CN104751450B - Paste the number of pest discrimination method and device on colour table in greenhouse - Google Patents
Paste the number of pest discrimination method and device on colour table in greenhouse Download PDFInfo
- Publication number
- CN104751450B CN104751450B CN201510097489.3A CN201510097489A CN104751450B CN 104751450 B CN104751450 B CN 104751450B CN 201510097489 A CN201510097489 A CN 201510097489A CN 104751450 B CN104751450 B CN 104751450B
- Authority
- CN
- China
- Prior art keywords
- colour table
- pest
- image
- component
- stickup
- 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.)
- Expired - Fee Related
Links
Landscapes
- Catching Or Destruction (AREA)
Abstract
The number of pest discrimination method on colour table is pasted the invention provides a kind of greenhouse, including:Stickup colour table picture noise to be counted is removed using color filter method;Obtain the DC component and substrate DC component for pasting colour table image;According to the DC component and substrate DC component, Fourier's index parameters are obtained;Using default index parameters and number of pest model, the number of pest pasted on colour table is obtained according to Fourier's index parameters.The number of pest device for identifying on colour table is pasted present invention also offers a kind of greenhouse, including pastes colour table, camera, fixing device, collector and intelligent terminal.The number of pest discrimination method device on colour table is pasted in the greenhouse provided by the present invention, can recognize the quantity of insect, and simple and fast, degree of accuracy height from colour table image is pasted automatically.
Description
Technical field
The present invention relates to crop pests Prevention Technique field, and in particular to pastes the number of pest on colour table in a kind of greenhouse
Discrimination method and device.
Background technology
The general habit by the yellow green that becomes of insect, some insects color tendency that becomes is particularly strong, thus can using the habit come
Trapping pests.The habit for becoming yellow according to insect or becoming green, makes yellow plate or backboard can be used to trap specific insect, and colour table is lured
Greenhouse insect can effectively be killed by killing, and substantially reduce spraying times and pesticide dosage, reduce environmental pollution, lifted quality of vegetable, kept away
Exempt from largely to kill pest natural enemy, it is to avoid insect develops immunity to drugs.
And the number of pest on colour table is counted, can estimate and monitor crop field or greenhouse in the class pest population
The dynamic change of quantity, to take effective pest control measure immediately.But, at present for pasting number of pest on colour table
Statistics is still manually to check as Main Means, and this method labor intensity is big, and operating efficiency is low.
The content of the invention
For defect of the prior art, the present invention provide a kind of greenhouse paste number of pest discrimination method on colour table and
Device, can recognize the quantity of insect, and simple and fast, degree of accuracy height from colour table image is pasted automatically.
In a first aspect, pasting the number of pest discrimination method on colour table, methods described bag the invention provides a kind of greenhouse
Include:
Stickup colour table picture noise to be counted is removed using color filter method;
Obtain the DC component and substrate DC component for pasting colour table image;
According to the DC component and substrate DC component, Fourier's index parameters are obtained;
Using default index parameters and number of pest model, the stickup color is obtained according to Fourier's index parameters
Number of pest on plate.
Preferably, the use color filter method removes stickup colour table picture noise to be counted, including:
If the stickup colour table is yellow, according to the red component R of described image>100 remove noise;
If the stickup colour table is blueness, according to the red component R of described image<180 and blue component B>150 remove
Noise.
Preferably, the DC component and substrate DC component for obtaining the stickup colour table image, including:
The stickup colour table image is converted into bianry image, and Fourier transformation is carried out to the bianry image, is obtained
DC component;
The image that blank pastes colour table is converted into bianry image, and Fourier transformation is carried out to the bianry image, is obtained
Obtain substrate DC component.
Preferably, it is described according to the DC component and substrate DC component, Fourier's index parameters are obtained, including:
According to following formula, calculating obtains Fourier's index parameters:
Wherein, DpestFor Fourier's index parameters, D0For substrate DC component, DiFor stickup colour table image to be counted
DC component.
Preferably, it is described to use default index parameters and number of pest model, obtained according to Fourier's index parameters
Before the step of obtaining the number of pest on the stickup colour table, this method also includes:
Set up the default index parameters and number of pest model.
Preferably, it is described to set up the default index parameters and number of pest model, including:
Choose multiple stickup colour table image patterns;
Obtain the actual number of pest of each sample;
Obtain Fourier's index parameters of each sample;
Using linear regression analysis, the relational expression of Fourier's index parameters and number of pest is obtained, default index is obtained
Parameter and number of pest model.
