CN104749134A - Method for detecting canopy moisture content of leaf vegetable crops - Google Patents
Method for detecting canopy moisture content of leaf vegetable crops Download PDFInfo
- Publication number
- CN104749134A CN104749134A CN201510147898.XA CN201510147898A CN104749134A CN 104749134 A CN104749134 A CN 104749134A CN 201510147898 A CN201510147898 A CN 201510147898A CN 104749134 A CN104749134 A CN 104749134A
- Authority
- CN
- China
- Prior art keywords
- canopy
- image
- color
- leaf vegetables
- refers
- 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
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention provides a method for detecting canopy moisture content of leaf vegetable crops. The method comprises the following steps: filtering spectrum, performing gradient extraction on characteristic wavelength by adopting a backward interval partial least square algorithm, a genetic algorithm and a continuous projection algorithm; performing wavelet denoising on a front view image and a top view image, extracting canopy projection area, canopy perimeter and plant height as growth characteristics of the leaf vegetable crops, extracting color component mean value of each of RGB space and HSI space as the color characteristic, extracting entropy, secondary moment, contrast ratio and homogeneity in six color co-occurrence matrixes constructed by the RGB space and the HSI space; and reducing dimension of the characteristic wavelength and the image characteristic by using kernel principle component analysis, establishing a detection model of the canopy moisture content of the leaf vegetable crops by using an extreme learning machine algorithm. Through the adoption of a plurality of chemometrics algorithms and image processing methods, the internal and external information of the canopy of the leaf vegetable crops are fully acquired, and the nondestructive detection of the canopy moisture content of the leaf vegetable crops is realized.
Description
Technical field
The invention belongs to crop water content detection field, especially a kind of method detecting leaf vegetables crop canopies moisture.
Background technology
Farmer's proverb is said " have and receive without being received in water; receive many receipts and be fertilizer less ", fully who understands the vital role of moisture in agricultural production to the words, leaf vegetables crop many genus shallow root system crop, to moisture-sensitive, and leaf vegetables crop leaf is many, leaf area is large, transpiration rate is large, water consumption is many, when moisture is coerced, in body, the photochemical conjunction activity of pigment weakens, and hinders the absorption of nutrition, limits nutrition by the transport of root system to leaf.
Traditional crop canopy moisture detects and adopts dry weight in wet base method, but the method is for damaging detection, needs to destroy sample; Modern crop canopies water content detection can adopt spectral technique, image technique, but spectroscopic data amount is very large, and containing much noise and redundant information, it is the key improving spectral technique accuracy of detection that characteristic wavelength extracts.View data contains abundant information, but mostly only with color and the texture information based on gray level co-occurrence matrixes, accuracy of detection is on the low side.
Summary of the invention
For Shortcomings in prior art, the invention provides a kind of method detecting leaf vegetables crop canopies moisture, combine and utilize number of chemical metrology algorithm and multiple image processing method to overcome characteristic wavelength to extract the problems such as under-represented and image characteristics extraction is not comprehensive, further increase accuracy of detection, for the accurate management of leaf vegetables crop water provides foundation.
The present invention realizes above-mentioned technical purpose by following technological means.
Detect a method for leaf vegetables crop canopies moisture, it is characterized in that, carry out in accordance with the following steps:
S1, spectroscopic data and image acquisition: described spectrum data gathering refers to and obtains leaf vegetables crop canopies visible ray-near infrared spectrum, described image acquisition refers to and utilizes the master of imaging device acquisition canopy depending on RGB image and overlook RGB image;
The mensuration of S2, crop canopies water percentage;
S3, canopy spectra pre-service and canopy Image semantic classification: described spectroscopic data pre-service refers to and adopts Savitzky-Golay convolution smoothly to carry out pre-service in conjunction with spectroscopic data described in log (1/R) transfer pair S1, described canopy Image semantic classification refers to and adopts Wavelet Denoising Method to carry out noise reduction to image described in S1;
S4, canopy spectra characteristic wavelength extract and canopy image characteristics extraction: described canopy spectra feature extraction refers to the extraction pretreated spectroscopic data described in S3 being carried out to characteristic wavelength, and described canopy image characteristics extraction refers to the image zooming-out color characteristic after to noise reduction described in S3, textural characteristics and growing way feature;
S5, Data Dimensionality Reduction: described Data Dimensionality Reduction refers to and utilizes core principle component analysis method to carry out dimensionality reduction to the characteristic wavelength described in S4 and characteristics of image;
S6, model are set up: described model is set up and referred to that limit of utilization study computing method sets up the nonlinear model of spectral signature wavelength major component described in S5 and image major component and the crop canopies water percentage described in S2;
S7, utilize the moisture of model inspection leaf vegetables crop canopies described in S6.
