CN111598181A - Banana flower and leaf heart rot APP identification method and system - Google Patents
Banana flower and leaf heart rot APP identification method and system Download PDFInfo
- Publication number
- CN111598181A CN111598181A CN202010437941.7A CN202010437941A CN111598181A CN 111598181 A CN111598181 A CN 111598181A CN 202010437941 A CN202010437941 A CN 202010437941A CN 111598181 A CN111598181 A CN 111598181A
- Authority
- CN
- China
- Prior art keywords
- image
- banana
- heart rot
- infection
- acquisition
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a banana mosaic heart rot APP identification method and system, relates to the technical field of big data and image identification, and solves the problems of low manual identification speed, high professional technical requirements and low accuracy rate, and the technical scheme is as follows: firstly, screening by an image recognition technology, and preliminarily eliminating other banana virus diseases except the banana mosaic heart rot and the banana streak disease; and probability statistics is carried out on the previous banana mosaic heart rot case characteristics by combining data statistics, image factor indexes of plant images are obtained through calculation, the banana streak is screened and eliminated after the weight value is calculated, the identification speed is high, the accuracy is high, and a basis is provided for distinguishing and preventing the banana mosaic heart rot and other banana virus diseases. The invention utilizes big data and image recognition technology to intelligently recognize the heart rot of banana mosaic, reduces the input cost of preventing and controlling banana virosis, and is beneficial to the large-scale popularization and planting of bananas.
Description
Technical Field
The invention relates to the technical field of big data and image identification, in particular to an APP identification method and system for banana mosaic heart rot.
Background
Domestic and foreign research shows that Cucumber Mosaic Virus (CMV) can infect monocotyledonsCucumber mosaic virus is a representative member of the genus Cucumovirus of the family Bromoviraceae (Cucumovirus), and is a single-stranded positive sense RNA (+ ssRNA) virus, with CMV virions in the form of a regular icosahedron, 28-30nm in diameter, and about 5.4 × 10 in molecular weight6Wherein the RNA and protein components account for 18% and 82%, respectively. CMV strains can be divided into 2 subgroups based on serological and genomic sequence differences, i.e. subgroup I and subgroup II.
The banana mosaic heart rot is one of important banana virus diseases, the pathogen of the banana mosaic heart rot is also Cucumber Mosaic Virus (CMV), and the banana mosaic heart rot belongs to subgroup I. The leaves of the CMV-infected banana plants are in a yellow and green stripe, and are in a typical mottled flower-leaf shape, and particularly 1-2 leaves near the top are most obvious. The adult plants are weak in growth, dwarfed and often unable to bear fruits, and even if the adult plants are fruited, the adult plants are difficult to grow into normal banana fruits. In addition, Banana streak disease caused by Banana Streak Virus (BSV) infection is very similar to the symptoms of Banana mosaic heart rot and is easily confused in the field.
However, at present, the judgment and the distinction of the heart rot of the banana leaves are both carried out by plant protection experts through visual observation and identification or detection through Reverse transcription-polymerase chain reaction (RT-PCR), and the judgment and the distinction have high requirements on professional technologies, need to be improved in accuracy and have higher investment cost. In addition, most banana growing areas are identified by professionals or molecular biological techniques after the banana mosaic heart rot is infected, and reliable basis is difficult to provide for early prevention and control of the banana mosaic heart rot. Therefore, how to research and design a banana mosaic heart rot APP identification method and system is a problem which is urgently needed to be solved at present.
Disclosure of Invention
The invention aims to provide an APP identification method for banana mosaic heart rot, which can quickly and accurately identify the banana mosaic heart rot, provides a basis for distinguishing and preventing the banana mosaic heart rot from other banana virus diseases, reduces the input cost of pest control, and is beneficial to large-scale popularization and planting of bananas.
