CN105574897A - Crop growth situation monitoring Internet of Things system based on visual inspection - Google Patents

Crop growth situation monitoring Internet of Things system based on visual inspection Download PDF

Info

Publication number
CN105574897A
CN105574897A CN201510908171.9A CN201510908171A CN105574897A CN 105574897 A CN105574897 A CN 105574897A CN 201510908171 A CN201510908171 A CN 201510908171A CN 105574897 A CN105574897 A CN 105574897A
Authority
CN
China
Prior art keywords
image
module
height
monitoring subsystem
crops
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
CN201510908171.9A
Other languages
Chinese (zh)
Inventor
李伟
徐海明
王儒敬
宋良图
王宁
孔斌
严曙
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.)
Hefei Institutes of Physical Science of CAS
Original Assignee
Hefei Institutes of Physical Science of CAS
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 Hefei Institutes of Physical Science of CAS filed Critical Hefei Institutes of Physical Science of CAS
Priority to CN201510908171.9A priority Critical patent/CN105574897A/en
Publication of CN105574897A publication Critical patent/CN105574897A/en
Pending legal-status Critical Current

Links

Classifications

    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20076—Probabilistic image processing
    • 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

Landscapes

  • Investigating Or Analysing Materials By Optical Means (AREA)

Abstract

The invention discloses a crop growth situation monitoring Internet of Things system based on visual inspection. The crop growth situation monitoring Internet of Things system comprises a plant height monitoring subsystem, a lodging monitoring subsystem and a leaf area index monitoring subsystem. The plant height monitoring subsystem is used for obtaining the relative distance between a crop and a height reference mark by setting the preset height reference mark and then obtaining the actual height of the crop according to the mapping relationship between the relative height and the actual crop height. The lodging monitoring subsystem is used for carrying out ashing processing, Gaussian Blur processing and binarization processing on an original image in sequence and then calculating a lodging image and further calculating the lodging rate according to the result of binarization processing. The improvement on precision and efficiency is facilitated through an automatic image analysis manner. The leaf area index monitoring subsystem is used for calculating the comprehensive coverage degree in combination with the green coverage degree of multiple images after the green coverage degree is obtained and calculating the leaf area index according to the comprehensive coverage degree and the plant height.