Further, described in S1, the assay method of crop canopies water percentage is: cultivate the leaf vegetables crop that water cut is different, weigh after whole strain crop is removed root, be placed in baking oven by going the crop after root and dry to constant weight, by drying the Mass Calculation crop canopies water percentage of front and back crop.
In such scheme, spectral signature wavelength extraction described in S4 refers to and utilizes backward interval offset minimum binary, genetic algorithm, successive projection algorithm three kinds of algorithms to extract characteristic wavelengths.
In such scheme, in canopy image characteristics extraction described in S4, color characteristic comprises the average of R (red) in RGB color space, G (green), B (indigo plant) three color components, the average of H (tone), S (color saturation), I (brightness) three color components in HSI color space, described textural characteristics comprises the entropy (ENT) of R-G, R-B, G-B, H-S, H-I and S-I 6 the color co-occurrence matrixs constructed based on rgb space and HSI spatial color, angle second moment (ASM), contrast (CON) and concertedness (HOM); Described growing way feature comprises the hat width projected area (TPCA) and hat width girth (TPCP) extracted from canopy overhead view image, the plant height (PH) extracted from canopy front view picture.
In such scheme, described leaf vegetables crop is romaine lettuce, Chinese cabbage, wild cabbage, rape or spinach.
Beneficial effect of the present invention:
(1) method of detection leaf vegetables crop canopies moisture of the present invention, by the characteristic wavelength of romaine lettuce canopy, growing way feature, color characteristic and the textural characteristics based on colored co-occurrence matrix being merged mutually, comprehensively evaluate the moisture state of romaine lettuce canopy.
(2) when leaf vegetables crop canopies generation water stress, no matter spectral technique or image technique can only get information in a certain respect, so the detection method merged based on spectrum and image technique is compared with single detection means, testing result is more objective, more accurate.
Accompanying drawing explanation
Fig. 1 is leaf vegetables crop spectrum data gathering schematic diagram of the present invention.
Fig. 2 is that leaf vegetables crop canopies Pretreated spectra of the present invention and canopy spectral signature wavelength extract schematic flow sheet.
Fig. 3 is leaf vegetables crop canopies Image semantic classification of the present invention and feature extraction schematic flow sheet.
Fig. 4 is leaf vegetables Plants high measurement process flow diagram of the present invention.
Fig. 5 is leaf vegetables crop canopies moisture overhaul flow chart of the present invention.
Embodiment
Below in conjunction with accompanying drawing and specific embodiment, the present invention is further illustrated, but protection scope of the present invention is not limited to this.
It is similar that the leaf vegetabless such as romaine lettuce, Chinese cabbage, wild cabbage, rape, spinach make properties, and its canopy water cut all can adopt the method for the invention to detect, and the present embodiment, with the example that is detected as of romaine lettuce canopy water cut, illustrates the detection method of leaf vegetables crop canopies water cut.
The detection method of the canopy moisture of romaine lettuce is:
Nutrient management is carried out by the rugged formula in mountain, 4 levels are divided into by sample to process, be respectively Severe drought, mild drought, mild drought and normal, irrigation volume is respectively 25%, 50%, 75% and 100% of matrix maximum water-holding capacity, and Different Irrigation amount sample amounts to 130 strains.
(1) spectrum data gathering
Spectral measuring devices adopts
type handheld portable spectroanalysis instrument (Analytical Spectral Devices (ASD), Boulder, CO, USA), this instrument spectral measurement range 350 ~ 2500nm is 1.4nm in 350 ~ 1000nm spectral region sampling interval, and resolution is 3nm; Be 2nm in 1000 ~ 2500nm spectral region sampling interval, resolution is 10nm, data output gap 1nm, and the field angle of spectrometer is 25 °, and light source is 50W Halogen lamp LED, putting as shown in Figure 1 of spectrometer 1 and light source 2.Ensure during collection that probe vertical is downward, optical fiber is 20cm to the vertical range in romaine lettuce Canopy face, gather spot diameter and be about 9cm, advanced column criterion blank (Labsphere Inc. before gathering, USA) demarcate, to eliminate the error that environmental factor causes, each sample collection 5 spectrum, using its mean value as 1 sampling spectrum.Original spectrum two ends are respectively removed the larger region of 50nm Noise, obtain the curve of spectrum as shown in Fig. 2 (a).