Second aspect, the number of pest device for identifying on colour table, described device bag are pasted the invention provides a kind of greenhouse
Include stickup colour table, camera, fixing device, collector and intelligent terminal;
Colour table is pasted, for trapping pests;
Camera, pastes colour table image, and described image is sent into collector for gathering;
Fixing device, for fixing the stickup colour table and the camera, and make it that the camera alignment is described viscous
Paste colour table;
Collector, the time interval for controlling the camera collection image, storage image, and described image is sent
To wireless network;
Intelligent terminal, for downloading image from the wireless network, and using any one of claim 1-6
Number of pest discrimination method carries out the identification of number of pest.
Preferably, the stickup colour table is that yellow pastes colour table or blueness pastes colour table.
Preferably, the fixing device is a rectangular body support frame;The camera is fixed respectively with the stickup colour table
On relative two face of the rectangular body support frame.
Preferably, described device also includes four post bases;
The rectangular body support frame is screwed on the four posts base, the screw according to the Level Change of crop
Fixed position to adjust the height of the rectangular body support frame.
As shown from the above technical solution, the present invention provides the number of pest discrimination method and dress on a kind of greenhouse stickup colour table
Put, this method is estimated by Fourier transform pairs number of pest, insect can be recognized from colour table image is pasted automatically
Quantity, and simple and fast, degree of accuracy height;The device can carry out height regulation according to the clear condition of crop height, with wide
Application.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below to embodiment or existing
The accompanying drawing used required in technology description is briefly described, it should be apparent that, drawings in the following description are only this hair
Some bright embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, can be with root
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is the flow signal that the number of pest discrimination method on colour table is pasted in the greenhouse that one embodiment of the invention is provided
Figure;
Fig. 2 is the flow for setting up the default index parameters and number of pest model that another embodiment of the present invention is provided
Schematic diagram;
Fig. 3 is the structural representation that the number of pest device for identifying on colour table is pasted in the greenhouse that one embodiment of the invention is provided
Figure;
Fig. 4 is the mounting structure that the number of pest device for identifying on colour table is pasted in the greenhouse that another embodiment of the present invention is provided
Schematic diagram.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, clear, complete description is carried out to the technical scheme in the embodiment of the present invention, it is clear that described embodiment is only
Only it is a part of embodiment of the invention, rather than whole embodiments.Based on embodiments of the invention, ordinary skill people
The every other embodiment that member is obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
As shown in figure 1, pasting the stream of the number of pest discrimination method on colour table for the greenhouse that one embodiment of the invention is provided
Journey schematic diagram, this method comprises the following steps:
101:Stickup colour table picture noise to be counted is removed using color filter method;
102:Obtain the DC component and substrate DC component for pasting colour table image;
103:According to the DC component and substrate DC component, Fourier's index parameters are obtained;
104:Using default index parameters and number of pest model, obtain described viscous according to Fourier's index parameters
Paste the number of pest on colour table.
In the present embodiment, step 101 is specifically included:
If the stickup colour table is yellow, according to the red component R of described image>100 remove noise;If described paste
Colour table is blueness, then according to the red component R of described image<180 and blue component B>150 remove noise.
In the present embodiment, step 102 is specifically included:
The stickup colour table image is converted into bianry image, and Fourier transformation is carried out to the bianry image, is obtained
DC component;
The image that blank pastes colour table is converted into bianry image, and Fourier transformation is carried out to the bianry image, is obtained
Obtain substrate DC component.
Wherein, blank is pasted colour table and referred to not adhere the pasting boards of insect, i.e. substrate.
In the present embodiment, step 103 is specifically included:
According to following formula, calculating obtains Fourier's index parameters:
Wherein, DpestFor Fourier's index parameters, D0For substrate DC component, DiFor stickup colour table image to be counted
DC component.
In the present embodiment, before step 104, this method also comprises the following steps:
Set up the default index parameters and number of pest model.
As shown in Fig. 2 above-mentioned set up the default index parameters and number of pest model, following steps are specifically included:
201:Choose multiple stickup colour table image patterns.
202:Obtain the actual number of pest of each sample.
203:Obtain Fourier's index parameters of each sample.
204:Using linear regression analysis, the relational expression of Fourier's index parameters and number of pest is obtained, obtains default
Index parameters and number of pest model.
