CN108876787A - A kind of sick monitoring master control borad of crops based on deep learning - Google Patents
A kind of sick monitoring master control borad of crops based on deep learning Download PDFInfo
- Publication number
- CN108876787A CN108876787A CN201810870335.7A CN201810870335A CN108876787A CN 108876787 A CN108876787 A CN 108876787A CN 201810870335 A CN201810870335 A CN 201810870335A CN 108876787 A CN108876787 A CN 108876787A
- Authority
- CN
- China
- Prior art keywords
- master control
- module
- control borad
- deep learning
- sick
- 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
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
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
-
- 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
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30188—Vegetation; Agriculture
Abstract
The invention discloses a kind of sick monitoring master control borads of crops based on deep learning, belong to, and structure includes mainboard MCU, CMOS camera module and NB-IOT module, the I of mainboard MCU2C interface is connect with the SCCB interface of CMOS camera module, and mainboard MCU is connect by UART with NB-IOT module.Compared to the prior art the sick monitoring master control borad of a kind of crops based on deep learning of the invention, has the characteristics that at low cost, monitoring effect is good, is conducive to mass market and promotes.
Description
Technical field
The present invention relates to crop monitoring technical field, the sick monitoring of specifically a kind of crops based on deep learning
Master control borad.
Background technique
Nowadays, with the continuous improvement of China's scientific and technological level, agricultural automation horizontal application is also more and more extensive, very much
Farm realizes unattended automatic management system, realizes the full-automatic control from irrigation, fertilising, ventilation and alarm.Make
Object monitoring system needs accurately estimate the growing environments of various crops, also can all kinds of crops of tracking and monitoring in different lifes
Long-term growing way is monitored the growth of crops to adopt an effective measure in time as needed, guarantees when annual output
Steady growth.Traditional crops data monitoring has significant limitations, the more especially limitation due to site environment factor
And the case where inconvenience construction of line, big inconvenience is brought to crops observation.
A kind of existing crops low latitude observation system（Application number：201520223754.3）, set in the multiple places in ground
Multiple groups temperature sensor and humidity sensor are set, every group of temperature sensor and humidity sensor are both connected to a single-chip microcontroller
Input terminal, single-chip microcontroller are connected on a less radio-frequency sending module；One aircraft is set, carries card form electricity on board the aircraft
Brain is connected with optical sensor, camera and less radio-frequency receiving module, the nothing in the interface end of the card computer
Pass through wireless network communication, the card computer and long-range PC between line Receiver Module and less radio-frequency sending module
Pass through cloud data sharing between machine.Although part, which solves bottom, carries out data acquisition by single-chip microcontroller, and passes through wireless network
Network transmits to realize, is monitored by PC machine cloud data；Although part solves the problems, such as crops automatic Observation,
The relatively low industry of crops inherently profit, if farm largely utilizes high-tech product, such as raspberry pie as master again
Plate is controlled, agricultural cost is greatly improved, reduces the market competitiveness.
Summary of the invention
Technical assignment of the invention is place against the above deficiency, provides that at low cost, monitoring effect is good, pushes away conducive to mass market
A kind of sick monitoring master control borad of wide crops based on deep learning.
The technical solution adopted by the present invention to solve the technical problems is：A kind of sick prison of crops based on deep learning
Survey master control borad, including mainboard MCU, CMOS camera and NB-IOT module, the I of mainboard MCU2C interface and CMOS camera
The connection of SCCB interface, mainboard MCU are connect by UART with NB-IOT module.
Further, preferred structure be further include power management module, the power management module be low pressure difference linearity
Voltage-stablizer.
Further, preferred structure is that the mainboard MCU is the STM32F401RCT6 using Cortex-M4 kernel.
Further, preferred structure is that the mainboard MCU realizes the control to NB-IOT module by AT instruction, main
Plate MCU is using tri- line communications of RXD, TXD, GND.
Further, preferred structure is that the CMOS camera is ov7740 module, and the data of ov7740 module pass through
Parallel interface connects MCU.
