CN105675821B - A kind of method for building up of the picture appraisal index of crop nitrogen nutrition Nondestructive - Google Patents
A kind of method for building up of the picture appraisal index of crop nitrogen nutrition Nondestructive Download PDFInfo
- Publication number
- CN105675821B CN105675821B CN201610094126.9A CN201610094126A CN105675821B CN 105675821 B CN105675821 B CN 105675821B CN 201610094126 A CN201610094126 A CN 201610094126A CN 105675821 B CN105675821 B CN 105675821B
- Authority
- CN
- China
- Prior art keywords
- wheat
- nitrogen
- ncmi
- image
- index
- 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
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 title claims abstract description 225
- 229910052757 nitrogen Inorganic materials 0.000 title claims abstract description 112
- 235000016709 nutrition Nutrition 0.000 title claims abstract description 39
- 230000035764 nutrition Effects 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 title claims abstract description 36
- 241000209140 Triticum Species 0.000 claims abstract description 89
- 235000021307 Triticum Nutrition 0.000 claims abstract description 80
- 238000000605 extraction Methods 0.000 claims abstract description 8
- 230000011218 segmentation Effects 0.000 claims abstract description 7
- 241000196324 Embryophyta Species 0.000 claims description 19
- 238000005070 sampling Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000009826 distribution Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000011156 evaluation Methods 0.000 abstract description 7
- 238000003745 diagnosis Methods 0.000 description 8
- 238000002310 reflectometry Methods 0.000 description 8
- 238000011160 research Methods 0.000 description 7
- 238000009395 breeding Methods 0.000 description 6
- 230000001488 breeding effect Effects 0.000 description 6
- 230000008859 change Effects 0.000 description 6
- 238000010219 correlation analysis Methods 0.000 description 5
- 230000000875 corresponding effect Effects 0.000 description 5
- 240000007594 Oryza sativa Species 0.000 description 4
- 235000007164 Oryza sativa Nutrition 0.000 description 4
- 240000008042 Zea mays Species 0.000 description 3
- 235000016383 Zea mays subsp huehuetenangensis Nutrition 0.000 description 3
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 3
- 238000012512 characterization method Methods 0.000 description 3
- 229930002875 chlorophyll Natural products 0.000 description 3
- 235000019804 chlorophyll Nutrition 0.000 description 3
- ATNHDLDRLWWWCB-AENOIHSZSA-M chlorophyll a Chemical compound C1([C@@H](C(=O)OC)C(=O)C2=C3C)=C2N2C3=CC(C(CC)=C3C)=[N+]4C3=CC3=C(C=C)C(C)=C5N3[Mg-2]42[N+]2=C1[C@@H](CCC(=O)OC\C=C(/C)CCC[C@H](C)CCC[C@H](C)CCCC(C)C)[C@H](C)C2=C5 ATNHDLDRLWWWCB-AENOIHSZSA-M 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000003337 fertilizer Substances 0.000 description 3
- 235000009973 maize Nutrition 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 235000015097 nutrients Nutrition 0.000 description 3
- 230000000050 nutritive effect Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 235000009566 rice Nutrition 0.000 description 3
- 239000002689 soil Substances 0.000 description 3
- 238000009331 sowing Methods 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 230000002596 correlated effect Effects 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000004720 fertilization Effects 0.000 description 2
- 239000004220 glutamic acid Substances 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- BASFCYQUMIYNBI-UHFFFAOYSA-N platinum Chemical compound [Pt] BASFCYQUMIYNBI-UHFFFAOYSA-N 0.000 description 2
- 238000000985 reflectance spectrum Methods 0.000 description 2
- 230000006641 stabilisation Effects 0.000 description 2
- 238000011105 stabilization Methods 0.000 description 2
- 229920000742 Cotton Polymers 0.000 description 1
- 244000068988 Glycine max Species 0.000 description 1
- 235000010469 Glycine max Nutrition 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
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 1
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 238000003556 assay Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 125000000058 cyclopentadienyl group Chemical group C1(=CC=CC1)* 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000012631 diagnostic technique Methods 0.000 description 1
- 238000011496 digital image analysis Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- ZSWFCLXCOIISFI-UHFFFAOYSA-N endo-cyclopentadiene Natural products C1C=CC=C1 ZSWFCLXCOIISFI-UHFFFAOYSA-N 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000013401 experimental design Methods 0.000 description 1
- 210000003608 fece Anatomy 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000002329 infrared spectrum Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000010871 livestock manure Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000000618 nitrogen fertilizer Substances 0.000 description 1
- 235000021049 nutrient content Nutrition 0.000 description 1
- 235000003715 nutritional status Nutrition 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000032696 parturition Effects 0.000 description 1
- 229910052698 phosphorus Inorganic materials 0.000 description 1
- 239000011574 phosphorus Substances 0.000 description 1
- 229910052697 platinum Inorganic materials 0.000 description 1
- 229910052700 potassium Inorganic materials 0.000 description 1
- 239000011591 potassium Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000004611 spectroscopical analysis Methods 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 235000013619 trace mineral Nutrition 0.000 description 1
- 239000011573 trace mineral Substances 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances 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
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0098—Plants or trees
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Physics & Mathematics (AREA)
- Wood Science & Technology (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Botany (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 invention discloses a kind of method for building up of the picture appraisal index of crop nitrogen nutrition Nondestructive, including：Obtain wheat canopy image, Leaf nitrogen concentration；Segmentation extraction wheat canopy image calculates the average pixel value of all non-zero pixel R, G of blade in every width wheat canopy image, B, H, S, I component as basic Color characteristics parameters r, g, b, h, s, i；Calculate 9 image features r, g, b, r-g-b, r-g, r-b, (r-g-b)/(r+g+b), (r-g)/(r+g+b), (r-b)/(r+g+b)；CMI=(xr-yg-zb) is built, is fitted with Leaf nitrogen concentration, is determined weight coefficient x, y, z, to CMI standardizations, determine NCMI=(xr-yg-zb)/(r+g+b).The NCMI that the present invention establishes is relatively suitable winter wheat nitrogen nutrition evaluation index, has Stability and veracity, can carry out quantitatively evaluating to crop nitrogen content.
Description
Technical field
The present invention relates to a kind of method for building up of the picture appraisal index of crop nitrogen nutrition Nondestructive.
Background technology
With remote sensing and the high speed development of image processing techniques, extraction canopy image parameter is examined into the lossless nitrogen nutrition of row crop
It is disconnected just to become current research hot spot[1-5].But it is complicated to obtain the data analysis that canopy reflectance spectra equipment is expensive, is related to, and limits
Extensive use of the remote sensing technology in agricultural production；And digital camera is easy to operate, quick, in the lossless Nitrogen nutritional status of crop
With certain application prospect[2].Crop leaf color changes with the variation of internal nutrition, the determination of leaf image characteristic parameter with
Acquisition is the key that Accurate Diagnosis crop N Nutrition.Related research result is shown, with the relevant base image of nutrient index
Parameter, Different Crop are different.J.Vollmann[3]And Shibayama[4]Studies have shown that with soybean and rice leaf leaf
The relevant image parameter of chlorophyll contents SPAD values be respectively green component G and green color index (leaf greenness index,
LGI), Kyu-Jong etc.[5]It was found that G and Nitrogen in Rice cumulant in 0.83 it is significantly correlated；Wang Fangyong[6]Analysis finds L*a*b*
The b* parameters in space and the S components in the spaces HSI and cotton SPAD values, Different Nitrogen Concentration good relationship.Compare forefathers the study found that
Is interacted by processing and is combined for canopy base image parameter, the parameter of acquisition and chlorophyll content in leaf blades, N content of crop tissue
Correlativity becomes apparent, and the experiment of Karcher, Wang Yuan and Robert L.Rorie are shown simultaneously, the bottle green under the spaces HSI
The Nitrogen Nutrition of index D GCI and green meadow[7], oryza sativa l. NC, SPAD[8]And maize leaf nitrogen content[9]Exist good
Good correlation；Image combination parameter (R-B), (G-B) under rgb space to the Top-three Leaves SPAD values of winter wheat each breeding time with
Nitrogen content, the expression of plant nitrogen content are ideal[10].In these parameters, DGCI=[(H-60)/60+ (1-S)+(1-I)]/3[7]Be to base image parameter H, S, I carried out after normalized etc. proportions be added；Feux rouges standardized value NRI=R/ (R+G
+B)[11]It is the ratio of red component and 3 monochromatic component summations, similar also has green light standard value (Normalized
Blueness Intensity, NGI)[12], blu-ray standard value (Normalized Redness Intensity, NBI)[13]。
As it can be seen that the conversion of crop base image nonlinearity in parameters and standardization, it is improved to a certain extent to nitrogen nutrition
Precise Diagnosis.But crop growth conditions and nutrient content change with the change of kind, breeding time, intensity of illumination, fertilising etc.
Become[14], and then cause difference of the canopy image index to its nutrition condition ability to express.Compare breeding time the study found that 12
The NBI of the leaf phase and NRI of pustulation period and spring maize nitrogen nutrition index degree of correlation are higher[13], NRI can preferably reflect period of seedling establishment with
The N Nutrition of jointing stage wheat[11,15], Li Hongjun etc.[16]Then find wheat period of seedling establishment good relationship is reflective blade face
Green light and feux rouges ratio G/R；Hu Hao[17]Researches show that each monochromatic component of rgb space and (R+G+B) and Wheat Leavess nitrogen
In negative correlation in various degree, (R-G-B's content) is proportionate.As it can be seen that wheat canopy leaf color be green 3 primary colors of Lan Hong synthesis it is anti-
It reflects, the change of any type monochrome can all cause whole canopy leaf color to change in various degree, the typical image under aforementioned rgb space
Characteristic parameter NRI, NGI, NBI, G/R etc. do not consider entirety of the remaining monochromatic component to Nutrition monitoring in prominent monochromatic component
It influences.
Bibliography：
[1] Ding Yongjun, Li Minzan, Sun Hong wait tomato nutrient diagnostic model [J] the agricultures of based on multispectral image technology
Industrial engineering (IE) journal, 2012,28 (8)：175‐180.
[2] Liu Ying, Li Zhi flood carry out research [J] the corns section of corn Nitrogen Nutrition Diagnosis using Digital image technology
It learns, 2010,18 (4)：147‐149.[3]J.Vollmann J,Walter H,Sato T,et al.Digital image
analysis and chlorophyll metering for phenotyping the effects of nodulation
in soybean.[J].Computers and Electronics in Agriculture,2011(1):190‐195.
[4]Shibayama M,Sakamoto T,Takada E,et al.Estimating rice leaf
greenness(SPAD)using Fixed‐Point continuous observations of visible red and
near infrared narrow‐band digital images[J].Plant Production Science,2012,15
(4):293‐309.
[5]Kyu J L.Byuu W L Estimation of rice growth and nitrogen nutrition
status using color digital camera image analysis[J].European jorunal of
Agronomy.2013.(6):57‐68.
[6] Wang Fangyong, Wang Keru, Li Shaokun wait using digital camera and imaging spectrometer estimation cotton leaf chlorophyll
With nitrogen content [J] Acta Agronomica Sinicas, 2010,36 (11)：1981‐1989.
[7]Karcher D E,Richardson M D.Quantifying turf grass color using
Digital image analysis [J] .Crop Sci, 2003,43:943‐951.
[8] Wang Yuan, Wang Dejian, Zhang Gang wait rice canopy image segmentation and Nitrogen Nutrition Diagnosis of the based on digital camera
[J] Journal of Agricultural Engineering, 2012,28 (17)：131‐136.
[9]Rorie R L,Purcell L C,Karcher D E,et al.The assessment of leaf
Nitrogen in corn from digital images [J] .Crop Sci, 2011 (51):2174‐2180.
[10] application [D] China Agricultural University of the Wu Funing image processing techniques in winter wheat Nitrogen nutritional status,
2004.
[11] Xiao Yanbo, Jia Liangliang, Chen Xinping wait application Digital image analysis techniques to carry out winter wheat jointing stage nitrogen battalion
Support diagnosis [J] China agronomy notification, 2008,24 (8)：448‐453.
[12] the towering applications Digital image technology of Li Lantao, Zhang Meng, Ren Tao, Li little Kun, Cong Huan, Wu Lishu, Lu Jian carries out
Nitrogen Nutrition of Paddy Rice Plant diagnosis [J] plant nutrients and fertilizer journal, 2015,01:259‐268.
[13] platinum is suitable, Cao Weidong, Xiong Jing, waits application digital cameras progress green manure to turn over rear spring maize nitrogen nutrition and examines
Disconnected and production forecast [J] spectroscopy and spectrum analysis, 2013, (12)：3334‐3338.
[14] Wang Renhong, Song Xiaoyu, Li Zhenhai wait winter wheat nitrogen nutrition index estimation [J] the agricultures of based on EO-1 hyperion
Industrial engineering (IE) journal, 2014,30 (19)：191‐198
[15] Zhang Lizhou, Hou Xiaoyu, Zhang Yuming wait digital pictures diagnostic techniques in winter wheat Nitrogen Nutrition Diagnosis
Using [J] Chinese Ecological Agriculture journals, 2011,19 (5)：1168‐1174.
[16] Li Hongjun, Zhang Lizhou, Chen Ximing wait application digital pictures to carry out image point in wheat nitrogen nutrient diagnosis
Research [J] Chinese Ecological Agriculture journals of analysis method, 2011,19 (1)：155‐159.
[17] Hu Hao are based on winter wheat Nitrogen Nutrition Diagnosis and growth monitoring [D] China of visible light-near infrared spectrum
Academy of Agricultural Sciences, 2009.
Invention content
The purpose of the present invention is being directed to the deficiencies in the prior art, a kind of crop nitrogen nutrition Nondestructive is provided
The method for building up of picture appraisal index, (different planting densities are horizontal, difference applies nitrogen water by analyzing different Plant planes by inventor
It is flat) under each base image parameter to the characterization ability of nitrogen, finding representative monochromatic component simultaneously enhances its proportion, and interaction tuning is surplus
The combining weights of remaining component, and further standardization search out more suitable picture appraisal index.9 are determined first
Image features, i.e. 3 monochromatic components r, g, b, 3 linear combination parameters r-g-b, r-g, r-b and 3 standardization are special
Parameter (r-g-b)/(r+g+b), (r-g)/(r+g+b), (r-b)/(r+g+b) are levied, more representative base image ginseng is explored
Number and its weight, and best fit is carried out with nitrogen nutrition index, determine the color combination standard index proposed under rgb space
(NCMI), it is found from the comparison of 3 typical image parameter (DGCI, NRI, G/R) different cultivars, different sowing schemes, with leaf
The correlation and error of fitting of piece nitrogen content (LNC) are relatively stablized, and are relatively suitable winter wheat nitrogen nutrition picture appraisal index.
The purpose of the present invention is what is be achieved through the following technical solutions：
A kind of method for building up of the picture appraisal index of crop nitrogen nutrition Nondestructive, it includes the following steps：
(1), it samples：Obtain the Leaf nitrogen concentration of wheat canopy image, wheat plant；
(2), using the K mean cluster method segmentation extraction wheat canopy image based on H components, every width wheat canopy is calculated
The average pixel value of all non-zero pixel R, G of blade, B, H, S, I component is fixed respectively as basic Color characteristics parameters in image
Justice is r, g, b, h, s, i；Calculate 9 image features, i.e. 3 monochromatic component r, g, b, 3 linear combination parameter r-g-b,
R-g, r-b and 3 normalizing parameter (r-g-b)/(r+g+b), (r-g)/(r+g+b), (r-b)/(r+g+b)；
(3), structure waits for color combinatorial index CMI (Color Mix Index)=(xr-yg-zb) of tuning, then will
The Leaf nitrogen concentration of CMI and identical field is fitted, and determines the weight coefficient x, y, z of 3 components, finally to CMI standardizations,
Determine NCMI：NCMI=(xr-yg-zb)/(r+g+b).
In step (1), the acquisition methods of wheat canopy image：In wheat during jointing stage, using camera away from canopy 1.0m height,
It is sampled with the shooting of 90 ° of ground.It is preferred that obtaining wheat canopy image under wheat during jointing stage, fair weather, the jointing stage is wheat life
The period of important monitoring and nitrogen fertilizer application in growth process；The picture shot under fair weather is clear, and segmentation effect is good.Concrete operations
When, slr camera Olympus E-620 may be used, fair weather is sampled away from canopy 1.0m height, with the shooting of 90 ° of ground, obtained
The wheat canopy image obtained should collect whole plant.
The acquisition methods of the Leaf nitrogen concentration of wheat plant：It is destructive to wheat overground part on the day of wheat canopy image taking
Sampling selects plant similar in 15~25 plants of growing ways, the Leaf nitrogen concentration of Kjeldahl nitrogen determination wheat plant to be averaged.
Sample point picks up from different cultivars, different growing, different nitrogen amount applieds, different planting densities and different year.
In step (3), fit procedure is as follows：
A, set x ∈ [1,2], y ∈ [- 1,1], z ∈ [- 1,1], the contribution degree of the more big then corresponding color component of absolute value more
Greatly, 0 i.e. without contribution degree；
B, within the above range, x, y are constantly adjusted by step-length (being set as 0.05), z values with Leaf nitrogen concentration return and divide
Analysis calculates x, y, z values and coefficient of determination R2, build four-dimensional array [x, y, z, R2]；
C, four-dimensional array [x, y, z, R are drawn2] three-dimensional distribution map (see Fig. 1)；Shade indicates R2Just, CMI and leaf
The highest red area of piece nitrogen content correlation is mainly distributed on x ∈ [1.5,2], z ∈ [- 1, -0.5] or y ∈ [- 0.5,0], z
∈[-1,-0.5]；
d、R2When being up to 0.83353, corresponding x, y, z are the optimal value of r, g, b linear fit, x=1.6, y=-
0.95, z=-0.8.
E, to CMI standardizations, determine that the specific formula of NCMI are as follows：
NCMI=(1.6r-0.95g-0.8b)/(r+g+b).
A kind of method of wheat nitrogen nutrition Nondestructive, includes the following steps：
(1) the wheat canopy image for obtaining field to be measured, with the K mean cluster method segmentation extraction wheat based on H components
Canopy image calculates 3 monochromatic components r, g, b；
(2) x, y, z in color combination standard index NCMI is determined according to the method described in the present invention, wherein NCMI
=(xr-yg-zb)/(r+g+b)；
(3) value of 3 monochromatic components r, g, b obtaining in step (1) are substituted into the NCMI determined in claim 2 to calculate
In formula, the color combination standard index NCMI being calculated is the wheat nitrogen content for the field to be measured predicted.
The definition of all parameters and computational methods are the same as above-mentioned a kind of for wheat nitrogen nutrition Nondestructive in method of the present invention
Picture appraisal index method for building up.
Beneficial effects of the present invention：
1, the method for the present invention passes through under different bearing stage difference Plant plane, NCMI and 3 typical image features is joined
Several comparisons of prediction error and correlation analysis to wheat leaf blade nitrogen content shows NCMI as winter wheat nitrogen nutrition evaluation index
Have suitability, Stability and veracity；
2, sampling digital camera carries out the data sampling of image, and method is easy, and equipment (camera) expense is low, facilitates practical big
Application under the environment of field；
3, quantitatively evaluating is carried out to crop nitrogen content, peasant can be instructed to carry out the rational application of fertilizer, that is, ensure the nitrogen needed for plant
Fertilizer, and excessive fertilization is can avoid, yield is improved, excessive fertilization is avoided to pollute environment；
4, the construction method of evaluation parameter can be adapted for other crops, but need to adopt Different Crop with reference to this method
Sample data are into row coefficient x, the fitting of y.z.
Description of the drawings
Fig. 1 is that 3 monochromatic components r, g, b and relative coefficient are distributed graphics.
Specific implementation mode
1 experiment and data
1.1 experimental design
2012-2014 is in national information agricultural centre Rugao (32 °~32 ° 30 ' of north latitude, 120 ° 20 '~120 ° of east longitude
50 ') Experimental Base rice and kernel wheel tills the land, 2 kinds：Life selects No. 6 (V1), raises wheat No. 18 (V2)；3 Nitrogen Levels：Purity nitrogen 0kg/
hm2(N0), purity nitrogen 150kg/hm2(N1), purity nitrogen 300kg/hm2(N2)；2 planting densities：D1 line-spacings 40cm (100,000 seedlings/mu),
D2 line-spacings 20cm (200,000 seedlings/mu).Using random split block design, 12 are handled, 3 repetitions, totally 36 cells.Plot area
35m2(7m × 5m), drilling, the gross area about 1080m2.Nitrogen is applied to carry out at twice：When sowing, N0, N1, N2, the jointing stage carry out second
As when secondary (mid-March), nitrogen amount applied and sowing.
1.2 data acquire
1.2.1 canopy Image Acquisition
Jointing stage is the nitrogen diagnosis critical period, using slr camera Olympus E-620 (abbreviation Olympus), 3-4 months
Fair weather away from canopy 1.0m height, with 90 ° of ground shooting sampling (table 1).Every sub-sampling 1 time per area, 36 cells take altogether
Sample 36 opens wheat canopy image.
1 wheat of table takes pictures, the Date of Sampling
1.2.2 Leaf nitrogen concentration measures
The chemical assay of wheat leaf blade nitrogen content is carried out with the Image Acquisition same period, and the shooting same day samples overground part destructiveness,
The close plant of 20 plants of growing ways, the Leaf nitrogen concentration (LNC) of Kjeldahl nitrogen determination wheat plant is selected to be averaged per cell.
1.2.3 model evaluation standard
Following index is selected to compare the degree of correlation of each image features and wheat leaf blade nitrogen content, evaluation and foreca value
The fitting effect of (NCMI being calculated according to method provided by the invention) and measured value (Leaf nitrogen concentration that the same period measures)
Fruit.
1) coefficient of determination R2：The square value of correlation coefficient r shows the degree that predicted value explains that actual value is deteriorated, and calculates public
Formula：
In formula, xiFor the measured value of sample i,For xiAverage value；yiFor the measured value of sample i,For yiAverage value；
N is sample number.
2) root-mean-square error RMSE：That examines predicted value and measured value meets accuracy, calculation formula：
In formula, yi' the actual value measured for sample i reference instrument methods.
2 wheat canopy picture appraisal index studies
Over-segmentation phenomenon caused by avoid uneven illumination under the environment of crop field, background complexity and shadow occlusion etc. as possible, profit
With the K mean cluster method based on H components, (Huang Fen, Yu Qi, Yao Xia wait the K mean cluster of wheat canopy image H components to divide
[J] computer engineering and application, 2014, (3)：129-134.) segmentation extraction wheat canopy image pattern, calculates every width blade
All non-zero pixel R, G, B, H, S, I component average pixel value as basic Color characteristics parameters, be respectively defined as r, g, b,
h,s,i；Calculate pseudoreduced 9 image features accordingly, i.e. 3 monochromatic component r, g, b, 3 linear combination parameter r-g-
B, r-g, r-b and 3 normalizing parameter (r-g-b)/(r+g+b), (r-g)/(r+g+b), (r-b)/(r+g+b), with blade
Nitrogen content carries out correlation analysis and best fit, determines wheat canopy picture appraisal index.
The correlation analysis of 2.1 image features and nitrogen nutrition index
Experimental data in 2013 is selected, compares different growing, kind, density and lower 9 images of nitrogen amount applied respectively
Correlativity (the R of characteristic parameter and Leaf nitrogen concentration (LNC)2)。
Table 2 shows that different bearing stage, monochromatic component r is apparently higher than g and b；3 linear combination parameter r-g-b, r-g,
R-b is then substantially higher than same period monochromatic component, and r-b is slightly higher, March 14 and April r-b and LNC on the 1st R2Respectively -0.74 and -
0.77；After this 3 linear combination parameters standardization, degree of correlation further increases, wherein March 14 (r-g-b)/(r+g+
B) it is extremely significantly correlated (R with LNC2=-0.85).
The coefficient of determination R of wheat canopy characteristic parameter and LNC under the different Plant planes of table 22(different cultivars, level of density,
Apply nitrogen scheme)
Note：V1, which makes a living, selects No. 6, and V2 is to raise wheat No. 18；D1 is line-spacing 40cm (100,000 seedlings/mu), and D2 is line-spacing 20cm (200,000
Seedling/mu)；N0 is purity nitrogen 0kg/hm2, N1 is purity nitrogen 75kg/hm2, N2 is purity nitrogen 150kg/hm2, similarly hereinafter.
For 2 kinds (V1, V2), the correlation of monochromatic component r and g are better than b；Linear combination parameter r-g-b, r-b
R2Then it is relatively higher than r and g, wherein the linear combination parameter r-b of V1 and V2 reaches -0.66；After standardization, it is compared
With 3 combination parameters (r-g-b, r-b, r-g), V1 kinds correlation is promoted to -0.73 from -0.48, -0.77, -0.55 respectively, -
0.78, -0.59, V2 kind correlations are promoted to -0.53, -0.67, -0.37 respectively from -0.45, -0.66, -0.31.
Related level is similar with kind to Leaf nitrogen concentration for lower 9 image features of 2 planting densities, monochromatic component
The correlation of r and g is higher than b；For the degree of correlation of linear combination parameter r-b better than 3 single amounts and other 2 combination parameters, D2 is close
The R of the lower r-b and LNC of degree2Up to -0.61；Relative to 3 monochromatic components and 3 linear combination parameters, the normalizing parameter of D2 density
Correlation promoted.
Correlation under 3 nitrogen amount applieds is similar to planting density, and monochromatic component is weaker；3 linear combination parameters are then
It is relatively strong, compared with r-g and r-g-b, r-b highers and stabilization；Meanwhile the correlation of 3 normalizing parameters further enhances,
The R of r-b under different Nitrogen applications2Respectively -0.62, -0.73 and -0.4, and the R of (r-b)/(r+g+b)2Then be respectively increased-
0.72, -0.74 and -0.41；The correlation that N1 applies nitrogen scheme is more notable with respect to N0 and N2.
2.2. the fitting and determination of image evaluation of nutrition index
Correlation analysis finds that 3 monochromatic components of rgb space differ to the characterization power of Leaf nitrogen concentration, but 3 linear
The related advantages of combination parameter are better than 3 monochromatic components, and the correlation ratio r-g and r-g-b highers and stabilization of r-b.Though as it can be seen that
Right g, b judge that the accuracy of Leaf nitrogen concentration is relatively low and built on the sand, but there is also the contribution degrees that can not ignore；Linear combination is joined
Further after standardization, the promotion of degree of correlation becomes apparent number.Therefore, the structure of wheat nitrogen nutrition picture appraisal index,
3 foundation characteristic component r, g, b and its weight should be weighed, optimize combination and standardization.
Structure waits for color combinatorial index CMI (Color Mix Index)=(xr-yg-zb) of tuning first, then with phase
LNC with field is fitted repeatedly through multi-scheme, determines the weight coefficient x, y, z of 3 components, finally to CMI standardizations, really
Determine NCMI.
If NCMI=(xr-yg-zb)/(r+g+b), fit procedure is as follows：
(1) set x ∈ [1,2], y ∈ [- 1,1], z ∈ [- 1,1], the contribution degree of the more big then corresponding color component of absolute value more
Greatly, 0 i.e. without contribution degree；
(2) within the above range, x, y are constantly adjusted by step-length (being set as 0.05), z values are returned with Leaf nitrogen concentration
Analysis calculates x, y, z values and coefficient of determination R2, build four-dimensional array [x, y, z, R2]。
(3) four-dimensional array [x, y, z, R are drawn2] three-dimensional distribution map (see Fig. 1).Distribution of color indicates R2Just, CMI with
The highest red area of nitrogen nutrition correlation is mainly distributed on x ∈ [1.5,2], z ∈ [- 1, -0.5] or y ∈ [- 0.5,0], z
∈[-1,-0.5]。
(4)R2When being up to 0.83353, corresponding x, y, z are the optimal value of r, g, b linear fit, x=1.6, y=-
0.95, z=-0.8.
(5) to CMI standardizations, determine that the specific formula of NCMI are as follows：
NCMI=(1.6r-0.95g-0.8b)/(r+g+b) (1)
R, g, b data of field to be measured are substituted into above-mentioned formula, so that it may the color combination standard of corresponding field be calculated
Change index NCMI, which is nitrogen content predicted value.
3 interpretations of result
The experimental data that independent time (2014) is divided by different growing and different Plant planes, using the coefficient of determination
(R2) and prediction error (RMSE) quantitative analysis NCMI and 3 the more mature image parameter feux rouges standardized value NRI of research, depths
The correlation of green color index DGCI and green light and feux rouges ratio G/R and Leaf nitrogen concentration, research NCMI characterize Wheat Leavess nitrogen
The feasibility of content.
G/R=g/r (4)
The analysis of 3.1 Wheat Cultivars compares
As a result (table 3) is shown, the R of 2 kinds, 4 image features2, March 8 is relatively low, April 15 highest,
Error is minimum.Think, March 8, wheat was in period of seedling establishment and jointing stage separation, and the wheat nitrogen of the growing stage is inhaled
Receipts, transhipment are more active, and the Nitrogen Accumulation of itself cauline leaf is in the dynamic change stage, affects measurement Leaf nitrogen concentration to a certain degree
The accuracy of LNC, and the unstable nutrition condition reflection of wheat is to canopy leaves surface, it is also possible to lead to the characteristics of image of extraction
Parameter further reduced correlation between the two there are deviation；Late growth stage (April 15) is entered, it is tired that wheat enters nitrogen
Product peak second stage, nitrogen conveying operating and other Related Physiological Characteristics all feed back to more completely canopy leaves surface and
Structure, the image and nutrition parameters obtained at this time is more firm, therefore degree of fitting and estimation precision are higher.
Because the different plant type of wheat breed causes the reflectivity curve of visible light region canopy spectra different with plant height, 2 product
Kind R2(being shown in Table 3) slightly is distinguished with RMSE, but compared to other 3 characteristic parameters, NCMI maintains relatively stable fitting degree
And estimation precision, the R of V1 and 2 nutritive index2- 0.76~-0.95, RMSE is maintained between 1.833~3.893；The R of V22
It floats -0.69~-0.98, RMSE is in 1.249~4.36 ranges.Wherein, V1 is higher, quasi- in the correlation of 3 breeding times
It is relatively low to close error, April 15, although the R of NRI and NCMI and LNC2It is -0.95, but the RMSE of NCMI is less than NRI；V2 kinds
The only R on March 82It is slightly weak with RMSE, March 31 and April NCMI and NRI and LNC on the 15th R2It is equal, respectively -0.84, -
0.94, NCMI equally obtains the RMSE value less than NRI.Think, the acquisition of image parameter and wheat canopy reflectivity are close
Cut phase is closed, research shows that from the jointing stage to florescence, it is seen that the reflection of light region takes the lead in rising after drop, and late growth stage, blade starts to become
It is yellow, it is seen that the canopy spectra reflectivity of light part rises.This of different growing wheat canopy EO-1 hyperion and multispectral reflectivity
Kind changing rule so that later stage NCMI value is because 3 monochromatic components are with the promotion of reflectivity, because the optimization proportion of setting is further
Different degrees of enhancing has been obtained, has compared the NRI and G/R for only considering single color component, degree of correlation and prediction error are
It improves.
The coefficient of determination R of table 3 different cultivars wheat canopy characteristic parameter and LNC2With root-mean-square error RMSE
By table 4 as it can be seen that giving birth to early stage, in addition to individual data, lower 4 image features of D2 density journey related to LNC's
Degree and estimation precision are higher than D1 in various degree；But with the passage of breeding time, the correlation gap of D1 and D2 taper into, and R2
Value rises, in peaking on April 15.It is analyzed from optics and imaging angle, the wheat image shot under the environment of crop field is by soil, stone
The background interferences such as gravel, weeds may cause wheat canopy spectrum " red shift " phenomenon occur in red border region, reduce correlation compared with
Strong long-wave band (feux rouges) reflectivity, and short-wave band (blue light and green light) reflectivity that correlation is weaker increases.March 8 wheat
Plant is smaller, and under low-density D1, the background interferences such as soil, weeds are more prominent with respect to D2, and later stage wheat plant is grown up, canopy cyclopentadienyl
It is close, it is reduced by the difference of background interference under D1 and D2 density, thus image parameter related levels and estimation precision step up, it is right
The characterization ability of nitrogen nutrition is more close.But under D1 density, the DGCI under March 8 and March 31 spaces HSI is slightly better than RGB
3 image parameters under space, think, are detached with brightness I with the relevant component H and S of color under HSI color spaces, because
And reduce influence of the soil environment to reflectance spectrum.
As it can be seen that lower 3 image features of rgb space are to having the wheat nitrogen nutrition condition of certain Canopy cover degrees
Reflection is more accurate, the NCMI of proposition showed under D2 density it is more prominent, with the coefficient of determination of 2 nutritive indexes be maintained at-
0.85~-0.97, estimation error is maintained at 1.299~3.505, wherein the R in March 8 and LNC2It is respectively -0.91 with RMSE
With 3.297, the R in April 15 and LNC2It is -0.97 and 1.299 with RMSE points, the R with SPAD2With RMSE point for -0.97 and
1.630。
The coefficient of determination R of 4 different densities of table horizontal wheat canopy characteristic parameter and LNC2With root-mean-square error RMSE
To reduce the interference of level of density, the correlation of different Nitrogen Levels under D2 density is only analyzed.The display of table 5, N0, N1
With the lower R of N2 processing2It differs greatly with RMSE, N1 is relatively strong.Think, wheat canopy visible light wave under different Nitrogen applications
Section reflectivity has differences, and as nitrogen amount applied increases, chlorophyll content increases, and the absorption of most of solar visible radiation has
Enhanced, canopy reflectance factor decreases；But excessive nitrogen (N2) of applying may inhibit wheat to phosphorus, potassium and other trace elements
It absorbs, causes canopy leaves to be off color, physiological status is abnormal, and the image parameter and nutritive index of acquisition have deviation, phase
Closing property is weakened.Meanwhile when wheat nitrogen stress (N0), blade LNC is relatively low, but due to the nitrogen in old leaf to young leaves turn
It moves, shows as the chlorisis yellow first of plant lower blade, and gradually to top leaf expansion, this easy service performance makes under N0
Red component r rise, b components decline, and g components are stablized relatively, and mistake causes NCMI values to go up not down (see formula (1)), drop
The low correlation with LNC.
Table 5 shows that NCMI shows the degree of correlation to match with above-mentioned analysis and rule under different nitrogen amount applieds simultaneously
Feature is restrained, under same Nitrogen Level, there is the fitting degree for being higher than other parameters and preferably estimation precision, the correlation under N1
Property it is the most notable, error precision is minimum, is respectively -0.78 and 1.960 with the correlation and error of LNC.
5 difference of table applies nitrogen scheme wheat canopy characteristic parameter and the coefficient of determination R of LNC2With root-mean-square error RMSE
Above-mentioned correlation analysis is shown with precision estimation, relative to other 3 typical image evaluation parameters, passes through each base of tuning
Plinth color component proportion and the linear fit parameter NCMI of standardization, in 3 breeding times, 2 wheat breeds, 2 density
Under horizontal and 3 nitrogen amount applieds, preferable stability is maintained with the correlation and fitting precision of Leaf nitrogen concentration LNC.
Claims (5)
1. a kind of method for building up of picture appraisal index for wheat nitrogen nutrition Nondestructive, it is characterised in that it include with
Lower step：
(1), it samples：Obtain the Leaf nitrogen concentration of wheat canopy image, wheat plant；
(2), using the K mean cluster method segmentation extraction wheat canopy image based on H components, every width wheat canopy image is calculated
All non-zero pixel R, G of middle blade, B, H, S, I component average pixel value as basic Color characteristics parameters, be respectively defined as
r,g,b,h,s,i；Calculate 9 image features, i.e. 3 monochromatic component r, g, b, 3 linear combination parameter r-g-b, r-g,
R-b and 3 normalizing parameter (r-g-b)/(r+g+b), (r-g)/(r+g+b), (r-b)/(r+g+b)；
(3), structure waits for the color combinatorial index CMI=(xr-yg-zb) of tuning, then quasi- with the Leaf nitrogen concentration of identical field
It closes, fit procedure is as follows：
A, x ∈ [1,2], y ∈ [- 1,1], z ∈ [- 1,1] are set, the contribution degree of the more big then corresponding color component of absolute value is bigger, and 0 is
Without contribution degree；
B, within the above range, if step-length is 0.05, x, y are constantly adjusted by step-length, z values with Leaf nitrogen concentration return and divide
Analysis calculates x, y, z values and coefficient of determination R2, build four-dimensional array [x, y, z, R2]；
C, four-dimensional array [x, y, z, R are drawn2] three-dimensional distribution map；Distribution of color indicates R2Just, CMI and Leaf nitrogen concentration phase
The highest region of closing property, is distributed in x ∈ [1.5,2], z ∈ [- 1, -0.5] or y ∈ [- 0.5,0], z ∈ [- 1, -0.5]；
D, for wheat crop, R2When being up to 0.83353, corresponding x, y, z are the optimal value of r, g, b linear fit, x=
1.6, y=-0.95, z=-0.8；
E, to CMI standardizations, determine that the specific formula of NCMI are as follows：
NCMI=(1.6r-0.95g-0.8b)/(r+g+b).
2. the method for building up of the picture appraisal index of wheat nitrogen nutrition Nondestructive according to claim 1, feature
It is in step (1), the acquisition methods of wheat canopy image：In wheat during jointing stage, using camera away from canopy 1.0m height and ground
The shooting sampling of 90 ° of face.
3. the method for building up of the picture appraisal index of wheat nitrogen nutrition Nondestructive according to claim 1, feature
It is in step (1), the acquisition methods of the Leaf nitrogen concentration of wheat plant：To wheat overground part on the day of wheat canopy image taking
Destructiveness sampling, selects 15~25 plants of plant, the Leaf nitrogen concentration of Kjeldahl nitrogen determination wheat plant to be averaged.
4. the method for building up of the picture appraisal index of wheat nitrogen nutrition Nondestructive according to claim 1, feature
It is in step (1), sample point picks up from different cultivars, different growing, different nitrogen amount applied, different planting densities and not the same year
Part.
5. a kind of method of wheat nitrogen nutrition Nondestructive, it is characterised in that include the following steps：
(1) the wheat canopy image for obtaining field to be measured, with the K mean cluster method segmentation extraction wheat canopy based on H components
Image calculates 3 monochromatic components r, g, b；
(2) x, y, z in color combination standard index NCMI is determined according to method according to any one of claims 1 to 4,
Wherein, NCMI=(xr-yg-zb)/(r+g+b)；
(3) value of 3 monochromatic components r, g, b being obtained in step (1) are substituted into the NCMI calculation formula determined in claim 1
In NCMI=(1.6r-0.95g-0.8b)/(r+g+b), the color combination standard index NCMI being calculated is to predict
The wheat nitrogen content of field to be measured.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610094126.9A CN105675821B (en) | 2016-02-21 | 2016-02-21 | A kind of method for building up of the picture appraisal index of crop nitrogen nutrition Nondestructive |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610094126.9A CN105675821B (en) | 2016-02-21 | 2016-02-21 | A kind of method for building up of the picture appraisal index of crop nitrogen nutrition Nondestructive |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105675821A CN105675821A (en) | 2016-06-15 |
| CN105675821B true CN105675821B (en) | 2018-11-02 |
Family
ID=56304756
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610094126.9A Expired - Fee Related CN105675821B (en) | 2016-02-21 | 2016-02-21 | A kind of method for building up of the picture appraisal index of crop nitrogen nutrition Nondestructive |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105675821B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106919740A (en) * | 2017-01-25 | 2017-07-04 | 广东省农业科学院农业资源与环境研究所 | Detect method, device and the electronic equipment of plant nitrogen content |
| CN106845554B (en) * | 2017-02-07 | 2019-11-19 | 中国林业科学研究院资源信息研究所 | A kind of image of santal plant strain growth soil iron content determines method and system |
| CN106770299A (en) * | 2017-03-14 | 2017-05-31 | 中国科学院遗传与发育生物学研究所农业资源研究中心 | The method and unmanned plane equipment that crop nitrogen analysis and soil application are instructed are carried out using unmanned plane crop canopies picture |
| CN107274002A (en) * | 2017-04-28 | 2017-10-20 | 河南农业大学 | The construction method of wheat nitrogen rich scarce diagnostic method and its diagnostic model |
| CN108510474B (en) * | 2018-03-09 | 2021-07-06 | 上海烟草集团有限责任公司 | Method and system for evaluating quality of tobacco leaf image, memory and electronic equipment |
| CN110378890A (en) * | 2019-07-23 | 2019-10-25 | 中国科学院东北地理与农业生态研究所 | A kind of prediction technique of hayashishita resource plant above-ground organs N content |
| CN110631995B (en) * | 2019-08-26 | 2021-09-10 | 江苏大学 | Method for synchronously diagnosing nitrogen, potassium and magnesium element deficiency by leaf chlorophyll and leaf surface distribution characteristics |
| CN110567892B (en) * | 2019-09-17 | 2020-11-24 | 中国水利水电科学研究院 | Summer corn nitrogen hyperspectral prediction method based on critical nitrogen concentration |
| CN110874617B (en) * | 2019-11-26 | 2023-05-05 | 南京农业大学 | Method for establishing winter wheat leaf nitrogen content estimation model |
| CN111418323B (en) * | 2020-05-12 | 2021-11-02 | 中国科学院南京土壤研究所 | Nitrogen fertilizer real-time recommendation method based on facility crop canopy coverage and plant height |
| CN112084462B (en) * | 2020-08-27 | 2023-06-23 | 江苏农林职业技术学院 | Crop nitrogen nutrition index estimation model evaluation method based on digital image |
| CN112595714B (en) * | 2020-11-26 | 2022-12-06 | 中国农业科学院农业资源与农业区划研究所 | Tobacco nutrition state discrimination method based on mobile phone image analysis |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5965801A (en) * | 1993-03-04 | 1999-10-12 | Queen's University At Kingston | Apparatus for rapid measurement of hydrogen concentration and its use in the measurement of nitrogenase activity |
| CN101915738A (en) * | 2010-06-23 | 2010-12-15 | 江苏大学 | Method and device for rapidly detecting nutritional information of tea tree based on hyperspectral imaging technique |
| CN101936882A (en) * | 2010-08-10 | 2011-01-05 | 江苏大学 | Nondestructive testing method and device for nitrogen and water of crops |
| CN102222234A (en) * | 2011-07-14 | 2011-10-19 | 苏州两江科技有限公司 | Image object extraction method based on mean shift and K-means clustering technology |
| CN102788752A (en) * | 2012-08-08 | 2012-11-21 | 江苏大学 | Non-destructive detection device and method of internal information of crops based on spectrum technology |
| CN104132897A (en) * | 2014-08-16 | 2014-11-05 | 西北农林科技大学 | Measuring method and device for nitrogen content of plant leaf on basis of handheld equipment |
-
2016
- 2016-02-21 CN CN201610094126.9A patent/CN105675821B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5965801A (en) * | 1993-03-04 | 1999-10-12 | Queen's University At Kingston | Apparatus for rapid measurement of hydrogen concentration and its use in the measurement of nitrogenase activity |
| CN101915738A (en) * | 2010-06-23 | 2010-12-15 | 江苏大学 | Method and device for rapidly detecting nutritional information of tea tree based on hyperspectral imaging technique |
| CN101936882A (en) * | 2010-08-10 | 2011-01-05 | 江苏大学 | Nondestructive testing method and device for nitrogen and water of crops |
| CN102222234A (en) * | 2011-07-14 | 2011-10-19 | 苏州两江科技有限公司 | Image object extraction method based on mean shift and K-means clustering technology |
| CN102788752A (en) * | 2012-08-08 | 2012-11-21 | 江苏大学 | Non-destructive detection device and method of internal information of crops based on spectrum technology |
| CN104132897A (en) * | 2014-08-16 | 2014-11-05 | 西北农林科技大学 | Measuring method and device for nitrogen content of plant leaf on basis of handheld equipment |
Non-Patent Citations (4)
| Title |
|---|
| "基于HSI空间和K-means方法的图像分割算法";李丹丹等;《微电子学与计算机》;20100705;第27卷(第7期);第121-124页 * |
| "小麦冠层图像H分量的K均值聚类分割";黄芬等;《计算机工程与应用》;20140201;第50卷(第3期);第130页第1栏最后一段，第2栏第1段，第130页3.1基于归一化的H分量K均值聚类算法，3.2图像预处理，第132页K均值聚类，3.4开运算平滑图像 * |
| "应用数字图像技术进行水稻氮素营养诊断";李岚涛等;《植物营养与肥料学报》;20150125;第21卷(第1期);第259-268页 * |
| "数字图像诊断技术在冬小麦氮素营养诊断中的应用";张立周等;《中国生态农业学报》;20110915;第19卷(第5期);第1169页1.3数字图像的获取与处理，第1170页常规测试项目与方法 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105675821A (en) | 2016-06-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105675821B (en) | A kind of method for building up of the picture appraisal index of crop nitrogen nutrition Nondestructive | |
| Zhang et al. | Model-based analysis of the relationship between sun-induced chlorophyll fluorescence and gross primary production for remote sensing applications | |
| Zhu et al. | Estimating leaf chlorophyll content of crops via optimal unmanned aerial vehicle hyperspectral data at multi-scales | |
| Sun et al. | Retrieval of rapeseed leaf area index using the PROSAIL model with canopy coverage derived from UAV images as a correction parameter | |
| CN105678281B (en) | Remote sensing monitoring method for mulching film farmland based on spectrum and texture characteristics | |
| CN105445229B (en) | Wheat spring nitrogen fertilizer applying method based on nitrogen balance spectroscopic methodology and its construction method for chasing after nitrogen quantity model | |
| CN110874617B (en) | Method for establishing winter wheat leaf nitrogen content estimation model | |
| Banerjee et al. | High-throughput phenotyping using digital and hyperspectral imaging-derived biomarkers for genotypic nitrogen response | |
| Lebourgeois et al. | A light-weight multi-spectral aerial imaging system for nitrogen crop monitoring | |
| Reyniers et al. | A linear model to predict with a multi‐spectral radiometer the amount of nitrogen in winter wheat | |
| Feng et al. | Advances in plant nutrition diagnosis based on remote sensing and computer application | |
| CN110927082A (en) | Winter wheat yield prediction method based on unmanned aerial vehicle imaging hyperspectral remote sensing | |
| CN110567892B (en) | Summer corn nitrogen hyperspectral prediction method based on critical nitrogen concentration | |
| Wen et al. | Estimating leaf nitrogen concentration considering unsynchronized maize growth stages with canopy hyperspectral technique | |
| Yu et al. | Prediction of soil properties using a hyperspectral remote sensing method | |
| Zhang et al. | Remote monitoring of heading rice growing and nitrogen content based on UAV images | |
| CN110189793A (en) | The building of wheat nitrogenous fertilizer physiological use efficiency estimation models and wheat varieties with different N efficiency classification based on EO-1 hyperion | |
| Meiyan et al. | Improved estimation of canopy water status in maize using UAV-based digital and hyperspectral images | |
| Li et al. | Monitoring of leaf nitrogen content of winter wheat using multi-angle hyperspectral data | |
| Fan et al. | Using an optimized texture index to monitor the nitrogen content of potato plants over multiple growth stages | |
| Li et al. | UAV hyperspectral remote sensing estimation of soybean yield based on physiological and ecological parameter and meteorological factor in China | |
| CN105678280B (en) | Mulching film mulching farmland remote sensing monitoring method based on textural features | |
| Su et al. | Grain yield prediction using multi-temporal UAV-based multispectral vegetation indices and endmember abundance in rice | |
| Paleari et al. | Estimating plant nitrogen content in tomato using a smartphone | |
| Liu et al. | Estimating potato above-ground biomass based on vegetation indices and texture features constructed from sensitive bands of UAV hyperspectral imagery |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20181102 |