Description

The crop growth condition monitoring Internet of things system that a kind of view-based access control model detects
Technical field
The present invention relates to crops monitoring technique field, particularly relate to the crop growth condition monitoring Internet of things system that a kind of view-based access control model detects.
Background technology
China is as large agricultural country, and various proportion of crop planting scope is very vast, variously also to emerge in an endless stream to the research that crops are improved meanwhile.In order to ensure the growth conditions of crops, to provide rational treatment, very important to the Real-Time Monitoring of crops, the test manufacture crops especially in experimental plot, need Real-Time Monitoring especially, obtain detailed data so that as experimental basis.
At present, to the monitoring of crop growth state, be mostly to be realized by staff's site observation, so, working strength is large, wastes time and energy, and work efficiency is difficult to improve.
Summary of the invention
Based on the technical matters that background technology exists, the present invention proposes the crop growth condition monitoring Internet of things system that a kind of view-based access control model detects.
The crop growth condition monitoring Internet of things system that a kind of view-based access control model that the present invention proposes detects, comprises plant height monitoring subsystem, lodging monitoring subsystem and leaf area index monitoring subsystem;
Plant height monitoring subsystem includes the crop map picture of height reference mark for obtaining, and according to the Distance Judgment crops height between crops top and height reference mark;
Crop map picture for obtaining crop map picture, and is carried out ashing process and binary conversion treatment by lodging monitoring subsystem, thus judges crops lodging region according to image texture, and calculates crops lodging rate;
Leaf area index monitoring subsystem is connected with plant height monitoring subsystem, for obtaining the crop map picture from being no less than two angle shots, and calculate the green coverage of each sub-picture by RGB color decomposition, then comprehensive multiple green coverage calculates mixed mulch degree, and calculates leaf area index according to crops height and mixed mulch degree.
Preferably, also comprise comprehensive assessment module, comprehensive assessment module is connected with plant height monitoring subsystem, lodge monitoring subsystem and leaf area index monitoring subsystem respectively, and it is assessed according to crops height, lodging rate and the upgrowth situation of leaf area index to crops.
Preferably, comprehensive assessment module is provided with the threshold value of the corresponding crops height of multiple difference, lodging rate and leaf area index for the growth phase that crops are different, the crops of acquisition height, lodging rate and leaf area index compare with corresponding threshold value by comprehensive assessment module respectively, and judge crop growth situation according to difference.
Preferably, also comprise image acquisition subsystem, it comprises image capture module and image buffer storage module, image capture module is used for from multiple angle Real-time Collection crop map picture and is sent to image buffer storage module and stores, and image capture module is connected with plant height monitoring subsystem, lodge monitoring subsystem and leaf area index monitoring subsystem respectively.
Preferably, plant height monitoring subsystem comprises: height reference mark, image processing module, mapping database and data processing module;
Height reference mark comprises and is no less than an altitude datum point;
Image processing module and image buffer storage model calling, its from image buffer storage module calls include height reference mark crop map picture, and extract crops top to be detected and closest to and higher than crops top altitude datum point between image distance;
Mapping database internal preset has distance height mapping collection, distance height mapping is concentrated and is comprised multipair reference mapping pair, each comprises the distance value crops height value corresponding with distance value with reference in mapping pair, and distance value is the distance between crops top and height reference mark;
Data processing module is connected with image processing module and mapping database respectively, and it infers actual distance value according to image distance, and concentrates the crops height value transferring corresponding actual distance value as object height value from distance height mapping.
Preferably, high any two altitude datum points are distinguished by color, length or shape.
Preferably, the monitoring subsystem that lodges comprises: ashing processing module, Gaussian Blur module, binary conversion treatment module and lodging computing module; Wherein,
Ashing processing module is used for the original image obtaining crops from image buffer storage module, and converts original image to gray level image;
