Tomato disease identification device based on artificial intelligence and drones

Abstract

The utility model relates to the field of agricultural technology, and provides a tomato disease identification device based on artificial intelligence and unmanned aerial vehicles, including: a control device, a collection device and an identification device; the control device is used to control the image collection process of the unmanned aerial vehicle based on a control instruction; the collection device is used to scan the target plot of land through the unmanned aerial vehicle to collect tomato leaf images; the identification device is used to identify tomato diseases based on the leaf images. The tomato disease identification device based on artificial intelligence and unmanned aerial vehicles provided by the utility model controls the image collection process of the unmanned aerial vehicle through the control device, and the collection device scans the target plot of land through the unmanned aerial vehicle to collect tomato leaf images, so as to achieve real-time monitoring of tomato leaf images, and to identify tomato diseases on the leaf images according to the identification device, so as to accurately identify the type of tomato disease, and the identification speed is fast.

Description

Technical Field

[0001] The utility model relates to the technical field of agriculture, and in particular to a tomato disease identification device based on artificial intelligence and unmanned aerial vehicles. Background Art

[0002] Tomato is one of the most widely cultivated vegetables in the world, and it also occupies a very important position in my country's agricultural production. With the development of science and technology, greenhouse cultivation technology can realize the four-season cultivation of tomatoes. However, poor greenhouse environment often leads to tomato diseases. During the growth process of tomatoes, diseases such as gray mold, early blight, and late blight are very likely to occur, which seriously affect the yield of tomatoes. Since tomato diseases are mostly caused by pathogens, the onset of the disease is similar and it is difficult to distinguish. For a long time, tomato diseases have been discovered relatively late and cannot be effectively prevented and controlled.

[0003] Traditional tomato disease identification requires identification by human eyes, which has the disadvantages of slow identification speed, low accuracy, strong subjectivity and large limitations. Utility Model Content

[0004] In view of the problems existing in the prior art, an embodiment of the utility model provides a tomato disease identification device based on artificial intelligence and drones.

[0005] The utility model provides a tomato disease identification device based on artificial intelligence and unmanned aerial vehicle, comprising:

[0006] Control device, collection device and identification device;

[0007] The control device is used to control the image acquisition process of the drone based on the control instructions;

[0008] The acquisition device is used to scan the target plot through the drone to acquire tomato leaf images;

[0009] The identification device is used to identify tomato diseases based on the leaf image.

[0010] In some embodiments, the acquisition device comprises:

[0011] UAV, flight control unit, first communication unit and acquisition unit;

[0012] The flight control unit is used to control the flight route and flight duration of the UAV;

[0013] The acquisition unit is used to acquire tomato leaf images and perform preprocessing;

[0014] The first communication unit is used to send the preprocessed leaf image to the recognition device.

[0015] In some embodiments, the acquisition unit includes:

[0016] A first camera, an image processing module and a first storage unit;

[0017] The first camera is used to capture images of tomato leaves;

[0018] The image processing module pre-processes the leaf image;

[0019] The first storage unit is used to store the preprocessed leaf image.

[0020] In some embodiments, the acquisition device further includes:

[0021] Environmental perception sensors are used to perceive environmental information and build terrain maps.

[0022] In some embodiments, the control device comprises:

[0023] an identification unit, an interaction unit, a second communication unit, and a second storage unit;

[0024] The identification unit is used to identify the identity information of the target user;

[0025] The interaction unit is used to generate a control instruction in response to the input of the target user;

[0026] The second communication unit is used to communicate with the collection device and the identification device;

[0027] The second storage unit is used to store the identity information and the control instruction.

[0028] In some embodiments, the interaction unit includes:

[0029] A first display screen, a touch panel and physical buttons;

[0030] The first display screen is used to display the flight route and flight time of the drone;

[0031] The touch panel is used to receive input from a target user and generate a control instruction;

[0032] The physical button is used to wake up the screen and input common commands.

[0033] In some embodiments, the identification unit comprises:

[0034] A second camera and an ID card reader module;

[0035] The second camera is used to capture the identity card of the target user;

[0036] The ID card reading module is used to identify the ID card and determine the identity information of the target user.

[0037] In some embodiments, the identification device comprises:

[0038] a third communication unit, a touch screen, a second display screen, a disease identification program memory, an embedded microprocessor and a third storage unit;

[0039] The third communication unit is used to communicate with the control device;

[0040] The disease recognition program memory is used to store the basic program in the tomato disease image recognition process;

[0041] The embedded microprocessor is used to identify tomato diseases on the preprocessed leaf images based on the basic program;

[0042] The touch screen is used to provide a manual operation interface;

[0043] The third storage unit is used to store the preprocessed leaf image;

[0044] The second display screen is used to display the identification result of tomato diseases.

