things technology includes: a data acquisition module, a transmission module, an audio analysis module, a compound analysis module, an image analysis and evaluation module and an interaction module; The data acquisition module includes a sound acquisition unit, a biochemical acquisition unit and an image acquisition unit. The sound acquisition unit is used to collect audio data of pest activities in the strawberry garden. The biochemical acquisition unit is used to collect concentration data of volatile organic compounds released by strawberry plants in the strawberry garden. The image acquisition unit continuously obtains image data of strawberry growth. The transmission module pre-processes and integrates the collected data and uploads them to the audio analysis module, compound analysis module and image analysis and evaluation module for subsequent analysis; The audio analysis module obtains audio data of pests in the strawberry garden based on the Internet of Things, compares the collected audio data with the audio data, and determines whether they are consistent. If they are consistent, it is determined that there is a pest threat in the strawberry garden and the degree of harm is analyzed. If they are inconsistent, it is determined that there is no pest threat in the strawberry garden. The compound analysis module monitors and determines the changes in concentration values ​​based on regularly collected data. If the concentration continues to increase, it is judged that the pest threat in the strawberry garden is serious. If the concentration does not increase significantly, it is judged that the pest threat in the strawberry garden is mild. If the concentration decreases, the pest threat in the strawberry garden is reduced. Different treatment measures are taken according to different degrees of damage. The image analysis and evaluation module obtains strawberry growth image data, extracts features from the image, obtains images regularly for analysis, evaluates the growth status of the strawberry, and determines the growth of the strawberry; The interactive module displays the results of monitoring and analysis for personnel to interact with the system.

[0018] This application can capture audio information of pest activities, such as chewing sounds, crawling sounds, and flying sounds. These sound signals can serve as important clues for early detection of pests. Some pests are active frequently at night. The sound collection unit can monitor signs of pests when growers are not easily aware of them, providing an opportunity for timely prevention and control. Monitoring the concentration changes of volatile organic compounds released by strawberry plants can provide early warning of pests. When strawberries are attacked by pests, the plants will produce a stress response and release specific compounds. The increase in their concentration often means that pests have occurred. When strawberries are attacked by mites, they will release special volatile substances. The biochemical collection unit can monitor this change in time, allowing growers to take measures before a large-scale outbreak of pests. Continuously acquiring strawberry growth image data provides an intuitive and visual record of the entire strawberry growth process, from plant morphology in the seedling stage to flower condition in the flowering stage, and then to fruit development in the fruiting stage, all can be clearly presented. Growers can check the images at any time to understand the growth stage and development progress of the strawberries, making it easier to arrange farming activities.

[0019] The sound collection unit is set at a key position in the strawberry garden. It collects data based on sound sensors, captures the subtle sounds made by strawberry pests, and continuously records audio data at a specific sampling frequency. The biochemical collection unit is distributed near the strawberry plants and is equipped with biochemical sensors. When pests attack strawberries, the strawberry plants produce a series of stress responses and release specific volatile organic compounds, which spread in the air and are collected by biochemical sensors. The image acquisition unit is located above the strawberry garden. It uses a camera to shoot strawberry plants at fixed time intervals to obtain image data of strawberry growth.

[0020] The present application can capture the subtle sounds made by strawberry pests, such as the crawling, gnawing or flapping sounds of pests on leaves. The sound collection unit can detect signs of pests when the pests just begin to move and have not yet caused large-scale obvious damage to strawberries. Some pests are active at night and are difficult to detect by manual inspections. The sound sensor can monitor 24 hours a day and can detect the occurrence of pests in time, providing growers with early warnings so that they have enough time to take appropriate prevention and control measures and effectively reduce the losses caused by pests.

[0021] The transmission module preprocessing includes denoising and format conversion of audio data, monitoring and filling of abnormal values ​​of compound concentration data, and compression and grayscale processing of image data; integrating different acquired data and uploading them separately.

