CN111507940A - Image recognition-based citrus orchard pest and disease identification and alarm system and method - Google Patents
Image recognition-based citrus orchard pest and disease identification and alarm system and method Download PDFInfo
- Publication number
- CN111507940A CN111507940A CN202010189457.7A CN202010189457A CN111507940A CN 111507940 A CN111507940 A CN 111507940A CN 202010189457 A CN202010189457 A CN 202010189457A CN 111507940 A CN111507940 A CN 111507940A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- image recognition
- data set
- training
- 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
- 241000607479 Yersinia pestis Species 0.000 title claims abstract description 30
- 239000002420 orchard Substances 0.000 title claims abstract description 29
- 241000207199 Citrus Species 0.000 title claims abstract description 27
- 235000020971 citrus fruits Nutrition 0.000 title claims abstract description 27
- 201000010099 disease Diseases 0.000 title claims abstract description 16
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 16
- 238000000034 method Methods 0.000 title claims abstract description 15
- 235000013399 edible fruits Nutrition 0.000 claims abstract description 33
- 238000012549 training Methods 0.000 claims abstract description 27
- 241000238631 Hexapoda Species 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 238000000605 extraction Methods 0.000 claims abstract description 5
- 230000002708 enhancing effect Effects 0.000 claims abstract description 4
- 239000000284 extract Substances 0.000 claims abstract description 4
- 238000009499 grossing Methods 0.000 claims abstract description 4
- 230000007246 mechanism Effects 0.000 claims description 19
- 239000000575 pesticide Substances 0.000 claims description 11
- 238000005507 spraying Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 9
- 239000003814 drug Substances 0.000 claims description 4
- 241000196324 Embryophyta Species 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 239000007921 spray Substances 0.000 claims description 3
- 230000006872 improvement Effects 0.000 abstract description 2
- 241000675108 Citrus tangerina Species 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01G—HORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING
- A01G13/00—Protecting plants
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01M—CATCHING, TRAPPING OR SCARING OF ANIMALS; APPARATUS FOR THE DESTRUCTION OF NOXIOUS ANIMALS OR NOXIOUS PLANTS
- A01M7/00—Special adaptations or arrangements of liquid-spraying apparatus for purposes covered by this subclass
- A01M7/0089—Regulating or controlling systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G06T5/70—
Abstract
An image recognition-based citrus orchard pest and disease identification and alarm method comprises the following steps: s1: collecting normal photos and photos of insect pests of the fruit trees, and storing the photos into a training database as a training data set; s2: the preprocessing module performs denoising and smoothing preprocessing on the pictures in the training data set and is used for enhancing the characteristics of the images in the data set; s3: the characteristic extraction module extracts the characteristics of the photos in the data set to obtain a characteristic data set; s4: the data processing module trains an image recognition model, the characteristic data set is used as input data, and the image recognition model outputs a result of whether the fruit tree has insect damage or not. Adopt the image acquisition system to gather fruit tree image, through, the image recognition model of training discerns the image, has got rid of and has leaned on error and interference that artifical experience brought, simultaneously, great improvement efficiency and accuracy.
Description
Technical Field
The invention relates to the field of pest control, in particular to a citrus orchard pest identification and alarm system and method based on image identification.
Background
In the traditional pest control process of the citrus orchard, workers perform data collection through experience, observe the citrus orchard by the workers and see whether fruit trees in the citrus orchard change relatively ordinarily or not. Meanwhile, only after a period of time of insect pest occurrence can the insect pest situation be judged. Spout the medicine to the oranges and tangerines orchard that takes place the insect pest, consequently, adopt traditional mode, often be passive operation, because need a period after spouting the medicine just can produce the effect, often lead to the fruit tree in the oranges and tangerines orchard to receive not little insect pest, cause not little loss to the fruit grower. Therefore, in order to predict whether insect damage occurs in advance, perform early warning and pesticide spraying in advance, avoid insect damage, and further enlarge loss, a citrus orchard insect damage recognition and alarm system and method based on image recognition are needed.
