CN105850930A - Machine vision based pre-warning system and method for pest and disease damage - Google Patents

Machine vision based pre-warning system and method for pest and disease damage Download PDF

Info

Publication number
CN105850930A
CN105850930A CN201610254139.8A CN201610254139A CN105850930A CN 105850930 A CN105850930 A CN 105850930A CN 201610254139 A CN201610254139 A CN 201610254139A CN 105850930 A CN105850930 A CN 105850930A
Authority
CN
China
Prior art keywords
pest
warning
disease damage
early warning
ambient parameter
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
Application number
CN201610254139.8A
Other languages
Chinese (zh)
Inventor
李昕
檀新瑞
柴宇燊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
University of Shanghai for Science and Technology
Original Assignee
University of Shanghai for Science and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by University of Shanghai for Science and Technology filed Critical University of Shanghai for Science and Technology
Priority to CN201610254139.8A priority Critical patent/CN105850930A/en
Publication of CN105850930A publication Critical patent/CN105850930A/en
Pending legal-status Critical Current

Links

Classifications

    • AHUMAN NECESSITIES
    • A01AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01MCATCHING, TRAPPING OR SCARING OF ANIMALS; APPARATUS FOR THE DESTRUCTION OF NOXIOUS ANIMALS OR NOXIOUS PLANTS
    • A01M1/00Stationary means for catching or killing insects
    • A01M1/02Stationary means for catching or killing insects with devices or substances, e.g. food, pheronones attracting the insects
    • A01M1/026Stationary means for catching or killing insects with devices or substances, e.g. food, pheronones attracting the insects combined with devices for monitoring insect presence, e.g. termites

Abstract

The invention provides a machine vision technology based pre-warning system and method for pest and disease damage of crops in greenhouses. According to the system, image monitoring data and environment parameters under the natural background are acquired by an in-situ Canon EOS7D camera image sensor and multiple environmental sensors, a dual pest and disease damage pre-warning system realizing warning source pre-warning and warning sign pre-warning is constructed, and meanwhile, an information processing function that a user can inquire pre-warning records at any time is realized. Real-time environmental parameters and environmental parameters suitable for crop growth are matched firstly to provide preliminary pre-warning, real-time image data are processed through filtering, segmentation, feature extraction and identification and classification with an image processing technology in machine vision, so that tomato early blight and leaf mold are automatically identified and classified, the pest and disease damage morbidity situation of crops at present is provided, and decision support and historical information record inquiry functions are supplied to the user. Manpower and material resources are greatly reduced, and meanwhile, the pest and disease damage management efficiency of the crops in the greenhouse is further improved.