[0022] The environment of the strawberry garden in this application is relatively complex, and the audio data may contain various background noises, such as wind, rain, and machine operation. Through denoising, these interfering sounds that are not related to pest activities are effectively removed, so that the subsequent audio analysis module can focus more on the audio features generated by pest activities. In a strawberry garden close to the road, the sound of vehicles driving may mask the faint sound of pests gnawing on leaves. After denoising, the pest-related audio signals can be captured more clearly, thereby improving the accuracy of pest monitoring; Grayscale processing can convert color images into black and white images, reduce the data dimension of the image, and reduce the computational complexity of subsequent image analysis without losing key characteristic information of strawberry growth; by integrating audio data, compound concentration data and image data, a multi-dimensional data model of the strawberry garden can be established. Different types of data can verify and complement each other to provide more comprehensive strawberry garden information.

[0023] The audio analysis module receives audio data from the Internet of Things transmission module, uses short-time Fourier transform to convert the audio signal from the time domain to the frequency domain, obtains the spectral characteristics of the audio, and obtains the pest audio feature database based on the Internet. For each pest, its typical audio features are recorded respectively; the features of the audio data collected and preprocessed from the strawberry garden are compared with the pest audio feature data, and the similarity between the collected audio and the audio of each type of pest in the database is calculated; a similarity threshold is established. During the comparison process, when the calculated similarity exceeds the threshold, it is judged that there is a pest threat in the strawberry garden and the hazard degree analysis stage is entered. When it is less than the threshold, it is judged that there is no pest threat in the strawberry garden and continuous monitoring is carried out.

[0024] This application uses short-time Fourier transform to convert audio signals from the time domain to the frequency domain to obtain spectral features, which can mine the frequency information hidden in the audio signal, because the sounds produced by different pest activities are different in frequency and frequency change pattern. For example, the sound frequency of aphids flying is relatively high and relatively stable, while the sound frequency of chewing pests gnawing on leaves is low and may have rhythmic changes. Through spectral feature analysis, these differences can be captured more accurately, providing strong support for accurate identification of pest species; In traditional audio analysis, time domain signals only show how the amplitude of the audio changes over time. This single-dimensional information presentation method can only provide limited effective information for complex audio content, especially audio signals of pests in strawberry gardens. This is because the uniqueness of audio signals generated by different types of pests during their activities is often more reflected in the frequency components and the frequency change patterns over time. The wingbeat audio produced by some small pests when flying may have a higher frequency band and show relatively stable frequency characteristics within a certain time range; while the sounds made by some chewing pests when gnawing on strawberry leaves may be concentrated in lower frequencies. The short-time Fourier transform cleverly introduces a time window function to divide the audio signal that was originally continuous in the time domain into a series of overlapping short-time segments. For each of these short-time segments, a Fourier transform operation is performed separately, which is equivalent to a localized frequency analysis of the audio signal in the time dimension. It not only retains the information on the change of the audio signal over time, but also successfully obtains the distribution of frequency components in each time segment. In this process, the selection of the length of the time window is crucial, which directly determines the trade-off between time resolution and frequency resolution. If the time window is short, the resolution in the time domain will be higher, and the details of the changes in the audio signal in a short period of time can be captured more accurately. However, this will lead to a relatively low frequency resolution, that is, the analysis accuracy of the frequency components will be reduced. On the contrary, if the time window is long, although a higher frequency resolution can be obtained, a certain amount of time resolution will be lost, and it will be difficult to accurately reflect the rapid changes of the audio signal in a short period of time. When applying short-time Fourier transform to the audio signal of insect pests in the strawberry garden, we can get a two-dimensional time-frequency representation result, which is usually called a spectrogram. In this spectrogram, the horizontal axis represents the time. The vertical axis represents frequency, and the grayscale value of each pixel in the figure corresponds to the energy of the audio signal at a specific time and frequency. Through careful observation and in-depth analysis of this spectrum diagram, we can clearly see the distribution characteristics of the audio of different pest activities in the frequency and time dimensions. In a certain period of time, if a continuous and relatively stable energy concentration area appears in the high-frequency area, this may indicate that flying pests are active; if a series of regular energy peaks appear in the low-frequency area, and these peaks match a certain rhythm in time, then it is very likely that chewing pests are gnawing on the strawberry leaves.