Disclosure of Invention
The invention provides a citrus orchard disease and pest identification and alarm system and method based on image identification, aiming at the defects of the prior art, wherein the citrus orchard disease and pest identification and alarm method based on image identification is characterized in that: the method comprises the following steps:
s1: collecting normal photos and photos of insect pests of the fruit trees, and storing the photos into a training database as a training data set;
s2: the preprocessing module performs denoising and smoothing preprocessing on the pictures in the training data set and is used for enhancing the characteristics of the images in the data set;
s3: the characteristic extraction module extracts the characteristics of the photos in the data set to obtain a characteristic data set;
s4: training an image recognition model, taking the characteristic data set as input data, and outputting a result of whether the fruit tree has insect damage by the image recognition model;
s5: the image acquisition system acquires fruit tree images in the citrus orchard at regular time;
s5: the image acquisition system transmits the fruit tree image to a data processing module through a communication module, and the data processing module inputs the fruit tree image into the image recognition model after processing the fruit tree image according to S2 and S3;
s6: the image recognition model recognizes whether the corresponding fruit tree has insect pests according to the input features, if so, the step goes to S7, otherwise, the step goes back to S5;
s7: the image recognition model stores the prediction data into a log database, and meanwhile, the intelligent recognition model informs an early warning module;
s8: the early warning module sends alarm information to the management client side on the one hand, and on the other hand, the early warning module starts a pesticide spraying system to spray pesticide to fruit trees in the citrus orchard.
Further: the image recognition model adopts a neural network model.
Wherein, a citrus orchard plant diseases and insect pests discernment and system of warning based on image recognition includes following technique, a citrus orchard plant diseases and insect pests discernment and system of warning based on image recognition, its characterized in that: the system comprises an acquisition module, a training database, a log database, an early warning module and a medicine spraying system;
the acquisition module is respectively in wireless connection with the training module and the data processing module through the communication module;
the data access port of the training module is connected with a training database, and the data access port of the data processing module is connected with a log database;
the data port of the data processing module is connected with the input port of the early warning module;
a first data port of the early warning module is connected with a signal input port of the pesticide spraying system;
and a second data port of the early warning module is connected with a communication module of the management terminal.
Further: the image acquisition system comprises a guide rail (1), a sliding plate (2), a first driving mechanism, a lifting rod (6), a second driving mechanism (7), a connecting rod (8) and a camera (9);
the two guide rails (1) are arranged side by side, the sliding plate (2) is installed on the guide rails (1), a first driving mechanism is arranged at the top of the sliding plate (2), and the first driving mechanism drives the sliding plate (2) to slide along the guide rails (1);
the bottom of the lifting rod (6) is fixedly installed at the top of the sliding plate (2), the lower end of the connecting rod (8) is hinged to the output end of the lifting rod (6), the second driving mechanism (7) drives the connecting rod (8) to swing relative to the lifting rod (6), and a camera (9) is arranged at the top of the connecting rod (8).
Further: the camera (9) rotates for 360 degrees.
Further: the first driving mechanism comprises a first driving gear (3), a first rack (4) and a first driving motor (5), the rack is installed on the outer side of the guide rail (1), the first driving motor (5) is arranged on the top of the sliding plate (2), the driving gear is fixedly sleeved at the output end of the first driving motor (5), and the driving gear is meshed with the first rack (4).
The invention has the beneficial effects that: firstly, adopt the image acquisition system to gather the fruit tree image of fruit tree, through, the image recognition model of training discerns the image, has got rid of and has leaned on error and interference that artificial experience brought, simultaneously, great improvement efficiency and accuracy. Secondly, automatic remote management can be achieved. And thirdly, the set log database can store the collected pictures for convenient backtracking and big data analysis.
Fourthly, the image acquisition device who adopts can carry out image acquisition to the fruit tree on a large scale according to the demand multi-angle, has effectively reduced the condition that the image is not up to standard.
Drawings
FIG. 1 is an overall block diagram of the present invention;
FIG. 2 is a diagram of an image acquisition device;
the figures in the figures illustrate a guide rail 1, a sliding plate 2, a first driving gear 3, a first rack 4, a first driving motor 5, a lifting rod 6, a second driving mechanism 7, a connecting rod 8, a camera 9 and a bracket 10.