Be preset with a series of Gaussian function in Gaussian Blur module, the relaxation parameter σ of any two Gaussian functions is different; Gaussian Blur module is connected with ashing processing module, and it receives gray level image, and by gray level image respectively with each relaxation parameter σ ncorresponding Gaussian blurring function carries out convolution budget, obtains multiple blurred picture g n;
Binary conversion treatment module and Gaussian Blur model calling, its internal preset has multiple with blurred picture g ndemarcation threshold one to one, and for according to the demarcation threshold of correspondence respectively to blurred picture g ncarry out binary conversion treatment, obtain multiple binary image gb n;
Lodging computing module and binary conversion treatment model calling, its internal preset has the first computation model and the second computation model; Lodging computing module is by multiple binaryzation result gb nsubstitute into the first computation model and carry out comprehensive computing, obtain lodging image R (x, y) of binaryzation, then calculate lodging rate R according to the second computation model and lodging image R (x, y) rite.
Preferably, the first computation model is: λ nfor preset constant; Second computation model is: k yfor scale-up factor.
Preferably, leaf area index monitoring subsystem comprises RGB decomposing module, green coverage computing module and leaf area index computing module;
RGB decomposing module is used for obtaining from image buffer storage module being no less than two original images, the acquisition angles of any two original images is different, RGB decomposing module extracts target image from original image, and RGB color decomposition is carried out to target image, according to G value, binary conversion treatment is carried out to target image, generate binary image;
Green coverage computing module is connected with RGB decomposing module, and it, according to photography geometrical principle, calculates the green coverage R of each secondary binary image n, and according to multiple green coverage R ncalculate mixed mulch degree R result;
Leaf area index computing module is connected with green coverage computing module and plant height monitoring subsystem respectively, and it is according to plant height h and mixed mulch degree R resultjudge the leaf area index BI of target area.
Plant height monitoring subsystem of the present invention, by preset height reference mark, obtains crops and the relative distance of height reference mark, then according to relative distance and actual crops mapping relations highly, obtains the true altitude of crops.
Lodging monitoring subsystem of the present invention carries out ashing process, Gaussian Blur process, binary conversion treatment successively to original image, then calculates lodging image according to binary conversion treatment result, and calculates lodging rate further.By the graphical analysis mode of robotization, be conducive to improving precision and efficiency.
Leaf area index monitoring subsystem of the present invention is by carrying out binary conversion treatment to target image, green point and partially green point are highlighted, then the calculating of green coverage is carried out according to binary image, intelligence degree is high, and, by the setting of the first model, definition that can be especially partially green to green as required regulates, and degree of flexibility is high.In the present invention, after obtaining green coverage, green coverage in conjunction with multiple image calculates and obtains mixed mulch degree, and calculate leaf area index according to mixed mulch degree and plant height, fully take into account in plant growing process, the relation that its leaf area is highly closely connected with it, is conducive to the rationality and the accuracy that improve leaf area calculating.
The present invention is by remote collection image, the pick-up unit of a set of full-automation is set up in the mode of image procossing, for completing infomation detection and the logger task of full time period on a large scale, the biological aspect parameter of the detection plant of intelligence comprises plant height, green coverage, leaf area index.Can set up a set of crops biological aspect index monitoring system based on Internet of Things by the present invention, its automaticity is high, does not need manually to detect on the spot, and by the growing state of camera head remote monitoring crops, work slightly low, monitoring range is wide.
Accompanying drawing explanation
Fig. 1 is the crop growth condition monitoring Internet of things system structural representation of a kind of view-based access control model detection that the present invention proposes.
Embodiment
With reference to Fig. 1, the crop growth condition monitoring Internet of things system that a kind of view-based access control model that the present invention proposes detects, comprises image acquisition subsystem, plant height monitoring subsystem, lodging monitoring subsystem, leaf area index monitoring subsystem and comprehensive assessment module.
Image acquisition subsystem comprises image capture module and image buffer storage module, image capture module is used for from multiple angle Real-time Collection crop map picture and is sent to image buffer storage module and stores, and image capture module is connected with plant height monitoring subsystem, lodge monitoring subsystem and leaf area index monitoring subsystem respectively.
