CN108519346A - The method that infrared thermal imagery is combined detection incubation period masaic of tomato near infrared spectrum - Google Patents
The method that infrared thermal imagery is combined detection incubation period masaic of tomato near infrared spectrum Download PDFInfo
- Publication number
- CN108519346A CN108519346A CN201810238429.2A CN201810238429A CN108519346A CN 108519346 A CN108519346 A CN 108519346A CN 201810238429 A CN201810238429 A CN 201810238429A CN 108519346 A CN108519346 A CN 108519346A
- Authority
- CN
- China
- Prior art keywords
- tomato
- near infrared
- incubation period
- thermal imaging
- masaic
- 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
- 235000007688 Lycopersicon esculentum Nutrition 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000002329 infrared spectrum Methods 0.000 title claims abstract description 38
- 238000011534 incubation Methods 0.000 title claims abstract description 34
- 238000001514 detection method Methods 0.000 title claims abstract description 27
- 240000003768 Solanum lycopersicum Species 0.000 title claims description 51
- 238000001931 thermography Methods 0.000 claims abstract description 49
- 201000010099 disease Diseases 0.000 claims abstract description 38
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 38
- 238000001228 spectrum Methods 0.000 claims description 23
- 238000011081 inoculation Methods 0.000 claims description 21
- 239000000523 sample Substances 0.000 claims description 18
- 241000700605 Viruses Species 0.000 claims description 15
- 208000015181 infectious disease Diseases 0.000 claims description 14
- 238000005259 measurement Methods 0.000 claims description 6
- 239000008363 phosphate buffer Substances 0.000 claims description 6
- 230000003595 spectral effect Effects 0.000 claims description 6
- 238000012706 support-vector machine Methods 0.000 claims description 5
- 238000000513 principal component analysis Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 208000035240 Disease Resistance Diseases 0.000 claims description 3
- 238000009395 breeding Methods 0.000 claims description 3
- 230000001488 breeding effect Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 239000007788 liquid Substances 0.000 claims description 3
- 239000013307 optical fiber Substances 0.000 claims description 3
- 239000002574 poison Substances 0.000 claims description 3
- 231100000614 poison Toxicity 0.000 claims description 3
- 239000007921 spray Substances 0.000 claims description 3
- 230000006835 compression Effects 0.000 claims description 2
- 238000007906 compression Methods 0.000 claims description 2
- 238000002255 vaccination Methods 0.000 claims description 2
- 230000003902 lesion Effects 0.000 abstract description 5
- 238000012360 testing method Methods 0.000 abstract description 4
- 230000000694 effects Effects 0.000 abstract description 3
- 238000007435 diagnostic evaluation Methods 0.000 abstract description 2
- 230000033001 locomotion Effects 0.000 abstract description 2
- 241000227653 Lycopersicon Species 0.000 abstract 4
- 229920003266 Leaf® Polymers 0.000 description 16
- 241000196324 Embryophyta Species 0.000 description 15
- 238000005516 engineering process Methods 0.000 description 9
- 206010039509 Scab Diseases 0.000 description 7
- 230000008859 change Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 239000005723 virus inoculator Substances 0.000 description 7
- 238000011160 research Methods 0.000 description 6
- 239000003814 drug Substances 0.000 description 5
- 238000001757 thermogravimetry curve Methods 0.000 description 5
- 230000009466 transformation Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000013399 early diagnosis Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 239000011521 glass Substances 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 235000009754 Vitis X bourquina Nutrition 0.000 description 3
- 235000012333 Vitis X labruscana Nutrition 0.000 description 3
- 240000006365 Vitis vinifera Species 0.000 description 3
- 235000014787 Vitis vinifera Nutrition 0.000 description 3
- 230000000875 corresponding effect Effects 0.000 description 3
- 229940079593 drug Drugs 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000005192 partition Methods 0.000 description 3
- 230000009385 viral infection Effects 0.000 description 3
- 238000004497 NIR spectroscopy Methods 0.000 description 2
- 238000012271 agricultural production Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 230000003028 elevating effect Effects 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 244000052769 pathogen Species 0.000 description 2
- 230000001717 pathogenic effect Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 239000011550 stock solution Substances 0.000 description 2
- 241000721047 Danaus plexippus Species 0.000 description 1
- 208000005156 Dehydration Diseases 0.000 description 1
- 244000287680 Garcinia dulcis Species 0.000 description 1
- 206010020751 Hypersensitivity Diseases 0.000 description 1
- 241000233855 Orchidaceae Species 0.000 description 1
- 244000131316 Panax pseudoginseng Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 241000921313 Phyllopodium Species 0.000 description 1
- 239000006004 Quartz sand Substances 0.000 description 1
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 1
- 241000723613 Tomato mosaic virus Species 0.000 description 1
- 208000026935 allergic disease Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000034303 cell budding Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 239000012153 distilled water Substances 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 210000002615 epidermis Anatomy 0.000 description 1