Detailed Description
The following detailed description of the preferred embodiments of the present invention, taken in conjunction with the accompanying drawings, will make the advantages and features of the invention easier to understand by those skilled in the art, and thus will clearly and clearly define the scope of the invention.
As shown in fig. 1 and 2:
a specific technical scheme of an image recognition-based citrus orchard pest and disease identification and alarm method is as follows:
an image recognition-based citrus orchard pest and disease identification and alarm method comprises the following steps:
s1: collecting normal photos and photos of insect pests of the fruit trees, and storing the photos into a training database as a training data set;
s2: the preprocessing module performs denoising and smoothing preprocessing on the pictures in the training data set and is used for enhancing the characteristics of the images in the data set;
s3: the characteristic extraction module extracts the characteristics of the photos in the data set to obtain a characteristic data set;
s4: training an image recognition model, taking the characteristic data set as input data, and outputting a result of whether the fruit tree has insect damage by the image recognition model;
s5: the image acquisition system acquires fruit tree images in the citrus orchard at regular time;
s5: the image acquisition system transmits the fruit tree image to the data processing module through the communication module, and the data processing module inputs the fruit tree image into the image recognition model after processing the fruit tree image according to S2 and S3;
s6: the image recognition model recognizes whether the corresponding fruit tree has insect pests according to the input characteristics, if so, the step S7 is carried out, otherwise, the step S5 is carried out;
s7: the image recognition model stores the prediction data into a log database, and meanwhile, the intelligent recognition model informs an early warning module;
s8: on one hand, the early warning module sends alarm information to the management client side, and on the other hand, the early warning module starts a pesticide spraying system to spray pesticide to fruit trees in the citrus orchard.
In the invention, the image recognition model adopts a neural network model.
The citrus orchard pest and disease identification and alarm system based on image identification comprises an acquisition module, a training database, a log database, an early warning module and a pesticide spraying system;
the acquisition module is respectively in wireless connection with the training module and the data processing module through the communication module;
the data access port of the training module is connected with a training database, and the data access port of the data processing module is connected with a log database;
the data port of the data processing module is connected with the input port of the early warning module;
a first data port of the early warning module is connected with a signal input port of the pesticide spraying system;
and a second data port of the early warning module is connected with the communication module of the management terminal.
In the invention, the image acquisition system has the specific structure that the image acquisition system comprises a guide rail 1, a sliding plate 2, a first driving mechanism, a lifting rod 6, a second driving mechanism 7, a connecting rod 8 and a camera 9;
the two guide rails 1 are arranged side by side, the sliding plate 2 is arranged on the guide rails 1, a first driving mechanism is arranged at the top of the sliding plate 2, and the first driving mechanism drives the sliding plate 2 to slide along the guide rails 1;
fixed mounting is in the top of sliding plate 2 in 6 bottoms of lifter, and the lower extreme of connecting rod 8 articulates at the output of lifter 6, and second actuating mechanism 7 drives the relative lifter 6 swing of connecting rod 8, is provided with camera 9 at the top of connecting rod 8.
In the present invention, the camera 9 is a 360 degree rotary camera.
Meanwhile, the first driving mechanism comprises a first driving gear 3, a first rack 4 and a first driving motor 5, the rack is installed on the outer side of the guide rail 1, the first driving motor 5 is arranged on the top of the sliding plate 2, the driving gear is fixedly sleeved at the output end of the first driving motor 5, and the driving gear is meshed with the first rack 4.