A kind of sick monitoring system of crops with the sick monitoring master control borad of the crops based on deep learning, including cloud service
Device, master control borad and camera；
Cloud Server uses linux operating system, convolutional neural networks model is constructed based on open source TensorFlow, for training
Sick crop characteristics of image, and the picture that computing unit is passed back is analyzed with trained convolutional neural networks, if result
It is abnormal then issue alarm；
Master control borad includes mainboard MCU, CMOS camera module and NB-IOT module, the I of mainboard MCU2C interface and CMOS camera
The SCCB interface of module connects, and mainboard MCU is connect by UART with NB-IOT module；Master control borad is protected by TCP and Cloud Server
Long connection status is held, and the picture that camera acquires periodically is uploaded to Cloud Server, by server end united analysis, originally
Ground is not processed；
Camera is connected by camera module with master control borad, for monitoring crops.
The sick monitoring master control borad of a kind of crops based on deep learning of the invention compared to the prior art, beneficial effect
It is as follows：
1, NB-IOT module can solve the drawbacks of raspberry pie WIFI is limited in scope；
2, Image Acquisition, analysis and the upload of the sick monitoring master control borad of the crops based on deep learning may be implemented；
3, still, in comparison but cost substantially reduces with raspberry pie；
4, the I of mainboard MCU2C interface and the SCCB interface of CMOS camera connect, and mainboard MCU passes through UART and NB-IOT module
Connection；To realize MCU to the control generic operation of camera, data connect MCU by parallel interface.
5, power management module can satisfy the power demands of master control borad.
6, this low-power consumption of the sick monitoring of NB-IOT module adaptive crops, long standby, large capacity, upstream data amount demand
Lesser scene.
7, the sick monitoring system of a kind of crops based on deep learning, the system are based on TensorFlow machine learning frame
Sick pattern input system is trained generation corresponding model by frame, terminal device acquire in real time crops leaf image into
Row analysis reaches the timely discovery crops state of an illness if appearance and the very high characteristic point of distortion, send a warning message
Effect, very good solution cause find the problem of crops state of an illness is to delay treatment in time because of manpower shortage.
8, because requirement of real-time is not high, which is taken the photograph using the method for cloud processing data, i.e. terminal computing unit driving
As head acquisition image information, and cloud server is sent by image information and is analyzed and processed using TensorFlow, if point
It analyses result and ill feature occurs, then peasant household is informed by short message mode, the method that can effectively substitute manual patrol is found in time
The state of an illness.
Detailed description of the invention
The following further describes the present invention with reference to the drawings.
Attached drawing 1 is a kind of schematic illustration of the sick monitoring master control borad of crops based on deep learning.
Attached drawing 2 is the annexation figure of master control borad and CMOS camera.
Attached drawing 3 is a kind of working principle block diagram of the sick monitoring system of crops based on deep learning.
Specific embodiment
The present invention will be further explained below with reference to the attached drawings and specific examples.
Embodiment 1：
A kind of sick monitoring master control borad of crops based on deep learning, including mainboard MCU, CMOS camera, NB-IOT module
And power management module；The mainboard MCU realizes the control to NB-IOT module by AT instruction；
The power management module is low pressure difference linear voltage regulator, and concrete model LT3645, maximum 500mA export electric current,
Master control borad power demands can be met.
The mainboard MCU is the STM32F401RCT6 using Cortex-M4 kernel, has 84 MHz dominant frequency, 256 Kb
Flash, 64 K SRAM, I2C interface.
CMOS camera uses ov7740 module, which is an IIC equipment, and sccb interface connects STM32's
I2c interface, to realize that MCU controls generic operation to camera, data connect MCU by parallel interface, and pins corresponding relation is such as
Shown in attached drawing 1；
The invention proposes a kind of sick monitoring master control borads of crops based on deep learning.The master control borad is relatively high using sexual valence
STM32 chip as mainboard MCU, Image Acquisition selects CMOS camera, and network selects NB-IOT module, can solve raspberry pie
The deficiencies of WiFi is limited in scope can realize that the image of the sick monitoring master control borad of the crops based on deep learning is adopted with upper module
Collection, analysis and upload, and cost is but substantially reduced compared with for raspberry pie.