The technical purpose of the invention is realized by the following technical scheme: an APP identification method for banana mosaic heart rot comprises the following steps:
s1: acquiring a plant image through a user terminal, and selecting a lesion area image in the plant image;
s2: extracting color, area and morphological characteristic information in the image of the lesion area by an image identification technology, identifying and matching the color, area and morphological characteristic information with banana mosaic heart rot characteristic data in a database, and solving the identification similarity of the characteristic information;
s3: acquiring acquisition position information and acquisition time information of a plant image through a user terminal, and acquiring corresponding real-time climate data from a meteorological data center according to the acquisition position information and the acquisition time information;
s4: matching and screening banana mosaic heart rot infection case quantity from a database according to the acquisition position information, the acquisition time information and the real-time climate data, and calculating corresponding infection probability;
s5: taking the infection probability as an image factor index of the plant image, and solving an image weight value by combining the recognition similarity;
s6: judging whether the image weighted value reaches the standard or not according to a preset weighted value; if the image weight value is larger than or equal to the preset weight value, judging that the banana mosaic heart rot is infected by the plant image, and outputting a judgment result.
Preferably, the selection of the lesion region image is specifically as follows: and taking a region with the color difference value CA ≧ 1 by the marking coil, wherein the region size is 30cm × 30 cm.
Preferably, the method for calculating the infection probability specifically comprises the following steps:
s41: matching and screening out the total infection quantity S of the banana mosaic heart rot at the corresponding position from the database according to the acquired position information;
s42: matching and screening all the infection amount A in the corresponding time period from the total infection amount S according to the acquisition time information;
s43: matching and screening out all the infection amount B corresponding to the climate from the total infection amount S according to the real-time climate data;
s44: calculating the infection probability according to the total infection amount S, the infection amount A and the infection amount B, wherein the calculation formula of the infection probability P is as follows:
wherein E1 is a weight index of infection amount A, and E2 is a weight index of infection amount B.
Preferably, the time period is 7 days, and the day of collecting the time information is used as a node to simultaneously extend forward and backward for three days.
Preferably, the weight index E1 is 0.3, and the weight index E2 is 0.7.
Preferably, the weight index E1 is 0.4, and the weight index E2 is 0.6.
Preferably, the formula for calculating the image weight value X is as follows: x is P × T × 100; wherein, T is the identification similarity of the characteristic information, and 100 is a percentile system.
Preferably, the preset weight value is 50.
Preferably, the user terminal is a smart phone, an ipad or a notebook computer.
The invention also aims to provide a banana flower and leaf heart rot APP identification system, which comprises a database, a meteorological data center, an image acquisition module, an image processing module, a climate acquisition module, a first calculation module, a second calculation module and a result display module;
the database stores the color, area, form, position, time and climate characteristic data of all banana mosaic heart rot cases;
the meteorological data center is used for updating and storing climate data;
the image acquisition module is used for acquiring a plant image through a user terminal and selecting a lesion area image in the plant image;
the image processing module is used for extracting color, area and morphological characteristic information in the image of the lesion area through an image recognition technology, carrying out recognition matching on the color, area and morphological characteristic information and banana mosaic heart rot characteristic data in a database, and solving recognition similarity of the characteristic information;
the weather acquisition module is used for acquiring acquisition position information and acquisition time information of the plant image through the user terminal and acquiring corresponding real-time weather data from the weather data center according to the acquisition position information and the acquisition time information;
the first calculation module is used for matching and screening the banana mosaic heart rot infection case quantity from the database according to the acquisition position information, the acquisition time information and the real-time climate data, and calculating the corresponding infection probability;
the second calculation module is used for taking the infection probability as an image factor index of the plant image and solving an image weight value by combining the identification similarity;
the result display module is used for judging whether the image weighted value reaches the standard or not according to a preset weighted value; if the image weight value is larger than or equal to the preset weight value, judging that the banana mosaic heart rot is infected by the plant image, and outputting a judgment result.
In conclusion, the invention has the following beneficial effects: the banana mosaic heart rot and other banana virus diseases except the banana streak disease are eliminated by preliminary screening through an image recognition technology; and probability statistics is carried out on the previous banana mosaic heart rot case characteristics by combining data statistics, image factor indexes of plant images are obtained through calculation, banana streak is screened and removed after the weighted value is calculated, the recognition speed is high, the accuracy rate is high, a basis is provided for distinguishing and preventing the banana mosaic heart rot and other banana virus diseases, the input cost of pest control is reduced, and large-scale popularization and planting of bananas are facilitated.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed for the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is an overall flow chart in embodiment 1 of the present invention;
FIG. 2 is a flowchart of calculation of an infection probability in example 1 of the present invention;
fig. 3 is an architecture diagram in embodiment 2 of the present invention.
