CN102759510A - Spectral detection method of rape canopy information - Google Patents
Spectral detection method of rape canopy information Download PDFInfo
- Publication number
- CN102759510A CN102759510A CN201210226049XA CN201210226049A CN102759510A CN 102759510 A CN102759510 A CN 102759510A CN 201210226049X A CN201210226049X A CN 201210226049XA CN 201210226049 A CN201210226049 A CN 201210226049A CN 102759510 A CN102759510 A CN 102759510A
- Authority
- CN
- China
- Prior art keywords
- information
- spectral
- rape
- detection
- canopy
- 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
Images
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a spectral detection method of rape canopy information. The spectral detection method comprise the following steps of: establishing a model based on spectral information acquired from a rape canopy through a readily pre-trained BP (Back Propagation) neural network by using an information detection mode integrating multi-channel spectra to obtain a SPAD value and total nitrogen content, wherein examination shows that the prediction performance and the effect of the model are better. According to the invention, by utilization of the information detection mode integrating the multi-channel spectra, mutual interferences are not generated among spectral channels, moreover, some spectral channel information detection without obvious effect can also be used as assisting channels in light correction and environment impact correction; through the BP neural network model, the accuracy of spectral detection of the rape canopy information is increased; and the method disclosed by the invention is high in accuracy, convenient for sample information acquisition and suitable for agricultural popularization and application.
Description
Technical field
The present invention relates to a kind of plant information spectral method of detection, relate in particular to a kind of rape canopy information spectral method of detection.
Background technology
Plant chlorophyll, total nitrogen content are the chief components of plant nutrient; It is the relevant most important factor of photosynthesis of plant; Chlorophyll is that all can be converted into the photosynthetic biosome of plant nutrient; Full nitrogen is one of essential nutrient of plant, is the main constituent of materials such as amino acid, protein, alkaloid, nucleic acid and chlorophyll.Their content can react the vital sign of plant directly or indirectly, and it is significant to study and detect the content of these parameters in plant.
Occurring in nature basically the color of all objects mainly by the spectral reflection characteristic decision in 400-700nm zone.The plant of normal growth, leaf color determines that by chlorophyllous spectral characteristic chlorophyll has than strong reflection green glow, so its blade is green.Chlorophyll is the important component of plant nitrogen content, and the depth of crop canopies color can reflect full nitrogen metabolism level in the plant body.Different plants all show increase trend in various degree at spectral reflectivity visible, near-infrared band during nitrogen stress.Chinese scholars shows through the research of different sensors and spectroscopic data all kinds of crops, and spectrum index can be used to estimate chlorophyll and the total nitrogen content of chief crop such as wheat, corn, paddy rice and cotton and vegetables.To sum up visible, the reflectance spectrum of visible region and color characteristic can be used to estimate crop leaf chlorophyll and total nitrogen content.
Publication number is the application for a patent for invention of CN1746660A; A kind of new method of canopy reflectance spectra crop crown layer pigment ratio and measuring instrument of design of utilizing disclosed; Can measure the SIPI value of crop quickly and easily; Exactly crop canopies characteristic pigment ratio is assessed, to judging crop growing state and instructing the nitrogenous fertilizer use that vital role is arranged.Utilize daylight to make light source; Through six identical photoelectric sensors,, respectively the reflected light of daylight incident light and vegetation is surveyed near infrared, ruddiness and three characteristic wave strong points of blue light with peculiar spectrum response characteristic; The signal that records is after the A/D conversion; Obtain the SIPI value by microcontroller by the computing formula of SIPI value, calculate the result who characterizes crop growthing state according to SIPI then, the gained result is by liquid crystal display displays.Measurement result can be kept in the instrument, and can be sent to the enterprising row of PC through the RS232 serial ports and further analyze.This detection method and instrument to the daylight illumination conditional request is lower, simple in structure, in light weight, cost is low, easy to use, be suitable for producing in enormous quantities and use.
Publication number is the application for a patent for invention of CN101403689A; Disclose a kind of plant leaf blade nondestructive detection method for physiological index, can carry out fast component contents such as chlorophyll, nitrogen, xenthophylls, moisture, multiparameter detects simultaneously based on visible-near-infrared spectrum.This invention is carried out spectra collection to the calibration set sample, sets up the calibration model between spectral value and the plant component content standard after preferred spectroscopic data being carried out pre-service and wave band; Gather the spectrum of unknown sample,, will select wave band data substitution calibration model components contents to be measured is predicted to spectroscopic data and after handling.This invention technical scheme adopts full spectrum information, and the measured parameter extensibility is strong and improved the precision of prediction and the model adaptability of calibration model; The detection mode that reflects thoroughly that this invention is adopted has increased spectrum sensitivity, and stronger to the adaptability of vane type; A kind of improved wavelet analysis method that this invention is adopted carries out noise remove and baseline correction pre-service simultaneously to the blade spectroscopic data, can effectively improve precision of prediction.
Detect effect in the prior art and receive the systematic error that aspect such as detecting instrument causes easily.
Summary of the invention
The invention discloses a kind of rape canopy information spectral method of detection, solved and detected the problem that effect receives the systematic error that causes aspect such as detecting instrument easily in the prior art.
A kind of rape canopy information spectral method of detection may further comprise the steps:
The spectral information of A, the some rape leaf samples of collection obtains its SPAD value;
B, to the rape leaf sample in the steps A, detect its total nitrogen content;
C, with the spectral information in the steps A as input variable, SPAD value that will be corresponding with said spectral information and total nitrogen content are set up neural network model as output variable;
D, gather the spectral information of rape to be detected and utilize described model to obtain the SPAD value and the total nitrogen content of this rape to be detected, with definite growth of rape state to be detected.
Said SPAD value is to weigh a parameter of the relative content of a strain plant chlorophyll, is the sign of chlorophyll content.
Total nitrogen content refers to the total content of nitrogen in the plant; Nitrogen is the necessary a great number of elements of plant, is the ingredient of important living matters such as protein, chlorophyll, nucleic acid, enzyme, bio-hormone, and contemporaneity Different Crop nitrogen requirement is different; Same crop different times nitrogen requirement is different; Simultaneously, difference is executed nitrogen and is handled the influence difference to crop nitrogen absorption and output, and it is very big to growth and the yield effect of crops to detect total nitrogen content.
Spectral information among described steps A and the step D is the spectral information of rape canopy partial blade.Detect canopy information and make things convenient for instrumentation, be beneficial to the spectral information that instrument detects plant dynamically, apace.
If no specified otherwise, following spectral information is all made a general reference the spectral information of rape canopy partial blade.
Among steps A and the step D; Detection light to rape leaf emission 450-1200nm; The detection light of collection after the rape leaf reflection; Obtain corresponding spectral information, in the 450-1200nm scope, SPAD value and total nitrogen content detected and have the sensitivity characteristic effect, this regional information is helpful to rape leaf SPAD value and the detection of total nitrogen content model.
16 tunnel, the 16 tunnel detection optical wavelength of said detection light in the 450-1200nm scope are respectively 450nm, 480nm, 550nm, 640nm, 680nm, 720nm, 780nm, 820nm, 860nm, 880nm, 940nm, 960nm, 1040nm, 1100nm, 1150nm, 1200nm.
Described neural network model is the BP neural network model.
Gather the rape leaf sample information among the present invention earlier, earlier through apparatus measures and the SPAD value and the total nitrogen content value that calculate the rape leaf sample.The rape leaf sample is carried out spectroscopic data scanning; And the reflectivity of each wave band in the recording feature wave band; As the neural network input variable, pass through the SPAD value and the total nitrogen content that apparatus measures obtains of correspondence are set up the BP neural network model as output variable with spectral reflectivity (being described spectral information).
The BP neural network model in order to improve its reliability, generally need be trained after setting up, and obtains weights and threshold values in the revised BP neural network, the error of computing equipment measured value and the actual output of BP neural network model through training.If error is not more than the anticipation error minimum value, or reached maximum cycle, then training finishes, otherwise continues.
Compared with prior art, the invention has the beneficial effects as follows:
(1) the BP neural network is revised the weights of output influence through each input variable and is obtained its contribution rate to this parameter; With the irrelevant input variable of output through the BP network training after its pairing weights will be reduced to and be close to 0; Improved the accuracy of rape canopy information spectral detection, be beneficial to managerial personnel and correctly apply fertilizer and cultivate.
(2) the information detecting pattern that utilizes multi-channel spectral to be integrated in one; Adopt BP neural net model establishing mode; Can make environmental factor drop to minimum to accuracy and the reliability effect that detects; Not only can not disturb mutually, and some do not have the accessory channel that the detection of spectrum channel information can also be proofreaied and correct as light, environmental impact is proofreaied and correct of obviously effect because of producing between the spectrum channel.Conformability to improving instrument improves helpful.
Description of drawings
Fig. 1 be the inventive method SPAD value and apparatus measures the graph of a relation of SPAD value.
Fig. 2 be the inventive method total nitrogen content and apparatus measures the graph of a relation of total nitrogen content.
Embodiment
A kind of rape canopy of the present invention information spectral method of detection is used for the mensuration of rape SPAD and total nitrogen content, and confirms the growth conditions of plant whereby.
The foundation of model
(1) select 60 sub-districts as training sample set in the rape leafiness phase; The canopy spectra experiment is carried out in this sub-district; Select 15 sub-districts as the forecast sample collection in addition; With the spectral detection of rape canopy information spectrum detection instrument probe the rape canopy of each sub-district is carried out canopy spectra scanning, sunshine earlier through after 16 tunnel spectral detection information channels, focuses on the filter plate center through the focus lamp optical channel with light beam at the spectral information that reflects on the rape canopy; Through optical filter the reflectance spectrum information of certain specific band is sent to photoelectric sensor; Photoelectric sensor obtains 16 band spectrum reflected values of each sub-district rape canopy through the amplification and the processing of feeble signal, and 16 band spectrum reflected values that dsp processor will obtain show on the display unit of MCU through interface circuit.
For the embodiment of the present invention method; Can adopt rape canopy information spectrum detection instrument; Comprise spectrographic detection head and the MCU that is used to receive and handle the spectrographic detection head output signal, MCU also is connected with instruction input block, display unit, storage unit and wireless transmit/receive units respectively.
The spectrographic detection head is included on the light path spectral detection information channel, optical filter, the photoelectric sensor of arranging successively, and the dsp processor that is connected with photoelectric sensor circuit, links to each other through interface circuit between dsp processor and the MCU.Be provided with between photoelectric sensor circuit and the dsp processor and be used for the output signal of photoelectric sensor is nursed one's health and the pretreatment unit that amplifies.
(2) each sub-district canopy SPAD value is measured 30 times through the SPAD-502 detecting instrument in each sub-district, obtain the SPAD value of this sub-district through averaging,, measure its total nitrogen content through Kjeldahl through winning the rape leaf in each cell area.
Wherein, SPAD-502 is the chlorophyll meter that Japanese MINOLTA company produces, and this detecting instrument is measured chlorophyll content of plant through the spectral absorption characteristics of measuring plant leaf blade.Kjeldahl is a kind of method of measuring nitrogen pool in compound or the potpourri; Promptly having under the condition of catalyzer; With the concentrated sulphuric acid sample digestion organic nitrogen all is transformed into inorganic ammonium salt, under alkali condition, ammonium salt is converted into ammonia then, distillate and absorb for excessive acid solution with water vapor; With the standard base (SB) titration, just can calculate the nitrogen amount in the sample again.
(3) 16 band spectrum reflected values concentrating with training sample in the step (1) are as input variable, and SPAD value that detecting instrument in the step (2) is measured and total nitrogen content are set up the BP neural network model as output variable.
In the BP neural network; Wherein input neuron is 16; Be respectively the spectral reflectance value of characteristic wave bands 450nm in the 450-1200nm scope, 480nm, 550nm, 640nm, 680nm, 720nm, 780nm, 820nm, 860nm, 880nm, 940nm, 960nm, 1040nm, 1100nm, 1150nm, 1200nm, with the reflected value of 16 wave bands as x
1, x
2 X
1616 input variables, SPAD value that detecting instrument measures and total nitrogen content are as y
1, y
22 output neurons, after the standardization of data process, Sigmoid selection of parameter 0.9 in the BP network; Get 6 implicit neurons, train 1000 times, obtain the mapping relations of result such as table 1; Present embodiment is chosen typical 15 samples and is listed in table 1 as space is limited.Its match residual values is 0.00019.
Wherein SY1 and SY2 are respectively actual measured value, are used for measuring result calculated with instrument models and compare.
NO. | X 1 | X 2 | ..... | X 16 | Y 1 | sY 1 | Y 2 | Sy 2 |
1 | 0.52 | 0.46 | ...... | ?0.47 | ?21.3 | 20.1 | 2.56 | 2.33 |
2 | 0.64 | 0.57 | ...... | ?0.64 | ?25.6 | 24.4 | 3.78 | 3.47 |
3 | 0.54 | 0.42 | ...... | ?0.54 | ?32.4 | 31.8 | 4.28 | 5.16 |
4 | 0.71 | 0.56 | ...... | ?0.41 | ?33.2 | 33.9 | 6.63 | 4.93 |
5 | 0.69 | 0.49 | ....... | 0.45 | ?35.9 | 34.3 | 7.48 | 7.58 |
6 | 0.56 | 0.34 | ....... | 0.67 | ?35.1 | 35.8 | 8.14 | 7.82 |
7 | 0.48 | 0.39 | ....... | 0.56 | ?38.4 | 39.2 | 7.45 | 7.35 |
8 | 0.34 | 0.30 | ....... | 0.32 | ?41.5 | 42.1 | 12.58 | 13.18 |
9 | 0.38 | 0.27 | ....... | 0.54 | ?42.8 | 43.4 | 13.36 | 15.02 |
10 | 0.24 | 0.20 | ....... | 0.28 | ?52.3 | 51.8 | 16.25 | 15.12 |
11 | 0.36 | 0.27 | ....... | 0.35 | ?52.0 | 52.6 | 14.36 | 14.73 |
12 | 0.17 | 0.15 | ....... | 0.62 | ?58.9 | 57.4 | 15.25 | 14.79 |
13 | 0.23 | 0.11 | ....... | 0.37 | ?55.4 | 57.2 | 13.32 | 12.80 |
14 | 0.15 | 0.10 | ....... | 0.25 | ?63.7 | 61.6 | 14.61 | 13.58 |
15 | 0.26 | 0.12 | ....... | 0.37 | ?50.1 | 47.5 | 13.32 | 14.51 |
Table 1
(4) through after the neural network model training managing; Set up the detection model of instrument; As the neural network input variable, utilize the BP neural network of training sample gained with 16 band spectrum reflected values of forecast sample collection in the step (1), obtain the SPAD value and the total nitrogen content of forecast sample collection; And compare the relation that obtains such as Fig. 1, shown in Figure 2 with the SPAD value and the total nitrogen content measured value that utilize the apparatus measures that obtains the forecast sample collection in the step (2) to obtain.
Coefficient R between predicted value and the measured value during model SPAD calculates
2=0.9361, the coefficient R between total nitrogen content predicted value and the measured value
2=0.8237, model prediction performance and effect are better, satisfy the nutrient detection requirement of agriculture rich water quality management to crop.
Said related coefficient is for utilizing least square-SVMs gained, and least square-SVMs is based on structural risk minimization, improves the generalization ability of learning machine preferably, still can access the mathematical statistics method of little error to test set independently.The related coefficient of model is nearer big, and root-mean-square error R is more little, and then the predictive ability of model is good more.
Embodiment 1~2
After accomplishing the foundation of model; Begin to survey the growth conditions of rape; Select 15 sub-districts, the rape canopy of each sub-district is carried out canopy spectra scanning, use the inventive method and record the SPAD value and the total nitrogen content of each sub-district with the spectral detection of rape canopy information spectrum detection instrument probe; And compare with SPAD value and total nitrogen content that SPAD502, triumphant formula survey nitrogen method gained, the partial data that obtains is shown in table 2, table 3.
Wherein, Y1 is a SPAD value of utilizing the BP network model to calculate, and SY1 is a SPAD value of utilizing SPAD502 to obtain, and Y2 is the total nitrogen content that utilizes the BP network model to calculate, and SY1 utilizes triumphant formula to survey the total nitrogen content that the nitrogen method obtains.
Table 2 (embodiment 1)
The sub-district sequence number | X 1 | X 2 | ....... | X 16 | ?Y 1 | sY 1 | Y 2 | Sy 2 |
1 | 0.32 | 0.26 | ....... | 0.42 | 48.3 | 48.1 | 12.56 | 12.33 |
2 | 0.23 | 0.32 | ....... | 0.54 | 55.8 | 54.7 | 14.24 | 14.29 |
3 | 0.24 | 0.37 | ....... | 0.66 | 41.4 | 31.8 | 9.28 | 8.76 |
4 | 0.75 | 0.58 | ....... | 0.46 | 33.5 | 34.1 | 6.67 | 5.03 |
5 | 0.68 | 0.51 | ....... | 0.44 | 36.2 | 34.8 | 7.51 | 7.62 |
6 | 0.59 | 0.36 | ....... | 0.65 | 35.6 | 36.1 | 8.21 | 7.89 |
7 | 0.43 | 0.36 | ....... | 0.59 | 38.6 | 39.1 | 8.39 | 8.36 |
8 | 0.34 | 0.30 | ....... | 0.32 | 41.5 | 42.1 | 12.58 | 13.18 |
9 | 0.28 | 0.34 | ....... | 0.45 | 35.7 | 34.9 | 7.27 | 7.68 |
10 | 0.37 | 0.42 | ....... | 0.58 | 22.4 | 21.8 | 4.25 | 4.02 |
11 | 0.36 | 0.27 | ....... | 0.35 | 52.0 | 52.6 | 14.36 | 14.73 |
12 | 0.47 | 0.23 | ....... | 0.42 | 28.2 | 27.9 | 5.25 | 5.42 |
13 | 0.59 | 0.61 | ....... | 0.67 | 25.4 | 27.2 | 5.32 | 5.80 |
14 | 0.11 | 0.14 | ....... | 0.25 | 65.9 | 66.7 | 16.21 | 16.58 |
15 | 0.14 | 0.20 | ....... | 0.22 | 55.1 | 56.5 | 15.18 | 15.05 |
[0047]Table 3 (embodiment 2)
The sub-district sequence number | X 1 | X 2 | ..... | ?X 16 | Y 1 | sY 1 | Y 2 | Sy 2 |
1 | 0.72 | 0.66 | ...... | 0.77 | 7.1 | 6.9 | 0.87 | 0.93 |
2 | 0.68 | 0.65 | ...... | 0.72 | 8.3 | 8.9 | 1.23 | 1.31 |
3 | 0.59 | 0.52 | ...... | 0.64 | 12.4 | 11.8 | 2.05 | 2.13 |
4 | 0.61 | 0.53 | ...... | 0.55 | 14.6 | 13.9 | 3.68 | 3.91 |
5 | 0.62 | 0.59 | ...... | 0.47 | 15.9 | 16.2 | 4.28 | 4.51 |
6 | 0.56 | 0.49 | ...... | 0.62 | 15.2 | 15.8 | 4.76 | 4.89 |
7 | 0.44 | 0.49 | ...... | 0.42 | 22.6 | 23.1 | 5.43 | 5.15 |
8 | 0.41 | 0.45 | ...... | 0.52 | 24.5 | 24.7 | 6.08 | 6.12 |
9 | 0.39 | 0.23 | ...... | 0.51 | 39.8 | 38.7 | 9.36 | 9.01 |
10 | 0.24 | 0.20 | ...... | 0.28 | 52.3 | 51.8 | 16.25 | 15.12 |
11 | 0.36 | 0.27 | ...... | 0.35 | 52.0 | 52.6 | 14.36 | 14.73 |
12 | 0.21 | 0.35 | ...... | 0.37 | 48.9 | 48.1 | 13.27 | 13.87 |
13 | 0.29 | 0.17 | ...... | 0.22 | 58.1 | 58.7 | 14.19 | 14.27 |
14 | 0.21 | 0.17 | ...... | 0.25 | 61.4 | 61.9 | 15.01 | 15.87 |
15 | 0.23 | 0.28 | ...... | 0.17 | 52.1 | 51.5 | 13.79 | 14.21 |
Can know by table 2 and table 3, utilize SPAD value and the total nitrogen content that the present invention obtains and utilize the SPAD502 instrument and triumphant formula is surveyed the nitrogen method to obtain measured value facies relationship number average very little, satisfy agriculture rich water quality management the nutrient of crop is detected requirement.
Claims (6)
1. a rape canopy information spectral method of detection is characterized in that, may further comprise the steps:
The spectral information of A, the some rape leaf samples of collection obtains its SPAD value;
B, to the rape leaf sample in the steps A, detect its total nitrogen content;
C, with the spectral information in the steps A as input variable, SPAD value that will be corresponding with said spectral information and total nitrogen content are set up neural network model as output variable;
D, gather the spectral information of rape leaf to be detected and utilize described model to obtain the SPAD value and the total nitrogen content of this rape leaf to be detected, with definite growth of rape state to be detected.
2. rape canopy information spectral method of detection as claimed in claim 1 is characterized in that the spectral information among described steps A and the step D is the spectral information of rape canopy partial blade.
3. rape canopy information spectral method of detection as claimed in claim 2 is characterized in that, among steps A and the step D, to the detection light of rape leaf emission 450-1200nm, gathers the detection light after the rape leaf reflection, obtains corresponding spectral information.
4. rape canopy information spectral method of detection as claimed in claim 3 is characterized in that, said detection light in the 450-1200nm scope 16 the tunnel.
5. rape canopy information spectral method of detection as claimed in claim 4 is characterized in that described neural network model is the BP neural network model.
6. rape canopy information spectral method of detection as claimed in claim 5; It is characterized in that said 16 tunnel detection optical wavelength are respectively 450nm, 480nm, 550nm, 640nm, 680nm, 720nm, 780nm, 820nm, 860nm, 880nm, 940nm, 960nm, 1040nm, 1100nm, 1150nm, 1200nm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210226049XA CN102759510A (en) | 2012-06-29 | 2012-06-29 | Spectral detection method of rape canopy information |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210226049XA CN102759510A (en) | 2012-06-29 | 2012-06-29 | Spectral detection method of rape canopy information |
Publications (1)
Publication Number | Publication Date |
---|---|
CN102759510A true CN102759510A (en) | 2012-10-31 |
Family
ID=47054040
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210226049XA Pending CN102759510A (en) | 2012-06-29 | 2012-06-29 | Spectral detection method of rape canopy information |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102759510A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105158408A (en) * | 2015-04-23 | 2015-12-16 | 安徽星鑫化工科技有限公司 | BP neural network-based chlorinated paraffin chlorinity indirect detection method |
CN106770072A (en) * | 2016-12-05 | 2017-05-31 | 青岛农业大学 | One kind arrives Wheat Leavess SPAD value evaluation methods before heading after turning green |
WO2017092136A1 (en) * | 2015-11-30 | 2017-06-08 | 江苏大学 | Quick measurement method for blade surface microstructure based on light interference technology |
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 |
CN107271382A (en) * | 2017-06-02 | 2017-10-20 | 西北农林科技大学 | A kind of different growing rape leaf SPAD value remote sensing estimation methods |
CN112287886A (en) * | 2020-11-19 | 2021-01-29 | 安徽农业大学 | Wheat plant nitrogen content estimation method based on hyperspectral image fusion map features |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN2854585Y (en) * | 2005-12-28 | 2007-01-03 | 浙江大学 | Multispectral image diagnostic system for rape nitrogen nutrition |
US8012912B1 (en) * | 2007-09-28 | 2011-09-06 | Bret Barrick | Method of increasing the yield of sugar from sugarcane |
-
2012
- 2012-06-29 CN CN201210226049XA patent/CN102759510A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN2854585Y (en) * | 2005-12-28 | 2007-01-03 | 浙江大学 | Multispectral image diagnostic system for rape nitrogen nutrition |
US8012912B1 (en) * | 2007-09-28 | 2011-09-06 | Bret Barrick | Method of increasing the yield of sugar from sugarcane |
Non-Patent Citations (2)
Title |
---|
裘正军: "应用SPAD和光谱技术研究油菜生长期间的氮素变化规律", 《农业工程学报》 * |
黄敏等: "基于可见-近红外光谱的油菜氮素预测的研究", 《第十二届国际油菜大会论文集》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105158408A (en) * | 2015-04-23 | 2015-12-16 | 安徽星鑫化工科技有限公司 | BP neural network-based chlorinated paraffin chlorinity indirect detection method |
WO2017092136A1 (en) * | 2015-11-30 | 2017-06-08 | 江苏大学 | Quick measurement method for blade surface microstructure based on light interference technology |
CN106770072A (en) * | 2016-12-05 | 2017-05-31 | 青岛农业大学 | One kind arrives Wheat Leavess SPAD value evaluation methods before heading after turning green |
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 |
CN107271382A (en) * | 2017-06-02 | 2017-10-20 | 西北农林科技大学 | A kind of different growing rape leaf SPAD value remote sensing estimation methods |
CN112287886A (en) * | 2020-11-19 | 2021-01-29 | 安徽农业大学 | Wheat plant nitrogen content estimation method based on hyperspectral image fusion map features |
CN112287886B (en) * | 2020-11-19 | 2023-09-22 | 安徽农业大学 | Wheat plant nitrogen content estimation method based on hyperspectral image fusion map features |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101718683B (en) | Method for fast detection of chlorophyll content in leaf blades, modeling method and detection method | |
CN101382488B (en) | Method for detecting nitrogen content in fresh tea by visible light-near infrared diffuse reflection spectrum technology | |
Feng et al. | Assessment of plant nitrogen status using chlorophyll fluorescence parameters of the upper leaves in winter wheat | |
CN102759510A (en) | Spectral detection method of rape canopy information | |
CN101706421B (en) | Characteristic wave bands based method and device for rapidly detecting content of proteins in black fungi | |
CN101884541B (en) | Non-invasive detector and detecting method for biochemical parameters of human blood | |
CN109187398A (en) | A kind of EO-1 hyperion measuring method of wheat plant nitrogen content | |
CN103940748B (en) | Based on the prediction of oranges and tangerines canopy nitrogen content and the visualization method of hyperspectral technique | |
CN110082309B (en) | Method for establishing SPAD value comprehensive spectrum monitoring model of winter wheat canopy | |
CN109187417A (en) | A kind of Terahertz of UAV system involves high-spectrum remote-sensing crops monitoring system | |
Patane et al. | Chlorophyll and nitrogen estimation techniques: A Review | |
CN112816618A (en) | Method for screening nitrogen-efficient wheat varieties | |
CN112362812A (en) | Remote sensing inversion model and method for rice leaf chlorophyll carotenoid content ratio based on Lars algorithm | |
CN108732137A (en) | The model and method of Species Diversity in Plant are estimated based on high-spectrum remote sensing data | |
CN102788796B (en) | Nutrient diagnosis device and nutrient diagnosis method for nitrogen of crops based on multi-information integration of high spectral images and fluorescent images | |
Jianfeng et al. | Non-destructive measurement of chlorophyll in tomato leaves using spectral transmittance | |
CN112632847A (en) | XGboost regression algorithm-based rice leaf starch content remote sensing inversion model and method | |
CN106404699A (en) | Nondestructive measurement method for contents of nitrogen elements of pear tree leaf blades | |
CN104977262A (en) | Portable detection apparatus for potato late blight | |
CN201555802U (en) | Black fungus protein content rapid-detection device based on characteristic bands | |
CN109932339B (en) | All-weather light environment self-adaptive crop growth detection device and method | |
Ni et al. | Application of monitoring system about plant growth information based on spectroscopy technique | |
Qiao et al. | Study on relationship between tobacco canopy spectra and LAI | |
CN107764767A (en) | The method of the corn protein and moisture of detection united reaper in real time | |
Zhang et al. | Research vertical distribution of chlorophyll content of wheat leaves using imaging hyperspectra |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C12 | Rejection of a patent application after its publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20121031 |