CN113033279A - Crop fine classification method and system based on multi-source remote sensing image - Google Patents
Crop fine classification method and system based on multi-source remote sensing image Download PDFInfo
- Publication number
- CN113033279A CN113033279A CN202011434641.XA CN202011434641A CN113033279A CN 113033279 A CN113033279 A CN 113033279A CN 202011434641 A CN202011434641 A CN 202011434641A CN 113033279 A CN113033279 A CN 113033279A
- Authority
- CN
- China
- Prior art keywords
- data
- crop
- classification
- spectral
- crops
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2134—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on separation criteria, e.g. independent component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a crop fine classification method and a crop fine classification system based on multi-source remote sensing images, wherein the method comprises the following steps: acquiring a first satellite image and a second satellite image; extracting cultivated land plot data based on the first satellite image; dividing the second satellite image based on the cultivated land plot data and extracting spectral data corresponding to the cultivated land plot data; calculating the normalized vegetation index and the spectral characteristics of the spectral data of each pixel in the farmland block data, respectively carrying out mean value calculation on the normalized vegetation index and the spectral characteristics, and generating a multivariate classification parameter set corresponding to the farmland block data; and extracting the crops contained in the multivariate classification parameter set based on the support vector machine to generate crop fine classification data. The crop type information extraction method based on the multi-source remote sensing image improves the classification precision and the land parcel integrity of the crop type, and solves the problem of low crop classification accuracy of the traditional crop classification method.
Description
Technical Field
The invention relates to the technical field of remote sensing image processing for crop classification, in particular to a crop fine classification method and a crop fine classification system based on multi-source remote sensing images.
Background
Crop remote sensing identification and classification are important contents of agricultural remote sensing, are the premises of crop area extraction, growth monitoring, disaster risk prediction, yield estimation and space-time distribution research, and are the basis of fine dynamic management of modern intelligent agriculture. The data of the variety, the area, the yield and the like of crops are important indexes of grain production, and are important basis for national establishment of grain policies and national economic development plans.
At first, the information of crop species, planting area, yield and the like is obtained by sampling mainly by an agronomic method, and an agronomic mode and a meteorological mode are adopted, but the modes are complex in calculation, large in field workload, high in cost, large in human factor influence and difficult to improve accuracy. The method mainly utilizes a plurality of time sequence data (such as NDVI) with medium-low spatial resolution to analyze the planting mode or the growing phenological period of crops, and monitors the conditions of the planting area, the variety and the like of the crops.
At present, with the emission of a high-resolution remote sensing satellite, a data source with higher spatial and spectral resolution is provided for farmland information extraction, and meanwhile, the method has great potential in crop classification, and different crops are identified mainly by using high-spatial resolution data and adopting a supervised or unsupervised classification method.
However, whether crop classification is based on high, medium, and low resolution data, conventional classification methods are based on a single data source. The phenomenon of identifying mixed pixels by crop classification based on medium-resolution and low-resolution data is serious, and the problem of insufficient spectral information exists based on single high-resolution data. Therefore, the traditional crop classification methods all have the problem of low crop classification accuracy.
Disclosure of Invention
In view of the above, the invention provides a crop fine classification method based on multi-source remote sensing images, and solves the problem of low crop classification accuracy existing in the traditional crop classification methods by improving an image detection method.
In order to solve the problems, the technical scheme of the invention is to adopt a crop fine classification method based on multi-source remote sensing images, which comprises the following steps: s1: acquiring a first satellite image with high spatial resolution and a second satellite image with high spectrum; s2: extracting cultivated land plot data based on the first satellite image; s3: dividing the second satellite image based on the cultivated land plot data and extracting spectral data corresponding to the cultivated land plot data; s4: calculating the normalized vegetation index of each pixel in the farmland land mass data and the spectral characteristics of the spectral data, respectively carrying out mean value calculation on the normalized vegetation index and the spectral characteristics, and generating a multivariate classification parameter set corresponding to the farmland land mass data; s5: and extracting the crops contained in the multivariate classification parameter set based on a support vector machine to generate crop fine classification data.
