CN112307910A - Orchard disease and pest detection system based on deep learning and detection method thereof - Google Patents
Orchard disease and pest detection system based on deep learning and detection method thereof Download PDFInfo
- Publication number
- CN112307910A CN112307910A CN202011108896.7A CN202011108896A CN112307910A CN 112307910 A CN112307910 A CN 112307910A CN 202011108896 A CN202011108896 A CN 202011108896A CN 112307910 A CN112307910 A CN 112307910A
- Authority
- CN
- China
- Prior art keywords
- detection
- orchard
- module
- disease
- deep learning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 69
- 241000607479 Yersinia pestis Species 0.000 title claims abstract description 42
- 201000010099 disease Diseases 0.000 title claims abstract description 33
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 33
- 239000002420 orchard Substances 0.000 title claims abstract description 31
- 238000013135 deep learning Methods 0.000 title claims abstract description 27
- 241000238631 Hexapoda Species 0.000 claims abstract description 14
- 238000000034 method Methods 0.000 claims abstract description 12
- 230000005540 biological transmission Effects 0.000 claims abstract description 11
- 238000005286 illumination Methods 0.000 claims description 5
- 230000035939 shock Effects 0.000 claims description 4
- 230000003203 everyday effect Effects 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract 1
- 238000010248 power generation Methods 0.000 abstract 1
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N2021/8466—Investigation of vegetal material, e.g. leaves, plants, fruits
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Analytical Chemistry (AREA)
- Immunology (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Pathology (AREA)
- Medical Informatics (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Catching Or Destruction (AREA)
Abstract
An orchard disease and pest detection system based on deep learning and a detection method thereof are disclosed, wherein the detection system comprises a detection device and a detection cloud; the detection device comprises a base, a camera, a telescopic motion module, a rotary motion module, a 5G transmission module, a photosensitive module, a power supply module and a controller. According to the invention, the image acquisition device, the transmission device and the power generation device are combined, the acquired leaf disease and insect pest information is timely sent to the cloud end for identifying the disease and insect pest, the decision result is sent to the client end, the deep learning method is applied to the disease and insect pest identification of the orchard, the image identification is carried out on the data received by the background, the problems that manual handheld equipment in the orchard is inconvenient to shoot and the like are effectively solved, the upper surface and the lower surface of the leaf can be shot, the effective disease and insect pest monitoring and detection can be carried out on the orchard, the labor force is saved, the detection efficiency is greatly improved, and the wide market application prospect is achieved.
Description
Technical Field
The invention relates to the technical field of agricultural pest detection, computer vision technology and artificial intelligence, in particular to an orchard pest detection system based on deep learning and a detection method thereof.
Background
In recent years, deep learning has become a major trend of machine learning, is widely applied to various fields, particularly shows obvious advantages in the aspect of image classification and recognition, and also brings a hot learning trend, and brings revolutionary progress to computer vision and machine learning. In the aspect of pest and disease detection, the deep learning method has good development prospect. At present, most of pest detection depends on human experience for judgment, or specific pests can be detected only after sampling and bringing back to a laboratory for culture, although the prevention and control scheme is strong in pertinence, the culture period is slow, the efficiency is low, and the optimal pest control time can be missed. If the type of the plant diseases and insect pests is accurately judged at the early stage of the occurrence of the plant diseases and insect pests, correct treatment measures are taken, and manpower, material resources and financial resources can be greatly saved. The orchard disease and pest detection device is combined with a deep learning method, the type of disease and pest can be accurately judged, and therefore a quick and effective disease and pest solution is provided.
With the continuous development of the big data era, the agricultural field continuously applies the deep learning technology, more and more data platforms are developed and applied, the existing deep learning method is utilized to automatically identify the types of the photographed pictures containing the diseases and insect pests, the characteristics of the orchard diseases and insect pests are specified and visualized, the artificial intelligence is used for replacing the traditional artificial naked eye judgment, and then a data management platform is developed, so that the cost can be effectively saved and the value can be effectively created for fruit growers. The existing orchard pest and disease detection method is combined with deep learning, but a high recognition rate model is not found yet.
Disclosure of Invention
Objects of the invention
The invention provides an orchard pest detection system and a detection method based on deep learning, aiming at solving various problems of manual identification of current orchard pests, such as low efficiency and poor accuracy of manual pest judgment, and building a deep learning model for pest detection by using the characteristics of high detection efficiency, fast timeliness and labor saving of deep learning images, and provides an orchard pest detection system and a detection method based on deep learning.
(II) technical scheme
The invention provides an orchard disease and pest detection system based on deep learning and a detection method thereof, wherein the detection system comprises a detection device and a detection cloud; the detection device comprises a base, a camera, a telescopic motion module, a rotary motion module, a 5G transmission module, a photosensitive module, a power supply module and a controller; the detection method comprises the following steps:
s1, controlling the camera to collect images of the orchard leaves twice every day by the photosensitive module according to different illumination intensities, and transmitting the images to the detection cloud end through the G transmission module;
s2, the detection cloud identifies whether the disease and insect damage exists in the collected images by using a yolo model, and extracts and classifies the characteristics of the images with the disease and insect damage;
s3, the detection cloud further processes the image with the diseases and the pests in the S2 and uploads the image to a yolo model;
s4, recognizing and classifying the image in S3 by the deep-learning yolo model;
and S5, sending the decision result to the client.
Preferably, the telescopic motion module is arranged as an electric push rod; the rotary motion module is provided with a stepping motor and a fixed rod; the photosensitive module is set as a photoresistor; the 5G transmission module is set as an embedded system and a 5G system; the power supply module comprises a solar panel and a storage battery; the electric push rod is arranged on the base; the photosensitive resistor is arranged on the electric push rod; the fixed rod driven by the stepping motor is rotationally arranged on the electric push rod and is close to the photosensitive resistor; the camera is arranged on the fixed rod; the solar panel is arranged on the base and is electrically connected with the storage battery; the embedded system and the 5G system are arranged on the base.
Preferably, the detection device further comprises a driving motor, a steering wheel and a universal wheel; a steering wheel driven by a driving motor is arranged on the base; the universal wheel is arranged on the base.
Preferably, the steering wheel and the universal wheel are provided with shock absorbing members.
Preferably, the photoresistor is provided with a transparent rainproof cover.
Compared with the prior art, the technical scheme of the invention has the following beneficial technical effects: the real-time online automatic identification of the diseases and pests in the orchard is realized, a reasonable basis can be provided for the disease and pest control in the orchard, a certain time is strived for providing a solution, the problems of low efficiency and poor timeliness of manual visual identification of the diseases and pests are avoided, the yield of relevant crops in the orchard is improved, and unnecessary economic loss is reduced.
Drawings
Fig. 1 is a flow chart of an orchard disease and pest detection system based on deep learning and a detection method thereof.
Fig. 2 is a schematic structural diagram of a detection device of the orchard disease and pest detection system and method based on deep learning.
Fig. 3 is a hardware structure schematic diagram of the orchard disease and pest detection system and method based on deep learning provided by the invention.
Reference numerals: 1. a base; 2. a solar panel; 3. a storage battery; 4. embedded systems and 5G systems; 5. a control system unit; 6. an electric push rod; 7. a photoresistor; 8. a transparent rain cover; 9. a stepping motor; 10. fixing the rod; 11. a camera; 12. a drive motor; 13. a steering wheel; 14. a universal wheel; 15. a shock absorbing member.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings in conjunction with the following detailed description. It should be understood that the description is intended to be exemplary only, and is not intended to limit the scope of the present invention. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present invention.
As shown in fig. 1-3, the orchard pest detection system based on deep learning and the detection method thereof provided by the invention comprise a detection system, a detection device and a detection cloud; the detection device comprises a base 1, a camera 11, a telescopic motion module, a rotary motion module, a 5G transmission module, a photosensitive module, a power supply module and a controller 5; the detection method comprises the following steps:
s1, controlling the camera 11 to acquire images of the orchard leaves twice a day by the photosensitive module according to different illumination intensities, and transmitting the images to the detection cloud end through the 5G transmission module;
s2, the detection cloud identifies whether the disease and insect damage exists in the collected images by using a yolo model, and extracts and classifies the characteristics of the images with the disease and insect damage;
s3, the detection cloud further processes the image with the diseases and the pests in the S2 and uploads the image to a yolo model;
s4, recognizing and classifying the image in S3 by the deep-learning yolo model;
and S5, sending the decision result to the client.