Plant height monitoring subsystem obtains the crop map picture including height reference mark from image buffer storage module, and according to the Distance Judgment crops height between crops top and height reference mark.Plant height monitoring subsystem comprises: height reference mark, image processing module, mapping database and data processing module.
Height reference mark comprises and is no less than an altitude datum point, such as, by arranging stone tablet, can portray markings as altitude datum point on the differing heights line of stone tablet.Wherein, any two altitude datum points are distinguished by color, length or shape.The setting of multiple altitude datum point, is conducive to the precision improving elevation carrection.
Image processing module and image buffer storage model calling, its from image buffer storage module calls include height reference mark crop map picture, and extract crops top to be detected and closest to and higher than crops top altitude datum point between image distance.
Mapping database internal preset has distance height mapping collection, distance height mapping is concentrated and is comprised multipair reference mapping pair, each comprises the distance value crops height value corresponding with distance value with reference in mapping pair, and distance value is the distance between crops top and height reference mark;
Data processing module is connected with image processing module and mapping database respectively, and it infers actual distance value according to image distance, and concentrates the crops height value transferring corresponding actual distance value as object height value from distance height mapping.
Because any two altitude datum points are distinguished by color, length or shape, so, clearly can know the height that each altitude datum point indicates.By obtain closest to and higher than crops top altitude datum point between image distance, the unavailability owing to causing when altitude datum point is hidden by crops can be avoided, distance due to distance altitude datum point when crops can be avoided again shorter is comparatively large, thus fault in enlargement.
In present embodiment, search is concentrated to be not more than the distance value of default float value as target range value with the difference of actual distance value at distance height mapping.Default float value is less, is more conducive to improving computational accuracy, and particularly, default float value can be less than or equal to 10mm, and in present embodiment, default float value is zero.That presets float value is provided with the data storage pressure being beneficial to and reducing distance height mapping collection.
Crop map picture for obtaining crop map picture, and is carried out ashing process and binary conversion treatment by lodging monitoring subsystem, thus judges crops lodging region according to image texture, and calculates crops lodging rate.
Lodging monitoring subsystem comprises: ashing processing module, Gaussian Blur module, binary conversion treatment module and lodging computing module.
Ashing processing module is used for the original image obtaining at least one secondary crops from image buffer storage module, and converts original image to gray level image.
Be preset with a series of Gaussian function in Gaussian Blur module, the relaxation parameter σ of any two Gaussian functions is different.
Gaussian function be a kind of conventional image processing function, relaxation parameter σ determines the shape of two-dimensional Gaussian function.In present embodiment, multiple relaxation parameter σ nchoose and meet following principle:
σ n=2 σ n-1=2 2σ n-2=...=2 nσ 0, wherein σ 0for constant.
In present embodiment, first choose relaxation parameter σ according to the size of imaging multiplying power and real image 0, then according to σ 0σ is obtained successively with above formula 1, σ 2, σ 3σ n-1, σ n, and successively by σ 1, σ 2, σ 3σ n-1, σ nsubstitute into the σ in Gaussian function, obtain a series of Gaussian function.During concrete enforcement, also σ can be selected 0=1.
Gaussian Blur module is connected with ashing processing module, and it receives gray level image, and by gray level image respectively with each relaxation parameter σ ncorresponding Gaussian blurring function carries out convolution budget, obtains multiple blurred picture g n, namely Gaussian Blur module utilizes σ respectively 0, σ 1, σ 2, σ 3σ n-1, σ ncorresponding Gaussian function carries out Gaussian Blur to gray level image, thus obtains a series of blurred picture g 0, g 1, g 2, g 3g n-1, g n.
Binary conversion treatment module and Gaussian Blur model calling, its internal preset has multiple with blurred picture g ndemarcation threshold one to one, and according to the demarcation threshold of correspondence respectively to blurred picture g 0, g 1, g 2, g 3g n-1, g ncarry out binaryzation, obtain multiple binary image gb 0, gb 1, gb 2, gb 3gb n-1, gb n.Concrete, when carrying out binaryzation, in blurred picture, colour is all converted to 0 lower than the some colour of demarcation threshold, and in blurred picture, colour is all converted to 255 higher than the some colour of demarcation threshold.