- 239000006260 foam Substances 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000009610 hypersensitivity Effects 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 230000009545 invasion Effects 0.000 description 1
- 238000003973 irrigation Methods 0.000 description 1
- 230000002262 irrigation Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000009659 non-destructive testing Methods 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 230000035764 nutrition Effects 0.000 description 1
- 239000000575 pesticide Substances 0.000 description 1
- 230000029553 photosynthesis Effects 0.000 description 1
- 238000010672 photosynthesis Methods 0.000 description 1
- 230000001766 physiological effect Effects 0.000 description 1
- 230000037039 plant physiology Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000005057 refrigeration Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 230000001235 sensitizing effect Effects 0.000 description 1
- 230000001568 sexual effect Effects 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000005068 transpiration Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N25/00—Investigating or analyzing materials by the use of thermal means
- G01N25/72—Investigating presence of flaws
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The method that the invention discloses infrared thermal imageries to be combined detection incubation period masaic of tomato near infrared spectrum, is related to the detection technique field of masaic of tomato.The present invention is based on the tomato disease incubation period detection method that infrared thermal imaging is combined near infrared spectrum, the Biochemical Information that near infrared spectrum detects crop disease has preferable effect, it can directly reflect intramolecule structure and motion state.The tomato disease incubation period diagnostic evaluation model of infrared thermal imaging and near infrared spectrum is established, there is intuitive in terms of obtaining the important informations such as lesions position, size.For the present invention compared with the method for general near infrared detection disease, detection speed is fast, finds disease earlier；Compared with single near-infrared spectrum technique means, obtained information is more acurrate, and the accuracy and stability of testing result all increase.
Description
Technical field
The present invention relates to the detection technique field of masaic of tomato, refers in particular to a kind of infrared thermal imaging and combined near infrared spectrum
The method for detecting incubation period masaic of tomato.
Background technology
Currently, China has become the world's second largest tomato planting state for being only second to the U.S. and the first big tomato product outlet
The annual capacity of state, only Xinjiang region tomato product has broken through 2,000,000 tons.Tomato virus disease is worldwide to occur extensively
Tomato Major Diseases, field symptom is various, and it is also one of maximum disease of harm, directly initiation that masaic of tomato, which is most common,
The underproduction, quality decline, even death so that agricultural production causes heavy losses, seriously affects economic benefit.In real time, sensitive, can
The detection and prevention leaned on are the bases of tomato science production management.
The research of plant physiology is it has been proved that plant by the infection processs of disease is referred to that pathogen invades host to posting
The overall process of main morbidity.This process is divided into as stage of invasion, incubation period, period of disease, wherein shortest several days of incubation period, and long can
Up to 1 year, and while being observed visually the scab of blade was period of disease, how to be identified as early as possible in the incubation period, and solution is applied in variable
Spray during medicine object positioning and the problem of sprinkling dosage be accuracy pesticide applying core problem.
Be detected to plant disease currently with computer non-destructive testing technology is that domestic and international crop nutrition and disease are examined
Disconnected common method.Mainly there are Vis/NIR technology and computer vision technique two major classes.Vis/NIR
Technology has randomness due to using point source sampling, can not solve the quick positioning of the lesion sensitizing range of pathogen early stage infringement
Problem.When computer vision technique detects crop disease, to fully understand and grasp the aggrieved correlated characteristic information of crop leaf, one
As be by extracting the gray level image under RGB image or a certain wavelength, extraction color, form, Texture eigenvalue variable carry out
Analysis, this is just needed in naked eyes it is observed that being tested after scab, and using plant leaf blade, area is larger after aobvious disease
Scab or withered spot are split with non-aobvious disease part, can not be differentiated at all before not aobvious disease, it is assumed that before the onset of blade is still in
Incubation period, then the technological means of view-based access control model image class also cannot achieve early diagnosis.Therefore new there is an urgent need to explore
Detection method realizes crop disease incubation period Accurate Diagnosis, and disease is eliminated in budding stage, guidance fertilising and irrigation, is realized
" early medication, few medication ", the decision-making foundation of science is provided for the integrated control of crop disease.