The number of pest discrimination method that the greenhouse that the present embodiment is provided is pasted on colour table passes through Fourier transform pairs insect number
Amount is estimated, and can recognize the quantity of insect, and simple and fast, degree of accuracy height from colour table image is pasted automatically.
Below by one more specifically embodiment come illustrate greenhouse paste colour table on number of pest discrimination method.It is first
First, onset index parameter and number of pest model, comprise the following steps:
A01, obtain multiple blue pasting boards for being stained with thrips, by human eye observation, select can embody thrips quantity by
20 sample images of many significant changes are arrived less;
Remove one most in A02, the insect number counted in same image by 10 people, one group of 10 number of gained simultaneously
Big value removes a minimum value, and remaining 8 number is averaging, and obtains the actual number N of insect in imagepest(8,32,61,98,
113,129,146,177,193,208,225,241,263,279,312,347,381,417,435,452).
A03, calculating Fourier indicate parameter Dpest(0.006199539,0.024250288,0.050980392,
0.085322953,0.095790081,0.105853518,0.129411765,0.153316032,0.172404844,
0.189619377,0.192589389,0.1977797,0.216320646,0.242964245,0.282179931,
0.293079585,0.326038062,0.352710496,0.352883506,0.386130334).
A04, D set up using linear regression analysispestWith NpestRelational expression be:Npest=1179.8Dpest-1.599。
Further, using step A01 to the step A04 instruction parameters set up and number of pest model, a pair is waited to count
The thrips that number is pasted on colour table is counted, and specifically includes following steps:
B01, using color filter method remove it is to be counted stickup colour table picture noise.Due to being stained with being pasted for blueness for thrips
Plate, if then in image pixel red component R<180 and blue component B>150 will be set R, G, B value of the pixel
It is otherwise constant for 255.
B02, the DC component for obtaining stickup colour table image to be counted.Image after step B01 processing is converted into two-value
Image, and Fourier transformation is carried out to the bianry image, take its DC component Di=341945.
B03, calculating Fourier indicate parameter.Substrate DC component D0=346800, Fourier is calculated by below equation
Indicate parameter Dpest=0.14:
B04, the number of pest utilized on Fourier's instruction parameter estimation stickup colour table to be counted.DpestSubstitute into Npest=
1179.8Dpest- 1.599, the thrips quantity calculated on stickup colour table to be counted is 164.
As shown in figure 3, pasting the knot of the number of pest device for identifying on colour table for the greenhouse that one embodiment of the invention is provided
Structure schematic diagram, the device includes pasting colour table S1, camera S2, fixing device S3, collector S4 and intelligent terminal S5;
Wherein, colour table S1 is pasted, for trapping pests.According to the difference of pest species, it can select and paste colour table for yellow
Paste colour table or blueness pastes colour table.Blue pasting boards for example for traping thrips in greenhouse.
Camera S2, pastes colour table S1 images, and described image is sent into collector for gathering.Camera can be
USB industry camera, pixel 2.0Megapixels, optical dimensions 1/3 are colored, and the focal length and aperture for adjusting camera cause entirely
Yellow plate is clearly in camera lens.
Fixing device S3, pastes colour table S1 and camera S2, and cause camera S2 alignments to paste colour table S1 for fixed.
Fixing device S3 concrete structure is as shown in figure 4, fixing device S3 is a rectangular body support frame.Support S31 passes through
Screw is fixed on two sides of rectangular body support frame, for supporting adn fixing device S3;Colour table S1 is pasted to be positioned on a bottom surface,
And camera S2 is screwed on support, and camera S2 is separately fixed at the rectangular body support frame with pasting colour table S1
Relative two face on;Wherein, S32 is fixed screw, and S33 is to prevent the hole of screw, then by changing fixed screw 32
Position can just adjust camera S2 with paste colour table S1 distance.
And as shown in figure 4, in the present embodiment, the device also includes four post base S4.Fixing device S3 is screwed
On the four posts base S4, and regulation fixing apparatus S3's be capable of in the fixed position of screw according to the Level Change of crop
Highly.
Collector S5, the time interval for controlling the camera collection image, storage image, and described image is sent out
Deliver to wireless network.The optional model Raspberry PI b+ of such as collector S5, and select 16G Samsung Micro SD cards
For storage image, then realized and be wirelessly transferred using TP-LINK TL-WN823N 3G Wireless USBs network interface card.Due to by 3G without
Image is transmitted by gauze network, then image, which is downloaded to, any available to obtain intelligent terminal.