Claims (6)
1. An image recognition-based citrus orchard pest and disease identification and alarm method is characterized by comprising the following steps: the method comprises the following steps:
s1: collecting normal photos and photos of insect pests of the fruit trees, and storing the photos into a training database as a training data set;
s2: the preprocessing module performs denoising and smoothing preprocessing on the pictures in the training data set and is used for enhancing the characteristics of the images in the data set;
s3: the characteristic extraction module extracts the characteristics of the photos in the data set to obtain a characteristic data set;
s4: the data processing module trains an image recognition model, the characteristic data set is used as input data, and the image recognition model outputs the result of whether the fruit tree has insect damage;
s5: the image acquisition system acquires fruit tree images in the citrus orchard at regular time;
s5: the image acquisition system transmits the fruit tree image to a data processing module through a communication module, and the data processing module inputs the fruit tree image into the image recognition model after processing the fruit tree image according to S2 and S3;
s6: the image recognition model recognizes whether the corresponding fruit tree has insect pests according to the input features, if so, the step goes to S7, otherwise, the step goes back to S5;
s7: the image recognition model stores the prediction data into a log database, and meanwhile, the intelligent recognition model informs an early warning module;
s8: the early warning module sends alarm information to the management client side on the one hand, and on the other hand, the early warning module starts a pesticide spraying system to spray pesticide to fruit trees in the citrus orchard.
2. The citrus orchard pest and disease identification and alarm method based on image identification according to claim 1, characterized in that: the image recognition model adopts a neural network model.
3. The utility model provides a citrus orchard plant diseases and insect pests discernment and system of reporting to police based on image recognition which characterized in that: the system comprises an image acquisition system, a preprocessing module, a feature extraction module, a log database, an early warning module and a medicine spraying system;
the acquisition module is respectively in wireless connection with the training module and the data processing module through the communication module;
the data access port of the training module is connected with a training database, and the data access port of the data processing module is connected with a log database;
the data port of the data processing module is connected with the input port of the early warning module;
a first data port of the early warning module is connected with a signal input port of the pesticide spraying system;
and a second data port of the early warning module is connected with a communication module of the management terminal.
4. The citrus orchard pest and disease identification and alarm system based on image identification is characterized in that: the image acquisition system comprises a guide rail (1), a sliding plate (2), a first driving mechanism, a lifting rod (6), a second driving mechanism (7), a connecting rod (8) and a camera (9);
the two guide rails (1) are arranged side by side, the sliding plate (2) is installed on the guide rails (1), a first driving mechanism is arranged at the top of the sliding plate (2), and the first driving mechanism drives the sliding plate (2) to slide along the guide rails (1);
the bottom of the lifting rod (6) is fixedly installed at the top of the sliding plate (2), the lower end of the connecting rod (8) is hinged to the output end of the lifting rod (6), the second driving mechanism (7) drives the connecting rod (8) to swing relative to the lifting rod (6), and a camera (9) is arranged at the top of the connecting rod (8).
5. The citrus orchard pest and disease identification and alarm system based on image identification is characterized in that: the camera (9) rotates for 360 degrees.
6. The citrus orchard pest and disease identification and alarm system based on image identification is characterized in that: the first driving mechanism comprises a first driving gear (3), a first rack (4) and a first driving motor (5), the rack is installed on the outer side of the guide rail (1), the first driving motor (5) is arranged on the top of the sliding plate (2), the driving gear is fixedly sleeved at the output end of the first driving motor (5), and the driving gear is meshed with the first rack (4).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010189457.7A CN111507940A (en) | 2020-03-18 | 2020-03-18 | Image recognition-based citrus orchard pest and disease identification and alarm system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010189457.7A CN111507940A (en) | 2020-03-18 | 2020-03-18 | Image recognition-based citrus orchard pest and disease identification and alarm system and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111507940A true CN111507940A (en) | 2020-08-07 |