(2) image acquisition
Romaine lettuce hat width image acquisition adopts Canon EOS 400D camera: a, before image acquisition, utilize standard white plate to carry out white balance demarcation to camera, to ensure the reduction of gained image color accurately; B, use the diaphragm priority mode of camera to take, and be 100 by aperture settings at F8, ISO, make camera imaging have the enough depth of field to ensure romaine lettuce all imaging clearly within the scope of whole growing height; C, adopt the self-timer mode postponing 2s, to reduce manual operation error in shooting process when each shooting; D, for being conducive to later image process, be image background with white plate when gathering image, concrete operations are employing two block edge place respectively has the white plate of a semicircle orifice to be stuck in romaine lettuce root symmetrically, but any constraint are not produced to romaine lettuce, ensure its most original growth conditions; E, the reference scale adopting normal graph paper to be later image process, before each collection image, normal graph paper is fixed in a plane, and the height of coordinate paper is adjusted according to canopy height, scale is tried one's best and hat width plane keeping parallelism, reduce the distortion error because Different Plane imaging occurs, the romaine lettuce of collection overlooks canopy image as Fig. 3 (a).
The collection of romaine lettuce front view picture gathers similar to overhead view image, and scale is positioned on the perpendicular bisector of romaine lettuce canopy.First mark is unified to flowerpot before collection, during collection, flowerpot there is index face as main apparent direction, because the indivedual blade growing way of romaine lettuce is given prominence to, for reflecting its upgrowth situation comprehensively, eliminate accidental error, flowerpot is turned clockwise 90 ° in test, again gather the front view picture of romaine lettuce, the average of twice Image Acquisition is as final feature, and the romaine lettuce canopy front view of collection is as Fig. 4 (a).
(3) mensuration of crop canopies water percentage
Weigh after whole strain romaine lettuce is removed root immediately, quality is designated as m
1, put it in 70 DEG C of baking ovens and dry to constant weight, claim its quality to be designated as m
2, the computing formula of romaine lettuce canopy water content is:
In formula: m
1, m
2for Fresh Yuxincao and the dry mass of test sample book, unit is mg.
(4) Spectra feature extraction
Utilize SPXY algorithm that 130 data are divided into calibration set and forecast set, wherein calibration set contains 90, sample, and forecast set contains 40, sample.9: 2 Savitzky-Golay convolution are carried out to original spectrum level and smooth, and then carry out log (1/R) conversion, can strengthen the SPECTRAL DIVERSITY of visible region, reduce because illumination condition changes the impact caused, pretreated spectrum is as shown in Fig. 2 (b).Backward interval partial least squares algorithm is utilized to extract the characteristic wave bands relevant to romaine lettuce canopy moisture, when spectrum is divided into 27 sub-ranges, associating 5, [8,11,14,15,21] the wherein partial least square model that sub-range is set up is optimum, spectrum range corresponding to 5 sub-ranges is 932 ~ 1007nm, 1160 ~ 1235nm, 1388 ~ 1463nm, 1464 ~ 1539nm and 1920 ~ 1995nm, contain 380 spectral wavelengths, between selected area as shown in Fig. 2 (c).Then utilize heredity-partial least squares algorithm to extract characteristic wavelength in five sub-ranges, Fig. 2 (d) is the selected frequency plot of each variable, and frequency is greater than the variable of solid black lines for selected wavelength, totally 48.Finally utilize successive projection algorithm to extract most optimum wavelengths in 48 wavelength, be respectively: 967,1170,1221,1406,1484,1942 and 1985nm, Fig. 2 (e) most optimum wavelengths that is romaine lettuce canopy moisture.Backward interval partial least squares algorithm is in conjunction with heredity-partial least squares algorithm and successive projection algorithm, spectral variables 7 have been reduced to from 2051,7 characteristic spectrums are utilized to set up extreme learning machine model, obtaining calibration set root-mean-square error is 162%, calibration set related coefficient is 0.8542, utilize independent sample to test to model performance, being verified collection root-mean-square error is 197%, verifies related coefficient to be 0.8243.
(5) image characteristics extraction
Wavelet Denoising Method is utilized to carry out denoising to the overhead view image of romaine lettuce canopy." 2G-R-B " operator is adopted to carry out binary conversion treatment in conjunction with appropriate threshold to romaine lettuce canopy overhead view image, as shown in Fig. 3 (b), the wherein white pixel region of selecting and romaine lettuce canopy region, then the computing formula of romaine lettuce hat width projected area (TPCA) is:
In formula: N
lto make a living the total pixel number in territory, vegetable-growing area, f
1for conversion factor, representation unit area (1cm
2) total pixel number that comprises.
Using Fig. 3 (b) as mask image, obtain romaine lettuce canopy and overlook direction background segment result as Fig. 3 (c), utilize canny operator extraction romaine lettuce to be preced with the edge of width, as shown in Fig. 3 (d), then the computing formula being preced with width girth (TPCP) is:
In formula: Np is the outer peripheral total pixel number of romaine lettuce canopy, be conversion factor, representation unit area (1cm
2) total pixel number that comprises.
The front view picture of Wavelet Denoising Method to romaine lettuce canopy is utilized to carry out denoising." 2G-R-B " operator is adopted to carry out binary conversion treatment in conjunction with appropriate threshold to romaine lettuce canopy front view picture, as shown in Fig. 4 (b), it can be used as mask image, obtain romaine lettuce canopy main apparent direction background segment result as shown in Fig. 4 (c), canny operator extraction romaine lettuce is utilized to be preced with the edge of width, as shown in Fig. 4 (d), then the computing formula of romaine lettuce plant height (PH) is:
In formula: NH be romaine lettuce from minimum point to the total pixel number of peak vertical direction, be conversion factor, the total pixel number that representation unit length (1cm) comprises.
Fig. 3 (c) overlooks RGB image for romaine lettuce canopy after background segment, and in calculating chart 3 (c), the average of each component of romaine lettuce hat width region R, G, B, is designated as
build R-G, R-B and G-B color co-occurrence matrix, from three matrixes, extract ENT, ASM, CON and HOM tetra-textural characteristics respectively.Fig. 3 (c) is extracted and is transformed into HSI space, calculate the average of each component of HSI space romaine lettuce hat width H, S, I, be designated as
build H-S, H-I and S-I color co-occurrence matrix, from three matrixes, extract ENT, ASM, CON and HOM tetra-textural characteristics respectively, then the corresponding textural characteristics of 6 color co-occurrence matrixs is averaged, using the textural characteristics of mean value as this sample.13 features extracted from romaine lettuce canopy overhead view image and front view picture are set up extreme learning machine model, obtaining calibration set root-mean-square error is 198%, calibration set related coefficient is 0.8109, independent sample is utilized to test to model performance, being verified collection root-mean-square error is 238%, verifies related coefficient to be 0.7794.
(6) Data Dimensionality Reduction and modeling
Core principle component analysis is utilized to carry out dimensionality reduction to 7 spectral signatures and 13 characteristics of image respectively, extract the input of front 4 major components in spectral signature in front 3 major components and characteristics of image as extreme learning machine network, obtaining correcting root-mean-square error is 137%, calibration set related coefficient is 0.9213, independent sample is utilized to test to model performance, being verified root-mean-square error is 169%, checking collection related coefficient is 0.8916, romaine lettuce canopy moisture testing process of the present invention as shown in Figure 5, by institute's established model precision after 7 spectral signatures and 13 multi-features apparently higher than single-sensor model.
Described embodiment is preferred embodiment of the present invention; but the present invention is not limited to above-mentioned embodiment; when not deviating from flesh and blood of the present invention, any apparent improvement that those skilled in the art can make, replacement or modification all belong to protection scope of the present invention.
Claims (5)
1. detect a method for leaf vegetables crop canopies moisture, it is characterized in that, carry out in accordance with the following steps:
S1, spectroscopic data and image acquisition: described spectrum data gathering refers to and obtains leaf vegetables crop canopies visible ray-near infrared spectrum, described image acquisition refers to and utilizes the master of imaging device acquisition canopy depending on RGB image and overlook RGB image;
The mensuration of S2, crop canopies water percentage;
S3, canopy spectra pre-service and canopy Image semantic classification: described spectroscopic data pre-service refers to and adopts Savitzky-Golay convolution smoothly to carry out pre-service in conjunction with spectroscopic data described in log (1/R) transfer pair S1, described canopy Image semantic classification refers to and adopts Wavelet Denoising Method to carry out noise reduction to image described in S1;
S4, canopy spectra characteristic wavelength extract and canopy image characteristics extraction: described canopy spectra feature extraction refers to the extraction pretreated spectroscopic data described in S3 being carried out to characteristic wavelength, and described canopy image characteristics extraction refers to the image zooming-out color characteristic after to noise reduction described in S3, textural characteristics and growing way feature;
S5, Data Dimensionality Reduction: described Data Dimensionality Reduction refers to and utilizes core principle component analysis method to carry out dimensionality reduction to the characteristic wavelength described in S4 and characteristics of image;
S6, model are set up: described model is set up and referred to that limit of utilization study computing method sets up the nonlinear model of spectral signature wavelength major component described in S5 and image major component and the crop canopies water percentage described in S2;
S7, utilize the moisture of model inspection leaf vegetables crop canopies described in S6.
2. the method detecting leaf vegetables crop canopies moisture as claimed in claim 1, it is characterized in that, described in S2, the assay method of crop canopies water percentage is: cultivate the leaf vegetables crop that water cut is different, weigh after whole strain crop is removed root, be placed in baking oven by going the crop after root to dry to constant weight, by drying the Mass Calculation crop canopies water percentage of front and back crop.
3. the method detecting leaf vegetables crop canopies moisture as claimed in claim 1, is characterized in that, spectral signature wavelength extraction described in S4 refers to and utilizes backward interval offset minimum binary, genetic algorithm, successive projection algorithm three kinds of algorithms to extract characteristic wavelengths.
4. the method detecting leaf vegetables crop canopies moisture as claimed in claim 1, it is characterized in that, in canopy image characteristics extraction described in S4, color characteristic comprises the average of R, G, B tri-color components in RGB color space, the average of H, S, I tri-color components in HSI color space, described textural characteristics comprises the entropy (ENT) of R-G, R-B, G-B, H-S, H-I and S-I 6 the color co-occurrence matrixs constructed based on rgb space and HSI spatial color, angle second moment (ASM), contrast (CON) and concertedness (HOM); Described growing way feature comprises the hat width projected area (TPCA) and hat width girth (TPCP) extracted from canopy overhead view image, the plant height (PH) extracted from canopy front view picture.
5., as the method for the detection leaf vegetables crop canopies moisture in Claims 1 to 4 as described in any one, it is characterized in that, described leaf vegetables crop is romaine lettuce, Chinese cabbage, wild cabbage, rape or spinach.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510147898.XA CN104749134A (en) | 2015-03-31 | 2015-03-31 | Method for detecting canopy moisture content of leaf vegetable crops |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510147898.XA CN104749134A (en) | 2015-03-31 | 2015-03-31 | Method for detecting canopy moisture content of leaf vegetable crops |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104749134A true CN104749134A (en) | 2015-07-01 |
Family
ID=53589142
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510147898.XA Pending CN104749134A (en) | 2015-03-31 | 2015-03-31 | Method for detecting canopy moisture content of leaf vegetable crops |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104749134A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105092509A (en) * | 2015-08-20 | 2015-11-25 | 东北大学 | Sample component measurement method based on PCR-ELM algorithm |
| CN105277517A (en) * | 2015-07-15 | 2016-01-27 | 电子科技大学 | Method for convenient and quick measurement of water content of arbor leaves |
| CN106134813A (en) * | 2016-07-25 | 2016-11-23 | 北京小米移动软件有限公司 | Plant cultural method, Apparatus and system |
| CN106770274A (en) * | 2015-11-25 | 2017-05-31 | 财团法人资讯工业策进会 | Physiological characterization detection method, portable detection device and detection system for crops |
| CN106971073A (en) * | 2017-03-28 | 2017-07-21 | 安徽理工大学 | A kind of identification of nonlinearity method at water bursting in mine water source |
| CN107014756A (en) * | 2017-04-17 | 2017-08-04 | 成都曙光光纤网络有限责任公司 | A kind of Spectrum testing systems light source design method |
| CN108387534A (en) * | 2018-03-15 | 2018-08-10 | 中国农业科学院农田灌溉研究所 | Measure plant water content method and apparatus |
| CN111539920A (en) * | 2020-04-16 | 2020-08-14 | 泸州老窖酿酒有限责任公司 | Automatic detection method for fermented grain quality in white spirit brewing process |
| CN111814545A (en) * | 2020-06-01 | 2020-10-23 | 北京简巨科技有限公司 | Crop identification method and device, electronic equipment and storage medium |
| CN112329856A (en) * | 2020-11-06 | 2021-02-05 | 神农智慧农业研究院南京有限公司 | Wheat nitrogen accumulation amount prediction method based on spectrum and RGB-D fusion image |
| CN112712568A (en) * | 2020-12-16 | 2021-04-27 | 杭州博联智能科技股份有限公司 | Color brightness recognition method, device, equipment and medium |
| CN113720797A (en) * | 2021-08-30 | 2021-11-30 | 四川轻化工大学 | Online rapid quality-measuring liquor taking method for liquor distillation |
| CN114273252A (en) * | 2021-11-26 | 2022-04-05 | 山东安信种苗股份有限公司 | Intelligent vegetable seedling grading method |
| US11895953B2 (en) | 2019-05-31 | 2024-02-13 | Argus Control Systems Ltd. | Plant health monitoring apparatus and methods |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101936882A (en) * | 2010-08-10 | 2011-01-05 | 江苏大学 | Nondestructive testing method and device for nitrogen and water of crops |
| CN102495005A (en) * | 2011-11-17 | 2012-06-13 | 江苏大学 | Method for diagnosing crop water deficit through hyperspectral image technology |
-
2015
- 2015-03-31 CN CN201510147898.XA patent/CN104749134A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101936882A (en) * | 2010-08-10 | 2011-01-05 | 江苏大学 | Nondestructive testing method and device for nitrogen and water of crops |
| CN102495005A (en) * | 2011-11-17 | 2012-06-13 | 江苏大学 | Method for diagnosing crop water deficit through hyperspectral image technology |
Non-Patent Citations (3)
| Title |
|---|
| YUSUF HENDRAWAN, HARUHIKO MURASE: "Bio-inspired feature selection to select informative image features for determining water content of cultured Sunagoke moss", 《EXPERT SYSTEMS WITH APPLICATIONS》 * |
| 劳东青，李发永: "计算机视觉在作物水分亏缺诊断中的应用进展", 《塔里木大学学报》 * |
| 高洪燕，毛罕平，张晓东，孙俊: "基于多信息融合的番茄冠层水分诊断", 《农业工程学报》 * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105277517A (en) * | 2015-07-15 | 2016-01-27 | 电子科技大学 | Method for convenient and quick measurement of water content of arbor leaves |
| CN105092509B (en) * | 2015-08-20 | 2017-09-22 | 东北大学 | A kind of sample component assay method of PCR-based ELM algorithms |
| CN105092509A (en) * | 2015-08-20 | 2015-11-25 | 东北大学 | Sample component measurement method based on PCR-ELM algorithm |
| CN106770274A (en) * | 2015-11-25 | 2017-05-31 | 财团法人资讯工业策进会 | Physiological characterization detection method, portable detection device and detection system for crops |
| CN106134813A (en) * | 2016-07-25 | 2016-11-23 | 北京小米移动软件有限公司 | Plant cultural method, Apparatus and system |
| CN106971073A (en) * | 2017-03-28 | 2017-07-21 | 安徽理工大学 | A kind of identification of nonlinearity method at water bursting in mine water source |
| CN107014756A (en) * | 2017-04-17 | 2017-08-04 | 成都曙光光纤网络有限责任公司 | A kind of Spectrum testing systems light source design method |
| CN108387534A (en) * | 2018-03-15 | 2018-08-10 | 中国农业科学院农田灌溉研究所 | Measure plant water content method and apparatus |
| US11895953B2 (en) | 2019-05-31 | 2024-02-13 | Argus Control Systems Ltd. | Plant health monitoring apparatus and methods |
| CN111539920A (en) * | 2020-04-16 | 2020-08-14 | 泸州老窖酿酒有限责任公司 | Automatic detection method for fermented grain quality in white spirit brewing process |
| CN111539920B (en) * | 2020-04-16 | 2022-03-15 | 泸州老窖酿酒有限责任公司 | Automatic detection method for fermented grain quality in white spirit brewing process |
| CN111814545A (en) * | 2020-06-01 | 2020-10-23 | 北京简巨科技有限公司 | Crop identification method and device, electronic equipment and storage medium |
| CN112329856A (en) * | 2020-11-06 | 2021-02-05 | 神农智慧农业研究院南京有限公司 | Wheat nitrogen accumulation amount prediction method based on spectrum and RGB-D fusion image |
| CN112329856B (en) * | 2020-11-06 | 2024-05-14 | 神农智慧农业研究院南京有限公司 | Wheat nitrogen accumulation amount prediction method based on spectrum and RGB-D fusion image |
| CN112712568A (en) * | 2020-12-16 | 2021-04-27 | 杭州博联智能科技股份有限公司 | Color brightness recognition method, device, equipment and medium |
| CN113720797A (en) * | 2021-08-30 | 2021-11-30 | 四川轻化工大学 | Online rapid quality-measuring liquor taking method for liquor distillation |
| CN113720797B (en) * | 2021-08-30 | 2024-02-09 | 四川轻化工大学 | Online rapid quality measuring and liquor picking method for distilled liquor |
| CN114273252A (en) * | 2021-11-26 | 2022-04-05 | 山东安信种苗股份有限公司 | Intelligent vegetable seedling grading method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104749134A (en) | Method for detecting canopy moisture content of leaf vegetable crops | |
| Qiao et al. | UAV-based chlorophyll content estimation by evaluating vegetation index responses under different crop coverages | |
| CN102495005B (en) | Method for diagnosing crop water deficit through hyperspectral image technology | |
| Zhang et al. | High throughput analysis of leaf chlorophyll content in sorghum using RGB, hyperspectral, and fluorescence imaging and sensor fusion | |
| Agarwal et al. | Assessment of spinach seedling health status and chlorophyll content by multivariate data analysis and multiple linear regression of leaf image features | |
| CN101718683B (en) | Method for fast detection of chlorophyll content in leaf blades, modeling method and detection method | |
| CN101881726B (en) | Nondestructive detection method for comprehensive character living bodies of plant seedlings | |
| CN102721651B (en) | Detection method and system of water content in plant leaf based on multispectral image | |
| CN103955938B (en) | A kind of wheat growth method for diagnosing status based on mobile Internet pattern and leaf color analysis | |
| CN110763698B (en) | Hyperspectral citrus leaf disease identification method based on characteristic wavelength | |
| Mao et al. | Nondestructive measurement of total nitrogen in lettuce by integrating spectroscopy and computer vision | |
| CN103940748B (en) | Based on the prediction of oranges and tangerines canopy nitrogen content and the visualization method of hyperspectral technique | |
| CN101604359A (en) | Rice nitrogen fertilizing recommending method using image method | |
| CN102519886A (en) | Method for detecting contents of chlorophyll a and carotinoid in crop laminas | |
| Chen et al. | Diagnosing of rice nitrogen stress based on static scanning technology and image information extraction | |
| CN105067532A (en) | Method for identifying early-stage disease spots of sclerotinia sclerotiorum and botrytis of rape | |
| CN103278503A (en) | Multi-sensor technology-based grape water stress diagnosis method and system therefor | |
| CN102445421A (en) | Preparation method of leaf colour card used for rapidly diagnosing nitrogen of flue-cured tobacco | |
| CN109738438B (en) | Method for rapidly measuring aging degree of wheat leaves | |
| Zakaluk et al. | Predicting the leaf water potential of potato plants using RGB reflectance. | |
| CN114219795A (en) | Hyperspectral imaging system-based tea tree drought induction component and drought degree assessment prediction method and system | |
| Xu et al. | Study of monitoring maize leaf nutrition based on image processing and spectral analysis | |
| Horgan et al. | Changes in reflectance of rice seedlings during planthopper feeding as detected by digital camera: Potential applications for high-throughput phenotyping | |
| CN112098415A (en) | Nondestructive testing method for quality of waxberries | |
| Zhou et al. | Hyperspectral imaging technology for detection of moisture content of tomato leaves |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150701 |
|
| WD01 | Invention patent application deemed withdrawn after publication |