CN110321861A - A kind of main crops production moon scale Dynamic Extraction method - Google Patents
A kind of main crops production moon scale Dynamic Extraction method Download PDFInfo
- Publication number
- CN110321861A CN110321861A CN201910613999.XA CN201910613999A CN110321861A CN 110321861 A CN110321861 A CN 110321861A CN 201910613999 A CN201910613999 A CN 201910613999A CN 110321861 A CN110321861 A CN 110321861A
- Authority
- CN
- China
- Prior art keywords
- texture
- image
- data
- main crops
- moon
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2431—Multiple classes
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of main crops production moon scale Dynamic Extraction methods, the following steps are included: S1: determining analyzed area spatial dimension and carry out data preparation, collect the time series satellite remote sensing date collection for being not more than moon scale, it is uniformly processed on time as moon scale data, is completed at the same time the pre-acquiring of sample data in survey region;S2: utilizing pretreated moon scale satellite remote-sensing image data, calculates textural characteristics and normalized differential vegetation index;S3: choosing abundant information degree, and high textural characteristics combine to form new image with vegetation index;The revisiting period for solving previous methods is long, it is difficult, at high price to obtain Optimum temoral and is difficult to meet the needs of problems that crop dynamic manages.
Description
Technical field
The present invention relates to remote sensing patterns of farming to monitor field, especially a kind of main crops production moon scale Dynamic Extraction
Method.
Background technique
Main crops production reflects the situation that human agriculture's production utilizes agricultural production resources in spatial dimension, is
The important information of crop specie, quantitative structure and spatial distribution characteristic is studied, and carries out Crop Structure Adjustment and optimization
And the foundation of agricultural water fine-grained management.The method that tradition obtains main crops production information relies primarily on local management
Department reports step by step to be investigated with territorial sampling, and both methods is not only spent human and material resources, and is difficult to obtain all kinds of crops
Space distribution information.
With the development of remote sensing technology, the acquisition modes of traditional crop pattern of farming information are changed.It generallys use at present
The remotely-sensed data of the low spatial resolutions such as spatial resolution or NOAA, MODIS in TM, SPOT, HJ etc..Pei Huan, horse are beautiful etc. to be utilized
Landsat8 data are based on vegetation index and Object--oriented method obtains land use classes result;Dong J etc. is based on L8 number
According to the spatial distribution of inverting rice;Liu Huanjun, Susan Ustin etc. are based on L8 data and establish Yield Estimation Model to cotton;Wu Jianping
Et al. use NOAA/AVHRR data estimation Estimating Paddy Area In Shanghai Region;Pan Yaozhong etc. utilizes MODIS-EVI time series pair
Typical crops carry out Classification and Identification, and Zhao Lihua, Liu Jia, Yu Supu Jiang Aimai such as mention at the sky that winter wheat etc. is extracted based on HJ satellite
Between distributed intelligence.The remotely-sensed data acquisition source of middle low resolution is more, and image wide coverage, is suitble to the single of large area
Crop identification;But due to the interference of middle low resolution image mixed pixel phenomenon, for complicated type of ground objects, seriously affect
The extraction accuracy of its crop.With the raising of sensor resolution, for Quick Bird, SPOT, SuperView-1, SAR etc.
High spatial resolution data are also used to extract crop acreage.Ye Shiping is mentioned based on the textural characteristics of gray level co-occurrence matrixes
Take the Land-use of Quick Bird image;Yang M D, Hou Xuehui etc. grow vegetation using SPOT image data
Phase detection;Dekker R J., Zhao Lingjun etc. establish textural characteristics based on SAR and analyze urban architecture region.High spatial point
Resolution image can show the characteristic informations such as atural object texture abundant, tone, shape and geometry, atural object interior details information
Obviously, edge is prominent, and resolving accuracy with higher and target identification reliability mention for main crops production extracted with high accuracy
New development space is supplied.But because its revisiting period is long, it is difficult, at high price to obtain Optimum temoral, it is difficult to meet crop dynamic
The demand of management.