Family
ID=71871632
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010189457.7A Pending CN111507940A (en) | 2020-03-18 | 2020-03-18 | Image recognition-based citrus orchard pest and disease identification and alarm system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111507940A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113907059A (en) * | 2021-10-09 | 2022-01-11 | 西南大学 | Fruit tree pesticide spraying device based on visual identification and identification method thereof |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100104191A1 (en) * | 2007-03-26 | 2010-04-29 | Mcgwire Kenneth C | Data analysis process |
CN104008551A (en) * | 2014-06-10 | 2014-08-27 | 华南农业大学 | Liberobacter asiaticum detection method based on visible light images |
CN208318037U (en) * | 2018-03-30 | 2019-01-04 | 华东交通大学 | Small rail car that a kind of full-automatic multiple medicine case sprays to target and to target pesticide spraying system |
CN109308697A (en) * | 2018-09-18 | 2019-02-05 | 安徽工业大学 | A kind of leaf disease recognition method based on machine learning algorithm |
CN109379557A (en) * | 2018-09-30 | 2019-02-22 | 田东县文设芒果专业合作社 | Mango insect pest intelligent monitor system based on image recognition |
CN209330740U (en) * | 2018-12-21 | 2019-09-03 | 广东农工商职业技术学院 | A kind of early warning system based on machine vision Citrus Huanglongbing pathogen |
-
2020
- 2020-03-18 CN CN202010189457.7A patent/CN111507940A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100104191A1 (en) * | 2007-03-26 | 2010-04-29 | Mcgwire Kenneth C | Data analysis process |
CN104008551A (en) * | 2014-06-10 | 2014-08-27 | 华南农业大学 | Liberobacter asiaticum detection method based on visible light images |
CN208318037U (en) * | 2018-03-30 | 2019-01-04 | 华东交通大学 | Small rail car that a kind of full-automatic multiple medicine case sprays to target and to target pesticide spraying system |
CN109308697A (en) * | 2018-09-18 | 2019-02-05 | 安徽工业大学 | A kind of leaf disease recognition method based on machine learning algorithm |
CN109379557A (en) * | 2018-09-30 | 2019-02-22 | 田东县文设芒果专业合作社 | Mango insect pest intelligent monitor system based on image recognition |
CN209330740U (en) * | 2018-12-21 | 2019-09-03 | 广东农工商职业技术学院 | A kind of early warning system based on machine vision Citrus Huanglongbing pathogen |
Non-Patent Citations (1)
Title |
---|
贾敬敦 等: "《农村信息化发展研究》", 31 May 2014, 科学技术文献出版社 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113907059A (en) * | 2021-10-09 | 2022-01-11 | 西南大学 | Fruit tree pesticide spraying device based on visual identification and identification method thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111767802B (en) | Method and device for detecting abnormal state of object | |
CN103248703A (en) | Automatic monitoring system and method for live pig action | |
CN104381231A (en) | Image-based field insect pest situation monitoring device | |
CN109379557A (en) | Mango insect pest intelligent monitor system based on image recognition | |
CN113379769A (en) | Intelligent defense platform for crop diseases and insect pests | |
CN105868784A (en) | Disease and insect pest detection system based on SAE-SVM | |
CN106094008A (en) | A kind of grain storage pest sound detection identification system | |
CN111507940A (en) | Image recognition-based citrus orchard pest and disease identification and alarm system and method | |
CN107681784A (en) | Steel tower ground wire monitoring system and method based on multisource data fusion | |
CN113785783A (en) | Livestock grouping system and method | |
CN114460080A (en) | Rice disease and pest intelligent monitoring system | |
CN115604301A (en) | Planting environment monitoring system based on artificial intelligence | |
CN114627411A (en) | Crop growth period identification method based on parallel detection under computer vision | |
CN114581948A (en) | Animal face identification method | |
CN112116206A (en) | Intelligent agricultural system based on big data | |
CN114847196A (en) | Intelligent beehive and bee identification tracking counting system based on deep learning | |
CN114429310A (en) | Database-based agricultural picking object identification algorithm | |
CN108462855A (en) | A kind of trapping lamp long-distance video monitoring system that can observe desinsection situation in real time | |
CN209330740U (en) | A kind of early warning system based on machine vision Citrus Huanglongbing pathogen | |
CN109087211A (en) | A kind of fertile mandarin orange wisdom implant system | |
CN116300608A (en) | Intelligent agriculture remote monitoring system based on big data | |
CN102608349A (en) | Intelligent greenhouse nectarine fruit growth rate wireless monitoring system based on embedded dual-camera platform | |
CN112019607A (en) | Intelligent farm comprehensive control method and system based on visual cloud platform | |
CN116824626A (en) | Artificial intelligent identification method for abnormal state of animal | |
CN114511801A (en) | Insect pest recognition model training method, insect pest monitoring method and electronic equipment |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200807 |