In the figure: 1. a database; 2. a meteorological data center; 3. an image acquisition module; 4. an image processing module; 5. a climate acquisition module; 6. a first calculation module; 7. a second calculation module; 8. and a result display module.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments.
Example 1: an APP identification method for banana mosaic heart rot (APP), as shown in figures 1 and 2, comprises the following steps:
s1: and acquiring a plant image through a user terminal, and selecting a lesion area image in the plant image. The selection of the lesion area image is specifically as follows: and taking a region with the color difference value CA ≧ 1 by the marking coil, wherein the region size is 30cm × 30 cm.
S2: and extracting color, area and morphological characteristic information in the image of the lesion area by an image identification technology, identifying and matching the color, area and morphological characteristic information with the banana mosaic heart rot characteristic data in the database 1, and solving the identification similarity of the characteristic information.
S3: acquiring the acquisition position information and the acquisition time information of the plant image through the user terminal, and acquiring corresponding real-time climate data from the meteorological data center 2 according to the acquisition position information and the acquisition time information.
S4: and screening the banana mosaic heart rot infection case quantity from the database 1 in a matching way according to the acquisition position information, the acquisition time information and the real-time climate data, and calculating the corresponding infection probability.
S5: and (4) taking the infection probability as an image factor index of the plant image, and solving the image weight value by combining the recognition similarity.
S6: judging whether the image weighted value reaches the standard or not according to a preset weighted value; if the image weight value is larger than or equal to the preset weight value, judging that the banana mosaic heart rot is infected by the plant image, and outputting a judgment result.
As shown in fig. 2, the method for calculating the infection probability is specifically as follows:
s41: and matching and screening out the total infection quantity S of the banana mosaic heart rot at the corresponding position from the database 1 according to the acquired position information.
S42: matching and screening all the infection amount A in the corresponding time period from the total infection amount S according to the acquisition time information; the time period is 7 days, and the time information is collected on the day and is simultaneously extended for three days for the node to move forwards and backwards.
S43: and matching and screening all the infection amount B of the corresponding climate from the total infection amount S according to the real-time climate data.
S44: calculating the infection probability according to the total infection amount S, the infection amount A and the infection amount B, wherein the calculation formula of the infection probability P is as follows:
wherein E1 is a weight index of infection amount A, and E2 is a weight index of infection amount B. In the present embodiment, the weight index E1 is 0.3, and the weight index E2 is 0.7; alternatively, the weight index E1 is 0.4 and the weight index E2 is 0.6.
In this embodiment, the formula for calculating the image weight value X is as follows: x is P × T × 100; wherein, T is the identification similarity of the characteristic information, and 100 is a percentile system.
In this embodiment, through analysis of test data, when the preset weight value is 50, the recognition accuracy is 96-98%, and the overall recognition time is within 3 minutes.
In this embodiment, the user terminal is a smart phone, and may also be an ipad or a notebook computer.
Example 2: a banana mosaic heart rot APP identification system is shown in figure 3 and comprises a database 1, a meteorological data center 2, an image acquisition module 3, an image processing module 4, a climate acquisition module 5, a first calculation module 6, a second calculation module 7 and a result display module 8.
The database 1 stores the color, area, shape, position, time and climate characteristic data of all banana mosaic heart rot cases.
The meteorological data center 2 is used for updating the stored climate data.
And the image acquisition module 3 is used for acquiring plant images through an automatic camera of the user terminal and selecting images of the lesion area in the plant images.
And the image processing module 4 is used for extracting color, area and morphological characteristic information in the image of the lesion area through an image identification technology, identifying and matching the color, area and morphological characteristic information with the banana mosaic heart rot characteristic data in the database 1, and solving the identification similarity of the characteristic information.
And the climate acquisition module 5 is used for acquiring the acquisition position information and the acquisition time information of the plant image through the user terminal and acquiring corresponding real-time climate data from the meteorological data center 2 according to the acquisition position information and the acquisition time information.