Description

Pest and disease damage early warning system based on machine vision and method
Technical field
The present invention relates to a kind of pest and disease damage early warning system, be specifically related to a kind of pest and disease damage early warning system based on machine vision And method.
Background technology
In industrialization, informationization, urbanization deeply develop, simultaneously advance agricultural modernization, be the one of " 12 " period Item significant task." 12 " are the critical periods built a well-off society in an all-round way, and being that in-depth reform is open, accelerate to change economy sends out The crucial period of exhibition mode, is to speed up the important opportunity period of developing modern agriculture.
Digital Agriculture and precision operation are direction and the requirements of modern agricultural development.In crop state of an illness insect pest situation analysis side Face, Digital Agriculture requires to obtain quickly and accurately the information that plant is infected by pest and disease damage, thus instructs in growing process Fine-grained management.
In the world, Japan in 20 end of the centurys, in the facilities horticulture field of technology-intensive type, to develop multiple pest and disease damage pre- Alarm system, not only saves manpower and materials, also substantially increases prevention and control of plant diseases, pest control effect;Holland's agricultural environment Graduate School of Engineering is opened The expert system of the pest and disease damage early warning sent out, uses image processing techniques and expert system technology to combine, achieves in application aspect Good result;And the warmhouse booth of the country such as the U.S., Britain combines machine vision technique while using intelligence control system Rating scale, the scope of pest and disease damage has been carried out early warning.
The scab that the Major Difficulties of diseases and pests of agronomic crop early warning at present is under complex background to be completed is split and uses A kind of discrimination is higher but recognizer that amount of calculation is less.But currently advanced greenhouse computer monitoring early warning system still relies on External importing technology, core technology is still grasped in abroad.Therefore diseases and pests of agronomic crop warning aspect in greenhouse Research remains a need for further making great efforts and innovating.
Summary of the invention
The invention aims to the defect solving that in prior art, diseases and pests of agronomic crop is realized early warning, it is provided that a kind of Pest and disease damage early warning system based on machine vision and method, be core by the otsu partitioning algorithm improved and KNN intelligent classification algorithm The heart solves the problems referred to above.
To achieve these goals, insight of the invention is that
Pest and disease damage early warning system based on machine vision is collectively constituted by two parts of software and hardware, again may be used according to function difference This system is divided image and environmental parameter acquisition system and image processing system;Wherein, image and ambient parameter collection system Unite and obtained image prison by on-the-spot Canon's EOS7D types of cameras and multiple environmental sensor
Survey data and ambient parameter, then data transmission cause image processing system is processed accordingly;Image processing system by Alert source early warning and alert million early warning and information processing form.Alert source early warning is by by real-time site environment parameter and according to expert The ambient parameter of the suitable crop growth provided is compared, and carries out the preliminary early warning of pest and disease damage;Alert million early warning are to utilize machine The view data of spot sensor collection is processed by device visual pattern treatment technology, it is judged that the classification of pest and disease damage;At information Reason realizes the result to system and relative recording write into Databasce, provides query function simultaneously.Each part is respectively arranged with it Task, modules software kit is integrated into an organic whole.
Described image (is mainly measured by Canon's EOS7D camera and environmental parameter sensor with environmental parameter acquisition system Parameters of temperature, humidity, light intensity) composition;The data that image is measured with data collecting system pass to figure by the way of being wirelessly transferred As processing system.
Described Canon EOS7D camera major parameter index is: camera lens model: EF-S 18-135mm f/3.5-5.6 IS;Real focal length: f=18-135mm;Size sensor APS picture (22.3*14.9mm);Highest resolution 5184 × 3456;Shadow As processor DIGIC 4+DIGIC 4;View finder: (type: eye flat pentaprism visual field rate: vertical/horizontal direction about 100%;Put Big multiplying power: about 1.0 times (-1m uses 50mm camera lens to focus unlimited distance);Eyespot: about 22mm(from eyepiece lens central authorities- 1m) built-in diopter regulation :-3.0-+1.0m(dpt);Focusing screen: fixed;Composition assists: grid lines and electronic level; Reflective mirror: fast hollow depth of field previewing).