Summary of the invention
To solve problems of the prior art, the present invention provides a kind of main crops production moon scale dynamics to mention
Method is taken, the revisiting period for solving previous methods is long, it is difficult, at high price to obtain Optimum temoral and is difficult to meet crop and moves
The needs of problems of state management.
The technical solution adopted by the present invention is that a kind of main crops production moon scale Dynamic Extraction method, including it is following
Step:
S1: determining analyzed area spatial dimension and carries out data preparation, collects the time series satellite for being not more than moon scale
Remotely-sensed data collection, using moon scale data as time data, while sample data in pre-acquiring survey region;
S2: according to pretreated moon scale satellite remote-sensing image data, textural characteristics and normalized differential vegetation index are calculated;
S3: choosing abundant information degree, and high textural characteristics combine to form new image with vegetation index;
S4: the new image data formed in conjunction with combination, using random forest grader to the crop planting of survey region
Structure extracts, and realizes the Dynamic Recognition of moon scale main crops production;
S5: as unit of the moon, to the Dynamic Recognition of main crops production, generate the crops of complete time sequence when
Space division cloth thematic map simultaneously verifies precision.
Preferably, S1 the following steps are included:
S11: according to the location and range in research area, select China's independent research has high time resolution and high spatial
The GF-1WFV data of resolution ratio the case where cannot being completely covered if there is data source, consider to use sention-2, high score two
Number, landsat8 or HJ-1A/B are replaced, while investigate scope of embodiments crop type and respective growth stage;
S12: carrying out the processing of remote sensing image to the data of collection, if there is alternate data, needs resampling unified empty
Between resolution ratio;
S13: needing to consider its representativeness, typicalness, timeliness to the acquisition of sample, will be studied by establishing regular grid
Zoning is divided into the identical region of n block area, and crop sample is chosen in each region.
Preferably, S2 the following steps are included:
S21: texture feature information amount is calculated based on gray level co-occurrence matrixes, is counted according to gray level co-occurrence matrixes GLCM certain
Gray scale related coefficient between two pixels of distance indicates the probability distribution that gray scale repeats, expression formula are as follows:
P (i, j)=[p (i, j, d, θ)]
Wherein, P (i, j) is the frequency of same pixel pair occur in the case where distance and direction determine;D is range pixel
The angle of the distance of point, two pixel line vectors is θ, and usual θ takes 0 °, 45 °, 90 ° and 135 °;
S22: calculating the normalized differential vegetation index of image data, its calculation formula is:
NDVI=(ρNIR-ρR)/(ρNIR+ρR)
In formula, ρNIRFor the reflectivity of near infrared band;ρRFor the reflectivity of red spectral band.
Preferably, it includes following parameter that the GLCM of S21, which calculates texture feature vector:
Average value: average value reflects average gray in window, reflects the regular degree of texture, calculation formula
Are as follows:
Variance: indicating the period of texture, reflects the nonuniformity characteristic of texture, the size of grey scale change, its calculation formula is:
Contrast: indicating gray difference in neighborhood, reflect the clarity of image and the degree of the texture rill depth, calculates
Formula are as follows:
Non- similarity: for the difference degree of detection image, when the high changes in contrast of regional area is big, then non-similarity is big,
Reflect the clarity of image and the degree of the texture rill depth, its calculation formula is:
Comentropy: entropy measures the randomness of image texture, and information content possessed by image, is image greyscale rank confusion journey
The characterization of degree, entropy is bigger, and the classification uncertainty of sample is bigger, its calculation formula is:
Angular second moment: reflecting image greyscale and be evenly distributed degree and texture fineness degree, its calculation formula is:
Correlation: correlated response spatial gray level co-occurrence matrix element be expert at or column direction on similarity degree, calculate
Formula are as follows:
Preferably, S3 the following steps are included:
S31: the process of optimal solution is sought based on Bhattacharyya distance building multiple target, texture characteristic amount is carried out
It chooses, its calculation formula is:
In formula, μ is 2 different classes of mean values on texture template image, and σ is 2 differences on texture template image
The standard deviation of classification;
S32: according to the size for calculating BD value, preceding 8 texture characteristic amounts are exported;
S33: it is combined preceding 8 texture characteristic amounts with the result of normalized differential vegetation index using the principle that wave band synthesizes, shape
At new images.