Optionally, calculating spectral features of the spectral data comprises: s11: extracting a plurality of canopy spectral reflectivity curves corresponding to crops contained in the spectral data, and calculating an average spectral reflectivity curve; s12: calculating the average reflectivity curve of the crop surface based on the average spectral reflectivity curve; s13: repeating steps S11-S12 until a curve of average reflectivity of the crop surface is generated for all of the crops included in the spectral data; s14: extracting wave bands belonging to a near-infrared spectrum interval in the average reflectivity curve of the crop surface corresponding to all the crops as original wave band characteristic variables, and extracting n groups of characteristic variables by performing wave band combination, multiple vegetation index transformation, principal component analysis, independent component analysis and minimum noise separation on the spectrum data, wherein n is the number of the types of the crops; s15: and extracting n characteristic variables with the largest information entropy in the n groups of the plurality of characteristic variables as the spectral characteristics.
Optionally, calculating a normalized vegetation index of each pixel in the farmland plot data includes: using formulas
And calculating the normalized vegetation index of each pixel, wherein NDVI is the normalized vegetation index, and NIR and Rad are the reflectivity of the near infrared band and the reflectivity of the red light band of each pixel respectively.
Optionally, the S2 includes: and carrying out segmentation and region classification on the first satellite image based on spatial, texture and spectral information contained in the first satellite image by using an object-oriented classification method to generate the farmland land block data.
Optionally, the S5 includes: based on field sampling data and pre-acquired high-resolution data and hyperspectral data, comprehensively considering spectrum and texture information for visual interpretation, and selecting different crop classification samples as training samples in a pixel pure area; training the support vector machine based on the training samples and constructing a classification model for fine classification of crops; the classification model of the support vector machine generates the crop fine classification data by extracting the crops contained in the multivariate classification parameter set.
Optionally, the S1 further includes: after a first satellite image with high spatial resolution and a second satellite image with high spectrum are obtained, image preprocessing is carried out on the first satellite image and the second satellite image, and the image preprocessing comprises radiometric calibration, atmospheric correction, geometric correction and image registration.
Optionally, the crop fine classification method further comprises: after the crop fine classification data are generated, the precision of the crop fine classification data is evaluated through a confusion matrix.
Correspondingly, the invention provides a crop fine classification system based on multi-source remote sensing images, which comprises: the data acquisition unit is used for acquiring a first satellite image with high spatial resolution and a second satellite image with high spectrum; the data processing unit is used for extracting farmland land block data based on the first satellite image, dividing the second satellite image based on the farmland land block data, extracting spectral data corresponding to the farmland land block data, calculating a normalized vegetation index of each pixel in the farmland land block data and spectral characteristics of the spectral data, performing mean value calculation on the normalized vegetation index and the spectral characteristics respectively, and generating a multivariate classification parameter set corresponding to the farmland land block data; and the support vector machine is used for extracting the crops contained in the multivariate classification parameter set and generating crop fine classification data.
Optionally, the data processing unit calculates an average spectral reflectance curve by extracting a plurality of canopy spectral reflectance curves corresponding to crops included in the spectral data, calculates the average spectral reflectance curve of the surface of the crop based on the average spectral reflectance curve, repeatedly calculates the average reflectance curve of the surface of the crop until generating the average reflectance curves corresponding to all the crops included in the spectral data, extracts a wavelength band belonging to a near-infrared spectral interval in the average reflectance curves of the surface of the crop corresponding to all the crops as an original wavelength band characteristic variable, extracting n groups of characteristic variables by performing wave band combination, multiple vegetation index transformation, principal component analysis, independent component analysis and minimum noise separation on the spectral data, wherein n is the number of the types of the crops, and extracting n characteristic variables with the largest information entropy from the n groups of the characteristic variables as the spectral characteristics.
Optionally, the obtaining of the training sample of the support vector machine includes: based on field sampling data and pre-acquired high-resolution data and hyperspectral data, comprehensively considering spectrum and texture information for visual interpretation, and selecting different crop classification samples as training samples in a pixel pure area; training the support vector machine based on the training samples and constructing a classification model for fine classification of crops; the classification model of the support vector machine generates the crop fine classification data by extracting the crops contained in the multivariate classification parameter set.
The primary improvement of the invention is to provide a crop fine classification method based on multi-source remote sensing images, by collecting a first satellite image with high spatial resolution and a second satellite image with high spectrum, the cultivated land plot data contained in the first satellite image is extracted based on an object-oriented method, the second satellite image is divided, a multi-source characteristic parameter set of each cultivated land plot data is established, and crop classification is carried out by adopting an SVM method, so that crop type information extraction based on a multi-source remote sensing image is realized, the problems of the conventional pixel classification method-based crop type extraction pattern spot breakage and the problems of over-segmentation and under-segmentation of the conventional object-oriented segmentation method are solved, the classification precision and the land parcel integrity of the crop type are improved, and the problem of low crop classification accuracy of the conventional crop classification method is solved.
Drawings
FIG. 1 is a simplified flow chart of a method for fine classification of crops based on multi-source remote sensing images according to the present invention;
FIG. 2 is a simplified module connection diagram of the crop fine classification system based on multi-source remote sensing images.
Detailed Description
In order to make the technical solutions of the present invention better understood by those skilled in the art, the present invention will be further described in detail with reference to the accompanying drawings and specific embodiments.
As shown in fig. 1, a method for finely classifying crops based on multi-source remote sensing images includes: s1: acquiring a first satellite image with high spatial resolution and a second satellite image with high spectrum; s2: extracting cultivated land plot data based on the first satellite image; s3: dividing the second satellite image based on the cultivated land plot data and extracting spectral data corresponding to the cultivated land plot data; s4: calculating the normalized vegetation index of each pixel in the farmland land mass data and the spectral characteristics of the spectral data, respectively carrying out mean value calculation on the normalized vegetation index and the spectral characteristics, and generating a multivariate classification parameter set corresponding to the farmland land mass data; s5: and extracting the crops contained in the multivariate classification parameter set based on a support vector machine to generate crop fine classification data. Wherein the S1 further includes: after a first satellite image with high spatial resolution and a second satellite image with high spectrum are obtained, image preprocessing is carried out on the first satellite image and the second satellite image, and the image preprocessing comprises radiometric calibration, atmospheric correction and geometric correction. Wherein, the radiometric calibration is to convert the original DN value into apparent reflectivity, in order to eliminate the error of the sensor; the atmospheric correction can be realized by converting pixel radiation brightness values into earth surface reflectivity by using a FLAASH atmospheric correction model, and the error caused by atmospheric scattering, absorption and reflection can be eliminated; the orthorectification is to correct the terrain of each pixel in the image by means of a terrain elevation model, so that the image meets the requirements of orthoprojection. Further, the image preprocessing also comprises image registration, wherein the image registration is to match and stack two or more images acquired at different time and under different sensors or under different conditions (weather, illumination, camera shooting position, angle and the like), so that points of the same position of the multiple images correspond one to one, information fusion is achieved, and information mismatching is avoided.
According to the method, the first satellite image with high spatial resolution and the second satellite image with high spectrum are acquired, the cultivated land plot data contained in the first satellite image is extracted based on an object-oriented method, the second satellite image is divided according to the cultivated land plot data, the multi-source characteristic parameter set of each cultivated land plot data is established, crop classification is carried out by adopting an SVM (support vector machine) method, crop type information extraction based on the multi-source remote sensing image is realized, the problem that the extracted map spots of the traditional crop type based on a pixel classification method are broken and the problems of over-segmentation and under-segmentation of the traditional object-oriented segmentation method are solved, the classification precision and the plot integrity of the crop type are improved, and the problem that the crop classification accuracy is low in the traditional crop classification method is solved.
Further, calculating spectral features of the spectral data includes: s11: extracting a plurality of canopy spectral reflectivity curves corresponding to crops contained in the spectral data, and calculating an average spectral reflectivity curve; s12: calculating the average reflectivity curve of the crop surface based on the average spectral reflectivity curve; s13: repeating steps S11-S12 until a curve of average reflectivity of the crop surface is generated for all of the crops included in the spectral data; s14: extracting wave bands belonging to a near-infrared spectrum interval in the average reflectivity curve of the crop surface corresponding to all the crops as original wave band characteristic variables, and extracting n groups of multiple characteristic variables by performing wave band combination, multiple vegetation index transformation, principal component analysis, independent component analysis and minimum noise separation on the spectrum data, wherein n is the number of the types of the crops; s15: since the features with the largest entropy content contain the largest amount of information, m feature variables with the largest information entropy in the n groups of the plurality of feature variables are extracted as the spectral features.
Further, calculating the normalized vegetation index of each pixel in the farmland plot data, which comprises the following steps: using formulas
And calculating the normalized vegetation index of each pixel, wherein NDVI is the normalized vegetation index, and NIR and Rad are the reflectivity of the near infrared band and the reflectivity of the red light band of each pixel respectively.
Further, the S2 includes: and carrying out segmentation and region classification on the first satellite image based on spatial, texture and spectral information contained in the first satellite image by using an object-oriented classification method to generate the farmland land block data. Specifically, the object-oriented classification method adopted by the invention adopts an edge-based multi-scale segmentation algorithm, can perform segmentation according to information such as brightness values, textures, colors and the like of adjacent pixels, and generates a multi-scale segmentation result by controlling the difference of boundaries under multi-scale.
Further, the S5 includes: based on field sampling data and pre-acquired high-resolution data and hyperspectral data, comprehensively considering spectrum and texture information for visual interpretation, and selecting different crop classification samples as training samples in a pixel pure area; training the support vector machine based on the training samples and constructing a classification model for fine classification of crops; the classification model of the support vector machine generates the crop fine classification data by extracting the crops contained in the multivariate classification parameter set. After the crop fine classification data are generated, the precision of the crop fine classification data can be evaluated through a confusion matrix.
Correspondingly, as shown in fig. 2, the present invention provides a crop fine classification system based on multi-source remote sensing images, including: the data acquisition unit is used for acquiring a first satellite image with high spatial resolution and a second satellite image with high spectrum; the data processing unit is used for extracting farmland land block data based on the first satellite image, dividing the second satellite image based on the farmland land block data, extracting spectral data corresponding to the farmland land block data, calculating a normalized vegetation index of each pixel in the farmland land block data and spectral characteristics of the spectral data, performing mean value calculation on the normalized vegetation index and the spectral characteristics respectively, and generating a multivariate classification parameter set corresponding to the farmland land block data; and the support vector machine is used for extracting the crops contained in the multivariate classification parameter set and generating crop fine classification data. The data processing unit is respectively in communication connection with the data acquisition unit and the support vector machine.
Further, the data processing unit calculates an average spectral reflectance curve by extracting a plurality of canopy spectral reflectance curves corresponding to crops included in the spectral data, calculates the crop surface average reflectance curve based on the average spectral reflectance curve, repeatedly calculates the crop surface average reflectance curve until the crop surface average reflectance curve corresponding to all the crops included in the spectral data is generated, extracts a band belonging to a near-infrared spectral interval in the crop surface average reflectance curve corresponding to all the crops as an original band characteristic variable, extracts n groups of a plurality of characteristic variables by performing band combination, multiple vegetation index transformation, principal component analysis, independent component analysis and minimum noise separation on the spectral data, where n is the number of types of the crops, and extracts m characteristic variables having the largest information entropy among the n groups of the plurality of characteristic variables as the spectral characteristic.
Further, the obtaining of the training sample of the support vector machine comprises: based on field sampling data and pre-acquired high-resolution data and hyperspectral data, comprehensively considering spectrum and texture information for visual interpretation, and selecting different crop classification samples as training samples in a pixel pure area; training the support vector machine based on the training samples and constructing a classification model for fine classification of crops; the classification model of the support vector machine generates the crop fine classification data by extracting the crops contained in the multivariate classification parameter set.
The above is only a preferred embodiment of the present invention, and it should be noted that the above preferred embodiment should not be considered as limiting the present invention, and the protection scope of the present invention should be subject to the scope defined by the claims. It will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the spirit and scope of the invention, and these modifications and adaptations should be considered within the scope of the invention.
Claims (10)
1. A crop fine classification method based on multi-source remote sensing images is characterized by comprising the following steps:
s1: acquiring a first satellite image with high spatial resolution and a second satellite image with high spectrum;
s2: extracting cultivated land plot data based on the first satellite image;
s3: dividing the second satellite image based on the cultivated land plot data and extracting spectral data corresponding to the cultivated land plot data;
s4: calculating the normalized vegetation index of each pixel in the farmland land mass data and the spectral characteristics of the spectral data, respectively carrying out mean value calculation on the normalized vegetation index and the spectral characteristics, and generating a multivariate classification parameter set corresponding to the farmland land mass data;
s5: and extracting the crops contained in the multivariate classification parameter set based on a support vector machine to generate crop fine classification data.
2. The method of fine classification of crops according to claim 1, wherein calculating the spectral characteristics of the spectral data comprises:
s11: extracting a plurality of canopy spectral reflectivity curves corresponding to crops contained in the spectral data, and calculating an average spectral reflectivity curve;
s12: calculating the average reflectivity curve of the crop surface based on the average spectral reflectivity curve;
s13: repeating steps S11-S12 until a curve of average reflectivity of the crop surface is generated for all of the crops included in the spectral data;
s14: extracting wave bands belonging to a near-infrared spectrum interval in the average reflectivity curve of the crop surface corresponding to all the crops as original wave band characteristic variables, and extracting n groups of characteristic variables by performing wave band combination, multiple vegetation index transformation, principal component analysis, independent component analysis and minimum noise separation on the spectrum data, wherein n is the number of the types of the crops;
s15: and extracting n characteristic variables with the largest information entropy in the n groups of the plurality of characteristic variables as the spectral characteristics.
3. The method of claim 2, wherein calculating the normalized vegetation index for each pixel in the farmland plot data comprises:
using formulas
And calculating the normalized vegetation index of each pixel, wherein NDVI is the normalized vegetation index, and NIR and Rad are the reflectivity of the near infrared band and the reflectivity of the red light band of each pixel respectively.
4. The method for fine classification of crops according to claim 1, wherein said S2 comprises:
and carrying out segmentation and region classification on the first satellite image based on spatial, texture and spectral information contained in the first satellite image by using an object-oriented classification method to generate the farmland land block data.
5. The method for fine classification of crops according to claim 1, wherein said S5 comprises:
based on field sampling data and pre-acquired high-resolution data and hyperspectral data, comprehensively considering spectrum and texture information for visual interpretation, and selecting different crop classification samples as training samples in a pixel pure area;
training the support vector machine based on the training samples and constructing a classification model for fine classification of crops;
the classification model of the support vector machine generates the crop fine classification data by extracting the crops contained in the multivariate classification parameter set.
6. The method for finely classifying crops according to claim 1, wherein said S1 further comprises:
after a first satellite image with high spatial resolution and a second satellite image with high spectrum are obtained, image preprocessing is carried out on the first satellite image and the second satellite image, and the image preprocessing comprises radiometric calibration, atmospheric correction, geometric correction and image registration.
7. The method of fine classification of crops as claimed in claim 1, further comprising:
after the crop fine classification data are generated, the precision of the crop fine classification data is evaluated through a confusion matrix.
8. A crop fine classification system based on multi-source remote sensing images is characterized by comprising:
the data acquisition unit is used for acquiring a first satellite image with high spatial resolution and a second satellite image with high spectrum;
the data processing unit is used for extracting farmland land block data based on the first satellite image, dividing the second satellite image based on the farmland land block data, extracting spectral data corresponding to the farmland land block data, calculating a normalized vegetation index of each pixel in the farmland land block data and spectral characteristics of the spectral data, performing mean value calculation on the normalized vegetation index and the spectral characteristics respectively, and generating a multivariate classification parameter set corresponding to the farmland land block data;
and the support vector machine is used for extracting the crops contained in the multivariate classification parameter set and generating crop fine classification data.
9. The crop fine classification system according to claim 8, wherein the data processing unit extracts n sets of characteristic variables by extracting a plurality of canopy spectral reflectance curves corresponding to crops included in the spectral data, calculating an average spectral reflectance curve, calculating the crop surface average reflectance curve based on the average spectral reflectance curve, repeatedly calculating the crop surface average reflectance curve until the crop surface average reflectance curves corresponding to all the crops included in the spectral data are generated, extracting a band belonging to a near-infrared spectral interval in the crop surface average reflectance curves corresponding to all the crops as an original band characteristic variable, and performing band combination, a plurality of vegetation index transformations, principal component analysis, independent component analysis, and minimum noise separation on the spectral data, and n is the number of the types of the crops, and n characteristic variables with the largest information entropy in the n groups of the plurality of characteristic variables are extracted as the spectral characteristics.
10. The crop fine classification system of claim 8, wherein the obtaining of the training samples of the support vector machine comprises: based on field sampling data and pre-acquired high-resolution data and hyperspectral data, comprehensively considering spectrum and texture information for visual interpretation, and selecting different crop classification samples as training samples in a pixel pure area;
training the support vector machine based on the training samples and constructing a classification model for fine classification of crops;
the classification model of the support vector machine generates the crop fine classification data by extracting the crops contained in the multivariate classification parameter set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011434641.XA CN113033279A (en) | 2020-12-10 | 2020-12-10 | Crop fine classification method and system based on multi-source remote sensing image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011434641.XA CN113033279A (en) | 2020-12-10 | 2020-12-10 | Crop fine classification method and system based on multi-source remote sensing image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113033279A true CN113033279A (en) | 2021-06-25 |
Family
ID=76459211
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011434641.XA Pending CN113033279A (en) | 2020-12-10 | 2020-12-10 | Crop fine classification method and system based on multi-source remote sensing image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113033279A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113591775A (en) * | 2021-08-11 | 2021-11-02 | 武汉工程大学 | Multispectral remote sensing image specific ground object extraction method combining hyperspectral features |
| CN113723228A (en) * | 2021-08-16 | 2021-11-30 | 北京大学 | Method and device for determining earth surface type ratio, electronic equipment and storage medium |
| CN113807219A (en) * | 2021-09-06 | 2021-12-17 | 苏州中科蓝迪软件技术有限公司 | Method for identifying types of grain and oil crops in planting land by steps |
| CN113901966A (en) * | 2021-12-07 | 2022-01-07 | 武汉光谷信息技术股份有限公司 | Crop classification method fusing multi-source geographic information data |
| CN116597318A (en) * | 2023-07-17 | 2023-08-15 | 山东锋士信息技术有限公司 | Irrigation area cultivated land precise extraction method, equipment and storage medium based on remote sensing image |
| CN117470789A (en) * | 2023-11-06 | 2024-01-30 | 中国自然资源航空物探遥感中心 | Method, device, equipment and readable storage medium for identifying dawsonite |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104794424A (en) * | 2014-01-20 | 2015-07-22 | 北京天合数维科技有限公司 | Novel middle-low resolution remote sensing data combined cultivated land identification method |
| CN105354534A (en) * | 2015-09-29 | 2016-02-24 | 南京林业大学 | Tree species classification method based on multi-source simultaneous high-resolution remote sensing data |
| CN105678281A (en) * | 2016-02-04 | 2016-06-15 | 中国农业科学院农业资源与农业区划研究所 | Plastic film mulching farmland remote sensing monitoring method based on spectrum and texture features |
| CN108764255A (en) * | 2018-05-21 | 2018-11-06 | 二十世纪空间技术应用股份有限公司 | A kind of extracting method of winter wheat planting information |
| CN109409261A (en) * | 2018-10-11 | 2019-03-01 | 北京师范大学 | A kind of Crop classification method and system |
| CN110163138A (en) * | 2019-05-13 | 2019-08-23 | 河南科技大学 | A kind of wheat tillering density measuring method based on unmanned plane multi-spectral remote sensing image |
| CN110598514A (en) * | 2019-06-10 | 2019-12-20 | 南京大学 | Method for monitoring plot scale crop seeding area of land reclamation project area |
| CN111444835A (en) * | 2020-03-26 | 2020-07-24 | 贵阳欧比特宇航科技有限公司 | Method for extracting ground object spatial distribution positions based on multi-source remote sensing data |
| CN111598019A (en) * | 2020-05-19 | 2020-08-28 | 华中农业大学 | Crop type and planting mode identification method based on multi-source remote sensing data |
-
2020
- 2020-12-10 CN CN202011434641.XA patent/CN113033279A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104794424A (en) * | 2014-01-20 | 2015-07-22 | 北京天合数维科技有限公司 | Novel middle-low resolution remote sensing data combined cultivated land identification method |
| CN105354534A (en) * | 2015-09-29 | 2016-02-24 | 南京林业大学 | Tree species classification method based on multi-source simultaneous high-resolution remote sensing data |
| CN105678281A (en) * | 2016-02-04 | 2016-06-15 | 中国农业科学院农业资源与农业区划研究所 | Plastic film mulching farmland remote sensing monitoring method based on spectrum and texture features |
| CN108764255A (en) * | 2018-05-21 | 2018-11-06 | 二十世纪空间技术应用股份有限公司 | A kind of extracting method of winter wheat planting information |
| CN109409261A (en) * | 2018-10-11 | 2019-03-01 | 北京师范大学 | A kind of Crop classification method and system |
| CN110163138A (en) * | 2019-05-13 | 2019-08-23 | 河南科技大学 | A kind of wheat tillering density measuring method based on unmanned plane multi-spectral remote sensing image |
| CN110598514A (en) * | 2019-06-10 | 2019-12-20 | 南京大学 | Method for monitoring plot scale crop seeding area of land reclamation project area |
| CN111444835A (en) * | 2020-03-26 | 2020-07-24 | 贵阳欧比特宇航科技有限公司 | Method for extracting ground object spatial distribution positions based on multi-source remote sensing data |
| CN111598019A (en) * | 2020-05-19 | 2020-08-28 | 华中农业大学 | Crop type and planting mode identification method based on multi-source remote sensing data |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113591775A (en) * | 2021-08-11 | 2021-11-02 | 武汉工程大学 | Multispectral remote sensing image specific ground object extraction method combining hyperspectral features |
| CN113591775B (en) * | 2021-08-11 | 2022-08-02 | 武汉工程大学 | Multispectral remote sensing image specific ground object extraction method combining hyperspectral features |
| CN113723228A (en) * | 2021-08-16 | 2021-11-30 | 北京大学 | Method and device for determining earth surface type ratio, electronic equipment and storage medium |
| CN113723228B (en) * | 2021-08-16 | 2024-04-26 | 北京大学 | Method and device for determining earth surface type duty ratio, electronic equipment and storage medium |
| CN113807219A (en) * | 2021-09-06 | 2021-12-17 | 苏州中科蓝迪软件技术有限公司 | Method for identifying types of grain and oil crops in planting land by steps |
| CN113901966A (en) * | 2021-12-07 | 2022-01-07 | 武汉光谷信息技术股份有限公司 | Crop classification method fusing multi-source geographic information data |
| CN113901966B (en) * | 2021-12-07 | 2022-03-11 | 武汉光谷信息技术股份有限公司 | Crop classification method fusing multi-source geographic information data |
| CN116597318A (en) * | 2023-07-17 | 2023-08-15 | 山东锋士信息技术有限公司 | Irrigation area cultivated land precise extraction method, equipment and storage medium based on remote sensing image |
| CN116597318B (en) * | 2023-07-17 | 2023-09-26 | 山东锋士信息技术有限公司 | Irrigation area cultivated land precise extraction method, equipment and storage medium based on remote sensing image |
| CN117470789A (en) * | 2023-11-06 | 2024-01-30 | 中国自然资源航空物探遥感中心 | Method, device, equipment and readable storage medium for identifying dawsonite |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113033279A (en) | Crop fine classification method and system based on multi-source remote sensing image | |
| Qiao et al. | UAV-based chlorophyll content estimation by evaluating vegetation index responses under different crop coverages | |
| Näsi et al. | Remote sensing of bark beetle damage in urban forests at individual tree level using a novel hyperspectral camera from UAV and aircraft | |
| Graesser et al. | Detection of cropland field parcels from Landsat imagery | |
| US7058197B1 (en) | Multi-variable model for identifying crop response zones in a field | |
| Donmez et al. | Computer vision-based citrus tree detection in a cultivated environment using UAV imagery | |
| Hall et al. | Optical remote sensing applications in viticulture‐a review | |
| CN112183209B (en) | Regional crop classification method and system based on multidimensional feature fusion | |
| US8300896B2 (en) | Remote sensing and probabilistic sampling based forest inventory method | |
| Jafarbiglu et al. | A comprehensive review of remote sensing platforms, sensors, and applications in nut crops | |
| George et al. | Forest tree species discrimination in western Himalaya using EO-1 Hyperion | |
| Kordi et al. | Crop classification based on phenology information by using time series of optical and synthetic-aperture radar images | |
| CN113505635B (en) | Winter wheat and garlic mixed seed area identification method and device based on optics and radar | |
| CN113029971B (en) | Crop canopy nitrogen monitoring method and system | |
| CN112131946B (en) | Automatic extraction method for vegetation and water information of optical remote sensing image | |
| CN114821362B (en) | Multi-source data-based rice planting area extraction method | |
| Ahmad | A review of remote sensing data change detection: Comparison of Faisalabad and Multan Districts, Punjab Province, Pakistan | |
| S Bhagat | Use of remote sensing techniques for robust digital change detection of land: A review | |
| Sagan et al. | Data-driven artificial intelligence for calibration of hyperspectral big data | |
| Miao et al. | Detection and classification of invasive saltcedar through high spatial resolution airborne hyperspectral imagery | |
| CN114612794A (en) | Remote sensing identification method for land covering and planting structure in finely-divided agricultural area | |
| Demir et al. | Determination of opium poppy (Papaver somniferum) parcels using high-resolution satellite imagery | |
| Veramendi et al. | Method for maize plants counting and crop evaluation based on multispectral images analysis | |
| Jia et al. | The influence of BRDF effects and representativeness of training data on tree species classification using multi-flightline airborne hyperspectral imagery | |
| Liu et al. | Semi-automatic extraction and mapping of farmlands based on high-resolution remote sensing images |
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 |