Described image processing system is formed with alert million early warning and information processing by warning source early warning;First carried out by alert source early warning Preliminary early warning, then pest and disease damage is identified by warning million early warning and classifies.It is equipped with the information processing for query history record simultaneously Function.
Described alert source early warning is to be obtained ambient parameter (temperature DEG C, humidity %, light intensity by on-the-spot multiple environmental sensor Lux), the ambient parameter of real time environment parameter with the suitable crop growth provided according to expert is compared, gives timely Go out early warning information, just can the generation of pre-preventing disease and pest before the most not falling ill.
Described police million early warning is by image filtering, image segmentation, feature extraction, morphological operation, image sharpening, training Self-learning module forms.Described police million early warning is the core of whole system, it is achieved the Classification and Identification to pest and disease damage, directly affects The early warning effect of system.
Described image filtering mainly has the filtering modes such as medium filtering, mean filter, KNN smothing filtering, threshold filter. Thus realize image gathering, quantify, transmit during the noise of generation be filtered, to reduce noise to successive image The impact processed and identify.
Described image segmentation mainly has the segmentation of OTSU automatic threshold segmentation, colour, automatic threshold segmentation, One-Dimensional Maximum-Entropy The partitioning schemes such as method segmentation.Realize image after pretreatment is split, be partitioned into complete scab, for subsequent extracted feature Preparing, it is the most abundant that image segmentation the most completely will directly affect extraction feature.
Scab pattern feature (perimeter L, area S, circularity C, complexity E) and color are mainly extracted in described feature extraction Feature (tone H, color saturation S, brightness I), these features well have expressed the substantive characteristics of every kind of scab, the spy obtained Levying parameter is the important evidence differentiating scab kind.
Described image sharpening mainly has Laplace operator, prewitt operator, gradient operator, kirsch operator, sobel Operator.In order to the segmentation of beneficially image can take different sharpening modes, segmentation is made to reach best effect.
Described morphological operation Main Means has out operation and closed operation.Morphological operation is primarily directed to segment Image, takes suitable morphological operation according to the effect segmented, in order to extract feature.
Described training is learnt by oneself module and is mainly comprised training and identify two modules.What training module was taked has supervision instruction Practice, before identification, i.e. take the view data input system of substantial amounts of known class, set up feature database.The process identified i.e. inputs Image to be identified differentiates image kind with the class libraries of known feature according to Intelligent Recognition algorithm.
The described information processing function makes software directly be connected with database (SQL serve 2008), it is achieved to system Result and relative recording write into Databasce, provide query function so that user can be with real-time query pest and disease damage simultaneously History processes record, understands morbidity course.
Conceiving according to foregoing invention, the present invention uses following technical proposals:
A kind of pest and disease damage early warning system based on machine vision and method, it is characterised in that comprise Canon's EOS7D camera (1) peace It is loaded on fixed position, warmhouse booth corner, for the temperature image data acquiring of indoor crops, ambient parameter integrated sensor (2) peace It is loaded on warmhouse booth top, is positioned at greenhouse central authorities for the various environmental parameters data acquisition of indoor, greenhouse, image processing system (3) In control room, it is used for the view data gathered in greenhouse and ambient parameter data processes, record.Canon's EOS7D camera (1) and ambient parameter integrated sensor (2) connect image processing system;
Described Canon EOS7D camera (1) major parameter index is: valid pixel 18,000,000;Real focal length: f=18-135mm;Literary composition Part form: JPEG, RAW (14), can record RAW+JPEG simultaneously.
Described ambient parameter integrated sensor (2) is formed by temperature, humidity, light intensity various environmental parameters set of sensors; Various ambient parameters in measuring greenhouse, utilize wireless network transmissions to image processing system (3), are used for warning source early warning Foundation.
Described image processing system (3) specifically includes:
Alert source warning module (3-1), obtains ambient parameter, real time environment parameter and farming according to on-the-spot multiple environmental sensor Thing suitable growth ambient parameter carries out coupling and provides preliminary early warning, and at software interface to information warning.