[0045] In some embodiments, it also includes:

[0046] power modules, controllers, hubs, and keyboards;

[0047] The power module is used for equipment power supply control;

[0048] The hub is used to expand the device;

[0049] The keyboard, as a manual operation interface of the system identification component, is used to provide key operation;

[0050] The acquisition device is connected to the embedded microprocessor through the hub and the controller;

[0051] The controller is used to transfer the pre-processed leaf image between the embedded microprocessor and the acquisition device.

[0052] In some embodiments, the third communication unit is used to receive the pre-processed leaf image sent by the acquisition device;

[0053] The third communication unit is used to send the preprocessed leaf image to the embedded microprocessor.

[0054] The tomato disease identification device based on artificial intelligence and unmanned aerial vehicle provided by the utility model controls the image acquisition process of the unmanned aerial vehicle through a control device. The acquisition device scans the target plot of land and acquires the leaf image of tomatoes through the unmanned aerial vehicle, so as to realize real-time monitoring of the leaf image of tomatoes, and tomato diseases are identified on the leaf image according to the identification device, so as to accurately identify the type of tomato diseases with a fast identification speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0056] Figure 1 It is a structural schematic diagram of a tomato disease identification device based on artificial intelligence and drone provided by an embodiment of the utility model;

[0057] Figure 2 It is a structural schematic diagram of a control device provided by an embodiment of the utility model;

[0058] Figure 3 It is a structural schematic diagram of a collection device provided by an embodiment of the utility model;

[0059] Figure 4 It is a structural schematic diagram of the identification device provided in an embodiment of the utility model. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solution and advantages of the utility model clearer, the technical solution of the utility model will be described clearly and completely in conjunction with the drawings in the utility model. Obviously, the described embodiments are part of the embodiments of the utility model, not all of the embodiments. Based on the embodiments in the utility model, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the utility model.

[0061] The terms "first", "second", etc. in the specification and claims of the present utility model are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the utility model can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first" and "second" are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0062] Figure 1 : is a schematic diagram of the structure of a tomato disease identification device based on artificial intelligence and drones provided in an embodiment of the utility model, such as Figure 1 As shown, the tomato disease identification device based on artificial intelligence and drone provided by the embodiment of the utility model includes:

[0063] Control device, collection device and identification device;

[0064] The control device is used to control the image acquisition process of the drone based on the control instructions;

[0065] The acquisition device is used to scan the target plot through the drone to acquire tomato leaf images;

[0066] The identification device is used to identify tomato diseases based on the leaf image.

[0067] The tomato disease identification device based on artificial intelligence and unmanned aerial vehicle provided in the embodiment of the utility model comprises: a collection device, a control device and an identification device.

[0068] Among them, the collection device is connected to the control device to realize the collection and remote control of disease data.

[0069] The collection device is connected to the identification device to realize the transmission, processing and identification of disease data.

[0070] The collection device can scan the target plot through a drone. The drone can realize real-time image monitoring, collect tomato leaf images along a preset route, and transmit the leaf image data to the recognition device through a communication unit for analysis and processing.

[0071] The recognition device can effectively identify the type of tomato disease through image recognition technology, achieve the effect of accurate disease identification and symptomatic treatment, and realize high-precision tomato disease identification. The recognition device receives the return data of the collection device in real time through the wireless transceiver module to realize the real-time disease identification function.

[0072] The control device is used to control the data collection process of the UAV. The instructions are transmitted to the collection device through the network via the remote communication module, and the collection process is monitored and controlled in real time in a visual way.

[0073] The tomato disease identification device based on artificial intelligence and drone provided by the embodiment of the utility model controls the image acquisition process of the drone through a control device. The acquisition device scans the target plot of land through the drone to collect tomato leaf images, thereby realizing real-time monitoring of tomato leaf images, and performing tomato disease identification on the leaf images according to the identification device, thereby accurately identifying the type of tomato disease with a fast identification speed.

[0074] In some embodiments, the acquisition device comprises:

[0075] UAV, flight control unit, first communication unit and acquisition unit;

[0076] The flight control unit is used to control the flight route and flight duration of the UAV;

[0077] The acquisition unit is used to acquire tomato leaf images and perform preprocessing;

[0078] The first communication unit is used to send the preprocessed leaf image to the recognition device.

[0079] Figure 2 Schematic diagram of the structure of the control device provided by the embodiment of the utility model, such as Figure 2 As shown, the collection device includes: a drone, a flight control unit, a first communication unit and a collection unit.

[0080] The UAV includes: UAV fuselage, frame, power system and distribution board, etc.

[0081] The flight control unit, which is composed of a single-chip microcomputer and a corresponding real-time operating system, has strong real-time performance and can quickly control the drone to ensure the balance and stability of the controlled object.

[0082] The first communication unit: including a data transmission radio, WiFi data transmission, 4G data transmission, etc., can send the pre-processed leaf image to the recognition device and report it to the cloud platform.

[0083] In some embodiments, the acquisition unit includes:

[0084] A first camera, an image processing module and a first storage unit;

[0085] The first camera is used to capture images of tomato leaves;

[0086] The image processing module pre-processes the leaf image;

[0087] The first storage unit is used to store the preprocessed leaf image.

[0088] The acquisition unit includes a first camera, an image processing module and a first storage unit.

[0089] The first camera is used to capture images of tomato leaves and collect images of tomato leaves.

[0090] The image processing module is used to pre-process the collected leaf images, for example, including: noise reduction, wide dynamic range, defogging, edge detection and other pre-processing.

[0091] Optionally, the image processing module can process the image through an image processing chip, and the data line and control line ports derived from the image processing chip are directly connected to the single-chip microcomputer to pre-process the acquired blade image.

[0092] The first storage unit is used to store the preprocessed leaf image.

[0093] In some embodiments, the acquisition device further includes:

[0094] Environmental perception sensors are used to perceive environmental information and build terrain maps.

[0095] Environmental perception sensors may include: structured light depth sensor, two-dimensional laser radar, or binocular vision, etc.

[0096] Environmental perception sensors can sense the surrounding environment and construct a topographic map so as to output a disease topographic map in combination with the final disease identification results.

[0097] The acquisition device may also include a perception and task management unit, which is responsible for calculation and decision-making, and completes complex calculations and environmental perception tasks.

[0098] The first communication unit can also report the environmental data collected by the environmental perception sensor to the cloud platform.

[0099] The tomato disease identification device based on artificial intelligence and drone provided by the embodiment of the utility model can realize real-time monitoring of tomato leaf images through a collection device, which can replace manual inspections, greatly improve inspection efficiency, significantly reduce the labor intensity of personnel, and effectively save labor costs.

[0100] In some embodiments, the control device comprises:

[0101] an identification unit, an interaction unit, a second communication unit, and a second storage unit;

[0102] The identification unit is used to identify the identity information of the target user;

[0103] The interaction unit is used to generate a control instruction in response to the input of the target user;

[0104] The second communication unit is used to communicate with the collection device and the identification device;

[0105] The second storage unit is used to store the identity information and the control instruction.

[0106] Figure 3 Schematic diagram of the structure of the collection device provided by the embodiment of the utility model, such as Figure 3 As shown, the control device includes: an identification unit, an interaction unit, a second communication unit and a second storage unit.

[0107] The identification unit is used to identify the identity information of the target user. Only when the identification is passed, the target user is allowed to perform relevant operations on the control device.

[0108] The interaction unit is used to respond to the input of the target user and generate a control instruction after the identity information of the target user is recognized.

[0109] The second communication unit is used to communicate with the collection device and the identification device, and is also used to report and communicate data with the remote platform in a WIFI manner.

[0110] The second storage unit is used to store identity information and control instructions. The second storage unit may include: a user behavior storage module, a timer, and a control instruction output module. The user behavior storage module is connected to the second communication unit and the interaction unit, and receives platform information and stores records through the second communication unit.

[0111] In some embodiments, the interaction unit includes:

[0112] A first display screen, a touch panel and physical buttons;

[0113] The first display screen is used to display the flight route and flight time of the drone;

[0114] The touch panel is used to receive input from a target user and generate a control instruction;

[0115] The physical button is used to wake up the screen and input common commands.

[0116] The interaction unit includes: a first display screen, a touch panel and physical buttons.

[0117] The first display screen may be a liquid crystal display screen, which is used to display the flight route and flight time of the drone or control interaction information.

[0118] The touch panel is used for user-controlled interactive input, that is, receiving input from the target user and generating control instructions.

[0119] Physical buttons are used for quick input of common commands and screen wake-up, etc.

[0120] In some embodiments, the identification unit comprises:

[0121] A second camera and an ID card reader module;

[0122] The second camera is used to capture the identity card of the target user;

[0123] The ID card reading module is used to identify the ID card and determine the identity information of the target user.

[0124] The identification unit is used to identify the identity information of the operator, and the identification unit includes: a second camera and an identity card reading module.

[0125] The second camera is used to capture the identity card of the target user.

[0126] The ID card reading module is used to identify the ID card of the target user to record manual inspection information and associate agricultural operations with operator information.

[0127] The tomato disease identification device based on artificial intelligence and drone provided by the embodiment of the utility model can replace manual inspection by controlling the data collection process of the collection device through the control device, greatly improves the inspection efficiency, greatly reduces the labor intensity of personnel, and effectively saves labor costs.

[0128] In some embodiments, the identification device comprises:

[0129] a third communication unit, a touch screen, a second display screen, a disease identification program memory, an embedded microprocessor and a third storage unit;

[0130] The third communication unit is used to communicate with the control device;

[0131] The disease recognition program memory is used to store the basic program in the tomato disease image recognition process;

[0132] The embedded microprocessor is used to identify tomato diseases on the preprocessed leaf images based on the basic program;

[0133] The touch screen is used to provide a manual operation interface;

[0134] The third storage unit is used to store the preprocessed leaf image;

[0135] The second display screen is used to display the identification result of tomato diseases.

[0136] Figure 4 is a schematic diagram of the structure of the identification device provided by the embodiment of the utility model, such as Figure 4 As shown, the identification device includes: a third communication unit, a touch screen, a second display screen, a disease identification program memory, an embedded microprocessor and a third storage unit.

[0137] The third communication unit may be a wireless transceiver module, which is used to communicate with the control device, for example, it may interact with the collection device for control instructions and tomato disease classification and identification results. The wireless transceiver module is a wireless data transceiver module, which has extremely low node static power consumption and supports large-scale star network networking.

[0138] A touch screen is used to provide a manual operation interface during the tomato disease image recognition process of the embedded microprocessor.

[0139] The second display screen adopts a display driver chip to drive a liquid crystal display screen. The circuit composed of this module is directly controlled by the processor and is used to receive tomato disease data information collected and reported by various terminals, and receive, interpret and store the data.

[0140] The second display screen can display disease data in real time and provide functions such as browsing, querying, and statistical analysis of historical data.

[0141] The second display screen can also display the tomato disease classification and identification results and conduct human-computer interaction.

[0142] The disease recognition program memory is used to store the basic program in the tomato disease image recognition process for the embedded microprocessor to call.

[0143] The embedded microprocessor is used to coordinate and process the relationship between the modules in a unified manner, exchange information, and call the basic program stored in the disease identification program memory to identify tomato diseases on the pre-processed leaf images.

[0144] The third storage unit receives and stores the blade images uploaded by the drone after preprocessing.

[0145] In some embodiments, the identification device further includes:

[0146] power modules, controllers, hubs, and keyboards;

[0147] The power module is used for equipment power supply control;

[0148] The hub is used to expand the device;

[0149] The keyboard, as a manual operation interface of the system identification component, is used to provide key operation;

[0150] The acquisition device is connected to the embedded microprocessor through the hub and the controller;

[0151] The controller is used to transfer the pre-processed leaf image between the embedded microprocessor and the acquisition device.

[0152] In some embodiments, the third communication unit is used to receive the pre-processed leaf image sent by the acquisition device;

[0153] The third communication unit is used to send the preprocessed leaf image to the embedded microprocessor.

[0154] The power module is used for equipment power supply control and to reduce equipment energy consumption. It is driven by DC power supply to stabilize the output voltage to the working voltage required by other modules, otherwise the components will not work properly.

[0155] The controller is used to transfer the acquired blade image between the embedded microprocessor and the acquisition device.

[0156] Hubs, for expansion devices;

[0157] External memory, used to expand storage devices.

[0158] The keyboard, as the manual operation interface of the system identification device, is used to provide key operation.

[0159] Specifically, the output end of the embedded microprocessor is connected to the third storage unit and the second display screen respectively, the received and processed data is transferred to the third storage unit for storage, and various processing results in the tomato disease image recognition process are displayed on the second display screen.

[0160] Embedded microprocessor uses lightweight convolutional neural network method for tomato disease image recognition.