Intelligent terminal S6, is pasted for downloading image from the wireless network, and using the greenhouse in above-described embodiment
Number of pest discrimination method on colour table carries out the identification of number of pest.The optional association Y40-70AT-IFI of such as intelligent terminal,
Download and paste colour table image, and insect is counted using based on Fourier transform theoretical stickup colour table borer population amount discrimination method.
The foregoing is only a specific embodiment of the invention, still, and protection scope of the present invention is not limited to this, appoints
What those familiar with the art the invention discloses technical scope in, the change that can be readily occurred in or replacement, all
It should be included within the scope of the present invention.Therefore, protection scope of the present invention should be with the scope of the claims
It is defined.
Claims (6)
1. the number of pest discrimination method on colour table is pasted in a kind of greenhouse, it is characterised in that methods described includes:
Stickup colour table picture noise to be counted is removed using color filter method;
Obtain the DC component and substrate DC component for pasting colour table image;
According to the DC component and substrate DC component, Fourier's index parameters are obtained;
Using default index parameters and number of pest model, obtained according to Fourier's index parameters on the stickup colour table
Number of pest;
Wherein, the DC component and substrate DC component for obtaining the stickup colour table image, including:
The stickup colour table image is converted into bianry image, and Fourier transformation is carried out to the bianry image, direct current is obtained
Component;The image that blank pastes colour table is converted into bianry image, and Fourier transformation is carried out to the bianry image, base is obtained
Plate DC component;
It is described to obtain Fourier's index parameters according to the DC component and substrate DC component, including:
According to following formula, calculating obtains Fourier's index parameters:
<mrow>
<msub>
<mi>D</mi>
<mrow>
<mi>p</mi>
<mi>e</mi>
<mi>s</mi>
<mi>t</mi>
</mrow>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<mo>(</mo>
<msub>
<mi>D</mi>
<mn>0</mn>
</msub>
<mo>-</mo>
<msub>
<mi>D</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<msub>
<mi>D</mi>
<mn>0</mn>
</msub>
</mfrac>
<mo>&times;</mo>
<mn>10</mn>
</mrow>
Wherein, DpestFor Fourier's index parameters, D0For substrate DC component, DiFor the direct current of stickup colour table image to be counted
Component;
This method also includes:Set up the default index parameters and number of pest;
It is described to set up the default index parameters and number of pest model, including:
Choose multiple stickup colour table image patterns;Obtain the actual number of pest of each sample;Obtain Fu of each sample
In leaf index parameters;Using linear regression analysis, the relational expression of Fourier's index parameters and number of pest is obtained, obtains default
Index parameters and number of pest model.
2. according to the method described in claim 1, it is characterised in that the use color filter method removes stickup color to be counted
Plate picture noise, including:
If the stickup colour table is yellow, according to the red component R of described image>100 remove noise;
If the stickup colour table is blueness, according to the red component R of described image<180 and blue component B>150 removals are made an uproar
Sound.
3. the number of pest device for identifying on colour table is pasted in a kind of greenhouse, it is characterised in that described device includes pasting colour table, taken the photograph
As head, fixing device, collector and intelligent terminal;
Colour table is pasted, for trapping pests;
Camera, pastes colour table image, and described image is sent into collector for gathering;
Fixing device, for fixing the stickup colour table and the camera, and causes the camera to be directed at the stickup color
Plate;
Collector, the time interval for controlling the camera collection image, storage image, and described image is sent to nothing
Gauze network;
Intelligent terminal, for downloading image from the wireless network, and using the number of pest described in claim 1 or 2
Discrimination method carries out the identification of number of pest.
4. device according to claim 3, it is characterised in that the stickup colour table is that yellow pastes colour table or blueness is pasted
Colour table.
5. device according to claim 3, it is characterised in that the fixing device is a rectangular body support frame;It is described to take the photograph
As head is separately fixed on two relative faces of the rectangular body support frame with the stickup colour table.
6. device according to claim 5, it is characterised in that described device also includes four post bases;
The rectangular body support frame is screwed on the four posts base, and the screw according to the Level Change of crop
Fixed position is to adjust the height of the rectangular body support frame.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510097489.3A CN104751450B (en) | 2015-03-05 | 2015-03-05 | Paste the number of pest discrimination method and device on colour table in greenhouse |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510097489.3A CN104751450B (en) | 2015-03-05 | 2015-03-05 | Paste the number of pest discrimination method and device on colour table in greenhouse |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104751450A CN104751450A (en) | 2015-07-01 |
CN104751450B true CN104751450B (en) | 2017-10-27 |
Family
ID=53591069
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510097489.3A Expired - Fee Related CN104751450B (en) | 2015-03-05 | 2015-03-05 | Paste the number of pest discrimination method and device on colour table in greenhouse |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104751450B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110659687B (en) * | 2019-09-24 | 2020-08-18 | 华南农业大学 | Yellow trapping plate-based phyllotreta striolata detection method, medium and equipment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1442786A (en) * | 2003-04-09 | 2003-09-17 | 沈佐锐 | Microinsect automatic counting system |
WO2003084319A1 (en) * | 2002-03-29 | 2003-10-16 | Ecolab Inc. | Light extinction based non-destructive flying insect detector |
CN103246872A (en) * | 2013-04-28 | 2013-08-14 | 北京农业智能装备技术研究中心 | Broad spectrum insect situation automatic forecasting method based on computer vision technology |
CN104186449A (en) * | 2014-08-15 | 2014-12-10 | 北京农业信息技术研究中心 | Pest monitoring system capable of automatically replacing pest sticky board and monitoring method |
-
2015
- 2015-03-05 CN CN201510097489.3A patent/CN104751450B/en not_active Expired - Fee Related
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2003084319A1 (en) * | 2002-03-29 | 2003-10-16 | Ecolab Inc. | Light extinction based non-destructive flying insect detector |
CN1442786A (en) * | 2003-04-09 | 2003-09-17 | 沈佐锐 | Microinsect automatic counting system |
CN103246872A (en) * | 2013-04-28 | 2013-08-14 | 北京农业智能装备技术研究中心 | Broad spectrum insect situation automatic forecasting method based on computer vision technology |
CN104186449A (en) * | 2014-08-15 | 2014-12-10 | 北京农业信息技术研究中心 | Pest monitoring system capable of automatically replacing pest sticky board and monitoring method |
Non-Patent Citations (1)
Title |
---|
"基于图像的昆虫自动识别与计数研究进展";姚青等;《中国农业科学》;20111231;第44卷(第14期);论文第2886-2899页 * |
Also Published As
Publication number | Publication date |
---|---|
CN104751450A (en) | 2015-07-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110455340A (en) | A kind of agricultural cultivation EMS based on big data | |
CN106570534B (en) | Full-automatic tiny insect traps detection method and its system | |
CN103336966B (en) | A kind of weed images discrimination method being applied to agricultural intelligent machine | |
CN108711455B (en) | Dengue fever prevention and control method and system | |
CN107292860A (en) | A kind of method and device of image procossing | |
CN105955158A (en) | Insect automatic monitoring system and method based on handset | |
CN104751450B (en) | Paste the number of pest discrimination method and device on colour table in greenhouse | |
CN109729332A (en) | A kind of automatic white balance antidote and system | |
DE102012010912B3 (en) | A method for contactless determination of the current nutritional status of a crop and for processing this information | |
CN104914797A (en) | Intelligent agricultural management system and management method | |
EP1213569A3 (en) | Device for the measurement by pixel of a plane measurement object | |
CN107609600A (en) | A kind of greenhouse insect-sticking plate insect automatic recognition classification method and system | |
KR101953515B1 (en) | Harmful insect intelligence report system | |
CN110379355A (en) | A kind of control system and control method of large screen display wall | |
CN107121535A (en) | A kind of effective crop growth environment monitoring system | |
CN106197549A (en) | A kind of flower planting ambient parameter detection method | |
CN112733958A (en) | Greenhouse ozone concentration control method and system | |
CN209462473U (en) | A kind of polyphaser full-face images acquisition device towards face skin state assessment | |
DE102009021375A1 (en) | Sensor for measuring a light size and method for calibrating a monitor | |
CN110301415B (en) | Simple tea lesser leafhopper measuring and reporting device | |
CN208908929U (en) | A kind of insect pest situation early warning system | |
CN103235935B (en) | A kind of method of estimation of trialeurodes vaporariorum population density | |
CN109934186A (en) | A kind of efficient monitoring method of wisdom of crops live streaming planting percent | |
JP6768767B2 (en) | Crop growth judgment system server device, crop growth judgment device, crop growth learning device, crop growth judgment method and program | |
CN212306585U (en) | Internet of things pest situation early warning system based on LED (light emitting diode) trap lamps and pest sticking plates |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20171027 Termination date: 20180305 |
|
CF01 | Termination of patent right due to non-payment of annual fee |