Alert million warning modules (3-2), on the basis of alert source early warning, obtain picture number according to on-the-spot Canon EOS7D camera According to, utilize image processing techniques in machine vision that view data is processed.By pretreatment, feature extraction, to pest and disease damage Kind is identified classification;
Message processing module (3-3), result and the relative recording write into Databasce to system, also provide for inquiring about merit simultaneously Can so that user's real-time query pest and disease damage history processes record, understand morbidity course.
A kind of pest and disease damage early warning system based on machine vision and method, use said system to operate, and its feature exists As follows in operating procedure:
Step 1: Canon's EOS7D camera (1) gathered a secondary data with ambient parameter integrated sensor (2) every 3 hours, and led to Cross wireless network and send data to image processing system (3).
Step 2: in image processing system (3), alert source warning module (3-1) starts, by the ambient parameter number of collection in worksite Mate according to pre-set expertise numerical value, it may be judged whether in the reasonable scope.
Step 3: if ambient parameter data is the most in the reasonable scope, then start alert million warning modules (3-2).For Canon The view data that EOS7D camera (1) gathers carries out image procossing, has discriminated whether pest and disease damage, and the class of pest and disease damage further Not.And provide early warning information in time.
Step 4: message processing module (3-3), for alert source warning module (3-1) and the place of alert million warning modules (3-2) Reason data and result write into Databasce are to be checked.
The present invention compared with prior art, has and the most obviously highlights substantive distinguishing features and remarkable advantage:
The pest and disease damage early warning by machine vision technique application with crops of novelty of the present invention, uses advanced person's the most at the scene Sensor replaces manual detection and achieves the pest and disease damage intellectuality early warning of two dimensions from environmental change to aura, and is dividing Cut and make optimization on algorithm and Intelligent Recognition algorithm, improve promptness and the accuracy of early warning, significantly have updated the efficiency of management Pattern.
Accompanying drawing explanation
Fig. 1 is disease pest early warning system structural representation
Fig. 2 image and environmental parameter acquisition system
Fig. 3 is alert source early warning runnable interface figure
Fig. 4 is alert million early warning runnable interface figures
Fig. 5 is image filtering, segmentation, feature extraction surface chart
Fig. 6 is image recognition early warning surface chart
Fig. 7 is that system information processes surface chart.
Detailed description of the invention
By making the early warning architectural feature to the present invention and effect of being reached have a better understanding and awareness, in order to excellent The embodiment of choosing and accompanying drawing coordinate detailed description, are described as follows:
Embodiment one:
Visit Fig. 1 ~ ~ Fig. 7, this pest and disease damage early warning system based on machine vision and method, it is characterised in that comprise Canon EOS7D camera (1) is installed on fixed position, warmhouse booth corner, for the temperature image data acquiring of indoor crops, ambient parameter Integrated sensor (2) is installed on warmhouse booth top, for the various environmental parameters data acquisition of indoor, greenhouse, image processing system (3) greenhouse central control room it is positioned at, for the view data and the ambient parameter data that gather in greenhouse are processed, remembered Record.Canon's EOS7D camera (1) and ambient parameter integrated sensor (2) connect image processing system;
Embodiment two: the present embodiment is essentially identical with embodiment one, and special feature is as follows:
Described Canon EOS7D camera (1) major parameter index is: valid pixel 18,000,000;Real focal length: f=18-135mm;Literary composition Part form: JPEG, RAW (14), can record RAW+JPEG simultaneously.
Described ambient parameter integrated sensor (2) is formed by temperature, humidity, light intensity various environmental parameters set of sensors; Various ambient parameters in measuring greenhouse, utilize wireless network transmissions to image processing system (3), are used for warning source early warning Foundation.
Described image processing system (3) specifically includes:
Alert source warning module (3-1), obtains ambient parameter, real time environment parameter and farming according to on-the-spot multiple environmental sensor Thing suitable growth ambient parameter carries out coupling and provides preliminary early warning, and at software interface to information warning.
Alert million warning modules (3-2), on the basis of alert source early warning, obtain picture number according to on-the-spot Canon EOS7D camera According to, utilize image processing techniques in machine vision that view data is processed.By pretreatment, feature extraction, to pest and disease damage Kind is identified classification;
Message processing module (3-3), result and the relative recording write into Databasce to system, also provide for inquiring about merit simultaneously Can so that user's real-time query pest and disease damage history processes record, understand morbidity course.