Infrared thermal imaging technique with it to the hypersensitivity of temperature and the feasibility of on-line checking, at present in electrical, aviation
The achievement in research for having comparative maturity with medicine etc., also has relevant application in the numerous areas of agricultural production.Utilize thermal imaging
Characteristic, be expected to realize the early diagnosis of plant disease in the incubation period that can not observe of naked eyes.Consolidate the reason is that plant is born
Qualitative to determine under the conditions of by disease or Nutrient Stress, plant is often gone by adjusting itself internal signal network
Continually changing environmental stimulus is adapted to, respiration, photosynthesis, transpiration, stomatal conductance etc. change, then exist
It changes in temperture of leaves, i.e., plant receives similar with human body when germ intrusion, its temperature has corresponding change before the onset of completely
Change.Blade face temperature is that can reflect that plant is strong in time as the important physiological property of plant and the basic parameter of ecological ragime research
One of index whether health.Li Guangjun establishes the water stress index CWSI and stomata of grape using hila grape leave as object
The prediction model related coefficient of degree of leading index IG respectively reaches 98.95% and 99.01%, it was demonstrated that thermal imaging and near-infrared
It is that (monarch Li Guang thermal imagings are combined lossless inspection with near-infrared spectrum technique for a kind of reliable lossless detection method that spectrum, which combines,
Survey hila grape leave moisture, Shanxi Agricultural science, 2016, (44):1467-1475.).Xu little Long etc. is tried by alternating temperature
It tests and blade is shot the method for Infrared Thermogram after low temperature refrigerator refrigeration is taken out again masaic of tomato is detected, obtain
It can be seen that can detect the conclusion of jump in temperature in the preceding 3d that scab occurs, however Caloric test method executes in actual production practice
With certain difficulty, (Xu little Long, Jiang Huanyu, Hang Yue orchid thermal infrared imagings are used for the research of masaic of tomato early detection, agriculture
Industrial engineering (IE) journal, 2012,28 (5):145-149).In recent years both at home and abroad some scholars mainly by near infrared technology and infrared
Thermal imaging is applied individually to any in the detection of crop disease, but is had no using infrared thermal imaging and near infrared technology in conjunction with examining
The method for surveying incubation period masaic of tomato.
Invention content
For the present invention in order to overcome above-mentioned deficiency in the prior art, the present invention, which carries out, is based on infrared thermal imaging and near infrared light
The tomato disease incubation period detection method research combined is composed, the Biochemical Information that near infrared spectrum detects crop disease has preferably
Effect, it can directly reflect intramolecule structure and motion state.Establish the tomato disease of infrared thermal imaging and near infrared spectrum
Evil incubation period diagnostic evaluation model has intuitive in terms of obtaining the important informations such as lesions position, size.Realize crop disease
Harmful early stage Accurate Diagnosis provides theoretical foundation and method reference for the research and development of the early diagnosis instrument of crop disease, has weight
The learning value and application prospect wanted.
The method that infrared thermal imaging of the present invention is combined detection incubation period masaic of tomato near infrared spectrum, according to following steps
It is rapid to carry out：
(1) sample is cultivated,
(2) infrared thermal imaging figure is acquired,
(3) it is determined according to the calculating of leaf table maximum temperature difference (maximum temperature difference, MTD) close red
The region of external spectrum acquisition,
(4) near infrared spectra collection,
(5) Pretreated spectra and characteristic processing
(6) identification model is established,
(7) whether fallen ill using the above-mentioned model inspection crop incubation period and disease light and heavy degree.
Wherein the sample, which is cultivated, refers to：The non-disease resistance tomato variety of selection and breeding carries out tomato seedling, is educated in organic active
Seedling matrix culture waits for that tomato seedling was grown to the strong sprout phase, using blade face frictional inoculation mosaic virus (Tobacccco mosaic
Virus, ToMV), it is divided into low-grade infection group (Low-grade infection, LI), severe infection group (Severe
Infection, SI), wherein LI groups are that phosphate buffer dilutes the poison disease vaccination after 500 times, and SI groups are inoculated with for virus stock solution used；
Control group (Control group, CG) sprays equivalent phosphate buffer.
Wherein the acquisition infrared thermal imaging figure refers to acquiring tomato by crop infrared thermal imaging information acquisition system
The infrared thermal imaging figure of blade.
The wherein described calculating according to leaf table maximum temperature difference determines that the region of near infrared spectra collection refers to passing through calculating
Optical fiber probe measurement institute when the MTD values on blade face determine near infrared spectra collection with the difference of control group (Control group, CG)
The band of position at place.
Wherein the near infrared spectra collection refers to being produced using ASD companiesThe portable spectrum of 3 types
Analyzer carries out spectra collection.
Wherein the Pretreated spectra and characteristic processing refers to carrying out spectrum using canonical variable transformation (SNV) in advance to locate
Reason carries out compression and feature extraction using the spectral information of principal component analysis wavelength points.
The wherein described identification model of establishing refers to establishing the identification of masaic of tomato incubation period using support vector machines (SVM)
Model.
Beneficial effects of the present invention：
The present invention considers the sensitive part information that incubation period disease is positioned by infrared thermal imaging figure, utilizes infrared heat
The characteristic that the advantage of " early to find " is capable of in imaging and near infrared spectrum can include intramolecule information can not be observed in naked eyes
Incubation period realize the early diagnosis of plant disease, to improve the reliability and accuracy of detection.Using artificial infection virus mode
Sample is cultivated, the infrared thermal imaging image capturing system gathered data voluntarily built is utilized；MTD is calculated with true with the difference of CG groups
Determine the location of optical fiber probe measurement region when near infrared spectra collection；Ask flat after this region measures near infrared spectrum three times
Mean value；Pretreated spectra is carried out using SNV, is compressed using the spectral information of 2 151 wavelength points of principal component analysis pair；It is right
All samples establish identification model using SVM algorithm and carry out discriminant analysis, and total discrimination of model is 99.77%, and precision is apparent
The identification model established higher than random acquisition near infrared spectrum.
For the present invention compared with the method for general near infrared detection disease, detection speed is fast, finds disease earlier；With it is single
Near-infrared spectrum technique means compare, obtained information is more acurrate, and the accuracy and stability of testing result all increase.
The rapid detection method of the incubation period masaic of tomato provided by the invention combined near infrared technology based on infrared thermal imaging, can
To realize tomato growth process defect information quick detection.The invention accurately irrigates for science and provides reference in time, to improving intelligence
Management level, foundation can be changed, and more accurately greenhouse intelligent expert system provides theoretical and method foundation.
Description of the drawings
Fig. 1 is infrared thermal imaging image capturing system, wherein：1. band door light box；2. circular lamp band light source；3. heating plate；
4. Lifting carrying platform；5. infrared thermography；6. temperature and elevating control panel；7. glass partition.
Fig. 2 is random acquisition method (Random collection method, RCM, Fig. 2 a) and thermal imagery acquisition method
(Thermal-imaging collection method, TCM, Fig. 2 b) takes a position to compare.
Fig. 3 is healthy leaves infrared thermal imaging figure (a), slight infected leaves infrared thermal imaging figure (b), severe infected leaves
Infrared thermal imaging figure (c).
Fig. 4 is nonvaccinated infrared thermal imaging figure (a), the infrared thermal imaging figure of 3d (b), 6d (c), 9d (d) after inoculation.
Fig. 5 is inoculation 6d rear blade SNV pre-processed spectrum figures；Masaic of tomato is inoculated with the spectrogram and light of sample after 6d
It is as shown in Figure 3a to compose pretreated spectrogram, preprocessing procedures are that standard normal variable converts (Standard Normal
Variate Transformation, SNV), spectrum is as shown in Figure 3b after transformation.
Fig. 6 is the situation of change of blade MTD values after being inoculated with 1d~9d of virus inoculation.
Specific implementation mode
Below by taking tomato as an example, the present invention is explained in further detail in conjunction with attached drawing.
Infrared thermal imaging image capturing system employed in the specific embodiment of the invention is refering to fig. 1.Shown in Fig. 1
Infrared thermal imaging image capturing system acquisition tomato leaf infrared thermal imaging comprising band door light box 1, circular lamp band light source
2, heating plate 3, Lifting carrying 4, infrared thermography 5 (FIUKE Ti55, USA), temperature and elevating control panel 6 and glass every
Plate 7.The system can be artificial to adjust shooting temperature according to the requirement of temperature start-stop node, realizes continuous in certain temperature threshold
The demand of shooting, Lifting carrying platform can easily adjust shooting distance.The fuselage and camera lens of infrared thermography 5 can 0 °~
It is rotated freely between 90 °.There are one the hole agreed with camera lens size, camera lens rotations for the center of glass partition 7
The thermograph of crop can be shot with through hole position afterwards.
The present invention is carried out in Jiangsu University's agriculture equipment with technology building by province and ministry key lab Venlo types greenhouse
Tomato seedling, Cultivars are non-disease resistance tomato variety.Select the organic active seedling medium training for meeting relative national standards
It supports.Wait for that tomato seedling was grown to the strong sprout phase, using blade face frictional inoculation virus, virus is provided by Institute of Plant Protection of academy of agricultural sciences of Jiangsu Province.Inoculation
After move to independent greenhouse and avoid infection other crops.Frictional inoculation method is used when inoculation, since to destroy blade epidermis thin for the method
Born of the same parents, therefore be inoculated with blade and select lower part Cheng Zhuanye, i.e. the 3rd or 4 pinnate compound leaf from top to bottom.Distilled water hydro-peening blade face is used first
Dust and silt are removed, then 15ml virus liquids are pipetted by liquid-transfering gun is sprayed on blade face and be inoculated with, finally uses fine quartz sand from leaf
Base is slightly rubbed three times to blade tip direction to ensure the generation of virus inoculation success and follow-up system sexual abuse.Virus inoculation according to
Sequence from light to heavy carries out, and inoculation group and healthy control group are respectively placed in different foam case dark guarantor under the conditions of 11 DEG C
It is wet to take out afterwards for 24 hours.Virus inoculation concentration point gradient carries out, and forms low-grade infection (Low-grade infection, LI) and severe
Infect the tomato sample of (Severe infection, SI).LI sample groups dilute the virus liquid after 500 times using phosphate buffer
Inoculation, and SI sample groups then use virus stock solution used to be inoculated with, while control group (Control group, CG) sample is cultivated, control group
Equivalent phosphate buffer is sprayed, and carries out detailed record.
Every morning 9:00~12:Plant is schemed to balance 30~40min in .1 detecting systems to eliminate environment by 00 period
Influence of the temperature to accuracy of measurement.The chamber door with door light box 1 is closed before shooting, by 5 fuselage of thermal infrared imager and rotation of lens
It is placed on after 90 ° on glass partition 7, lens location agrees with reserved shooting Kong Weixiang, and camera lens is located at right over plant.Pass through
It is 30 ± 5cm that Lifting carrying platform, which controls camera lens with blade distance,.
All inoculation plant start scab occur after inoculation 10d, illustrate that masaic of tomato is inoculated with successfully, the entire incubation period is
9d.Every morning 9 in incubation period:00~12:00 acquisition Infrared Thermogram, 3d, 6d and 9d, after having acquired infrared thermal imaging figure
The acquisition of near infrared spectrum data is carried out to the blade immediately.144 tomato leafs are chosen altogether in being inoculated with plant as sample,
Wherein each 48 of LI, SI and CG group.Two ways is used when measurement, a kind of mode is as shown in Figure 2 a, acquisition blade tip, Ye Zhong, leaf
Three regions of base, the spectrum that each region acquires a point are averaged, and random acquisition method (Random collection are denoted as
method,RCM)；Another way is as shown in Figure 2 b, and carrying out spectrum three times to the temperature jump region that Infrared Thermogram is shown adopts
It averages after collection, is denoted as thermal imagery acquisition method (Thermal-imaging collection method, TCM).Stain in Fig. 2
Detecting location is put for the fibre-optical probe of spectrometer detectors.It is carried out respectively by both the above mode after 3d, 6d, 9d after inoculation
Spectra collection.
Fig. 3 (a) (b) (c) respectively illustrates the infrared thermal imagery that CG, LI and SI group tomato plant blade are shot after being inoculated with 3d
Figure.More uniform low temperature blue is presented in thermograph in the region of the healthy tomato leaf of Fig. 3 (a), temperature does not occur
Jumping phenomenon, integral blade temperature are very smooth.In slight infected leaves shown in Fig. 3 (b), blade shows as yellow, though at this time
Right susceptible degree is still shallow, is only inoculated with 3d, but can be obviously distinguished with control group from hygrogram.Fig. 3 (c)
Shown in severe infected leaves, find out in conjunction with right side temperature stick, orange red high-temperature area represents 24.8 DEG C on the right side of middle part of blade
Left and right, remaining yellow represent 24.3 DEG C or so, and inoculation 3d has just shown certain temperature difference.It can be seen that when blade rubbing is inoculated with
After virus, virus enters living cells breeding through microtrauma mouth, is quickly moved to adjacent cells by plasmodesmus, then manage via dimension
Beam, screen casing are quickly moved to new growing point, are infected to blade.May indicate that by the analysis of Fig. 3 visually observe it is infrared
Thermography can be earlier capture morbidity information.
48 blades of 96 blades of LI and SI groups and CG groups of virus inoculation are carried out with the acquisition of infrared thermal imaging figure.Leaf
Shown in the Infrared Thermogram such as Fig. 4 (a) of piece before aobvious disease.In entire infection processs, Fig. 4 (a) is infrared before non-virus inoculation
Thermograph, blade presentation is uniform light blue, by SmartViewTMSoftware automatic identification calculates being averaged for light blue region
Temperature is 23.2 DEG C.Fig. 4 (b) is the thermograph of 3d after inoculation, and blade presentation is uniformly raised faint yellow, and mean temperature is
24.1 DEG C, blade MTD values are smaller at this time, however bulk temperature averagely still rises 0.6 DEG C before not being inoculated with.Fig. 4 (c) is to connect
The thermograph of 6d after kind, orange red temperature jump region, also being demonstrate,proved after the 10d of the region occurs in left side blade leaf tip position in figure
Actually occurs the region of scab at first.Remaining position of sick leaf show as it is faint yellow, by Fig. 4 (c) analytic explanations be inoculated with after 6d can
Tentatively judge lesions position.Bulk temperature averagely rises 1 DEG C before left side blade is not inoculated in figure, and continuous increase of MTD reaches
1.2℃.Fig. 4 (d) is the thermograph of 9d after inoculation, in figure in the blade and blade of right side and pale orange occurs in phyllopodium position, compared with left side
The susceptible degree of blade is slightly light, the reason is that based on left side blade closer to new growing point, and left side blade leaf margin has turned into obviously
It is orange red, represent 24.8 DEG C according to right side temperature stick is orange red.Infrared hot line map analysis from the virus infection process of Fig. 4 can
To find along with the raised process of infected leaves temperature, can after tentatively judging virus infection in thermography lesion position
It sets.
48 blades of 96 blades of LI and SI groups and CG groups leaf table maximum temperature difference after being inoculated with 1d~9d of virus inoculation
The situation of change of (maximum temperature difference, MTD) value is shown in Fig. 6.It is sick that MTD can characterize blade surface
Poison infects rear damage field and intact interregional temperature difference.The blade of normal growth remains pole at room temperature in stable
Small temperature difference, with the propulsion of virus infection time, significant change has occurred in the MTD for being inoculated with blade.After being inoculated with 6d
Difference reaches maximum, and corresponding Infrared Thermogram obviously observes scab.7d starts difference diminution, shows the diffusion model of virus
Enclosing increase causes the more and more regions of disease leaf to be infected so that bulk temperature rises.Intuitive according to Fig. 5 differentiates with Fig. 6's
MTD values calculate, final to determine that the principle of TCM spectra collections point selection three times is：The temperature jump of 3d, 6d and 9d after the inoculation of LI groups
The MTD value ratio CG groups mean temperatures in region are higher by 0.3 DEG C, 0.7 DEG C, 0.5 DEG C respectively.The temperature of 3d, 6d and 9d after the inoculation of SI groups
The MTD value ratio CG groups mean temperatures of sudden change region are higher by 0.5 DEG C, 1.2 DEG C, 0.8 DEG C respectively.According to this MTD calculating principle, in height
Go out the blade face region acquisition near infrared spectrum of relevant temperature.
The spectral measuring devices of the acquisition of near infrared spectrum data of the present invention are the production of ASD companies of the U.S.
The portable spectroanalysis instrument of 3 types, 350~2 500nm of measurement range acquire 2 151 wavelength points altogether；In 350~1 000nm light
Spectrum area's sampling interval is 1.4nm, resolution ratio 3nm；It is 2nm in 1 000~2 500nm spectral regions sampling intervals, resolution ratio is
10nm。
Shown in the original spectrum of acquisition such as Fig. 5 (a), Pretreated spectra is carried out to original spectrum, masaic of tomato is inoculated with 6d
Sick leaf Pretreated spectra after spectrogram such as Fig. 5 (b) shown in, preprocessing procedures be standard normal variable transformation
(Standard Normal Variate Transformation, SNV).
The present invention compresses the spectral information of 2 151 wavelength points collected using using principal component analysis,
It can either reflect the most information of original variable, and information contained does not repeat mutually, the cumulative variance corresponding to preceding 6 principal components
Contribution rate arrived 99%, can explain 99% information of initial data.By each 72 test specimens of LI and SI groups with classification
By 2:1 ratio random division calibration set and forecast set.It is trained with calibration set sample, selects radial basis function (Radial
Basis function, RBF) as kernel function establish SVM multiclass identification models.Penalty factor=48.7653, kernel function ginseng
Number g=0.1281.Back substitution identification is carried out to forecast set sample with this model, the result is shown in tables 1.It can be with from the recognition result of RCM
Find out that the correct recognition rata of CG, LI and SI of 3d after being inoculated with are respectively 95.83%, 87.50% and 89.58%；6d points after inoculation
It Wei 95.83%, 89.58% and 91.67%；9d is respectively 97.92%, 91.67% and 93.75% after inoculation.And pass through heat
Imaging uses after judging positioning focal area in the identification model that TCM is established, in addition to a LI sample of 3d after inoculation fails to know
It does not come out, misjudged at CG samples, discrimination is outside 97.92%, remaining group discrimination has reached 100%.The result shows that close
Incubation period masaic of tomato can tentatively be identified that total discrimination is 92.59% by infrared spectrum；And infrared thermal imaging with it is close
Infrared spectrum combines, and total discrimination is 99.77%, can reach more preferably recognition effect.
The present invention the above results show near infrared spectroscopy identification masaic of tomato be feasible, and use it is infrared heat at
As combine near infrared spectroscopy can establish the higher masaic of tomato incubation period identification model of discrimination, overcome a source sampling with
Machine breaks through follow-up management and control flow and research the key technology of crop early stage accurate medication, establishes more accurately greenhouse intelligence
Energy dispenser system provides new thinking.
The SVC Forecasting recognition model results of table 1 random acquisition method (RCM) and thermal imagery acquisition method (TCM)
Claims (7)
1. the method that infrared thermal imaging is combined detection incubation period masaic of tomato near infrared spectrum, it is characterised in that according to following
Step carries out：
(1) sample is cultivated,
(2) infrared thermal imaging figure is acquired,
(3) region of near infrared spectra collection is determined according to the calculating of leaf table maximum temperature difference,
(4) near infrared spectra collection,
(5) Pretreated spectra and characteristic processing
(6) identification model is established,
(7) whether fallen ill using the above-mentioned model inspection crop incubation period and disease light and heavy degree.
2. infrared thermal imaging according to claim 1 is combined the side of detection incubation period masaic of tomato near infrared spectrum
Method, it is characterised in that wherein the sample, which is cultivated, refers to：The non-disease resistance tomato variety of selection and breeding carries out tomato seedling, in organic work
Property seedling medium culture, wait for that tomato seedling was grown to the strong sprout phase, using blade face frictional inoculation mosaic virus, be divided into low-grade infection group, weight
Infected group is spent, wherein low-grade infection group is that phosphate buffer dilutes the poison disease vaccination after 500 times, and severe infection group is that virus is former
Liquid is inoculated with；Control group sprays equivalent phosphate buffer.
3. infrared thermal imaging according to claim 1 is combined the side of detection incubation period masaic of tomato near infrared spectrum
Method, it is characterised in that wherein the acquisition infrared thermal imaging figure refers to being acquired by crop infrared thermal imaging information acquisition system
The infrared thermal imaging figure of tomato leaf.
4. infrared thermal imaging according to claim 1 is combined the side of detection incubation period masaic of tomato near infrared spectrum
Method, it is characterised in that the wherein described calculating according to leaf table maximum temperature difference determines that the region of near infrared spectra collection refers to passing through
When the difference of the leaf table maximum temperature difference value and control group that calculate blade face determines near infrared spectra collection residing for optical fiber probe measurement
The band of position.
5. infrared thermal imaging according to claim 1 is combined the side of detection incubation period masaic of tomato near infrared spectrum
Method, it is characterised in that wherein the near infrared spectra collection refers to carrying out spectra collection using portable spectroanalysis instrument.
6. infrared thermal imaging according to claim 1 is combined the side of detection incubation period masaic of tomato near infrared spectrum
Method, it is characterised in that wherein the Pretreated spectra and characteristic processing refers to converting progress spectrum using canonical variable in advance to locate
Reason carries out compression and feature extraction using the spectral information of principal component analysis wavelength points.
7. infrared thermal imaging according to claim 1 is combined the side of detection incubation period masaic of tomato near infrared spectrum
Method, it is characterised in that the wherein described identification model of establishing refers to establishing the identification of masaic of tomato incubation period using support vector machines
Model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810238429.2A CN108519346A (en) | 2018-03-22 | 2018-03-22 | The method that infrared thermal imagery is combined detection incubation period masaic of tomato near infrared spectrum |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810238429.2A CN108519346A (en) | 2018-03-22 | 2018-03-22 | The method that infrared thermal imagery is combined detection incubation period masaic of tomato near infrared spectrum |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108519346A true CN108519346A (en) | 2018-09-11 |
Family
ID=63432960
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810238429.2A Pending CN108519346A (en) | 2018-03-22 | 2018-03-22 | The method that infrared thermal imagery is combined detection incubation period masaic of tomato near infrared spectrum |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108519346A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109540814A (en) * | 2019-01-12 | 2019-03-29 | 合肥工业大学 | A kind of iris gray mold early detection method based on multi-optical spectrum imaging technology |
| CN109632688A (en) * | 2018-11-28 | 2019-04-16 | 北京农业智能装备技术研究中心 | A kind of plant seedlings Apparent nutrient profit or loss state identification method and spectral detection system |
| CN110598732A (en) * | 2019-08-02 | 2019-12-20 | 佛山职业技术学院 | Plant health detection method and device based on image recognition |
| CN111553943A (en) * | 2020-06-09 | 2020-08-18 | 山西农业大学 | Leaf area automatic measurement system based on multivariate normal distribution statistics and level set variational method |
| CN112326585A (en) * | 2020-10-28 | 2021-02-05 | 南京农业大学 | Infrared spectrum device and detection method for rapidly detecting powdery mildew of strawberries |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103336010A (en) * | 2013-07-10 | 2013-10-02 | 江苏大学 | Early tobacco virus disease detection method based on infrared thermal imaging technology |
| CN105527254A (en) * | 2015-12-01 | 2016-04-27 | 浙江大学 | Rapid detection method for infection severity of mosaic disease of tobacco |
-
2018
- 2018-03-22 CN CN201810238429.2A patent/CN108519346A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103336010A (en) * | 2013-07-10 | 2013-10-02 | 江苏大学 | Early tobacco virus disease detection method based on infrared thermal imaging technology |
| CN105527254A (en) * | 2015-12-01 | 2016-04-27 | 浙江大学 | Rapid detection method for infection severity of mosaic disease of tobacco |
Non-Patent Citations (3)
| Title |
|---|
| SINDHUJA SANKARAN等: "Huanglongbing（Citrus Greening）Detecting Using Visible,Near Infrared and Thermal Imaging Techniques", 《SENSORS》 * |
| 刘飞等: "基于曲线拟合的普通花叶病烟叶与正常烟叶的FTIR研究", 《玉溪师范学院学报》 * |
| 徐小龙等: "热红外成像用于番茄花叶病早期检测的研究", 《农业工程学报》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109632688A (en) * | 2018-11-28 | 2019-04-16 | 北京农业智能装备技术研究中心 | A kind of plant seedlings Apparent nutrient profit or loss state identification method and spectral detection system |
| CN109632688B (en) * | 2018-11-28 | 2021-05-28 | 北京农业智能装备技术研究中心 | Plant seedling nutrient profit and loss state identification method and spectrum detection system |
| CN109540814A (en) * | 2019-01-12 | 2019-03-29 | 合肥工业大学 | A kind of iris gray mold early detection method based on multi-optical spectrum imaging technology |
| CN110598732A (en) * | 2019-08-02 | 2019-12-20 | 佛山职业技术学院 | Plant health detection method and device based on image recognition |
| CN111553943A (en) * | 2020-06-09 | 2020-08-18 | 山西农业大学 | Leaf area automatic measurement system based on multivariate normal distribution statistics and level set variational method |
| CN112326585A (en) * | 2020-10-28 | 2021-02-05 | 南京农业大学 | Infrared spectrum device and detection method for rapidly detecting powdery mildew of strawberries |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108519346A (en) | The method that infrared thermal imagery is combined detection incubation period masaic of tomato near infrared spectrum | |
| Bagheri | Application of aerial remote sensing technology for detection of fire blight infected pear trees | |
| Huang et al. | Phenotypic techniques and applications in fruit trees: a review | |
| CN106718363B (en) | Irrigation test method and test platform for fine agriculture | |
| He et al. | Monitoring of wheat powdery mildew disease severity using multiangle hyperspectral remote sensing | |
| CN103278503B (en) | Multi-sensor technology-based grape water stress diagnosis method and system therefor | |
| US7271386B2 (en) | Method for detecting and managing nematode population | |
| CN109613022A (en) | A kind of method, apparatus and system of low latitude high-spectrum remote-sensing detection Citrus Huanglongbing pathogen | |
| Huang et al. | Detection of scab in wheat ears using in situ hyperspectral data and support vector machine optimized by genetic algorithm | |
| CN107328735A (en) | Rape species discrimination method based on terahertz light spectral technology | |
| CN109187417A (en) | A kind of Terahertz of UAV system involves high-spectrum remote-sensing crops monitoring system | |
| CN109389581A (en) | The method of wheat leaf rust classification based on infrared thermal imaging edge detection process | |
| Tung et al. | Evaluation of water potentials of leafy vegetables using hyperspectral imaging | |
| CN111751347A (en) | Barley leaf pigment imaging method under powdery mildew stress based on Raman spectrum | |
| Zhu et al. | Nondestructive diagnostics of soluble sugar, total nitrogen and their ratio of tomato leaves in greenhouse by polarized spectra–hyperspectral data fusion | |
| Qian et al. | Development and application of crop monitoring system for detecting chlorophyll content of tomato seedlings | |
| CN105891130B (en) | A method of the different spectral informations of correction determine material information error | |
| Lyu et al. | Feasibility of SSC prediction for navel orange based on origin recognition using NIR spectroscopy | |
| Li et al. | Tomato seeds maturity detection system based on chlorophyll fluorescence | |
| Xu et al. | A Band Math-ROC operation for early differentiation between sclerotinia sclerotiorum and botrytis cinerea in oilseed rape | |
| Dragavtsev et al. | Application of thermal imaging in agriculture and forestry | |
| Wu et al. | Recognition of wheat preharvest sprouting based on hyperspectral imaging | |
| CN105675533B (en) | Method based on FTIR spectrum technology early detection fingered citron anthracnose | |
| Zhang et al. | Research vertical distribution of chlorophyll content of wheat leaves using imaging hyperspectra | |
| Ni et al. | Application of monitoring system about plant growth information based on spectroscopy technique |
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: 20180911 |
|
| RJ01 | Rejection of invention patent application after publication |