[0025] The similarity calculation is done by assuming that the feature vector of the collected audio data after feature extraction is A=(a1,a2,……a n ), the feature vector of a pest audio in the database is B=(b1,b2,……b n), calculate the Euclidean distance between the two, the calculation formula is: Where d(A, B) is the Euclidean distance between the feature vector after feature extraction and the feature vector of a pest audio in the database, and the similarity between the two is calculated by the Euclidean distance value; The similarity calculation formula is: Among them, S (A, B) is the similarity value between the two, n is the number of selected audio features, and the calculated S (A, B) value is compared with the similarity threshold for judgment.

[0026] The compound analysis module arranges the received volatile organic compound concentration data in chronological order and constructs time series data. The collection time is used as the horizontal axis and the corresponding compound concentration value is used as the vertical axis. The concentration change curve over time is drawn and the concentration difference between adjacent time points is calculated. E=C(t)-C(t-1), where C(t) is the compound concentration collected at the current time t, t is the time, E is the concentration change value, C(t-1) is the concentration collected before time t-1, and the concentration change rate is calculated. The initial calculated concentration value is set to E1, and the concentration value after the time is E2. The concentration change rate calculation formula is: R={(E1-E2) / E2}*100% Where R is the calculated concentration change rate, and the strawberry garden pest situation is judged by analyzing the concentration change rate.

[0027] A concentration change threshold is set. Based on the experimental data and the actual monitoring data of the strawberry garden, different concentration change thresholds are set to distinguish the degree of pest threat. When the concentration change rate at multiple consecutive time points is greater than the concentration change threshold, it is judged that the concentration continues to increase, that is, the pest threat in the strawberry garden is serious; when the concentration change rate continues to fluctuate around the threshold and there is no obvious upward trend overall, it is judged that the concentration has not increased significantly, that is, the pest threat is mild; if the concentration change rate continues to be lower than the concentration change threshold, it is judged that the concentration is decreasing, that is, the pest threat is reduced.

[0028] This application sets concentration change thresholds based on a large amount of experimental data and actual monitoring data, so that the judgment of the degree of pest threat has a scientific and objective quantitative standard, which no longer relies on the subjective experience of growers, reducing human errors and uncertainties. After in-depth research on the relationship between changes in the concentration of volatile organic compounds and a variety of common strawberry pests, precise thresholds for different pest types or pest scenarios are determined. When the change rate of the compound concentration is monitored to exceed a specific threshold, the severity of the pest can be accurately judged, providing a reliable basis for subsequent targeted prevention and control.

[0029] The image analysis and evaluation module obtains the captured images and extracts features. Based on image analysis technology, it focuses on the size, shape, color, maturity, and whether there are deformities or damages of the strawberry fruit. By comparing the changes in the morphology, leaves, and fruit characteristics of strawberry plants at different time points, it constructs a dynamic change curve and evaluation model of the strawberry growth status. It is found that the height of the strawberry plant grows slowly, the leaf color gradually fades, and a small number of spots appear in a certain period of time. At the same time, the fruit is sluggish and the maturity is uneven. Based on the comprehensive feature change information, combined with environmental data and past planting experience data, the current growth status of the strawberry is evaluated to judge the growth of the strawberry. If all feature indicators are in line with or better than the normal standard range of the variety of strawberry at the corresponding growth stage, the strawberry is judged to be growing well. On the contrary, if there are multiple feature indicators that deviate from the normal range and show an unfavorable change trend, the strawberry is judged to be growing poorly.

[0030] The present application can comprehensively and meticulously understand the growth status of strawberries by conducting a comprehensive analysis of the size, shape, color, maturity, deformity and damage of strawberry fruits, as well as plant morphology and leaf characteristics. Judging only from the size of the fruit may ignore whether the shape of the fruit is normal and whether the color meets the mature characteristics. Multi-dimensional evaluation can more accurately detect subtle abnormalities in the growth process. For example, local color abnormalities in strawberry fruits may indicate local nutrient deficiencies or minor pests and diseases. This situation is easily missed in a single-dimensional evaluation, but multi-dimensional analysis can accurately capture and prompt growers to pay attention. By comparing the characteristic changes at different time points to construct a dynamic change curve and an evaluation model, growers can not only know the current growth status of the strawberries, but also understand their development trends. By observing that the height growth curve of the strawberry plant gradually slows down, combined with the fading of leaf color and the appearance of lesions, it can be predicted in advance that the health of the plant may deteriorate, so that timely measures can be taken, such as adjusting the fertilization plan or conducting pest and disease control, to avoid further aggravation of the problem, rather than dealing with it only after the problem has obviously appeared, which greatly improves the foresight and effectiveness of planting management.

[0031] The interactive module provides a comprehensive and multi-level display of the results obtained through monitoring and analysis. The interactive module uses visualization technology to convert data into intuitive and easy-to-understand charts for display, and provides detailed data reporting functions.

[0032] This application uses visualization technology to convert data into intuitive and easy-to-understand charts, such as line graphs, bar graphs, and pie charts, which can make complex monitoring and analysis results clear at a glance. By showing the changing trends of audio data of pest activities in strawberry gardens in different time periods through line graphs, growers can quickly and intuitively see the peak and trough periods of pest activities, and whether there are abnormal changes in their activity patterns. In contrast, simple data listing makes it difficult for people to grasp the overall characteristics and changing trends of the data in a short period of time. Visual charts greatly improve the efficiency of information transmission, helping growers quickly understand the key information of the strawberry garden, so as to make corresponding decisions in a timely manner.

[0033] The strawberry planting monitoring method based on the Internet of Things technology includes the following steps: S1, collecting audio data of pest activities in the strawberry garden, concentration data of volatile organic compounds released by pests in the strawberry garden, and image data of strawberry growth through a data acquisition module; S2. Preprocess and integrate the collected data and upload them to the audio analysis module, compound analysis module and image analysis and evaluation module for subsequent analysis; S3. Obtain frequency data of insect pests in the strawberry garden through the Internet of Things, compare the collected audio data with the frequency data, and determine whether they are consistent. If they are consistent, it is determined that there is an insect pest threat in the strawberry garden and the degree of harm is analyzed. If they are inconsistent, it is determined that there is no insect pest threat in the strawberry garden and the strawberry garden is continuously monitored. S4. Continuously monitor and judge the changes in the concentration of volatile organic compounds released by strawberry plants. If the concentration continues to increase, it is judged that the pest threat in the strawberry garden is serious. If the concentration does not increase significantly, it is judged that the pest threat in the strawberry garden is mild. If the concentration decreases, the pest threat in the strawberry garden is reduced; take different treatment measures according to different degrees of harm; S5. Obtain strawberry growth image data, extract features from the image, regularly obtain images for analysis, evaluate the growth status of the strawberries, determine the growth of the strawberries, further analyze the reasons leading to poor growth, and make targeted treatments.

[0034] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments, and the above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention, and these changes and improvements fall within the scope of the present invention claimed.

Claims

1. A strawberry planting monitoring system based on Internet of Things technology, characterized in that: include: Data acquisition module, Transmission module, audio analysis module, compound analysis module, image analysis and evaluation module and interaction module; The data acquisition module includes a sound acquisition unit, a biochemical acquisition unit and an image acquisition unit. The sound acquisition unit is used to collect audio data of pest activities in the strawberry garden. The biochemical acquisition unit is used to collect concentration data of volatile organic compounds released by strawberry plants in the strawberry garden. The image acquisition unit continuously obtains image data of strawberry growth. The transmission module pre-processes and integrates the collected data and uploads them to the audio analysis module, compound analysis module and image analysis and evaluation module for subsequent analysis; The audio analysis module obtains audio data of pests in the strawberry garden based on the Internet of Things, compares the collected audio data with the audio data, and determines whether they are consistent. If they are consistent, it is determined that there is a pest threat in the strawberry garden and the degree of harm is analyzed. If they are inconsistent, it is determined that there is no pest threat in the strawberry garden. The compound analysis module monitors and determines the changes in concentration values ​​based on regularly collected data. If the concentration continues to increase, it is judged that the pest threat in the strawberry garden is serious. If the concentration does not increase significantly, it is judged that the pest threat in the strawberry garden is mild. If the concentration decreases, the pest threat in the strawberry garden is reduced. Different treatment measures are taken according to different degrees of damage. The image analysis and evaluation module obtains strawberry growth image data, extracts features from the image, obtains images regularly for analysis, evaluates the growth status of the strawberry, and determines the growth of the strawberry; The interactive module displays the results of monitoring and analysis, allowing personnel to interact with the system.

2. The strawberry planting monitoring system based on Internet of Things technology according to claim 1, characterized in that, The sound collection unit is set at a key position in the strawberry garden. It collects data based on sound sensors, captures the subtle sounds made by strawberry pests, and continuously records audio data at a specific sampling frequency. The biochemical collection unit is distributed near the strawberry plants and is equipped with biochemical sensors. When pests attack strawberries, the strawberry plants produce a series of stress responses and release specific volatile organic compounds, which spread in the air and are collected by biochemical sensors. The image acquisition unit is located above the strawberry garden. It uses a camera to shoot strawberry plants at fixed time intervals to obtain image data of strawberry growth.

3. The strawberry planting monitoring system based on Internet of Things technology according to claim 1, characterized in that, The transmission module preprocessing includes denoising and format conversion of audio data, monitoring and filling of abnormal values ​​of compound concentration data, and compression and grayscale processing of image data; integrating different acquired data and uploading them separately.

4. The strawberry planting monitoring system based on Internet of Things technology according to claim 1, characterized in that, The audio analysis module receives audio data from the IoT transmission module, uses short-time Fourier transform to convert the audio signal from the time domain to the frequency domain, obtains the spectral characteristics of the audio, obtains the audio feature database of insect pests based on the Internet, and records the typical audio features of each insect pest; The features of the audio data collected and preprocessed from the strawberry garden are compared with the pest audio feature data, and the similarity between the collected audio and various pest audios in the database is calculated; a similarity threshold is established, and during the comparison process, when the calculated similarity exceeds the threshold, it is judged that there is a pest threat in the strawberry garden and the hazard level analysis stage is entered; when it is less than the threshold, it is judged that there is no pest threat in the strawberry garden and continuous monitoring is carried out.

5. The strawberry planting monitoring system based on Internet of Things technology according to claim 4, characterized in that, The similarity calculation is done by assuming that the feature vector of the collected audio data after feature extraction is A=(a1,a2,……a n ), the feature vector of a pest audio in the database is B=(b1,b2,……b n ), calculate the Euclidean distance between the two, the calculation formula is: Where d(A, B) is the Euclidean distance between the feature vector after feature extraction and the feature vector of a pest audio in the database, and the similarity between the two is calculated by the Euclidean distance value; The similarity calculation formula is: Among them, S (A, B) is the similarity value between the two, n is the number of selected audio features, and the calculated S (A, B) value is compared with the similarity threshold for judgment.