Embodiment three:
This pest and disease damage early warning system based on machine vision and method, use said system to operate, it is characterised in that operation Step is as follows:
Step 1: Canon's EOS7D camera (1) gathered a secondary data with ambient parameter integrated sensor (2) every 3 hours, and led to Cross wireless network and send data to image processing system (3).
Step 2: in image processing system (3), alert source warning module (3-1) starts, by the ambient parameter number of collection in worksite Mate according to pre-set expertise numerical value, it may be judged whether in the reasonable scope.
Step 3: if ambient parameter data is the most in the reasonable scope, then start alert million warning modules (3-2).For Canon The view data that EOS7D camera (1) gathers carries out image procossing, has discriminated whether pest and disease damage, and the class of pest and disease damage further Not.And provide early warning information in time.
Step 4: message processing module (3-3), for alert source warning module (3-1) and the place of alert million warning modules (3-2) Reason data and result write into Databasce are to be checked.
Shown in Fig. 1 ~ ~ Fig. 7, this pest and disease damage early warning system based on machine vision and method are mainly by image and ambient parameter Acquisition system and image processing system (mainly comprising the early warning of alert source, alert million early warning, information processing three part composition), each function mould The mutually complementary overall work task of having arranged in pairs or groups of block.
First, when running software, system calls the site environment data parameters that in database, on-the-spot each sensor is passed back (temperature DEG C, humidity %, light intensity Lux), and show that now program backstage is existing these on the interface of alert source early warning as shown in Figure 3 The suitable ambient parameter excursion that the ambient parameter of field is suitable with the crops according to expert advice is compared, it is judged that this Time ambient parameter whether in suitable scope, and provide corresponding treatment advice, and show on the interface of alert source early warning.This Sample realizes the preliminary early warning to pest and disease damage early warning, prevents before morbidity.
On alert million interfaces, the view data parameter at the system scene of calling shows on interface (as shown in Figure 4) and carries out Corresponding process.As it is shown in figure 5, image is via medium filtering, and split with OTSU automatic threshold segmentation algorithm, divided The complete scab cut.On this basis, program utilizes the full screen scanning to image to extract scab pattern feature (girth simultaneously L, area S, circularity C, complexity E) and color characteristic (tone H, color saturation S, brightness I), and this characteristic parameter is shown in real time Show on software interface (as shown in Figure 5), and by arest neighbors sorting algorithm (kNN) scab is identified classification, and be given and sentence Other result (as shown in Figure 5).And in the write into Databasce during fructufy that these process, in order to follow-up inquiry and management.
On the interface of information processing, process record and the relevant parameter of recent system can be shown as shown in Figure 7 in real time, Can also from database the record of query history, it is simple to complete monitoring and subsequent calls related data for pest and disease damage enter Row research.
At the scene under the cooperation of sensor, native system achieves from alert source early warning to alert million early warning dual pest and disease damage early warning, Be equipped with offer user can be with the information processing function of real-time query early warning record simultaneously.First fitted with crops by real time environment parameter Preferably growing environment parameter carries out coupling and provides preliminary early warning, then uses in machine vision image processing techniques to realtime graphic number According to carrying out processing (filter, split, feature extraction, identification classification), it is achieved to early blight of tomato and leaf mold automatically identify with Classification, provides the pest and disease damage incidence of current crops, provides the user decision support and historical information record queries.The biggest Decrease greatly manpower and materials, improve again the efficiency of crops in greenhouse pest management simultaneously.
The general principle of the present invention, principal character and advantages of the present invention have more than been shown and described.The technology of the industry The personnel simply present invention it should be appreciated that the present invention is not restricted to the described embodiments, described in above-described embodiment and specification Principle, the present invention also has various changes and modifications without departing from the spirit and scope of the present invention, these change and Improvement both falls within the range of claimed invention.The protection domain of application claims by appending claims and Equivalent defines.

Claims (5)

1. a pest and disease damage early warning system based on machine vision and method, it is characterised in that comprise Canon's EOS7D camera (1), Ambient parameter integrated sensor (2), image processing system (3);It is characterized in that,
Described Canon EOS7D camera, (1) is installed on fixed position, warmhouse booth corner, for the view data of temperature indoor crops Gather;
Described ambient parameter integrated sensor, (2) are installed on warmhouse booth top, for indoor, greenhouse various environmental parameters data Gather;
Described image processing system, (3) are positioned at greenhouse central control room, for the view data gathered in greenhouse and environment Supplemental characteristic carries out processing, record;
Described Canon's EOS7D camera (1) and ambient parameter integrated sensor (2) connect image processing system.
Pest and disease damage early warning system based on machine vision the most according to claim 1, is characterized in that, described Canon EOS7D camera (1) major parameter index is: valid pixel 18,000,000;Real focal length: f=18-135mm;File format: JPEG, RAW (14), can record RAW+JPEG simultaneously.
Pest and disease damage early warning system based on machine vision the most according to claim 1, is characterized in that, described ambient parameter Integrated sensor (2) is formed by temperature, humidity, light intensity various environmental parameters set of sensors;Various in measuring greenhouse Ambient parameter, utilizes wireless network transmissions to image processing system (3), is used for warning the foundation of source early warning.
Pest and disease damage early warning system based on machine vision the most according to claim 1, it is characterised in that described image procossing System (3) specifically includes:
Alert source warning module (3-1), obtains ambient parameter, real time environment parameter and farming according to on-the-spot multiple environmental sensor Thing suitable growth ambient parameter carries out coupling and provides preliminary early warning, and at software interface to information warning;
Alert million warning modules (3-2), on the basis of alert source early warning, obtain view data, profit according to on-the-spot Canon EOS7D camera By image processing techniques in machine vision, view data is processed, by pretreatment, feature extraction, pest species is entered Row identifies classification;
Message processing module (3-3), result and the relative recording write into Databasce to system, also provide for inquiring about merit simultaneously Can so that user's real-time query pest and disease damage history processes record, understand morbidity course.
5. pest and disease damage early warning system based on machine vision and a method, use according to claim 1 based on machine The pest and disease damage early warning system of vision operates, it is characterised in that operating procedure is as follows:
Step 1: Canon's EOS7D camera (1) gathered a secondary data with ambient parameter integrated sensor (2) every 3 hours, and passed through Wireless network sends data to image processing system (3);
Step 2: in image processing system (3), alert source warning module (3-1) starts, by the ambient parameter data of collection in worksite with Pre-set expertise numerical value mates, it may be judged whether in the reasonable scope;
Step 3: if ambient parameter data is the most in the reasonable scope, then start alert million warning modules (3-2), for Canon EOS7D The view data that camera (1) gathers carries out image procossing, has discriminated whether pest and disease damage, and the classification of pest and disease damage further, and Provide early warning information in time;
Step 4: message processing module (3-3), for alert source warning module (3-1) and the process number of alert million warning modules (3-2) According to and result write into Databasce to be checked.
CN201610254139.8A 2016-04-23 2016-04-23 Machine vision based pre-warning system and method for pest and disease damage Pending CN105850930A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610254139.8A CN105850930A (en) 2016-04-23 2016-04-23 Machine vision based pre-warning system and method for pest and disease damage