[0161] The pre-processed leaf image acquired by the acquisition device can be uploaded to the recognition device in two ways:

[0162] The first storage unit of the acquisition unit of the acquisition device and the output end of the hub are connected to the input end of the embedded microprocessor through the interface of the controller, and the pre-processed leaf image acquired by the acquisition device is transmitted to the embedded microprocessor for image processing.

[0163] Alternatively, the third communication unit performs data communication with the first communication unit to transmit the pre-processed blade image acquired by the acquisition device to the embedded microprocessor for image processing.

[0164] The tomato disease identification device based on artificial intelligence and drone provided by the embodiment of the utility model improves the classification accuracy and realizes the portability of the system by embedding the identification device into the drone. Tomato disease images are recognized through the embedded system. Since the device has the characteristics of an embedded system, it has comprehensive functions, high reliability, good interchangeability, strong anti-interference ability, easy maintenance, and convenient installation and use, thereby achieving a high level of image recognition.

[0165] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0166] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0167] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the utility model, rather than to limit it. Although the utility model has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the utility model.

Claims

1. A tomato disease identification device based on artificial intelligence and drones, characterized in that: include: Control device, collection device and identification device; The acquisition device is connected to the control device, and the acquisition device is connected to the identification device; The control device is used to control the image acquisition process of the drone based on the control instructions; The acquisition device is used to scan the target plot through the drone to acquire tomato leaf images; The identification device is used to identify tomato diseases based on the leaf image; The collection device comprises: UAV, flight control unit, first communication unit and acquisition unit; the flight control unit is composed of a single chip microcomputer and a corresponding real-time operating system, and the first communication unit includes a data transmission radio, WiFi data transmission and 4G data transmission; The flight control unit is used to control the flight route and flight duration of the UAV; The acquisition unit is used to acquire tomato leaf images and perform preprocessing; The first communication unit is used to send the preprocessed leaf image to the recognition device; The acquisition unit comprises: A first camera, an image processing module and a first storage unit; the image processing module includes an image processing chip, and the data line and control line ports led out of the image processing chip are directly connected to the single chip microcomputer; The first camera is used to capture images of tomato leaves; The image processing module is used to pre-process the leaf image; The first storage unit is used to store the preprocessed leaf image; The control device comprises: an identification unit, an interaction unit, a second communication unit, and a second storage unit; The identification unit is used to identify the identity information of the target user; The interaction unit is used to generate a control instruction in response to the input of the target user; The second communication unit is used to communicate with the collection device and the identification device; The second storage unit is used to store the identity information and the control instruction; The identification device comprises: a third communication unit, a touch screen, a second display screen, a disease identification program memory, an embedded microprocessor and a third storage unit; The third communication unit is used to communicate with the control device; The disease recognition program memory is used to store the basic program in the tomato disease image recognition process; The embedded microprocessor is used to identify tomato diseases on the preprocessed leaf images based on the basic program; The touch screen is used to provide a manual operation interface; The third storage unit is used to store the preprocessed leaf image; The second display screen is used to display the identification result of tomato diseases.

2. The tomato disease identification device based on artificial intelligence and drone according to claim 1 is characterized in that: The collection device further includes: Environmental perception sensors, used to perceive environmental information; The acquisition device also includes a perception and task management unit, which is responsible for calculation and decision-making, and completes the work of calculation and environmental perception.

3. The tomato disease identification device based on artificial intelligence and drone according to claim 1 is characterized in that: The interaction unit comprises: A first display screen, a touch panel and physical buttons; The first display screen is used to display the flight route and flight time of the drone; The touch panel is used to receive input from a target user and generate a control instruction; The physical button is used to wake up the screen and input common commands.

4. The tomato disease identification device based on artificial intelligence and drone according to claim 1 is characterized in that: The identification unit comprises: A second camera and an ID card reader module; The second camera is used to capture the identity card of the target user; The ID card reading module is used to identify the ID card and determine the identity information of the target user.

5. The tomato disease identification device based on artificial intelligence and drone according to claim 1 is characterized in that: Also includes: power modules, controllers, hubs, and keyboards; The power module is used for equipment power supply control; The hub is used to expand the device; The keyboard, as a manual operation interface of the system identification component, is used to provide key operation; The acquisition device is connected to the embedded microprocessor through the hub and the controller; The controller is used to transfer the pre-processed leaf image between the embedded microprocessor and the acquisition device.

6. The tomato disease identification device based on artificial intelligence and drone according to claim 1, characterized in that: The third communication unit is used to receive the pre-processed leaf image sent by the acquisition device; The third communication unit is used to send the preprocessed leaf image to the embedded microprocessor.

Images