And the first calculation module 6 is used for matching and screening the banana mosaic heart rot infection case quantity from the database 1 according to the acquisition position information, the acquisition time information and the real-time climate data, and calculating the corresponding infection probability.
And the second calculating module 7 is used for taking the infection probability as an image factor index of the plant image and solving the image weight value by combining the identification similarity.
The result display module 8 is used for judging whether the image weighted value reaches the standard according to the preset weighted value; if the image weight value is larger than or equal to the preset weight value, judging that the banana mosaic heart rot is infected by the plant image, and outputting a judgment result.
The working principle is as follows: the banana mosaic heart rot and other banana virus diseases except the banana streak disease are eliminated by preliminary screening through an image recognition technology; and probability statistics is carried out on the previous banana mosaic heart rot case characteristics by combining data statistics, image factor indexes of plant images are obtained through calculation, banana streak is screened and removed after the weighted value is calculated, the recognition speed is high, the accuracy rate is high, a basis is provided for distinguishing and preventing the banana mosaic heart rot and other banana virus diseases, the input cost of pest control is reduced, and large-scale popularization and planting of bananas are facilitated.
The present embodiment is only for explaining the present invention, and it is not limited to the present invention, and those skilled in the art can make modifications of the present embodiment without inventive contribution as needed after reading the present specification, but all of them are protected by patent law within the scope of the claims of the present invention.
Claims (10)
1. An APP identification method for banana mosaic heart rot is characterized by comprising the following steps:
s1: acquiring a plant image through a user terminal, and selecting a lesion area image in the plant image;
s2: extracting color, area and morphological characteristic information in the image of the lesion area by an image identification technology, identifying and matching the color, area and morphological characteristic information with banana mosaic heart rot characteristic data in a database (1), and solving the identification similarity of the characteristic information;
s3: acquiring acquisition position information and acquisition time information of the plant image through a user terminal, and acquiring corresponding real-time climate data from a meteorological data center (2) according to the acquisition position information and the acquisition time information;
s4: screening the amount of banana mosaic heart rot infection cases from the database (1) in a matching manner according to the acquisition position information, the acquisition time information and the real-time climate data, and calculating the corresponding infection probability;
s5: taking the infection probability as an image factor index of the plant image, and solving an image weight value by combining the recognition similarity;
s6: judging whether the image weighted value reaches the standard or not according to a preset weighted value; if the image weight value is larger than or equal to the preset weight value, judging that the banana mosaic heart rot is infected by the plant image, and outputting a judgment result.
2. The APP identification method for banana mosaic heart rot (APP) according to claim 1, wherein the selection of the lesion area image specifically comprises: and taking a region with the color difference value CA ≧ 1 by the marking coil, wherein the region size is 30cm × 30 cm.
3. The APP identification method for banana mosaic heart rot (APP) as claimed in claim 1, wherein the calculation method for the infection probability specifically comprises the following steps:
s41: matching and screening out the total infection quantity S of the heart rot of the banana leaves at the corresponding position from the database (1) according to the acquired position information;
s42: matching and screening all the infection amount A in the corresponding time period from the total infection amount S according to the acquisition time information;
s43: matching and screening out all the infection amount B corresponding to the climate from the total infection amount S according to the real-time climate data;
s44: calculating the infection probability according to the total infection amount S, the infection amount A and the infection amount B, wherein the calculation formula of the infection probability P is as follows:
wherein E1 is a weight index of infection amount A, and E2 is a weight index of infection amount B.
4. The APP identification method for banana mosaic heart rot (APP) as claimed in claim 3, wherein the time period is 7 days, and the time period is extended by three days forward and backward simultaneously by taking the day of collecting time information as a node.
5. The APP identification method for banana mosaic heart rot as claimed in claim 3, wherein the weight index E1 is 0.3, and the weight index E2 is 0.7.
6. The APP identification method for banana mosaic heart rot as claimed in claim 3, wherein the weight index E1 is 0.4, and the weight index E2 is 0.6.
7. The APP identification method for banana mosaic heart rot (APP) as claimed in claim 3, wherein the image weight value X is calculated by the following formula: x is P × T × 100; wherein, T is the identification similarity of the characteristic information, and 100 is a percentile system.
8. The APP identification method for banana mosaic heart rot (APP) as claimed in claim 7, wherein the preset weight value is 50.
9. The APP identification method for the heart rot of banana leaves according to claim 1, wherein the user terminal is a smart phone, an ipad or a notebook computer.
10. An APP identification system for banana mosaic heart rot is characterized by comprising a database (1), a meteorological data center (2), an image acquisition module (3), an image processing module (4), a climate acquisition module (5), a first calculation module (6), a second calculation module (7) and a result display module (8);
the database (1) is used for storing the color, area, form, position, time and climate characteristic data of all banana mosaic heart rot cases;
the meteorological data center (2) is used for updating the stored climate data;
the image acquisition module (3) is used for acquiring a plant image through a user terminal and selecting a lesion area image in the plant image;
the image processing module (4) is used for extracting color, area and morphological characteristic information in the image of the lesion area through an image identification technology, identifying and matching the color, area and morphological characteristic information with banana mosaic heart rot characteristic data in the database (1), and solving the identification similarity of the characteristic information;
the climate acquisition module (5) is used for acquiring acquisition position information and acquisition time information of the plant image through the user terminal and acquiring corresponding real-time climate data from the meteorological data center (2) according to the acquisition position information and the acquisition time information;
the first calculation module (6) is used for matching and screening the banana mosaic heart rot infection case quantity from the database (1) according to the acquisition position information, the acquisition time information and the real-time climate data, and calculating the corresponding infection probability;
the second calculating module (7) is used for taking the infection probability as an image factor index of the plant image and solving an image weight value by combining the identification similarity;
the result display module (8) is used for judging whether the image weighted value reaches the standard or not according to a preset weighted value; if the image weight value is larger than or equal to the preset weight value, judging that the banana mosaic heart rot is infected by the plant image, and outputting a judgment result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010437941.7A CN111598181B (en) | 2020-05-21 | 2020-05-21 | Banana flower and leaf heart rot APP identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010437941.7A CN111598181B (en) | 2020-05-21 | 2020-05-21 | Banana flower and leaf heart rot APP identification method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111598181A true CN111598181A (en) | 2020-08-28 |
| CN111598181B CN111598181B (en) | 2023-04-07 |
Family
ID=72186008
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010437941.7A Active CN111598181B (en) | 2020-05-21 | 2020-05-21 | Banana flower and leaf heart rot APP identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111598181B (en) |
Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0892286A1 (en) * | 1997-07-18 | 1999-01-20 | Deutsches Zentrum für Luft- und Raumfahrt e.V. | Method of adaptive and combined thresholding for daytime aerocosmic remote detection of hot targets on the earth surface |
| US20050283314A1 (en) * | 2004-06-10 | 2005-12-22 | Pioneer Hi-Bred International, Inc. | Apparatus, method and system of information gathering and use |
| CN103034910A (en) * | 2012-12-03 | 2013-04-10 | 北京农业信息技术研究中心 | Regional scale plant disease and insect pest prediction method based on multi-source information |
| CN105787446A (en) * | 2016-02-24 | 2016-07-20 | 上海劲牛信息技术有限公司 | Smart agricultural insect disease remote automatic diagnosis system |
| CA2937574A1 (en) * | 2015-07-30 | 2017-01-30 | Ecoation Innovative Solutions Inc. | Multi-sensor platform for crop health monitoring |
| US9563852B1 (en) * | 2016-06-21 | 2017-02-07 | Iteris, Inc. | Pest occurrence risk assessment and prediction in neighboring fields, crops and soils using crowd-sourced occurrence data |
| CN107475449A (en) * | 2017-09-12 | 2017-12-15 | 中国热带农业科学院热带生物技术研究所 | A kind of transcript profile sequence measurement spliced suitable for dwarf virus section and geminivirus infection coe virus genome |
| CN107742290A (en) * | 2017-10-18 | 2018-02-27 | 成都东谷利农农业科技有限公司 | Plant disease identifies method for early warning and device |
| CA3039557A1 (en) * | 2016-10-13 | 2018-04-19 | Mccain Foods Limited | Method, medium, and system for detecting potato virus in a crop image |
| US20180253600A1 (en) * | 2017-03-02 | 2018-09-06 | Basecamp Networks, LLC | Automated diagnosis and treatment of crop infestations |
| CN108734710A (en) * | 2018-06-14 | 2018-11-02 | 厦门理工学院 | A kind of intelligence fruits and vegetables selection method |
| US20180373937A1 (en) * | 2012-12-19 | 2018-12-27 | Alan Shulman | Methods and systems for automated micro farming |
| CN109100506A (en) * | 2018-08-17 | 2018-12-28 | 中国热带农业科学院热带生物技术研究所 | Citrus Huanglongbing pathogen bacterium PAP protein antibodies are preparing the application in Citrus Huanglongbing pathogen early infection detection kit |
| CN109754423A (en) * | 2018-11-28 | 2019-05-14 | 中国农业科学院农业信息研究所 | A kind of extracting method and equipment of leaf spot lesion overlay area |
| CN109840549A (en) * | 2019-01-07 | 2019-06-04 | 武汉南博网络科技有限公司 | A kind of pest and disease damage recognition methods and device |
| US20190259108A1 (en) * | 2018-02-20 | 2019-08-22 | Osram Gmbh | Controlled Agricultural Systems and Methods of Managing Agricultural Systems |
| CN110458109A (en) * | 2019-08-13 | 2019-11-15 | 西南林业大学 | A kind of tealeaves disease recognition system and working method based on image recognition technology |
| US20200117897A1 (en) * | 2018-10-15 | 2020-04-16 | Walt Froloff | Adaptive Artificial Intelligence Training Data Acquisition and Plant Monitoring System |
| CN111080524A (en) * | 2019-12-19 | 2020-04-28 | 吉林农业大学 | Plant disease and insect pest identification method based on deep learning |
| EP3654272A1 (en) * | 2018-11-15 | 2020-05-20 | Korea Institute of Science and Technology | Crop injury diagnosis system and method |
-
2020
- 2020-05-21 CN CN202010437941.7A patent/CN111598181B/en active Active
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0892286A1 (en) * | 1997-07-18 | 1999-01-20 | Deutsches Zentrum für Luft- und Raumfahrt e.V. | Method of adaptive and combined thresholding for daytime aerocosmic remote detection of hot targets on the earth surface |
| US20050283314A1 (en) * | 2004-06-10 | 2005-12-22 | Pioneer Hi-Bred International, Inc. | Apparatus, method and system of information gathering and use |
| CN103034910A (en) * | 2012-12-03 | 2013-04-10 | 北京农业信息技术研究中心 | Regional scale plant disease and insect pest prediction method based on multi-source information |
| US20180373937A1 (en) * | 2012-12-19 | 2018-12-27 | Alan Shulman | Methods and systems for automated micro farming |
| CA2937574A1 (en) * | 2015-07-30 | 2017-01-30 | Ecoation Innovative Solutions Inc. | Multi-sensor platform for crop health monitoring |
| CN105787446A (en) * | 2016-02-24 | 2016-07-20 | 上海劲牛信息技术有限公司 | Smart agricultural insect disease remote automatic diagnosis system |
| US9563852B1 (en) * | 2016-06-21 | 2017-02-07 | Iteris, Inc. | Pest occurrence risk assessment and prediction in neighboring fields, crops and soils using crowd-sourced occurrence data |
| CA3039557A1 (en) * | 2016-10-13 | 2018-04-19 | Mccain Foods Limited | Method, medium, and system for detecting potato virus in a crop image |
| US20180253600A1 (en) * | 2017-03-02 | 2018-09-06 | Basecamp Networks, LLC | Automated diagnosis and treatment of crop infestations |
| CN107475449A (en) * | 2017-09-12 | 2017-12-15 | 中国热带农业科学院热带生物技术研究所 | A kind of transcript profile sequence measurement spliced suitable for dwarf virus section and geminivirus infection coe virus genome |
| CN107742290A (en) * | 2017-10-18 | 2018-02-27 | 成都东谷利农农业科技有限公司 | Plant disease identifies method for early warning and device |
| US20190259108A1 (en) * | 2018-02-20 | 2019-08-22 | Osram Gmbh | Controlled Agricultural Systems and Methods of Managing Agricultural Systems |
| CN108734710A (en) * | 2018-06-14 | 2018-11-02 | 厦门理工学院 | A kind of intelligence fruits and vegetables selection method |
| CN109100506A (en) * | 2018-08-17 | 2018-12-28 | 中国热带农业科学院热带生物技术研究所 | Citrus Huanglongbing pathogen bacterium PAP protein antibodies are preparing the application in Citrus Huanglongbing pathogen early infection detection kit |
| US20200117897A1 (en) * | 2018-10-15 | 2020-04-16 | Walt Froloff | Adaptive Artificial Intelligence Training Data Acquisition and Plant Monitoring System |
| EP3654272A1 (en) * | 2018-11-15 | 2020-05-20 | Korea Institute of Science and Technology | Crop injury diagnosis system and method |
| CN109754423A (en) * | 2018-11-28 | 2019-05-14 | 中国农业科学院农业信息研究所 | A kind of extracting method and equipment of leaf spot lesion overlay area |
| CN109840549A (en) * | 2019-01-07 | 2019-06-04 | 武汉南博网络科技有限公司 | A kind of pest and disease damage recognition methods and device |
| CN110458109A (en) * | 2019-08-13 | 2019-11-15 | 西南林业大学 | A kind of tealeaves disease recognition system and working method based on image recognition technology |
| CN111080524A (en) * | 2019-12-19 | 2020-04-28 | 吉林农业大学 | Plant disease and insect pest identification method based on deep learning |
Non-Patent Citations (3)
| Title |
|---|
| 张领先等: "蔬菜病害识别诊断与预警物联网技术研究与应用", 《蔬菜》 * |
| 范武波;吴多清;王健华;刘志昕;: "香蕉条斑病毒及其所致病害研究进展" * |
| 范武波等: "香蕉条斑病毒及其所致病害研究进展", 《热带农业科学》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111598181B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100416590C (en) | Method for automatically identifying field weeds in crop seeding-stage using site and grain characteristic | |
| CN110598532B (en) | Tree pest and disease damage monitoring system and method | |
| CN107680098A (en) | A kind of recognition methods of sugarcane sugarcane section feature | |
| CN114818909A (en) | Weed detection method and device based on crop growth characteristics | |
| CN113011221A (en) | Crop distribution information acquisition method and device and measurement system | |
| CN117561964B (en) | Agricultural data management system and method based on artificial intelligence | |
| CN116051996A (en) | Two-stage crop growth prediction method based on multi-mode information | |
| CN110660070A (en) | Rice vein image extraction method and device | |
| CN112580671A (en) | Automatic detection method and system for multiple development stages of rice ears based on deep learning | |
| CN115456476A (en) | Territorial space planning data acquisition and analysis system based on machine vision | |
| Ouyang et al. | Assessment of canopy size using UAV-based point cloud analysis to detect the severity and spatial distribution of canopy decline | |
| CN115620151A (en) | Method and device for identifying phenological period, electronic equipment and storage medium | |
| CN111598181B (en) | Banana flower and leaf heart rot APP identification method and system | |
| Zhao et al. | A dataset of pomegranate growth stages for machine learning-based monitoring and analysis | |
| CN117392535A (en) | Fruit tree flower bud target detection and white point rate estimation method oriented to complex environment | |
| CN115205701A (en) | Method for extracting sample based on rice phenological characteristics | |
| CN110135481B (en) | Crop lesion detection method and detection device | |
| Qi et al. | Mapping tea plantations using multitemporal spectral features by harmonised Sentinel-2 and Landsat images in Yingde, China | |
| Li et al. | A longan yield estimation approach based on uav images and deep learning | |
| Shaik | Species delimitation and speciation process in the Seriphium plumosum L. complex (Gnaphalieae: Asteraceae) in South Africa | |
| CN111932551A (en) | Missing transplanting rate detection method of rice transplanter | |
| Dai et al. | Recognition of cutting region for pomelo picking robot based on machine vision | |
| Burton | Phenotypic evaluation and genetic basis of anatomical and architectural root traits in the genus Zea | |
| CN116757867B (en) | Digital village construction method and system based on multi-source data fusion | |
| CN106897827A (en) | A kind of intelligent flower culture person's performance appraisal method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |