CN111122447B - Multispectral wave band correction method for unmanned aerial vehicle - Google Patents
Multispectral wave band correction method for unmanned aerial vehicle Download PDFInfo
- Publication number
- CN111122447B CN111122447B CN201911166080.7A CN201911166080A CN111122447B CN 111122447 B CN111122447 B CN 111122447B CN 201911166080 A CN201911166080 A CN 201911166080A CN 111122447 B CN111122447 B CN 111122447B
- Authority
- CN
- China
- Prior art keywords
- image data
- rows
- corrected
- multispectral
- value
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/255—Details, e.g. use of specially adapted sources, lighting or optical systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N2021/1765—Method using an image detector and processing of image signal
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N2021/1793—Remote sensing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N2021/1793—Remote sensing
- G01N2021/1797—Remote sensing in landscape, e.g. crops
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a method for correcting multispectral wave bands of an unmanned aerial vehicle, and belongs to the technical field of correction of multispectral wave bands of unmanned aerial vehicles. The method comprises the following steps: a. sorting the spectrums; b. creating a two-dimensional array Corr with the pixel size of 301 multiplied by 301; c. acquiring a correlation coefficient matrix of the image data b and the image data a; d. correcting the image data according to the position b; d. and storing each corrected image data under a corresponding folder. The method has the characteristics of simplicity, convenience, rapidness, high correction precision and the like.
Description
Technical Field
The invention relates to the technical field of unmanned aerial vehicle multispectral wave band correction.
Background
In recent years, science and technology of China are rapidly developed, wherein the technology of the low-altitude unmanned aerial vehicle is rapidly developed, gradually enters the field of vision of the public, and is well known by the people due to the characteristics of wide application, obvious advantages and the like. Because unmanned aerial vehicles have unique superiority in the aspects of mobility, flexibility, timeliness and the like, more and more industries begin to utilize unmanned aerial vehicles to carry out related work, wherein unmanned aerial vehicles have been widely applied in the field of remote sensing. The unmanned aerial vehicle remote sensing technology can overcome the restriction of the traditional aviation or aerospace remote sensing technology due to factors such as long revisit period, low image spatial resolution, high takeoff condition requirement, high operation and management cost and the like.
With the continuous development of the unmanned aerial vehicle remote sensing technology and the remote sensing data processing and analyzing technology, the multispectral remote sensing data of the unmanned aerial vehicle is widely applied to various fields. The unmanned aerial vehicle multispectral image can show many ground feature characteristics which cannot be reflected in the satellite multispectral image originally. The multispectral remote sensing image of the unmanned aerial vehicle has a large amount of wave band information, and the information can save manpower and material resources for the work of ground feature interpretation, crop identification and the like, and can improve the interpretation efficiency and accuracy of ground feature information, but the multispectral remote sensing image of the unmanned aerial vehicle also has a plurality of problems, for example, when the unmanned aerial vehicle shoots images at a lower height (below 50 m), multispectral data has larger deviation on different wave bands and the deviation changes along with different shooting positions, the wave band correction needs to be carried out on the multispectral unmanned aerial vehicle data, and the perfect correction among the wave bands is the premise of developing the application and analysis of the multispectral data.
In order to solve the problem of correcting multispectral wave bands of the unmanned aerial vehicle and accelerate the application of the unmanned aerial vehicle to be multispectral. The invention provides an unmanned aerial vehicle multispectral correction technology utilizing a regional correlation analysis algorithm, so that high-precision correction of multispectral data of an unmanned aerial vehicle can be effectively realized, and necessary basic technical support is provided for application and popularization of the multispectral data of the unmanned aerial vehicle.
Disclosure of Invention
The invention aims to provide a method for correcting multispectral wave bands of an unmanned aerial vehicle, which has the characteristics of simplicity, convenience, rapidness, high correction precision and the like.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
an unmanned aerial vehicle multispectral wave band correction method comprises the following steps:
a. spectrum sequencing, wherein multispectral image data acquired by the unmanned aerial vehicle are subjected to forward sequence sequencing or reverse sequence sequencing according to the wavelength, and the forward sequence and the backward sequence of the multispectral image data are as follows: blue band image data, green band image data, red band image data, near infrared band image data; the order of the multispectral image data in the reverse order is as follows: near-infrared band image data, red band image data, green band image data, and blue band image data; enabling the first wave band image data in the forward sequence arrangement and the reverse sequence arrangement of the multispectral image data to be image data a, the second wave band image data to be image data b, the third wave band image data to be image data c, and the fourth wave band image data to be image data d;
b. creating a two-dimensional array Corr with the pixel size of 301 multiplied by 301 for recording the correlation analysis result of the area, namely a correlation coefficient;
c. acquiring a correlation coefficient matrix of image data b and image data a, setting the position of the image data a as the image data of a relative standard position, intercepting 100 multiplied by 100 pixels from the image data a by taking the central position of the image data a as a center to serve as a standard sample, and intercepting 100 multiplied by 100 pixels from the image data b by taking the upper 150 row position as the center to serve as a sample b to be corrected by taking the left 150 rows position of the central position of the image data b as a center to serve as a sample b to be corrected1Calculating the standard sample and the sample to be corrected b1The correlation coefficient calculation result is stored at the position of the upper left start (1, 1) in a correlation number matrix in the two-dimensional array Corr; taking the position of the upper 150 rows of the left 149 columns of the central position of the image data b in the image data b as the center, cutting 100 × 100 pixels as a sample b to be corrected2Calculating the standard sample and the sample to be corrected b2The correlation coefficient calculation result is stored at the position of the upper left start (1, 2) in a correlation number matrix in the two-dimensional array Corr; by analogy, calculating a standard sample and a sample b to be correctednCorrelation coefficient of, samples to be corrected b1～bnSequentially arranging the left 150 rows, the upper 150 rows to the right 150 rows and the lower 150 rows of pixels of the image data b, thereby obtaining a correlation coefficient matrix of the image data b and the image data a in the two-dimensional array Corr;
d. correcting the position of the image data b, acquiring a subscript position x value and a y value with the maximum absolute value in the correlation coefficient matrix of the image data b and the image data a according to the correlation coefficient matrix of the image data b and the image data a acquired in the step c, subtracting 150 from the acquired x value to obtain a row correction value x, moving the image data b upwards by x rows when the row correction value x is a positive value, and moving the image data b downwards by-x rows when the row correction value x is a negative value; subtracting 150 from the obtained y value to obtain a row correction value y, moving the image data b to the left by y rows when the row correction value y is straight, and moving the image data b to the right by-y rows when the row correction value y is negative so as to correct the position of the image data b;
e. correcting multispectral image data, namely performing correction process analogy on the positions of the image data b according to the steps c and d, correcting the positions of the image data c and the image data d, and correcting each image data by taking a standard sample obtained by the image data which is corrected in the front adjacent position as a reference;
d. and storing each corrected image data under a corresponding folder, so that the correction of the position of the image data acquired by the unmanned aerial vehicle can be completed.
The invention further improves that:
and saving each corrected image data under a corresponding folder by utilizing an imwrite () function in the Matlab language.
Adopt the produced beneficial effect of above-mentioned technical scheme to lie in:
(1) the method is based on the theory of geographic correlation and spectral analysis correlation, has strong universality, is simple, convenient and quick, realizes quick and automatic correction of the multispectral wave bands of the unmanned aerial vehicle, and can provide basic technical support for popularization and application of multispectral data of the unmanned aerial vehicle.
(2) The invention can effectively make up the defects of the multispectral wave band registration technology of the unmanned aerial vehicle, has higher detection precision and efficiency, better accords with the practical application, and can meet the basic requirements of the multispectral data processing and analysis of the unmanned aerial vehicle.
(3) At present, the research of the automatic correction technology of the multispectral wave bands of the unmanned aerial vehicle is developed, technical support is provided for the application and popularization of the multispectral technology of the unmanned aerial vehicle, the technology is favorable for the development of the remote sensing technology of the unmanned aerial vehicle, and the technology has practical significance for accelerating the application of the remote sensing of the unmanned aerial vehicle.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a diagram illustrating the effect of correcting the green band image data by the method.
Note: in the present application, the rows and columns are rows and columns formed by the arrangement of pixels in each image data.
For the same ground object, the correlation inside the spectral data is inversely proportional to the interval of wave bands, namely the closer the wave bands are adjacent, the stronger the correlation is, and the adjacent spectral correlation among different substances is weaker; therefore, the multispectral image data in the same region has the strongest correlation of adjacent wave bands, and the correlation coefficient data is higher than 0.95; if there is a spatial shift in the bands of the multispectral image data, the correlation between adjacent spectra in the bands is poor, and within a certain range, the correlation between adjacent bands is reduced sharply with the increase of the spatial shift.
Detailed Description
The invention will be described in further detail below with reference to the figures and specific examples.
An unmanned aerial vehicle multispectral wave band correction method comprises the following steps:
a. spectrum sequencing, wherein multispectral image data acquired by the unmanned aerial vehicle are subjected to forward sequence sequencing or reverse sequence sequencing according to the wavelength, and the forward sequence and the backward sequence of the multispectral image data are as follows: blue band image data, green band image data, red band image data, near infrared band image data; the order of the multispectral image data in the reverse order is as follows: near-infrared band image data, red band image data, green band image data, and blue band image data; enabling the first wave band image data in the forward sequence arrangement and the reverse sequence arrangement of the multispectral image data to be image data a, the second wave band image data to be image data b, the third wave band image data to be image data c, and the fourth wave band image data to be image data d;
b. creating a two-dimensional array Corr with the pixel size of 301 multiplied by 301 for recording the correlation analysis result of the area, namely a correlation coefficient;
c. acquiring a correlation coefficient matrix of image data b and image data a, setting the position of the image data a as the image data of a relative standard position, intercepting 100 multiplied by 100 pixels from the image data a by taking the central position of the image data a as a center to serve as a standard sample, and intercepting 100 multiplied by 100 pixels from the image data b by taking the upper 150 row position as the center to serve as a sample b to be corrected by taking the left 150 rows position of the central position of the image data b as a center to serve as a sample b to be corrected1Calculating the standard sample and the sample to be corrected b1The correlation coefficient of (2), calculating the correlation coefficientStoring the calculation result in the upper left starting (1, 1) position in a relational number matrix in the two-dimensional array Corr; taking the position of the upper 150 rows of the left 149 columns of the central position of the image data b in the image data b as the center, cutting 100 × 100 pixels as a sample b to be corrected2Calculating the standard sample and the sample to be corrected b2The correlation coefficient calculation result is stored at the position of the upper left start (1, 2) in a correlation number matrix in the two-dimensional array Corr; by analogy, calculating a standard sample and a sample b to be correctednCorrelation coefficient of, samples to be corrected b1～bnSequentially arranging the left 150 rows, the upper 150 rows to the right 150 rows and the lower 150 rows of pixels of the image data b, thereby obtaining a correlation coefficient matrix of the image data b and the image data a in the two-dimensional array Corr;
d. correcting the position of the image data b, acquiring a subscript position x value and a y value with the maximum absolute value in the correlation coefficient matrix of the image data b and the image data a according to the correlation coefficient matrix of the image data b and the image data a acquired in the step c, subtracting 150 from the acquired x value to obtain a row correction value x, moving the image data b upwards by x rows when the row correction value x is a positive value, and moving the image data b downwards by-x rows when the row correction value x is a negative value; subtracting 150 from the obtained y value to obtain a row correction value y, moving the image data b to the left by y rows when the row correction value y is straight, and moving the image data b to the right by-y rows when the row correction value y is negative so as to correct the position of the image data b;
e. correcting multispectral image data, namely performing correction process analogy on the positions of the image data b according to the steps c and d, correcting the positions of the image data c and the image data d, and correcting each image data by taking a standard sample obtained by the image data which is corrected in the front adjacent position as a reference;
d. and storing each corrected image data under a corresponding folder, so that the correction of the position of the image data acquired by the unmanned aerial vehicle can be completed.
And saving each corrected image data under a corresponding folder by utilizing an imwrite () function in the Matlab language.
And (3) correlation analysis: the correlation analysis and the regression analysis have close relation in practical application. In regression analysis, however, the functional form of the dependence of one random variable Y on another (or a group of) random variables X is heavily studied. While in correlation analysis the variables in question are in the same place, the analysis focuses on a myriad of correlation features between random variables. The correlation coefficient is calculated according to a product difference method, and the correlation degree between the two variables is reflected by multiplying the two dispersion differences on the basis of the dispersion difference between the two variables and the respective average value; the linear single correlation coefficient is heavily studied. The correlation coefficient, or linear correlation coefficient, generally denoted by the letter R, is used to measure the linear relationship between two variables: the calculation method is as follows:
wherein Cov (X, Y) is the covariance of X and Y, Var [ X ] is the variance of X, and Var [ Y ] is the variance of Y. The study focuses on the analysis of linear correlation by calculating the correlation coefficient R between variables to analyze the correlation between the two.
Claims (2)
1. An unmanned aerial vehicle multispectral wave band correction method is characterized by comprising the following steps: the method comprises the following steps:
a. spectrum sequencing, wherein multispectral image data acquired by the unmanned aerial vehicle are subjected to forward sequence sequencing or reverse sequence sequencing according to the wavelength, and the forward sequence and the backward sequence of the multispectral image data are as follows: blue band image data, green band image data, red band image data, near infrared band image data; the order of the multispectral image data in the reverse order is as follows: near-infrared band image data, red band image data, green band image data, and blue band image data; enabling the first wave band image data in the forward sequence arrangement and the reverse sequence arrangement of the multispectral image data to be image data a, the second wave band image data to be image data b, the third wave band image data to be image data c, and the fourth wave band image data to be image data d;
b. creating a two-dimensional array Corr with the pixel size of 301 multiplied by 301 for recording the correlation analysis result of the area, namely a correlation coefficient;
c. acquiring a correlation coefficient matrix of the image data b and the image data a, setting the image data with the position of the image data a as a relative standard position, intercepting 100 × 100 pixels from the image data a by taking the central position of the image data a as a standard sample, and intercepting 100 × 100 pixels from the image data b by taking the upper 150 rows of the central position of the image data b as a to-be-corrected sample b1Calculating the standard sample and the sample to be corrected b1Storing the correlation coefficient calculation result at the upper left starting (1, 1) position in the correlation number matrix in the two-dimensional array Corr; intercepting 100 multiplied by 100 pixels from the image data b by taking the position of the upper 150 rows of the left 149 columns and the upper 150 rows of the central position of the image data b as a center to be used as a sample b to be corrected2Calculating the standard sample and the sample to be corrected b2Storing the correlation coefficient calculation result at the upper left starting (1, 2) position in the correlation number matrix in the two-dimensional array Corr; and calculating the standard sample and the sample b to be corrected by analogynThe sample to be corrected b1～bnSequentially arranging the left 150 rows, the upper 150 rows to the right 150 rows and the lower 150 rows of the pixels of the image data b, thereby obtaining a correlation coefficient matrix of the image data b and the image data a in the two-dimensional array Corr;
d. correcting the position of the image data b, namely acquiring a subscript position x value and a y value with the maximum absolute value in the correlation coefficient matrix of the image data b and the image data a according to the correlation coefficient matrix of the image data b and the image data a acquired in the step c, subtracting 150 from the acquired x value to obtain a row correction value x, moving the image data b upwards by x rows when the row correction value x is a positive value, and moving the image data b downwards by-x rows when the row correction value x is a negative value; subtracting 150 from the obtained y value to obtain a row correction value y, moving the image data b to the left by y rows when the row correction value y is a positive value, and moving the image data b to the right by-y rows when the row correction value y is a negative value so as to correct the position of the image data b;
e. correcting multispectral image data, namely correcting the positions of the image data c and the image data d according to the correction process analogizing on the position of the image data b in the step c and the step d, wherein each image data is corrected by taking a standard sample obtained by the image data corrected in the front adjacent position as a reference;
d. and storing each corrected image data under a corresponding folder, so that the correction of the position of the image data acquired by the unmanned aerial vehicle can be completed.
2. The method for correcting multispectral bands of an unmanned aerial vehicle according to claim 1, wherein the method comprises the following steps: and saving each corrected image data under a corresponding folder by utilizing an imwrite () function in the Matlab language.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911166080.7A CN111122447B (en) | 2019-11-25 | 2019-11-25 | Multispectral wave band correction method for unmanned aerial vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911166080.7A CN111122447B (en) | 2019-11-25 | 2019-11-25 | Multispectral wave band correction method for unmanned aerial vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111122447A CN111122447A (en) | 2020-05-08 |
| CN111122447B true CN111122447B (en) | 2022-03-25 |
Family
ID=70496611
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911166080.7A Active CN111122447B (en) | 2019-11-25 | 2019-11-25 | Multispectral wave band correction method for unmanned aerial vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111122447B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010220076A (en) * | 2009-03-18 | 2010-09-30 | Ricoh Co Ltd | Image-reading apparatus, image forming apparatus, shading correction method, and shading correction control program |
| CN105891147A (en) * | 2016-03-30 | 2016-08-24 | 浙江中烟工业有限责任公司 | Near infrared spectrum information extraction method based on canonical correlation coefficients |
| CN106023130A (en) * | 2016-06-07 | 2016-10-12 | 中山大学 | Gradient filtering and PCA-based unmanned aerial vehicle (UAV) image and multispectral image fusion method |
| CN108985311A (en) * | 2018-05-08 | 2018-12-11 | 中国电力科学研究院有限公司 | A kind of dimension reduction method and system of high-spectrum remote sensing data |
| CN109118525A (en) * | 2017-06-23 | 2019-01-01 | 北京遥感设备研究所 | A kind of dual-band infrared image airspace method for registering |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102006053788A1 (en) * | 2006-11-15 | 2008-05-21 | Giesecke & Devrient Gmbh | Method for detecting contamination in the area of color transitions on value documents and means for carrying out the method |
-
2019
- 2019-11-25 CN CN201911166080.7A patent/CN111122447B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010220076A (en) * | 2009-03-18 | 2010-09-30 | Ricoh Co Ltd | Image-reading apparatus, image forming apparatus, shading correction method, and shading correction control program |
| CN105891147A (en) * | 2016-03-30 | 2016-08-24 | 浙江中烟工业有限责任公司 | Near infrared spectrum information extraction method based on canonical correlation coefficients |
| CN106023130A (en) * | 2016-06-07 | 2016-10-12 | 中山大学 | Gradient filtering and PCA-based unmanned aerial vehicle (UAV) image and multispectral image fusion method |
| CN109118525A (en) * | 2017-06-23 | 2019-01-01 | 北京遥感设备研究所 | A kind of dual-band infrared image airspace method for registering |
| CN108985311A (en) * | 2018-05-08 | 2018-12-11 | 中国电力科学研究院有限公司 | A kind of dimension reduction method and system of high-spectrum remote sensing data |
Non-Patent Citations (1)
| Title |
|---|
| "SPOT6卫星图像处理关键技术研究";马世斌 等;《国土资源遥感》;20150930;第27卷(第3期);30-35 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111122447A (en) | 2020-05-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108428220B (en) | Automatic geometric correction method for ocean island reef area of remote sensing image of geostationary orbit satellite sequence | |
| CN110186822B (en) | Aerosol optical thickness remote sensing inversion method | |
| CN111062991A (en) | Method and device for positioning inspection target of photovoltaic scene and readable storage medium | |
| CN103942555B (en) | Method for detecting nitrogen content of plant through images | |
| CN112766155A (en) | Deep learning-based mariculture area extraction method | |
| CN109557030A (en) | A kind of water quality element inversion method based on unmanned aerial vehicle remote sensing | |
| CN109522929A (en) | It is a kind of based on multi-source image fusion natural environment under wheat weeds recognition methods | |
| CN109919930A (en) | The statistical method of fruit number on tree based on convolutional neural networks YOLO V3 | |
| CN108133471B (en) | Robot navigation path extraction method and device based on artificial bee colony algorithm | |
| CN113920376B (en) | Wheat seed variety identification method based on lightweight convolutional neural network | |
| CN110705449A (en) | Land utilization change remote sensing monitoring analysis method | |
| CN106997591A (en) | A kind of super voxel dividing method of RGB D image mutative scales | |
| CN112557307B (en) | Space-air-ground integrated lake and reservoir water quality monitoring fusion data method | |
| CN111008642A (en) | High-resolution remote sensing image classification method and system based on convolutional neural network | |
| CN113902759B (en) | Space-spectrum information combined satellite-borne hyperspectral image segmentation and clustering method | |
| CN102881007A (en) | Image processing method and system for plane separation result of compound | |
| CN116337781A (en) | Sorghum variety identification method based on spectral image reconstruction | |
| CN112164055A (en) | Photovoltaic cell color difference classification method based on color segmentation | |
| CN117058522A (en) | Remote sensing earth surface ecological change detection method integrating spectral neural network and leaf area index | |
| CN111122447B (en) | Multispectral wave band correction method for unmanned aerial vehicle | |
| CN114332534A (en) | Hyperspectral image small sample classification method | |
| CN112184785B (en) | Multi-mode remote sensing image registration method based on MCD measurement and VTM | |
| CN113627329A (en) | Wheat seed hyperspectral image classification method and system based on hybrid convolutional network | |
| CN110298347B (en) | Method for identifying automobile exhaust analyzer screen based on GrayWorld and PCA-CNN | |
| CN113702377B (en) | Glucose degree nondestructive testing method based on deep learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |