Strawberry disease early warning method and system based on Internet of Things

Abstract

The invention discloses a strawberry disease early warning method and system based on the Internet of Things. The method comprises the following steps: S1, acquiring historical data of a strawberry planting field in a coverage area, current growth environment temperature data, real-time meteorological data and soil temperature and humidity data, and dividing the planting field and performing filing management; s2, collecting spore quantity data and strawberry morbidity degree data, preprocessing the strawberry morbidity degree data and the spore quantity data, and dividing the strawberry morbidity degree data and the spore quantity data into a test set, a verification set and a training set; and S3, preprocessing the acquired data of the strawberry planting field based on a wavelet transform algorithm. Strawberry plant growth images are collected through multiple cameras, the coverage range is wider, disease monitoring and management are conducted on strawberry planting, disease types are accurately detected, corresponding biological prevention and control are conducted according to the disease types, statistical analysis is conducted on disease data in the production cycle, disease areas are treated regularly, and the disease occurrence rate is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of strawberry disease identification, and in particular to a strawberry disease early warning method and system based on the Internet of Things. Background Art

[0002] As the living standards of residents improve, strawberries are loved by more and more people, and the planting area of ​​strawberries has increased accordingly. Crop diseases have a huge impact on agricultural output. If the types of agricultural diseases cannot be identified in time, agricultural output will be greatly impacted. Especially for fruits such as strawberries that have high environmental requirements, if the types of strawberry diseases are not discovered in time, the strawberry yield can be reduced by more than 50%. Therefore, the timely identification of strawberry diseases is the basis for strawberry disease prevention and control.

[0003] In traditional agricultural work, virus screening is generally carried out by manual inspection and camera image acquisition. The manual inspection method can only check strawberry diseases based on the inspection of inspectors and fixed seasons. This method is often not timely and labor-intensive. In addition, the traditional strawberry disease identification environment is complex, which makes it difficult to identify strawberry diseases, resulting in high costs and inaccurate identification. The method of collecting images with cameras and using local computers for identification results in high space and hardware costs, and data is easily lost.

[0004] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0005] In view of the problems in the related art, the present invention proposes a strawberry disease early warning method and system based on the Internet of Things to overcome the above-mentioned technical problems existing in the existing related technology.

[0006] To this end, the specific technical solution adopted by the present invention is as follows: A strawberry disease early warning method and system based on the Internet of Things, comprising the following steps: S1. Obtain historical data of strawberry planting areas within the coverage area, as well as current growth environment temperature data, real-time meteorological data, and soil temperature and humidity data, divide the planting areas, and establish files for management; S2, collecting spore quantity data and strawberry disease degree data, preprocessing the strawberry disease degree data and spore quantity data, and dividing them into a test set, a validation set and a training set; S3, preprocessing the acquired data of the strawberry planting site based on a wavelet transform algorithm; S4. When the temperature data threshold, real-time meteorological data threshold and soil temperature and humidity data threshold set for strawberries are not within the range, an early warning is issued; S5. Establish a strawberry disease target detection model, use multiple cameras to collect strawberry plant growth images, upload the strawberry plant growth images to the cloud, and generate a training data set; S6. Preprocessing the acquired strawberry disease image dataset using the strawberry disease target detection model and performing data enhancement on it to obtain a strawberry disease image dataset; S7, construct a strawberry disease classification and recognition model, which includes a dimensionality reduction module, a sampling module and a classification module. Once a disease occurs, the management personnel are reminded to treat it in time; S8, using the pretreated growth environment temperature data, real-time meteorological data, soil temperature and humidity data and spore count data of step S3 as input, using strawberry disease degree data as output, using convolutional neural network-long short-term memory network CNN-LSTM network model to establish strawberry disease early warning model; S9. Use the strawberry disease early warning model to predict the strawberry disease severity data to obtain the recognition result of the strawberry disease image.

[0007] Preferably, the areas where diseases occur during the production cycle are recorded and the diseased areas are treated regularly.

[0008] Preferably, in step S1, the growth environment temperature data includes indoor and outdoor data, and when processing the meteorological data outside the greenhouse, the meteorological data outside the greenhouse and the future weather forecast data: the average temperature and average humidity inside the greenhouse, the average temperature and average humidity outside the greenhouse, and the rainfall outside the greenhouse are recorded every hour, the daily average of the above recorded data is calculated, and the data are numbered in date order and normalized.

[0009] Preferably, when processing the disease degree data and spore quantity data of strawberries in the greenhouse: the disease degree data and spore quantity data of strawberries in the greenhouse are normalized.

[0010] Preferably, in step S9, the recognition results of the strawberry disease images are labeled using the LabelImg image annotation tool, and the diseases in each image are framed with rectangular frames and their categories are indicated.

[0011] Preferably, in step S4, the data is input into the CNN convolution layer to adaptively extract features; the extracted features are subjected to a pooling operation of a maximum pooling layer to reduce the data dimension and retain the main feature information.

[0012] Preferably, in step S4, when the strawberry is not within the planting and growth environment temperature data threshold, real-time meteorological data threshold and soil temperature and humidity data threshold set for the strawberry, an early warning is issued, including: an early warning via SMS, in which the monitoring center automatically sends the alarm information via SMS to the mobile phone reserved in the strawberry manager's information file; an early warning via telephone, in which the monitoring center automatically dials the mobile phone number reserved in the strawberry manager's information file, and automatically broadcasts the early warning information by voice through artificial intelligence.

[0013] According to another aspect of the present invention, there is provided a strawberry disease early warning system based on the Internet of Things, which is used for the strawberry disease early warning method based on the Internet of Things, and includes a spore quantity collection module, a meteorological data collection module, an incidence degree data collection module, a disease early warning model module and an identification module; The spore quantity collection module is used to capture the airborne disease spores spread in the strawberry planting field through the spore capture device to collect spore quantity data; The meteorological data acquisition module is used to monitor environmental parameters in real time, and the environmental parameters include at least soil temperature and humidity, air temperature and humidity, light, wind speed and carbon dioxide concentration. The meteorological data acquisition module includes at least a soil temperature and humidity sensor, an air temperature and humidity sensor, a light sensor, a wind speed sensor and a carbon dioxide sensor; The disease degree data collection module is used to collect strawberry disease degree data; The recognition module is used to predict the strawberry disease severity data to obtain a recognition result of the strawberry disease image.

[0014] According to another aspect of the present invention, there is provided a method comprising: at least one memory for storing computer instructions; At least one processor in communication with the memory, wherein when the at least one processor executes the computer instructions, the at least one processor causes the system to execute: a data acquisition module, a file creation module, and an early warning module.

[0015] According to another aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method according to any one of claims 1 to 7.

[0016] The beneficial effects of the present invention are as follows: by utilizing multiple cameras to collect growth images of strawberry plants, the coverage is wider, and incomplete images caused by a single camera can be avoided; a strawberry disease target detection model is trained in the cloud to reduce space and hardware costs, disease monitoring and management are performed on strawberry planting, disease types are accurately detected, corresponding biological control is performed according to the disease types, disease data within the production cycle are statistically analyzed, disease areas are regularly treated, the disease incidence rate is reduced, thresholds for soil moisture requirements and temperature tolerance of crops in various periods such as strawberry breeding, topdressing and weeding, and picking are set, soil moisture content and temperature conditions during strawberry planting are monitored, an alarm is triggered when the threshold is exceeded, and operators are notified by text message or phone call, thereby realizing automatic monitoring of the temperature and humidity conditions of the crop growth environment, making agricultural planting management more scientific, efficient, and precise, and improving the quality and efficiency of planting management. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 is a flow chart of a strawberry disease early warning method based on the Internet of Things according to an embodiment of the present invention; Figure 2 2 is a schematic structural diagram of a strawberry disease early warning system based on the Internet of Things according to an embodiment of the present invention; Figure 3 An electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0019] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention and are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, ordinary technicians in the field should be able to understand other possible implementations and advantages of the present invention. The components in the figures are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0020] According to an embodiment of the present invention, a strawberry disease early warning method and system based on the Internet of Things are provided.

[0021] Embodiment 1; like Figure 1-2 As shown, the strawberry disease early warning method and system based on the Internet of Things according to an embodiment of the present invention include the following steps: Step S1, obtaining historical data of strawberry planting land within the coverage area, as well as current growth environment temperature data, real-time meteorological data and soil temperature and humidity data, dividing the planting land and building files for management; Step S2, collecting spore quantity data and strawberry disease degree data, pre-processing the strawberry disease degree data and the spore quantity data, and dividing them into a test set, a validation set and a training set; Step S3, preprocessing the acquired data of the strawberry planting site based on a wavelet transform algorithm; Step S4: When the temperature data threshold of the planting and growth environment, the real-time meteorological data threshold and the soil temperature and humidity data threshold set for the strawberry are not within the range, an early warning is issued; Step S5, establishing a strawberry disease target detection model, using multiple cameras to collect strawberry plant growth images, uploading the strawberry plant growth images to the cloud, and generating a training data set; Step S6, using the strawberry disease target detection model to preprocess the acquired strawberry disease image data set, and perform data enhancement on it to obtain a strawberry disease image data set; Step S7, constructing a strawberry disease classification and identification model, which includes a dimensionality reduction module, a sampling module and a classification module. Once a disease occurs, the management personnel are promptly reminded to treat it; Step S8, using the pretreated growth environment temperature data, real-time meteorological data, soil temperature and humidity data, and spore quantity data of step S3 as input, using the strawberry disease degree data as output, and using convolutional neural network-long short-term memory network CNN-LSTM network model to establish a strawberry disease early warning model; Step S9: using the strawberry disease early warning model to predict the strawberry disease severity data to obtain a recognition result of the strawberry disease image.

[0022] Embodiment 2: like Figure 1-2 As shown, record the areas where diseases occur during the production cycle and treat the diseased areas regularly.

[0023] In step S1, the growth environment temperature data includes indoor and outdoor data. When processing the meteorological data outside the greenhouse, the meteorological data outside the greenhouse and the future weather forecast data: record the average temperature and average humidity inside the greenhouse, the average temperature and average humidity outside the greenhouse, and the rainfall outside the greenhouse every hour, calculate the daily average of the above recorded data, number them in date order, and normalize them.

[0024] When processing the disease severity data and spore count data of strawberries in the greenhouse: normalize the disease severity data and spore count data of strawberries in the greenhouse.

[0025] In step S9, the recognition results of the strawberry disease images are labeled using the LabelImg image labeling tool, and the diseases in each image are framed with rectangular frames and the categories to which they belong are indicated.

[0026] In step S4, the data is input into the CNN convolution layer to adaptively extract features; the extracted features are pooled by the maximum pooling layer to reduce the data dimension and retain the main feature information.

[0027] Preferably, in step S4, when the strawberry is not within the planting and growth environment temperature data threshold, real-time meteorological data threshold and soil temperature and humidity data threshold set for the strawberry, an early warning is issued, including: an early warning via SMS, in which the monitoring center automatically sends the alarm information via SMS to the mobile phone reserved in the strawberry manager's information file; an early warning via telephone, in which the monitoring center automatically dials the mobile phone number reserved in the strawberry manager's information file, and automatically broadcasts the early warning information by voice through artificial intelligence.

[0028] Embodiment three; like Figure 1-3 As shown, a strawberry disease early warning system based on the Internet of Things is provided, which is used for the strawberry disease early warning method based on the Internet of Things, including a spore quantity collection module, a meteorological data collection module, an incidence degree data collection module, a disease early warning model module and an identification module; The spore quantity collection module is used to capture the airborne disease spores spread in the strawberry planting field through the spore capture device to collect spore quantity data; The meteorological data acquisition module is used to monitor environmental parameters in real time, and the environmental parameters include at least soil temperature and humidity, air temperature and humidity, light, wind speed and carbon dioxide concentration. The meteorological data acquisition module includes at least a soil temperature and humidity sensor, an air temperature and humidity sensor, a light sensor, a wind speed sensor and a carbon dioxide sensor; The disease degree data collection module is used to collect strawberry disease degree data; The recognition module is used to predict the strawberry disease severity data to obtain a recognition result of the strawberry disease image.

[0029] Embodiment 4: like Figure 1-3 As shown, provided, including: at least one memory for storing computer instructions; At least one processor in communication with the memory, wherein when the at least one processor executes the computer instructions, the at least one processor causes the system to execute: a data acquisition module, a file creation module, and an early warning module.

[0030] Embodiment five; like Figure 1-3As shown, a computer-readable storage medium is provided, on which a computer program is stored, characterized in that when the computer program is executed by a processor, the method as described in any one of claims 1-7 is implemented.

[0031] In summary, by means of the above technical scheme of the present invention, by utilizing multiple cameras to collect strawberry plant growth images, the coverage is wider, and the incomplete image caused by a single camera can be avoided; the strawberry disease target detection model is trained in the cloud, the space and hardware costs are reduced, the strawberry planting is monitored and managed for diseases, the disease type is accurately detected, the corresponding biological control is carried out according to the disease type, the disease data in the production cycle is statistically analyzed, the disease area is regularly disposed, the disease incidence rate is reduced, and the threshold value of the soil moisture demand of crops in each period such as strawberry breeding, topdressing and weeding, and picking, and the threshold value of the temperature tolerance are set, the soil moisture content and temperature in strawberry planting are monitored, and an alarm is triggered when the threshold value is exceeded, and the operating personnel are notified by text message or telephone, so as to realize the automatic monitoring of the temperature and humidity conditions of the crop growth environment, make agricultural planting management more scientific, efficient and precise, and improve the quality and efficiency of planting management.

[0032] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A strawberry disease early warning method based on the Internet of Things, characterized in that: The steps include: S1. Obtain historical data of strawberry planting areas within the coverage area, as well as current growth environment temperature data, real-time meteorological data, and soil temperature and humidity data, divide the planting areas, and establish files for management; S2, collecting spore quantity data and strawberry disease degree data, preprocessing the strawberry disease degree data and spore quantity data, and dividing them into a test set, a validation set and a training set; S3, preprocessing the acquired data of the strawberry planting site based on a wavelet transform algorithm; S4. When the temperature data threshold, real-time meteorological data threshold and soil temperature and humidity data threshold set for strawberries are not within the range, an early warning is issued; S5. Establish a strawberry disease target detection model, use multiple cameras to collect strawberry plant growth images, upload the strawberry plant growth images to the cloud, and generate a training data set; S6. Preprocessing the acquired strawberry disease image dataset using the strawberry disease target detection model and performing data enhancement on it to obtain a strawberry disease image dataset; S7, construct a strawberry disease classification and recognition model, which includes a dimensionality reduction module, a sampling module and a classification module. Once a disease occurs, the management personnel are reminded to treat it in time; S8, using the pretreated growth environment temperature data, real-time meteorological data, soil temperature and humidity data and spore count data of step S3 as input, using strawberry disease degree data as output, using convolutional neural network-long short-term memory network CNN-LSTM network model to establish strawberry disease early warning model; S9. Use the strawberry disease early warning model to predict the strawberry disease severity data to obtain the recognition result of the strawberry disease image.

2. A strawberry disease early warning method based on the Internet of Things according to claim 1, characterized in that, Record the areas where diseases occur during the production cycle and dispose of the diseased areas regularly.

3. A strawberry disease early warning method based on the Internet of Things according to claim 1, characterized in that, In step S1, the growth environment temperature data includes indoor and outdoor data. When processing the meteorological data outside the greenhouse, the meteorological data outside the greenhouse and the future weather forecast data: record the average temperature and average humidity inside the greenhouse, the average temperature and average humidity outside the greenhouse, and the rainfall outside the greenhouse every hour, calculate the daily average of the above recorded data, number them in date order, and normalize them.

4. A strawberry disease early warning method based on the Internet of Things according to claim 1, characterized in that, When processing the disease severity data and spore count data of strawberries in the greenhouse: normalize the disease severity data and spore count data of strawberries in the greenhouse.

5. A strawberry disease early warning method based on the Internet of Things according to claim 1, characterized in that, In step S9, the recognition results of the strawberry disease images are labeled using the LabelImg image labeling tool, and the diseases in each image are framed with rectangular frames and the categories to which they belong are indicated.

6. A strawberry disease early warning method based on the Internet of Things according to claim 1, characterized in that, In step S4, the data is input into the CNN convolution layer to adaptively extract features; the extracted features are pooled by the maximum pooling layer to reduce the data dimension and retain the main feature information.

7. A strawberry disease early warning method based on the Internet of Things according to claim 1, characterized in that, In step S4, when the temperature data threshold, real-time meteorological data threshold and soil temperature and humidity data threshold set for the strawberry planting and growth environment are not within the threshold, an early warning is issued, including: an early warning via SMS, in which the monitoring center automatically sends the alarm information to the mobile phone reserved in the strawberry manager's information file via SMS; an early warning via telephone, in which the monitoring center automatically dials the mobile phone number reserved in the strawberry manager's information file, and automatically broadcasts the early warning information by voice through artificial intelligence.

8. A strawberry disease early warning system based on the Internet of Things, characterized in that: The strawberry disease early warning method based on the Internet of Things as described in any one of claims 1 to 7 comprises a spore quantity collection module, a meteorological data collection module, an incidence degree data collection module, a disease early warning model module and an identification module; The spore quantity collection module is used to capture the airborne disease spores spread in the strawberry planting field through the spore capture device to collect spore quantity data; The meteorological data acquisition module is used to monitor environmental parameters in real time, and the environmental parameters include at least soil temperature and humidity, air temperature and humidity, light, wind speed and carbon dioxide concentration. The meteorological data acquisition module includes at least a soil temperature and humidity sensor, an air temperature and humidity sensor, a light sensor, a wind speed sensor and a carbon dioxide sensor; The disease degree data collection module is used to collect strawberry disease degree data; The recognition module is used to predict the strawberry disease severity data to obtain a recognition result of the strawberry disease image.

9. A strawberry disease early warning system based on the Internet of Things according to claim 8, characterized in that: include: at least one memory for storing computer instructions; At least one processor in communication with the memory, wherein when the at least one processor executes the computer instructions, the at least one processor causes the system to execute: a data acquisition module, a file creation module, and an early warning module.

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

Images