Preferably, S4 the following steps are included:
S41: it is extracted according to main crops production of the random forest principle to survey region;
S42: all kinds of parameters needed for setting classifier, input classification samples carry out the main crops production of survey region
Identification classification, completes Dynamic Recognition.
Preferably, the forest principle of S41 are as follows:
Basic unit is CART decision tree, is substantially the improvement to single decision tree, so that nicety of grading is improved, core
The heart is the differentiation to tree node, and specific algorithmic formula is as follows:
In formula, Gini (D) is the gini index calculated result of crops training sample;I indicates the class number of crops,
Respectively refer to winter wheat, summer corn, economic gardens classification;Pi is the probability that each Crop Group occurs in choosing sample set D;
The Gini coefficient of two subsets is divided into for the training sample D that calculating is each drawn, it is two that sample set D, which is divided to,
Subset D 1 and D2, then standard sample set divided are as follows:
If the coefficient value of crop sample set D is greater than the coefficient value of subset D 1 and D2, decision tree continues to divide;If calculating
When crop Geordie index is calculated as 0 or when all samples in the crop subset of refinement are all classified as a kind of crop, then tree stops
It only divides, completes building process.
Preferably, S5 the following steps are included:
S51: as unit of the moon, to research area carry out pattern of farming identification, generate the crops of complete time sequence when
Space division cloth thematic map;
S52: result verification is carried out according to verifying sample, obtains overall classification accuracy and Kappa coefficient.
Main crops production moon scale Dynamic Extraction method of the present invention has the beneficial effect that:
1. the present invention combines the comprehensive identification main crops production of texture, vegetation index, agriculture can not only be effectively identified
Crop Planting Structure, additionally it is possible to dynamically analyzed for agricultural irrigation water amount,
2. the technology has the characteristics that calculate quick, strong applicability, single vegetation index crops identification is effectively improved
Or the dependence of high-resolution data, solve the problems, such as single index, improve precision that remote sensing identifies crops with
Efficiency is of great significance to the popularization of main crops production identification technology businessization.
Detailed description of the invention
Fig. 1 is the overall block flow diagram of main crops production moon scale Dynamic Extraction method of the present invention.
Fig. 2 is the flow chart step by step of the S1 of main crops production moon scale Dynamic Extraction method of the present invention.
Fig. 3 is the flow chart step by step of the S2 of main crops production moon scale Dynamic Extraction method of the present invention.
Fig. 4 is the flow chart step by step of the S3 of main crops production moon scale Dynamic Extraction method of the present invention.
Fig. 5 is the flow chart step by step of the S4 of main crops production moon scale Dynamic Extraction method of the present invention.
Fig. 6 is the flow chart step by step of the S5 of main crops production moon scale Dynamic Extraction method of the present invention.
Specific embodiment
A specific embodiment of the invention is described below, in order to facilitate understanding by those skilled in the art this hair
It is bright, it should be apparent that the present invention is not limited to the ranges of specific embodiment, for those skilled in the art,
As long as various change is in the spirit and scope of the present invention that the attached claims limit and determine, these variations are aobvious and easy
See, all are using the innovation and creation of present inventive concept in the column of protection.
As shown in Figure 1, a kind of main crops production moon scale Dynamic Extraction method, comprising the following steps:
S1: determining analyzed area spatial dimension and carries out data preparation, collects the time series satellite for being not more than moon scale
Remotely-sensed data collection, using moon scale data as time data, while sample data in pre-acquiring survey region;
S2: according to pretreated moon scale satellite remote-sensing image data, textural characteristics and normalized differential vegetation index are calculated;
S3: choosing abundant information degree, and high textural characteristics combine to form new image with vegetation index;
S4: the new image data formed in conjunction with combination, using random forest grader to the crop planting of survey region
Structure extracts, and realizes the Dynamic Recognition of moon scale main crops production;
S5: as unit of the moon, to the Dynamic Recognition of main crops production, generate the crops of complete time sequence when
Space division cloth thematic map simultaneously verifies precision.
As shown in Fig. 2, the S1 of the present embodiment the following steps are included:
S11: according to the location and range in research area, select China's independent research has high time resolution and high spatial
The GF-1WFV data of resolution ratio the case where cannot being completely covered if there is data source, consider to use sention-2, high score two
Number, landsat8 or HJ-1A/B are replaced, while investigate scope of embodiments crop type and respective growth stage;
S12: carrying out the processing of remote sensing image to the data of collection, if there is alternate data, needs resampling unified empty
Between resolution ratio;
S13: needing to consider its representativeness, typicalness, timeliness to the acquisition of sample, will be studied by establishing regular grid
Zoning is divided into the identical region of n block area, and crop sample is chosen in each region.
As shown in figure 3, the S2 of the present embodiment the following steps are included:
S21: texture feature information amount is calculated based on gray level co-occurrence matrixes, is counted according to gray level co-occurrence matrixes GLCM certain
Gray scale related coefficient between two pixels of distance indicates the probability distribution that gray scale repeats, expression formula are as follows:
P (i, j)=[p (i, j, d, θ)]
Wherein, P (i, j) is the frequency of same pixel pair occur in the case where distance and direction determine;D is range pixel
The angle of the distance of point, two pixel line vectors is θ, and usual θ takes 0 °, 45 °, 90 ° and 135 °;
S22: calculating the normalized differential vegetation index of image data, its calculation formula is:
NDVI=(ρNIR-ρR)/(ρNIR+ρR)
In formula, ρNIRFor the reflectivity of near infrared band;ρRFor the reflectivity of red spectral band.
The present embodiment, it includes following parameter that the GLCM of S21, which calculates texture feature vector:
Average value: average value reflects average gray in window, reflects the regular degree of texture, calculation formula
Are as follows:
Variance: indicating the period of texture, reflects the nonuniformity characteristic of texture, the size of grey scale change, its calculation formula is:
Contrast: indicating gray difference in neighborhood, reflect the clarity of image and the degree of the texture rill depth, calculates
Formula are as follows:
Non- similarity: for the difference degree of detection image, when the high changes in contrast of regional area is big, then non-similarity is big,
Reflect the clarity of image and the degree of the texture rill depth, its calculation formula is:
Comentropy: entropy measures the randomness of image texture, and information content possessed by image, is image greyscale rank confusion journey
The characterization of degree, entropy is bigger, and the classification uncertainty of sample is bigger, its calculation formula is:
Angular second moment: reflecting image greyscale and be evenly distributed degree and texture fineness degree, its calculation formula is:
Correlation: correlated response spatial gray level co-occurrence matrix element be expert at or column direction on similarity degree, calculate
Formula are as follows:
As shown in figure 4, the S3 of the present embodiment the following steps are included:
S31: the process of optimal solution is sought based on Bhattacharyya distance building multiple target, texture characteristic amount is carried out
It chooses, its calculation formula is:
In formula, μ is 2 different classes of mean values on texture template image, and σ is 2 differences on texture template image
The standard deviation of classification;
S32: according to the size for calculating BD value, preceding 8 texture characteristic amounts are exported;
S33: it is combined preceding 8 texture characteristic amounts with the result of normalized differential vegetation index using the principle that wave band synthesizes, shape
At new images.
As shown in figure 5, the S4 of the present embodiment the following steps are included:
S41: it is extracted according to main crops production of the random forest principle to survey region;
S42: all kinds of parameters needed for setting classifier, input classification samples carry out the main crops production of survey region
Identification classification, completes Dynamic Recognition.
As shown in figure 5, the forest principle of the S41 of the present embodiment are as follows:
Basic unit is CART decision tree, is substantially the improvement to single decision tree, so that nicety of grading is improved, core
The heart is the differentiation to tree node, and specific algorithmic formula is as follows:
In formula, Gini (D) is the gini index calculated result of crops training sample;I indicates the class number of crops,
Respectively refer to winter wheat, summer corn, economic gardens classification;Pi is the probability that each Crop Group occurs in choosing sample set D;
The Gini coefficient of two subsets is divided into for the training sample D that calculating is each drawn, it is two that sample set D, which is divided to,
Subset D 1 and D2, then standard sample set divided are as follows:
If the coefficient value of crop sample set D is greater than the coefficient value of subset D 1 and D2, decision tree continues to divide;If calculating
When crop Geordie index is calculated as 0 or when all samples in the crop subset of refinement are all classified as a kind of crop, then tree stops
It only divides, completes building process.
As shown in fig. 6, the S5 of the present embodiment the following steps are included:
S51: as unit of the moon, to research area carry out pattern of farming identification, generate the crops of complete time sequence when
Space division cloth thematic map;
S52: result verification is carried out according to verifying sample, obtains overall classification accuracy and Kappa coefficient.
The present embodiment implement when, method proposed by the present invention be based on different crops on image have it is different
The principle of textural characteristics and difference spectrally carries out analysis summary to the crop type of test block first, then is based on
Multiple features seek the principle of optimal solution, form the combination of new characteristic quantity, and then new images are formed in conjunction with vegetation index, use
Random forest classification method identifies to obtain main crops production information.The technical program has simple, effective, strong applicability
Feature can reasonably obtain large-scale crops space distribution information, improve conventional method and relatively rely on ground actual measurement number
According to the shortcomings that, improve the computational efficiency and precision of remote sensing monitoring main crops production, facilitate remote sensing technology monitoring farming
The businessization of object pattern of farming is promoted.
Claims (8)
1. a kind of main crops production moon scale Dynamic Extraction method, which comprises the following steps:
S1: determining analyzed area spatial dimension and carries out data preparation, collects the time series satellite remote sensing for being not more than moon scale
Data set, using moon scale data as time data, while sample data in pre-acquiring survey region;
S2: according to pretreated moon scale satellite remote-sensing image data, textural characteristics and normalized differential vegetation index are calculated;
S3: choosing abundant information degree, and high textural characteristics combine to form new image with vegetation index;
S4: the new image data formed in conjunction with combination, using random forest grader to the main crops production of survey region
It extracts, realizes the Dynamic Recognition of moon scale main crops production;
S5: as unit of the moon, to the Dynamic Recognition of main crops production, the when space division of the crops of complete time sequence is generated
Cloth thematic map simultaneously verifies precision.
2. main crops production moon scale Dynamic Extraction method according to claim 1, which is characterized in that the S1 packet
Include following steps:
S11: according to the location and range in research area, select China's independent research has high time resolution and high-space resolution
The GF-1WFV data of rate, the case where cannot being completely covered if there is data source, consider use sention-2, high score two,
Landsat8 or HJ-1A/B are replaced, at the same investigate scope of embodiments crop type and respective growth stage;
S12: carrying out the processing of remote sensing image to the data of collection, if there is alternate data, needs resampling uniform spaces point
Resolution;
S13: needing to consider its representativeness, typicalness, timeliness to the acquisition of sample, will study zoning by establishing regular grid
It is divided into the identical region of n block area, crop sample is chosen in each region.
3. main crops production moon scale Dynamic Extraction method according to claim 1, which is characterized in that the S2 packet
Include following steps:
S21: texture feature information amount is calculated based on gray level co-occurrence matrixes, is counted according to gray level co-occurrence matrixes GLCM in certain distance
Two pixels between gray scale related coefficient, indicate the probability distribution that repeats of gray scale, expression formula are as follows:
P (i, j)=[p (i, j, d, θ)]
Wherein, P (i, j) is the frequency of same pixel pair occur in the case where distance and direction determine;D is Range Profile vegetarian refreshments
The angle of distance, two pixel line vectors is θ, and usual θ takes 0 °, 45 °, 90 ° and 135 °;
S22: calculating the normalized differential vegetation index of image data, its calculation formula is:
NDVI=(ρNIR-ρR)/(ρNIR+ρR)
In formula, ρNIRFor the reflectivity of near infrared band;ρRFor the reflectivity of red spectral band.
4. main crops production moon scale Dynamic Extraction method according to claim 3, which is characterized in that the S21
GLCM calculate texture feature vector include following parameter:
Average value: average value reflects average gray in window, reflects the regular degree of texture, its calculation formula is:
Variance: indicating the period of texture, reflects the nonuniformity characteristic of texture, the size of grey scale change, its calculation formula is:
Contrast: it indicates gray difference in neighborhood, reflects the clarity of image and the degree of the texture rill depth, calculation formula
Are as follows:
Non- similarity: for the difference degree of detection image, when the high changes in contrast of regional area is big, then non-similarity is big, reflection
The clarity of image and the degree of the texture rill depth, its calculation formula is:
Comentropy: entropy measures the randomness of image texture, and information content possessed by image, is image greyscale rank confusion degree
Characterization, entropy is bigger, and the classification uncertainty of sample is bigger, its calculation formula is:
Angular second moment: reflecting image greyscale and be evenly distributed degree and texture fineness degree, its calculation formula is:
Correlation: correlated response spatial gray level co-occurrence matrix element be expert at or column direction on similarity degree, calculation formula
Are as follows:
5. main crops production moon scale Dynamic Extraction method according to claim 1, which is characterized in that the S3 packet
Include following steps:
S31: being sought the process of optimal solution based on Bhattacharyya distance building multiple target, chosen to texture characteristic amount,
Its calculation formula is:
In formula, μ be on texture template image 2 different classes of mean values, σ be on texture template image 2 it is different classes of
Standard deviation;
S32: according to the size for calculating BD value, preceding 8 texture characteristic amounts are exported;
S33: being combined preceding 8 texture characteristic amounts with the result of normalized differential vegetation index using the principle that wave band synthesizes, and is formed new
Image.
6. main crops production moon scale Dynamic Extraction method according to claim 1, which is characterized in that the S4 packet
Include following steps:
S41: it is extracted according to main crops production of the random forest principle to survey region;
S42: all kinds of parameters needed for setting classifier, input classification samples identify the main crops production of survey region
Dynamic Recognition is completed in classification.
7. main crops production moon scale Dynamic Extraction method according to claim 6, which is characterized in that the S41
Forest principle are as follows:
Basic unit is CART decision tree, is substantially the improvement to single decision tree, to improve nicety of grading, core is
Differentiation to tree node, specific algorithmic formula are as follows:
In formula, Gini (D) is the gini index calculated result of crops training sample;I indicates the class number of crops, respectively
Refer to winter wheat, summer corn, economic gardens classification;Pi is the probability that each Crop Group occurs in choosing sample set D;
It is divided into the Gini coefficient of two subsets for the training sample D that calculating is each drawn, sample set D is divided to for two subsets
D1 and D2, then standard sample set divided are as follows:
If the coefficient value of crop sample set D is greater than the coefficient value of subset D 1 and D2, decision tree continues to divide;If the crop calculated
When all samples are all classified as a kind of crop when Geordie index is calculated as 0 or in the crop subset of refinement, then stopping point being set
It splits, completes building process.
8. main crops production moon scale Dynamic Extraction method according to claim 1, which is characterized in that the S5 packet
Include following steps:
S51: as unit of the moon, pattern of farming identification is carried out to research area, generates the when space division of the crops of complete time sequence
Cloth thematic map;
S52: result verification is carried out according to verifying sample, obtains overall classification accuracy and Kappa coefficient.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910613999.XA CN110321861A (en) | 2019-07-09 | 2019-07-09 | A kind of main crops production moon scale Dynamic Extraction method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910613999.XA CN110321861A (en) | 2019-07-09 | 2019-07-09 | A kind of main crops production moon scale Dynamic Extraction method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110321861A true CN110321861A (en) | 2019-10-11 |
Family
ID=68121638
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910613999.XA Pending CN110321861A (en) | 2019-07-09 | 2019-07-09 | A kind of main crops production moon scale Dynamic Extraction method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110321861A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110909652A (en) * | 2019-11-16 | 2020-03-24 | 中国水利水电科学研究院 | Method for dynamically extracting monthly scale of crop planting structure with optimized textural features |
CN111144335A (en) * | 2019-12-30 | 2020-05-12 | 自然资源部国土卫星遥感应用中心 | Method and device for building deep learning model |
CN111310639A (en) * | 2020-02-11 | 2020-06-19 | 中国气象科学研究院 | Evergreen artificial forest remote sensing identification method and evergreen artificial forest growth remote sensing monitoring method |
CN111798132A (en) * | 2020-07-06 | 2020-10-20 | 北京师范大学 | Dynamic farmland monitoring method and system based on multi-source time sequence remote sensing depth coordination |
CN111950530A (en) * | 2020-09-08 | 2020-11-17 | 中国水利水电科学研究院 | Multi-feature optimization and fusion method for extracting crop planting structure |
CN112949607A (en) * | 2021-04-15 | 2021-06-11 | 辽宁工程技术大学 | Wetland vegetation feature optimization and fusion method based on JM Relief F |
CN113537705A (en) * | 2021-06-07 | 2021-10-22 | 中山大学 | Method for measuring vegetation health polarization degree |
CN113673628A (en) * | 2021-09-07 | 2021-11-19 | 中国气象科学研究院 | Corn planting distribution extraction method based on high-resolution satellite data |
CN114494882A (en) * | 2022-02-07 | 2022-05-13 | 中国科学院空天信息创新研究院 | Winter wheat remote sensing identification analysis method and system based on random forest |
CN114782324B (en) * | 2022-03-31 | 2024-05-17 | 中国科学院东北地理与农业生态研究所 | Farmland crop line direction remote sensing identification method based on land block morphological characteristics |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN108596029A (en) * | 2018-03-20 | 2018-09-28 | 尚正(北京)信息技术有限公司 | Crop classification method, apparatus, computer equipment and storage medium |
-
2019
- 2019-07-09 CN CN201910613999.XA patent/CN110321861A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN108596029A (en) * | 2018-03-20 | 2018-09-28 | 尚正(北京)信息技术有限公司 | Crop classification method, apparatus, computer equipment and storage medium |
Non-Patent Citations (3)
Title |
---|
宋茜: "基于GF-1/WFV和面向对象的农作物种植结构提取方法研究", 《中国博士学位论文全文数据库农业科技辑》 * |
徐佳 等: "综合灰度与纹理特征的高分辨率星载SAR图像建筑区提取方法研究", 《遥感技术与应用》 * |
黄健熙 等: "基于GF-1 WFV影像的作物面积提取方法研究", 《农业机械学报》 * |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110909652B (en) * | 2019-11-16 | 2022-10-21 | 中国水利水电科学研究院 | Method for dynamically extracting monthly scale of crop planting structure with optimized textural features |
CN110909652A (en) * | 2019-11-16 | 2020-03-24 | 中国水利水电科学研究院 | Method for dynamically extracting monthly scale of crop planting structure with optimized textural features |
CN111144335A (en) * | 2019-12-30 | 2020-05-12 | 自然资源部国土卫星遥感应用中心 | Method and device for building deep learning model |
CN111310639A (en) * | 2020-02-11 | 2020-06-19 | 中国气象科学研究院 | Evergreen artificial forest remote sensing identification method and evergreen artificial forest growth remote sensing monitoring method |
CN111310639B (en) * | 2020-02-11 | 2020-10-23 | 中国气象科学研究院 | Evergreen artificial forest remote sensing identification method and evergreen artificial forest growth remote sensing monitoring method |
CN111798132A (en) * | 2020-07-06 | 2020-10-20 | 北京师范大学 | Dynamic farmland monitoring method and system based on multi-source time sequence remote sensing depth coordination |
CN111798132B (en) * | 2020-07-06 | 2023-05-02 | 北京师范大学 | Cultivated land dynamic monitoring method and system based on multi-source time sequence remote sensing depth cooperation |
CN111950530A (en) * | 2020-09-08 | 2020-11-17 | 中国水利水电科学研究院 | Multi-feature optimization and fusion method for extracting crop planting structure |
CN111950530B (en) * | 2020-09-08 | 2024-04-12 | 中国水利水电科学研究院 | Multi-feature optimization and fusion method for crop planting structure extraction |
CN112949607A (en) * | 2021-04-15 | 2021-06-11 | 辽宁工程技术大学 | Wetland vegetation feature optimization and fusion method based on JM Relief F |
CN113537705A (en) * | 2021-06-07 | 2021-10-22 | 中山大学 | Method for measuring vegetation health polarization degree |
CN113673628A (en) * | 2021-09-07 | 2021-11-19 | 中国气象科学研究院 | Corn planting distribution extraction method based on high-resolution satellite data |
CN114494882A (en) * | 2022-02-07 | 2022-05-13 | 中国科学院空天信息创新研究院 | Winter wheat remote sensing identification analysis method and system based on random forest |
CN114782324B (en) * | 2022-03-31 | 2024-05-17 | 中国科学院东北地理与农业生态研究所 | Farmland crop line direction remote sensing identification method based on land block morphological characteristics |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110321861A (en) | A kind of main crops production moon scale Dynamic Extraction method | |
Tian et al. | Calibrating vegetation phenology from Sentinel-2 using eddy covariance, PhenoCam, and PEP725 networks across Europe | |
Tao et al. | Mapping winter wheat using phenological feature of peak before winter on the North China Plain based on time-series MODIS data | |
CN111368736B (en) | Rice refined estimation method based on SAR and optical remote sensing data | |
CN109726698B (en) | Method for identifying seasonal irrigation area based on remote sensing data | |
Zhang et al. | Estimating wheat yield by integrating the WheatGrow and PROSAIL models | |
CN110363246A (en) | A kind of fusion method of high-spatial and temporal resolution vegetation index NDVI | |
Yao et al. | Spatiotemporal changes of eco-environmental quality based on remote sensing-based ecological index in the Hotan Oasis, Xinjiang | |
CN114821362A (en) | Multi-source data-based rice planting area extraction method | |
CN114926748A (en) | Soybean remote sensing identification method combining Sentinel-1/2 microwave and optical multispectral images | |
CN110189043B (en) | Usable land resource analysis system based on high-score satellite remote sensing data | |
CN111222539B (en) | Method for optimizing and expanding supervision classification samples based on multi-source multi-temporal remote sensing image | |
CN112836725A (en) | Weak supervision LSTM recurrent neural network rice field identification method based on time sequence remote sensing data | |
CN102156886A (en) | Statistical data and remote sensing image data based regional fertilizer application spatialization method | |
Wang et al. | Research on cropping intensity mapping of the Huai River Basin (China) based on multi-source remote sensing data fusion | |
Zhu et al. | Identification of soybean based on Sentinel-1/2 SAR and MSI imagery under a complex planting structure | |
Wei et al. | Dynamic simulation of leaf area index for the soybean canopy based on 3D reconstruction | |
CN114821360A (en) | Method and device for intelligently extracting crop leaf area index and electronic equipment | |
Kang et al. | Construction of multidimensional features to identify tea plantations using multisource remote sensing data: A case study of Hangzhou city, China | |
Cheng et al. | Evaluation of UAV-based drought indices for crop water conditions monitoring: A case study of summer maize | |
CN110610438A (en) | Crop canopy petiole included angle calculation method and system | |
CN114119575A (en) | Spatial information change detection method and system | |
TAO et al. | Fusing multi-source data to map spatio-temporal dynamics of winter rape on the Jianghan Plain and Dongting Lake Plain, China | |
Shen et al. | A Gaussian Kernel-based spatiotemporal fusion model for agricultural remote sensing monitoring | |
Li et al. | Performance of GEDI data combined with Sentinel-2 images for automatic labelling of wall-to-wall corn mapping |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191011 |