6. The strawberry planting monitoring system based on Internet of Things technology according to claim 1, characterized in that: The compound analysis module arranges the received volatile organic compound concentration data in chronological order and constructs time series data. The collection time is used as the horizontal axis and the corresponding compound concentration value is used as the vertical axis. The concentration change curve over time is drawn and the concentration difference between adjacent time points is calculated. E=C(t)-C(t-1), where C(t) is the compound concentration collected at the current time t, t is the time, E is the concentration change value, C(t-1) is the concentration collected before time t-1, and the concentration change rate is calculated. The initial calculated concentration value is set to E1, and the concentration value after the time is E2. The concentration change rate calculation formula is: R={(E1-E2) / E2}*100% Where R is the calculated concentration change rate, and the strawberry garden pest situation is judged by analyzing the concentration change rate.

7. The strawberry planting monitoring system based on Internet of Things technology according to claim 1, characterized in that: A concentration change threshold is set. Based on the experimental data and the actual monitoring data of the strawberry garden, different concentration change thresholds are set to distinguish the degree of pest threat. When the concentration change rate at multiple consecutive time points is greater than the concentration change threshold, it is judged that the concentration continues to increase, that is, the pest threat in the strawberry garden is serious; when the concentration change rate continues to fluctuate around the threshold and there is no obvious upward trend overall, it is judged that the concentration has not increased significantly, that is, the pest threat is mild; if the concentration change rate continues to be lower than the concentration change threshold, it is judged that the concentration is decreasing, that is, the pest threat is reduced.

8. The strawberry planting monitoring system based on Internet of Things technology according to claim 1, characterized in that: The image analysis and evaluation module obtains the captured images and extracts features. Based on image analysis technology, it focuses on the size, shape, color, maturity, and whether there are deformities or damages of the strawberry fruit. By comparing the changes in the morphology, leaves, and fruit characteristics of strawberry plants at different time points, it constructs a dynamic change curve and evaluation model of the strawberry growth status. It is found that the height of the strawberry plant grows slowly, the leaf color gradually fades, and a small number of spots appear in a certain period of time. At the same time, the fruit is sluggish and the maturity is uneven. Based on the comprehensive feature change information, combined with environmental data and past planting experience data, the current growth status of the strawberry is evaluated to judge the growth of the strawberry. If all feature indicators are in line with or better than the normal standard range of the variety of strawberry at the corresponding growth stage, the strawberry is judged to be growing well. On the contrary, if there are multiple feature indicators that deviate from the normal range and show an unfavorable change trend, the strawberry is judged to be growing poorly.

9. The strawberry planting monitoring system based on Internet of Things technology according to claim 1, characterized in that: The interactive module provides a comprehensive and multi-level display of the results obtained through monitoring and analysis. The interactive module uses visualization technology to convert data into intuitive and easy-to-understand charts for display, and provides detailed data reporting functions.

10. A strawberry planting monitoring method based on Internet of Things technology, characterized in that: The monitoring steps are: S1, collecting audio data of pest activities in the strawberry garden, concentration data of volatile organic compounds released by pests in the strawberry garden, and image data of strawberry growth through a data acquisition module; S2. Preprocess and integrate the collected data and upload them to the audio analysis module, compound analysis module and image analysis and evaluation module for subsequent analysis; S3. Obtain frequency data of insect pests in the strawberry garden through the Internet of Things, compare the collected audio data with the frequency data, and determine whether they are consistent. If they are consistent, it is determined that there is an insect pest threat in the strawberry garden and the degree of harm is analyzed. If they are inconsistent, it is determined that there is no insect pest threat in the strawberry garden and the strawberry garden is continuously monitored. S4. Continuously monitor and judge the changes in the concentration of volatile organic compounds released by strawberry plants. If the concentration continues to increase, it is judged that the pest threat in the strawberry garden is serious. If the concentration does not increase significantly, it is judged that the pest threat in the strawberry garden is mild. If the concentration decreases, the pest threat in the strawberry garden is reduced; take different treatment measures according to different degrees of harm; S5. Obtain strawberry growth image data, extract features from the image, regularly obtain images for analysis, evaluate the growth status of the strawberries, determine the growth of the strawberries, further analyze the reasons leading to poor growth, and make targeted treatments.

Images