In an alternative embodiment, the telescopic motion module is provided as an electric push rod 6; the rotary motion module is provided with a stepping motor 9 and a fixed rod 10; the photosensitive module is set as a photoresistor 7; the 5G transmission module is arranged as an embedded system and a 5G system 4, can be directly connected with various configuration software through virtual serial ports, transmits wireless data and sends acquired images to a cloud; the power supply module comprises a solar panel 2 and a storage battery 3; the electric push rod 6 is arranged on the base 1; the photosensitive resistor 7 is arranged on the electric push rod 6, and the electric push rod 6 can adjust the length of the whole rod, so that the device is suitable for taking pictures of orchard blades at different heights; a fixed rod 10 driven by a stepping motor 9 is rotationally arranged on the electric push rod 6 and is close to the photosensitive resistor 7; the camera 11 is arranged on the fixing rod 10; the solar panel 2 is arranged on the base 1 and is electrically connected with the storage battery 3, so that light energy is collected and converted into electric energy, the storage battery 3 is utilized for storing energy, and power is supplied to a system device; the embedded system and the 5G system 4 are arranged on the base 1.
In an alternative embodiment, the detection device further comprises a driving motor 12, a steering wheel 13 and a universal wheel 14; a steering wheel 13 driven by a driving motor 12 is arranged on the base 1; the universal wheel 14 is arranged on the base 1, and the driving motor 12 is internally provided with a steering control mechanism connected with the control system 5.
In an alternative embodiment, shock absorbing members 15 are provided on the steerable wheels 13 and the universal wheels 14.
In an alternative embodiment, a transparent rain cover 8 is arranged on the photoresistor 7.
The use principle of the invention is as follows: when the time reaches six morning hours every day, the photoresistor and the camera start to work, the camera 10 takes pictures of the front sides of the blades once when the illumination reaches a set threshold value, and takes pictures of the back sides of the blades once when the telescopic rods and the rotary rods reach the back sides of the blades, and the photoresistor 7 can take pictures at a proper time according to the threshold value set by the illumination intensity; the stepping motor 9 can control the camera 11 to rotate for 720 degrees, so that the upper surface and the lower surface of the blade are shot; electric putter 6 and step motor cooperation, extension, the shrink that electric putter 6 can be arbitrary, 720 rotations of step motor 9 ability control dead lever 10 can let the camera clap the positive and negative two sides of orchard blade.
It is to be understood that the above-described embodiments of the present invention are merely illustrative of or explaining the principles of the invention and are not to be construed as limiting the invention. Therefore, any modification, equivalent replacement, improvement and the like made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention. Further, it is intended that the appended claims cover all such variations and modifications as fall within the scope and boundaries of the appended claims or the equivalents of such scope and boundaries.
Claims (5)
1. An orchard disease and pest detection system based on deep learning and a detection method thereof are characterized in that the detection system comprises a detection device and a detection cloud end; the detection device comprises a base (1), a camera (11), a telescopic motion module, a rotary motion module, a 5G transmission module, a photosensitive module, a power supply module and a controller (5); the detection method comprises the following steps:
s1, controlling a camera (11) to collect images of the orchard leaves twice every day by the photosensitive module according to different illumination intensities, and transmitting the images to a detection cloud end through a 5G transmission module;
s2, the detection cloud identifies whether the disease and insect damage exists in the collected images by using a yolo model, and extracts and classifies the characteristics of the images with the disease and insect damage;
s3, the detection cloud further processes the image with the diseases and the pests in the S2 and uploads the image to a yolo model;
s4, recognizing and classifying the image in S3 by the deep-learning yolo model;
and S5, sending the decision result to the client.
2. The orchard pest detection system and method based on deep learning according to claim 1, wherein the telescopic motion module is set as an electric push rod (6); the rotary motion module is provided with a stepping motor (9) and a fixed rod (10); the photosensitive module is arranged as a photosensitive resistor (7); the 5G transmission module is set as an embedded system and a 5G system (4); the power supply module comprises a solar panel (2) and a storage battery (3); the electric push rod (6) is arranged on the base (1); the photoresistor (7) is arranged on the electric push rod (6); a fixed rod (10) driven by a stepping motor (9) is rotationally arranged on the electric push rod (6) and is close to the photosensitive resistor (7); the camera (11) is arranged on the fixed rod (10); the solar panel (2) is arranged on the base (1) and is electrically connected with the storage battery (3); the embedded system and the 5G system (4) are arranged on the base (1).
3. The orchard pest detection system based on deep learning and the detection method thereof according to claim 2 are characterized in that the detection device further comprises a driving motor (12), a steering wheel (13) and a universal wheel (14); a steering wheel (13) driven by a driving motor (12) is arranged on the base (1); the universal wheel (14) is arranged on the base (1).
4. An orchard pest detection system based on deep learning and a detection method thereof according to claim 3, wherein shock absorbing pieces (15) are arranged on the steering wheels (13) and the universal wheels (14).