Lodging computing module and binary conversion treatment model calling, its internal preset has the first computation model and the second computation model.Lodging computing module is by multiple binaryzation result gb nsubstitute into the first computation model and carry out comprehensive computing, obtain lodging image R (x, y) of binaryzation, then calculate lodging rate R according to the second computation model and lodging image R (x, y) rite.
First computation model is:
R ( x , y ) = Σ n ( λ n × gb n ) , λ nfor preset constant.
During concrete enforcement, λ nconstant constant can be selected, i.e. λ n=λ n-1=λ n-2=...=λ 0;
λ nalso can according to formula: λ n=ω 1λ n-1=ω 2λ n-2=...=ω nλ 0carry out value, wherein, ω 1, ω 2, ω nand λ 0be constant.
Second computation model is:
R r it e = Σ y k y Σ x R ( x , y ) , K yfor scale-up factor.
Leaf area index monitoring subsystem comprises RGB decomposing module, green coverage computing module and leaf area index computing module.
RGB decomposing module is used for obtaining from image buffer storage module being no less than two original images, and the acquisition angles of any two original images is different, to avoid the image fault caused because shooting angle is single.RGB decomposing module extracts target image from original image, and target image is the image of monitored area.RGB decomposing module carries out RGB color decomposition to target image, carries out binary conversion treatment according to G value to target image, generates binary image.
Particularly, RGB decomposing module is preset with the first model and green color point set, and target image is carried out RGB color decomposition by RGB decomposing module, extracts G value and meets the color dot of the first model and reflex in green color point set; Then according to green color point set and each color dot position in the target image, binary image is generated for each target image.First model comprises condition: G value > R value, and G value > B value.In this step, all corresponding green color point set of each target image.By binary conversion treatment by the green in target image and partially green color point and other color dots make a distinction, be convenient to subsequent treatment.
Green coverage computing module is connected with RGB decomposing module, and it, according to photography geometrical principle, calculates the green coverage R of each secondary binary image n, and according to multiple green coverage R ncalculate mixed mulch degree R result.
Calculate the green coverage R of binary image ncomputing formula be:
wherein, k yfor scale-up factor, G n(x, y) is green color point.
In present embodiment, extract and have four width target images, in above formula, R n, G nin n can value 1,2,3 or 4, to represent four width binary images respectively.Particularly:
The green coverage of piece image is:
The green coverage of the second width image is:
The green coverage of the 3rd width image is:
The green coverage of the 4th width image is:
Calculate mixed mulch degree R resultformula be:
wherein, λ nfor scale-up factor.
In present embodiment, by the green coverage R to several binary images ncarry out comprehensive computing, single binary image can be avoided due to the image fault error that the shooting angle of the target image of correspondence is complete, optical aberrations causes.That is, in this step, by multiple green coverage R ncomprehensive computing, is conducive to improving mixed mulch degree R resultthe accuracy calculated.
Leaf area index computing module is connected with green coverage computing module and plant height monitoring subsystem respectively, and it is according to plant height h and mixed mulch degree R resultjudge the leaf area index BI of target area.
Particularly, preset leaf area mapping set in leaf area index computing module, include multiple by plant height and mixed mulch degree R in leaf area mapping set resultthe condition subset of composition, any two condition subsets, plant height and mixed mulch degree R resulthas a difference at least, all corresponding leaf area index BI of each condition subset; According to plant height h and mixed mulch degree R resultdirectly can transfer corresponding leaf area index BI from leaf area mapping set.
Comprehensive assessment module is connected with plant height monitoring subsystem, lodge monitoring subsystem and leaf area index monitoring subsystem respectively, and it is assessed according to crops height, lodging rate and the upgrowth situation of leaf area index to crops.
Particularly, comprehensive assessment module is provided with the threshold value of the corresponding crops height of multiple difference, lodging rate and leaf area index for the growth phase that crops are different, the crops of acquisition height, lodging rate and leaf area index compare with corresponding threshold value by comprehensive assessment module respectively, and judge crop growth situation according to difference.
The above; be only the present invention's preferably embodiment; but protection scope of the present invention is not limited thereto; anyly be familiar with those skilled in the art in the technical scope that the present invention discloses; be equal to according to technical scheme of the present invention and inventive concept thereof and replace or change, all should be encompassed within protection scope of the present invention.

Claims (9)

1. a crop growth condition monitoring Internet of things system for view-based access control model detection, is characterized in that, comprises plant height monitoring subsystem, lodging monitoring subsystem and leaf area index monitoring subsystem;
Plant height monitoring subsystem includes the crop map picture of height reference mark for obtaining, and according to the Distance Judgment crops height between crops top and height reference mark;
Crop map picture for obtaining crop map picture, and is carried out ashing process and binary conversion treatment by lodging monitoring subsystem, thus judges crops lodging region according to image texture, and calculates crops lodging rate;
Leaf area index monitoring subsystem is connected with plant height monitoring subsystem, for obtaining the crop map picture from being no less than two angle shots, and calculate the green coverage of each sub-picture by RGB color decomposition, then comprehensive multiple green coverage calculates mixed mulch degree, and calculates leaf area index according to crops height and mixed mulch degree.
2. the crop growth condition monitoring Internet of things system of view-based access control model detection as claimed in claim 1, it is characterized in that, also comprise comprehensive assessment module, comprehensive assessment module is connected with plant height monitoring subsystem, lodge monitoring subsystem and leaf area index monitoring subsystem respectively, and it is assessed according to crops height, lodging rate and the upgrowth situation of leaf area index to crops.
3. the crop growth condition monitoring Internet of things system of view-based access control model detection as claimed in claim 3, it is characterized in that, comprehensive assessment module is provided with the threshold value of the corresponding crops height of multiple difference, lodging rate and leaf area index for the growth phase that crops are different, the crops of acquisition height, lodging rate and leaf area index compare with corresponding threshold value by comprehensive assessment module respectively, and judge crop growth situation according to difference.
4. the crop growth condition monitoring Internet of things system of view-based access control model detection as claimed in claim 1, it is characterized in that, also comprise image acquisition subsystem, it comprises image capture module and image buffer storage module, image capture module is used for from multiple angle Real-time Collection crop map picture and is sent to image buffer storage module and stores, and image capture module is connected with plant height monitoring subsystem, lodge monitoring subsystem and leaf area index monitoring subsystem respectively.
5. the crop growth condition monitoring Internet of things system of view-based access control model detection as claimed in claim 4, it is characterized in that, plant height monitoring subsystem comprises: height reference mark, image processing module, mapping database and data processing module;
Height reference mark comprises and is no less than an altitude datum point;
Image processing module and image buffer storage model calling, its from image buffer storage module calls include height reference mark crop map picture, and extract crops top to be detected and closest to and higher than crops top altitude datum point between image distance;
Mapping database internal preset has distance height mapping collection, distance height mapping is concentrated and is comprised multipair reference mapping pair, each comprises the distance value crops height value corresponding with distance value with reference in mapping pair, and distance value is the distance between crops top and height reference mark;
Data processing module is connected with image processing module and mapping database respectively, and it infers actual distance value according to image distance, and concentrates the crops height value transferring corresponding actual distance value as object height value from distance height mapping.
6. the crop growth condition monitoring Internet of things system of view-based access control model detection as claimed in claim 5, is characterized in that, high any two altitude datum points are distinguished by color, length or shape.
7. the crop growth condition monitoring Internet of things system of view-based access control model detection as claimed in claim 4, is characterized in that, lodging monitoring subsystem comprises: ashing processing module, Gaussian Blur module, binary conversion treatment module and lodging computing module; Wherein,
Ashing processing module is used for the original image obtaining crops from image buffer storage module, and converts original image to gray level image;
Be preset with a series of Gaussian function in Gaussian Blur module, the relaxation parameter σ of any two Gaussian functions is different; Gaussian Blur module is connected with ashing processing module, and it receives gray level image, and by gray level image respectively with each relaxation parameter σ ncorresponding Gaussian blurring function carries out convolution budget, obtains multiple blurred picture g n;
Binary conversion treatment module and Gaussian Blur model calling, its internal preset has multiple with blurred picture g ndemarcation threshold one to one, and for according to the demarcation threshold of correspondence respectively to blurred picture g ncarry out binary conversion treatment, obtain multiple binary image gb n;
Lodging computing module and binary conversion treatment model calling, its internal preset has the first computation model and the second computation model; Lodging computing module is by multiple binaryzation result gb nsubstitute into the first computation model and carry out comprehensive computing, obtain lodging image R (x, y) of binaryzation, then calculate lodging rate R according to the second computation model and lodging image R (x, y) rite.
8. the crop growth condition monitoring Internet of things system of view-based access control model detection as claimed in claim 7, it is characterized in that, the first computation model is: λ nfor preset constant; Second computation model is: k yfor scale-up factor.
9. the crop growth condition monitoring Internet of things system of view-based access control model detection as claimed in claim 4, it is characterized in that, leaf area index monitoring subsystem comprises RGB decomposing module, green coverage computing module and leaf area index computing module;
RGB decomposing module is used for obtaining from image buffer storage module being no less than two original images, the acquisition angles of any two original images is different, RGB decomposing module extracts target image from original image, and RGB color decomposition is carried out to target image, according to G value, binary conversion treatment is carried out to target image, generate binary image;
Green coverage computing module is connected with RGB decomposing module, and it, according to photography geometrical principle, calculates the green coverage R of each secondary binary image n, and according to multiple green coverage R ncalculate mixed mulch degree R result;
Leaf area index computing module is connected with green coverage computing module and plant height monitoring subsystem respectively, and it is according to plant height h and mixed mulch degree R resultjudge the leaf area index BI of target area.
CN201510908171.9A 2015-12-07 2015-12-07 Crop growth situation monitoring Internet of Things system based on visual inspection Pending CN105574897A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510908171.9A CN105574897A (en) 2015-12-07 2015-12-07 Crop growth situation monitoring Internet of Things system based on visual inspection

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510908171.9A CN105574897A (en) 2015-12-07 2015-12-07 Crop growth situation monitoring Internet of Things system based on visual inspection

Publications (1)

Publication Number Publication Date
CN105574897A true CN105574897A (en) 2016-05-11

Family

ID=55884984

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510908171.9A Pending CN105574897A (en) 2015-12-07 2015-12-07 Crop growth situation monitoring Internet of Things system based on visual inspection

Country Status (1)

Country Link
CN (1) CN105574897A (en)

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105872478A (en) * 2016-05-30 2016-08-17 苏州铭冠软件科技有限公司 Agricultural intelligent analyzing and monitoring method based on image processing
CN105955079A (en) * 2016-05-16 2016-09-21 苏州铭冠软件科技有限公司 Agricultural crop fine seed selection system based on internet of things
CN106370110A (en) * 2016-08-30 2017-02-01 深圳前海弘稼科技有限公司 Determination method and system of heights of plants in plantation box
GB2553631A (en) * 2017-06-19 2018-03-14 Earlham Inst Data Processing of images of a crop
CN108171615A (en) * 2017-12-28 2018-06-15 河南中原光电测控技术有限公司 A kind of crops lodging disaster monitoring method and its system
CN108240792A (en) * 2018-01-11 2018-07-03 刘小勇 Crop maturity judgment means and method
CN109272416A (en) * 2018-10-13 2019-01-25 莫彪 A kind of greenhouse corps implant system
CN111024710A (en) * 2019-12-17 2020-04-17 江苏恒宝智能系统技术有限公司 Crop abnormity detection system and method
CN111476488A (en) * 2020-04-09 2020-07-31 吴昊 Quality evaluation and estimation system and method for strain culture and growth products
CN111855653A (en) * 2019-04-25 2020-10-30 河南中原光电测控技术有限公司 Plant drought monitoring method, monitoring module and monitoring device
CN112084921A (en) * 2020-09-01 2020-12-15 无为县年香马蹄种植专业合作社 Method and device for measuring plant growth condition
CN112215522A (en) * 2020-10-29 2021-01-12 中国水利水电科学研究院 Crop growth monitoring system, method, computer equipment and storage medium
CN112633047A (en) * 2019-10-28 2021-04-09 中国科学院地理科学与资源研究所 Visual stereo monitoring device and monitoring method for growth vigor of sedge
CN113628185A (en) * 2021-08-09 2021-11-09 海南青峰生物科技有限公司 Rice plant height measuring method and device based on 5G communication and image recognition processing
CN113870529A (en) * 2021-08-23 2021-12-31 湖北工程学院 Garden monitoring method, device and equipment for dealing with strong wind and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101324427A (en) * 2008-07-31 2008-12-17 华中科技大学 Device and method for automatically measuring greenery area
CN102072745A (en) * 2009-11-20 2011-05-25 中国农业科学院农业资源与农业区划研究所 Remote monitoring-based device, system and method for measuring crop yield in real time
CN102254144A (en) * 2011-07-12 2011-11-23 四川大学 Robust method for extracting two-dimensional code area in image
CN102564593A (en) * 2011-12-30 2012-07-11 河海大学常州校区 Plant growth condition monitoring system based on compute vision and internet of things
JP5020444B2 (en) * 2001-06-29 2012-09-05 独立行政法人農業・食品産業技術総合研究機構 Crop growth measuring device, crop growth measuring method, crop growth measuring program, and computer-readable recording medium recording the crop growth measuring program
CN204831093U (en) * 2015-05-27 2015-12-02 成都溯码信息科技有限公司 Meadow height monitoring device

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5020444B2 (en) * 2001-06-29 2012-09-05 独立行政法人農業・食品産業技術総合研究機構 Crop growth measuring device, crop growth measuring method, crop growth measuring program, and computer-readable recording medium recording the crop growth measuring program
CN101324427A (en) * 2008-07-31 2008-12-17 华中科技大学 Device and method for automatically measuring greenery area
CN102072745A (en) * 2009-11-20 2011-05-25 中国农业科学院农业资源与农业区划研究所 Remote monitoring-based device, system and method for measuring crop yield in real time
CN102254144A (en) * 2011-07-12 2011-11-23 四川大学 Robust method for extracting two-dimensional code area in image
CN102564593A (en) * 2011-12-30 2012-07-11 河海大学常州校区 Plant growth condition monitoring system based on compute vision and internet of things
CN204831093U (en) * 2015-05-27 2015-12-02 成都溯码信息科技有限公司 Meadow height monitoring device

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
张雪芬 等: "自动农业气象观测系统功能与设计", 《应用气象学报》 *

Cited By (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105955079A (en) * 2016-05-16 2016-09-21 苏州铭冠软件科技有限公司 Agricultural crop fine seed selection system based on internet of things
CN105872478A (en) * 2016-05-30 2016-08-17 苏州铭冠软件科技有限公司 Agricultural intelligent analyzing and monitoring method based on image processing
CN106370110A (en) * 2016-08-30 2017-02-01 深圳前海弘稼科技有限公司 Determination method and system of heights of plants in plantation box
GB2553631A (en) * 2017-06-19 2018-03-14 Earlham Inst Data Processing of images of a crop
GB2553631B (en) * 2017-06-19 2019-10-30 Earlham Inst Data Processing of images of a crop
CN108171615A (en) * 2017-12-28 2018-06-15 河南中原光电测控技术有限公司 A kind of crops lodging disaster monitoring method and its system
CN108171615B (en) * 2017-12-28 2021-12-17 河南中原光电测控技术有限公司 Crop lodging disaster monitoring method and system thereof
CN108240792A (en) * 2018-01-11 2018-07-03 刘小勇 Crop maturity judgment means and method
CN109272416A (en) * 2018-10-13 2019-01-25 莫彪 A kind of greenhouse corps implant system
CN109272416B (en) * 2018-10-13 2022-06-03 临沂确信软件技术有限公司 Greenhouse crop planting system
CN111855653A (en) * 2019-04-25 2020-10-30 河南中原光电测控技术有限公司 Plant drought monitoring method, monitoring module and monitoring device
CN111855653B (en) * 2019-04-25 2023-11-28 河南中原光电测控技术有限公司 Plant drought monitoring method, monitoring module and monitoring device
CN112633047A (en) * 2019-10-28 2021-04-09 中国科学院地理科学与资源研究所 Visual stereo monitoring device and monitoring method for growth vigor of sedge
CN111024710B (en) * 2019-12-17 2022-04-08 江苏恒宝智能系统技术有限公司 Crop abnormity detection system and method
CN111024710A (en) * 2019-12-17 2020-04-17 江苏恒宝智能系统技术有限公司 Crop abnormity detection system and method
CN111476488B (en) * 2020-04-09 2021-08-13 乐清市泰博恒电子科技有限公司 Quality evaluation and estimation system and method for strain culture and growth products
CN111476488A (en) * 2020-04-09 2020-07-31 吴昊 Quality evaluation and estimation system and method for strain culture and growth products
CN112084921A (en) * 2020-09-01 2020-12-15 无为县年香马蹄种植专业合作社 Method and device for measuring plant growth condition
CN112215522A (en) * 2020-10-29 2021-01-12 中国水利水电科学研究院 Crop growth monitoring system, method, computer equipment and storage medium
CN113628185A (en) * 2021-08-09 2021-11-09 海南青峰生物科技有限公司 Rice plant height measuring method and device based on 5G communication and image recognition processing
CN113628185B (en) * 2021-08-09 2024-02-13 海南青峰生物科技有限公司 Rice plant height measuring method and device based on 5G communication and image recognition processing
CN113870529A (en) * 2021-08-23 2021-12-31 湖北工程学院 Garden monitoring method, device and equipment for dealing with strong wind and storage medium

Similar Documents

Publication Publication Date Title
CN105574897A (en) Crop growth situation monitoring Internet of Things system based on visual inspection
CN107527352A (en) Remote sensing Ship Target contours segmentation and detection method based on deep learning FCN networks
CN112132874B (en) Calibration-plate-free heterogeneous image registration method and device, electronic equipment and storage medium
Zhang et al. 3D monitoring for plant growth parameters in field with a single camera by multi-view approach
CN104976960A (en) Raindrop physical property observation method and device
CN104318583B (en) Visible light broadband spectrum image registration method
CN114239756B (en) Insect pest detection method and system
CN103090946B (en) Method and system for measuring single fruit tree yield
CN104121850A (en) Canopy density measurement method and device
CN110648020A (en) Greenhouse crop water demand prediction method and device
CN109631766A (en) A kind of wood plank dimension measurement method based on image
CN115687850A (en) Method and device for calculating irrigation water demand of farmland
CN113537293A (en) Wheat lodging area identification method based on unmanned aerial vehicle and full convolution neural network
CN115861859A (en) Slope farmland environment monitoring method and system
CN104089607A (en) Normal case photography forest metrology method through common digital camera
CN109827503B (en) Method and device for accurately positioning field crops
CN105574852A (en) Method and system for detecting plant height based on image identification
CN105844264B (en) It is a kind of based on the recognition methods of tree peony fruit image of the oil of stress
CN108985292A (en) A kind of SAR image CFAR object detection method and system based on multi-scale division
CN103218820A (en) Camera calibration error compensation method based on multi-dimensional characteristics
CN103471514B (en) A kind of garlic stage division based on machine vision and simple linear regression analysis
CN112967257B (en) Subway nut looseness detection method based on visual angle conversion
CN114998425A (en) Target object geographic coordinate positioning method and device based on artificial intelligence
CN114463343A (en) Method and device for automatically extracting contour of coastal zone culture factory
CN106340017B (en) A kind of farmland rice transplanting detection method and system based on image procossing

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

Application publication date: 20160511

RJ01 Rejection of invention patent application after publication