It includes Cloud Server, master that the invention also provides a kind of with the sick monitoring system of crops based on deep learning
Control plate and camera；
Cloud Server uses linux operating system, convolutional neural networks model is constructed based on open source TensorFlow, for training
Sick crop characteristics of image, and the picture that computing unit is passed back is analyzed with trained convolutional neural networks, if result
It is abnormal then issue alarm；
Master control borad includes mainboard MCU, CMOS camera module and NB-IOT module, the I of mainboard MCU2C interface and CMOS camera
The SCCB interface of module connects, and mainboard MCU is connect by UART with NB-IOT module；Master control borad is protected by TCP and Cloud Server
Long connection status is held, and the picture that camera acquires periodically is uploaded to Cloud Server, by server end united analysis, originally
Ground is not processed；
Camera is connected by camera module with master control borad, for monitoring crops.
The technical personnel in the technical field can readily realize the present invention with the above specific embodiments,.But it answers
Work as understanding, the present invention is not limited to above-mentioned several specific embodiments.On the basis of the disclosed embodiments, the technology
The technical staff in field can arbitrarily combine different technical features, to realize different technical solutions.
Claims (6)
1. a kind of sick monitoring master control borad of crops based on deep learning, which is characterized in that imaged including mainboard MCU, CMOS
Head module and NB-IOT module, the I of mainboard MCU2C interface is connect with the SCCB interface of CMOS camera module, and mainboard MCU passes through
UART is connect with NB-IOT module.
2. the sick monitoring master control borad of a kind of crops based on deep learning according to claim 1, which is characterized in that also
Including power management module, the power management module is low pressure difference linear voltage regulator.
3. the sick monitoring master control borad of a kind of crops based on deep learning according to claim 1, which is characterized in that institute
The mainboard MCU stated is the STM32F401RCT6 using Cortex-M4 kernel.
4. the sick monitoring master control borad of a kind of crops based on deep learning according to claim 3, which is characterized in that institute
The mainboard MCU stated realizes the control to NB-IOT module by AT instruction, and mainboard MCU is logical using tri- lines of RXD, TXD, GND
Letter.
5. the sick monitoring master control borad of a kind of crops based on deep learning according to claim 1, which is characterized in that institute
The CMOS camera module stated is ov7740 module, and the data of ov7740 module connect MCU by parallel interface.
6. a kind of sick monitoring system of crops with the sick monitoring master control borad of the crops based on deep learning, feature exist
In, including Cloud Server, master control borad and camera；
Cloud Server uses linux operating system, convolutional neural networks model is constructed based on open source TensorFlow, for training
Sick crop characteristics of image, and the picture that computing unit is passed back is analyzed with trained convolutional neural networks, if result
It is abnormal then issue alarm；
Master control borad includes mainboard MCU, CMOS camera module and NB-IOT module, the I of mainboard MCU2C interface and CMOS camera
The SCCB interface of module connects, and mainboard MCU is connect by UART with NB-IOT module；Master control borad is protected by TCP and Cloud Server
Long connection status is held, and the picture that camera acquires periodically is uploaded to Cloud Server, by server end united analysis, originally
Ground is not processed；
Camera is connected by camera module with master control borad, for monitoring crops.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810870335.7A CN108876787A (en) | 2018-08-02 | 2018-08-02 | A kind of sick monitoring master control borad of crops based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810870335.7A CN108876787A (en) | 2018-08-02 | 2018-08-02 | A kind of sick monitoring master control borad of crops based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108876787A true CN108876787A (en) | 2018-11-23 |
Family
ID=64307471
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810870335.7A Pending CN108876787A (en) | 2018-08-02 | 2018-08-02 | A kind of sick monitoring master control borad of crops based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108876787A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110113575A (en) * | 2019-05-14 | 2019-08-09 | 嘉应学院 | A kind of agriculture feelings information real-time monitoring platform based on NB-IoT |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103985056A (en) * | 2014-05-06 | 2014-08-13 | 北京农业信息技术研究中心 | Method and system for collecting agricultural product production records under WSN farmland free partitions |
| CN106682704A (en) * | 2017-01-20 | 2017-05-17 | 中国科学院合肥物质科学研究院 | Method of disease image identification based on hybrid convolutional neural network fused with context information |
| CN107247957A (en) * | 2016-12-16 | 2017-10-13 | 广州中国科学院先进技术研究所 | A kind of intelligent agricultural product sorting technique and system based on deep learning and cloud computing |
| CN107249042A (en) * | 2017-07-17 | 2017-10-13 | 广东工业大学 | A kind of agricultural monitoring system based on arrowband Internet of Things |
| US20170316307A1 (en) * | 2016-04-29 | 2017-11-02 | Intel Corporation | Dynamic management of numerical representation in a distributed matrix processor architecture |
-
2018
- 2018-08-02 CN CN201810870335.7A patent/CN108876787A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103985056A (en) * | 2014-05-06 | 2014-08-13 | 北京农业信息技术研究中心 | Method and system for collecting agricultural product production records under WSN farmland free partitions |
| US20170316307A1 (en) * | 2016-04-29 | 2017-11-02 | Intel Corporation | Dynamic management of numerical representation in a distributed matrix processor architecture |
| CN107247957A (en) * | 2016-12-16 | 2017-10-13 | 广州中国科学院先进技术研究所 | A kind of intelligent agricultural product sorting technique and system based on deep learning and cloud computing |
| CN106682704A (en) * | 2017-01-20 | 2017-05-17 | 中国科学院合肥物质科学研究院 | Method of disease image identification based on hybrid convolutional neural network fused with context information |
| CN107249042A (en) * | 2017-07-17 | 2017-10-13 | 广东工业大学 | A kind of agricultural monitoring system based on arrowband Internet of Things |
Non-Patent Citations (2)
| Title |
|---|
| 曾文兵: "基于STM32F407的视频采集与传输系统设计", 《万方数据库》 * |
| 汪懋华，李民赞: "《现代精细农业理论与实践》", 30 October 2012, 中国农业大学出版社 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110113575A (en) * | 2019-05-14 | 2019-08-09 | 嘉应学院 | A kind of agriculture feelings information real-time monitoring platform based on NB-IoT |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN205103592U (en) | Aquaculture thing networking monitored control system of area feedback | |
| CN107728680A (en) | A kind of remote pig house environment multiparameter measurement and control system and its method based on LoRa | |
| CN204613795U (en) | A kind of soil fertility integrated management system based on mobile terminal | |
| CN103763516A (en) | Livestock breeding intelligent management system based on internet-of-things and high-definition camera shooting integrated gateway | |
| CN207612812U (en) | A kind of Internet of Things control irrigation unit | |
| CN104731135A (en) | Control device and method for family farm | |
| CN103907571B (en) | A kind of silkworm room based on Internet of Things hasten the hatching of silkworms control method and system | |
| CN204796453U (en) | Live pig system of feeding | |
| CN109407624A (en) | A kind of cowshed environment conditioning system and its regulation method based on humidity-temperature index | |
| CN202904667U (en) | Crop disease identifying system based on mobile terminal | |
| CN103869780A (en) | Smart agriculture greenhouse terminal information processing system | |
| CN205375166U (en) | Agriculture monitored control system of intelligence based on thing networking | |
| CN108613703A (en) | Multiple types data monitoring system and method | |
| CN204496318U (en) | A kind of long-distance monitorng device of home farm | |
| CN108876787A (en) | A kind of sick monitoring master control borad of crops based on deep learning | |
| CN210982781U (en) | Low-power-consumption digital agricultural monitoring station | |
| CN210038479U (en) | Multi-point wireless intelligent monitoring system for livestock and poultry breeding environment parameters | |
| CN206650698U (en) | A kind of reading intelligent agriculture detection control apparatus based on internet | |
| CN204302791U (en) | A kind of water quality monitoring system be applied in aquaculture | |
| CN104764492A (en) | Crop remote accurate plant protection diagnostic method and device | |
| CN113625639A (en) | Agricultural intelligent monitoring system and monitoring method thereof | |
| CN110673483B (en) | Intelligent livestock and poultry breeding system and method based on mobile Internet of things technology | |
| CN112362102A (en) | Monitoring system for immediately monitoring agricultural production environment | |
| CN214315614U (en) | Broiler chicken breeding environment real-time monitoring system based on NB-IoT technology | |
| Wu et al. | An RFID-assisted smart livestock and poultry farming system on the cloud |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181123 |
|
| RJ01 | Rejection of invention patent application after publication |