5. The orchard pest detection system and method based on deep learning according to claim 2 is characterized in that a transparent rain cover (8) is arranged on the photoresistor (7).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011108896.7A CN112307910A (en) | 2020-10-16 | 2020-10-16 | Orchard disease and pest detection system based on deep learning and detection method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011108896.7A CN112307910A (en) | 2020-10-16 | 2020-10-16 | Orchard disease and pest detection system based on deep learning and detection method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112307910A true CN112307910A (en) | 2021-02-02 |
Family
ID=74327872
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011108896.7A Pending CN112307910A (en) | 2020-10-16 | 2020-10-16 | Orchard disease and pest detection system based on deep learning and detection method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112307910A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114640766A (en) * | 2022-03-14 | 2022-06-17 | 广西大学 | Multi-sensor-based real-time pest and disease monitoring system and working method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105868784A (en) * | 2016-03-29 | 2016-08-17 | 安徽大学 | Disease and insect pest detection system based on SAE-SVM |
| CN108921849A (en) * | 2018-09-30 | 2018-11-30 | 靖西海越农业有限公司 | For preventing and treating the wisdom Agricultural Monitoring early warning system of fertile mandarin orange pest and disease damage |
| CN209248554U (en) * | 2018-12-28 | 2019-08-13 | 华南农业大学 | A kind of field crops insect pest automatic identification and job management system |
-
2020
- 2020-10-16 CN CN202011108896.7A patent/CN112307910A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105868784A (en) * | 2016-03-29 | 2016-08-17 | 安徽大学 | Disease and insect pest detection system based on SAE-SVM |
| CN108921849A (en) * | 2018-09-30 | 2018-11-30 | 靖西海越农业有限公司 | For preventing and treating the wisdom Agricultural Monitoring early warning system of fertile mandarin orange pest and disease damage |
| CN209248554U (en) * | 2018-12-28 | 2019-08-13 | 华南农业大学 | A kind of field crops insect pest automatic identification and job management system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114640766A (en) * | 2022-03-14 | 2022-06-17 | 广西大学 | Multi-sensor-based real-time pest and disease monitoring system and working method |
| CN114640766B (en) * | 2022-03-14 | 2023-11-28 | 广西大学 | Multi-sensor-based real-time monitoring system for plant diseases and insect pests and working method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN205983216U (en) | Agricultural information acquisition robot of new forms of energy | |
| CN107553497A (en) | The edge positioner and its localization method of solar panel sweeping robot | |
| CN203748503U (en) | Insect capturing, automatic identifying, classifying and counting device | |
| CN206132218U (en) | A real -time spectral imaging and light quality intelligence control system for plant factory | |
| CN209313951U (en) | A kind of greenhouse intelligent movable monitoring system based on ARM9 | |
| CN112307910A (en) | Orchard disease and pest detection system based on deep learning and detection method thereof | |
| CN106976062A (en) | A kind of intelligent pest and disease damage identification robot | |
| CN203934545U (en) | Utilize the Insect infestation monitoring device of imaging technique | |
| CN215219537U (en) | Visual warmhouse booth monitored control system | |
| CN114779692A (en) | Linear sliding table type weeding robot and control method thereof | |
| CN213152184U (en) | Animal identification type field monitoring system based on convolutional neural network | |
| CN212279561U (en) | Solar insect killing device for insect pest situation measurement and control | |
| CN206744351U (en) | One kind is equipped based on Internet of Things drosophila fruit fly | |
| CN204948760U (en) | Intelligent mower | |
| CN116859987A (en) | Unmanned aerial vehicle automatic acquisition blade photo system | |
| CN206237830U (en) | A kind of Kiwi berry picking robot navigation system based on thermal camera | |
| CN110826531A (en) | Unmanned plant cultivation system, device and method based on image recognition | |
| CN109451279A (en) | A kind of greenhouse intelligent movable monitoring system based on ARM9 | |
| CN210428196U (en) | Agricultural environment information acquisition dolly | |
| WO2022022007A1 (en) | Photovoltaic tracking support rotation system and controller | |
| CN114235841A (en) | Agricultural greenhouse crop image automatic acquisition device and operation method | |
| CN210329057U (en) | Mobile imaging pest and disease identification system | |
| CN111347388B (en) | Crawler-type multifunctional robot and weed identification method | |
| CN106713869B (en) | Cloud intelligent pasture wireless monitoring and tracking method, device and system | |
| CN210959570U (en) | Indoor plant intelligent monitoring device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210202 |
|
| RJ01 | Rejection of invention patent application after publication |