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610254139.8A CN105850930A (en) 2016-04-23 2016-04-23 Machine vision based pre-warning system and method for pest and disease damage

Publications (1)

Publication Number Publication Date
CN105850930A true CN105850930A (en) 2016-08-17

Family

ID=56632698

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610254139.8A Pending CN105850930A (en) 2016-04-23 2016-04-23 Machine vision based pre-warning system and method for pest and disease damage

Country Status (1)

Country Link
CN (1) CN105850930A (en)

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106779188A (en) * 2016-11-30 2017-05-31 深圳前海弘稼科技有限公司 Plant pest Forecasting Methodology and device in a kind of plantation equipment
CN106780443A (en) * 2016-11-30 2017-05-31 深圳前海弘稼科技有限公司 The method for early warning of crop pest and the prior-warning device of crop pest
CN106846462A (en) * 2016-12-30 2017-06-13 北京农业信息技术研究中心 Insect identifying device and method based on three-dimensional simulation
CN107168367A (en) * 2017-06-08 2017-09-15 中科院合肥技术创新工程院 Accurate pesticide spraying system based on machine vision industry
CN107272620A (en) * 2017-06-23 2017-10-20 深圳市盛路物联通讯技术有限公司 A kind of method and device of the intelligent monitoring greenhouse based on Internet of Things
CN107301605A (en) * 2017-06-29 2017-10-27 深圳前海弘稼科技有限公司 The control method and device of crop pest
CN107357271A (en) * 2017-06-30 2017-11-17 深圳前海弘稼科技有限公司 The prevention and controls of chamber crop pest and disease damage, preventing and treating system
CN108040997A (en) * 2017-12-25 2018-05-18 仲恺农业工程学院 A kind of insect pest monitoring method based on machine vision
WO2019126971A1 (en) * 2017-12-25 2019-07-04 仲恺农业工程学院 Pest disaster monitoring method based on machine vision
CN110167344A (en) * 2016-11-11 2019-08-23 生物生态服务提供商 System and method for detecting flight animal
CN110427922A (en) * 2019-09-03 2019-11-08 陈�峰 One kind is based on machine vision and convolutional neural networks pest and disease damage identifying system and method
IT201900002249A1 (en) * 2019-02-15 2020-08-15 Agrorobotica S R L System and method of predicting the risk of insect attack
CN112034912A (en) * 2020-09-03 2020-12-04 山东锋士信息技术有限公司 Greenhouse crop disease control method based on real-time feedback
CN112055079A (en) * 2020-09-03 2020-12-08 华艺生态园林股份有限公司 Disease and pest monitoring and early warning system based on cloud computing platform
CN114342717A (en) * 2021-12-27 2022-04-15 深圳市金阳盛城市服务集团有限公司 Insect pest detecting and reporting method, device, equipment and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1462913A (en) * 2003-05-15 2003-12-24 沈佐锐 Intelligent system for monitoring healthy of ecology in greenhouse
CN100493212C (en) * 2007-05-24 2009-05-27 中国科学院合肥物质科学研究院 Intelligent early warning system for field crop pest and disease disasters
CN101938512A (en) * 2010-08-13 2011-01-05 仲恺农业工程学院 Internet of thing based automatic monitoring system of crop disease and pest image information
CN103139937A (en) * 2013-03-12 2013-06-05 山东科技大学 Crop disease and pest information real-time collection and interactive service technology and system based on mobile terminal
US20140259898A1 (en) * 2013-03-15 2014-09-18 Stephen Jens Selectively eradicating plants
CN204482814U (en) * 2015-03-17 2015-07-22 李玉杰 A kind of autonomous check processing device of damage by disease and insect being applicable to green house of vegetables

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1462913A (en) * 2003-05-15 2003-12-24 沈佐锐 Intelligent system for monitoring healthy of ecology in greenhouse
CN100493212C (en) * 2007-05-24 2009-05-27 中国科学院合肥物质科学研究院 Intelligent early warning system for field crop pest and disease disasters
CN101938512A (en) * 2010-08-13 2011-01-05 仲恺农业工程学院 Internet of thing based automatic monitoring system of crop disease and pest image information
CN103139937A (en) * 2013-03-12 2013-06-05 山东科技大学 Crop disease and pest information real-time collection and interactive service technology and system based on mobile terminal
US20140259898A1 (en) * 2013-03-15 2014-09-18 Stephen Jens Selectively eradicating plants
CN204482814U (en) * 2015-03-17 2015-07-22 李玉杰 A kind of autonomous check processing device of damage by disease and insect being applicable to green house of vegetables

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
田杰: "基于图像分析的小麦叶部病害识别方法研究", 《中国博士学位论文全文数据库信息科技辑》 *

Cited By (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110167344A (en) * 2016-11-11 2019-08-23 生物生态服务提供商 System and method for detecting flight animal
CN106780443A (en) * 2016-11-30 2017-05-31 深圳前海弘稼科技有限公司 The method for early warning of crop pest and the prior-warning device of crop pest
CN106779188A (en) * 2016-11-30 2017-05-31 深圳前海弘稼科技有限公司 Plant pest Forecasting Methodology and device in a kind of plantation equipment
CN106846462A (en) * 2016-12-30 2017-06-13 北京农业信息技术研究中心 Insect identifying device and method based on three-dimensional simulation
CN106846462B (en) * 2016-12-30 2019-12-17 北京农业信息技术研究中心 insect recognition device and method based on three-dimensional simulation
CN107168367A (en) * 2017-06-08 2017-09-15 中科院合肥技术创新工程院 Accurate pesticide spraying system based on machine vision industry
CN107272620A (en) * 2017-06-23 2017-10-20 深圳市盛路物联通讯技术有限公司 A kind of method and device of the intelligent monitoring greenhouse based on Internet of Things
CN107301605A (en) * 2017-06-29 2017-10-27 深圳前海弘稼科技有限公司 The control method and device of crop pest
CN107357271B (en) * 2017-06-30 2018-07-17 深圳春沐源控股有限公司 The control method of chamber crop pest and disease damage, prevention system
CN107357271A (en) * 2017-06-30 2017-11-17 深圳前海弘稼科技有限公司 The prevention and controls of chamber crop pest and disease damage, preventing and treating system
CN108040997B (en) * 2017-12-25 2020-09-11 仲恺农业工程学院 Insect pest monitoring method based on machine vision
WO2019126971A1 (en) * 2017-12-25 2019-07-04 仲恺农业工程学院 Pest disaster monitoring method based on machine vision
CN108040997A (en) * 2017-12-25 2018-05-18 仲恺农业工程学院 A kind of insect pest monitoring method based on machine vision
US10729117B2 (en) 2017-12-25 2020-08-04 Zhongkai University Of Agriculture And Engineer Pest monitoring method based on machine vision
IT201900002249A1 (en) * 2019-02-15 2020-08-15 Agrorobotica S R L System and method of predicting the risk of insect attack
WO2020165701A1 (en) * 2019-02-15 2020-08-20 AGROROBOTICA S.r.l. Insect attack risk prediction system and method
CN110427922A (en) * 2019-09-03 2019-11-08 陈�峰 One kind is based on machine vision and convolutional neural networks pest and disease damage identifying system and method
CN112034912A (en) * 2020-09-03 2020-12-04 山东锋士信息技术有限公司 Greenhouse crop disease control method based on real-time feedback
CN112055079A (en) * 2020-09-03 2020-12-08 华艺生态园林股份有限公司 Disease and pest monitoring and early warning system based on cloud computing platform
CN112055079B (en) * 2020-09-03 2022-08-23 华艺生态园林股份有限公司 Disease and pest monitoring and early warning system based on cloud computing platform
CN114342717A (en) * 2021-12-27 2022-04-15 深圳市金阳盛城市服务集团有限公司 Insect pest detecting and reporting method, device, equipment and storage medium

Similar Documents

Publication Publication Date Title
CN105850930A (en) Machine vision based pre-warning system and method for pest and disease damage
Sun et al. Northern maize leaf blight detection under complex field environment based on deep learning
JP2019520632A (en) Weed recognition in the natural environment
CN101701906A (en) Method and device for detecting stored-grain insects based on near infrared super-spectral imaging technology
CN101021939A (en) Computer image processing-based crops disease diagnosing system
CN102759528A (en) Method for detecting diseases of crop leaves
CN104813993B (en) Small agricultural pests automated watch-keeping facility and method based on machine vision
Xu et al. Wheat ear counting using K-means clustering segmentation and convolutional neural network
CN110532961B (en) Semantic traffic light detection method based on multi-scale attention mechanism network model
CN107609600A (en) A kind of greenhouse insect-sticking plate insect automatic recognition classification method and system
CN109672863A (en) A kind of construction personnel's safety equipment intelligent monitoring method based on image recognition
CN106332855A (en) Automatic early warning system for pests and diseases
CN109325495A (en) A kind of crop image segmentation system and method based on deep neural network modeling
CN112613454A (en) Electric power infrastructure construction site violation identification method and system
CN102915432A (en) Method and device for extracting vehicle-bone microcomputer image video data
CN110458082A (en) A kind of city management case classification recognition methods
CN114359727A (en) Tea disease identification method and system based on lightweight optimization Yolo v4
CN111179216A (en) Crop disease identification method based on image processing and convolutional neural network
CN109711348A (en) Intelligent monitoring method and system based on the long-term real-time architecture against regulations in hollow panel
Zheng et al. Real-time vegetables recognition system based on deep learning network for agricultural robots
Quan et al. Two-Stream Dense Feature Fusion Network Based on RGB-D Data for the Real-Time Prediction of Weed Aboveground Fresh Weight in a Field Environment
Ärje et al. Automatic flower detection and classification system using a light-weight convolutional neural network
CN107064159A (en) A kind of apparatus and system that growth tendency is judged according to the detection of plant yellow leaf
CN111967441A (en) Crop disease analysis method based on deep learning
CN109287477A (en) A kind of screening technique and device of the capsicum variety of tolerance to low temperature and weak light

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into 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: 20160817