CN112766036A - Remote sensing extraction method and device for lodging corn - Google Patents
Remote sensing extraction method and device for lodging corn Download PDFInfo
- Publication number
- CN112766036A CN112766036A CN202011441317.0A CN202011441317A CN112766036A CN 112766036 A CN112766036 A CN 112766036A CN 202011441317 A CN202011441317 A CN 202011441317A CN 112766036 A CN112766036 A CN 112766036A
- Authority
- CN
- China
- Prior art keywords
- lodging
- corn
- condition
- ndvi
- green
- 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
- 240000008042 Zea mays Species 0.000 title claims abstract description 78
- 235000002017 Zea mays subsp mays Nutrition 0.000 title claims abstract description 78
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 title claims abstract description 74
- 235000005822 corn Nutrition 0.000 title claims abstract description 74
- 238000000605 extraction Methods 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 claims abstract description 27
- 235000007164 Oryza sativa Nutrition 0.000 claims abstract description 16
- 235000009566 rice Nutrition 0.000 claims abstract description 16
- 208000003643 Callosities Diseases 0.000 claims abstract description 14
- 206010020649 Hyperkeratosis Diseases 0.000 claims abstract description 14
- 238000003066 decision tree Methods 0.000 claims abstract description 6
- 238000002310 reflectometry Methods 0.000 claims description 23
- 239000011159 matrix material Substances 0.000 claims description 18
- 238000009826 distribution Methods 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 16
- 241000209094 Oryza Species 0.000 claims description 15
- 238000011160 research Methods 0.000 claims description 13
- 238000012795 verification Methods 0.000 claims description 11
- 238000012805 post-processing Methods 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 7
- 230000003595 spectral effect Effects 0.000 claims description 6
- 241001270131 Agaricus moelleri Species 0.000 claims description 4
- 235000016383 Zea mays subsp huehuetenangensis Nutrition 0.000 claims description 4
- 235000009973 maize Nutrition 0.000 claims description 4
- 238000007619 statistical method Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 2
- 238000001228 spectrum Methods 0.000 abstract description 3
- 240000007594 Oryza sativa Species 0.000 abstract 1
- 238000012544 monitoring process Methods 0.000 description 6
- 238000007781 pre-processing Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 238000012952 Resampling Methods 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
- G06T7/45—Analysis of texture based on statistical description of texture using co-occurrence matrix computation
-
- 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
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10036—Multispectral image; Hyperspectral image
-
- 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
- G06V10/58—Extraction of image or video features relating to hyperspectral data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/68—Food, e.g. fruit or vegetables
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a remote sensing extraction method and device for lodging corn. The invention creatively provides that lodging corns and non-lodging corns can be distinguished by adopting a green band texture Mean value (B2_ Mean), and DVI is constructedG‑BThe method has the advantages that the lodging corn and the rice are distinguished, the lodging corn extraction decision tree model combining the spectrum and the texture is created, the corn planting area range does not need to be obtained in advance, the lodging corn can be extracted from the preprocessed image by directly using the model, the used data does not need complex multispectral wave bands, the lodging corn can be extracted only by containing image data of blue, green, red and near-infrared wave bands, and the corn lodging condition can be rapidly and accurately monitored.
Description
Technical Field
The application belongs to the technical field of agricultural disasters and remote sensing monitoring application, particularly relates to a lodging corn remote sensing extraction method and device, and particularly relates to a northeast region oriented lodging corn remote sensing extraction method and device.
Background
In summer, the heavy wind, the heavy rain and other disastrous weather are frequent, and the corn is easy to fall down due to the high stems and stems of the corn during the growth period, particularly in the large-scale corn planting area in the northeast. The lodging area is an important index for evaluating the lodging disaster degree of the crops. The method has important significance for the work of post-disaster agricultural production management, agricultural disaster insurance, agricultural subsidy and the like by investigating the lodging area of crops. After the corn is lodging, the canopy structure of the corn is changed, so that the radiation transmission characteristic and the spectral characteristic of the canopy are changed, and the possibility is provided for the remote sensing monitoring of the lodging of the corn in a large area.
In recent years, with the development of remote sensing technology, remote sensing monitoring research on crop lodging has attracted attention of scholars. Remote sensing can quickly acquire information such as spectrum, texture and the like of a target ground object in a remote detection mode, and the method is a quick and effective technical method for investigating the lodging condition of crops. The current remote sensing monitoring research on corn lodging mainly focuses on the research on spectral characteristic change of the lodging corn and the extraction of the lodging corn by using a common supervision and unsupervised classification method. The texture is used as a large characteristic of the remote sensing image and plays an important role in crop classification. In the aspect of lodging monitoring, the combination of spectral and textural features becomes the development direction of remote sensing application. In order to quickly and accurately obtain the distribution and the area of large-scale lodging corns, the northeast plain area is used as a research area to explore the invention of the lodging corn remote sensing high-efficiency extraction method.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: provides a method based on remote sensing spectral indexes (NDVI, RVI and DVI) for rapidly and accurately acquiring the distribution and the area of large-scale lodging cornsG-BEtc.) and textural features.
The technical scheme adopted by the invention for solving the technical problems is as follows: the invention provides a remote sensing extraction method of lodging corn, which comprises the following steps:
(1) acquiring remote sensing multispectral images after lodging in a research area, wherein the images comprise red, green, blue and near-infrared wave bands, such as GF1 images and sentinel 2 images, and then preprocessing the images, wherein the image preprocessing mainly comprises the following steps: radiometric calibration, atmospheric correction, orthometric correction, image registration, cutting and the like;
(2) NDVI, RVI, DVI on the calculated imageG-BSVI vegetation index;
the NDVI is a normalized vegetation index which is the ratio of the difference of the reflectivity of the near infrared band and the reflectivity of the red light band to the sum of the reflectivity of the near infrared band and the red light band, and can be used for distinguishing vegetation from non-vegetation;
DVIG-Bthe vegetation index is defined by the invention, is the difference between the blue and green wave band reflectivities, can reflect the spectrum difference between the lodging corns and the paddy rice caused by typhoons in the wax ripeness stage, and can be used for removing the paddy rice in crops;
RVI is a ratio vegetation index, is the ratio of the reflectivity of a near infrared band and the reflectivity of a red light band, is used for removing other vegetation, and is vegetation except non-lodging corns and rice;
SVI is a shadow vegetation index, is the product of NDVI and near infrared reflectivity, and is used for eliminating influences caused by vegetation shadows, ridges and the like;
(3) calculating texture information of lodging and non-lodging corns, rice and other crops by adopting a gray level co-occurrence matrix (GLCM) based on a statistical analysis method;
the GLCM is a matrix that statistically describes a certain relationship between gray levels of two pixels in a local area or adjacent pixels in the whole area or within a certain distance, and describes the probability that a pair of pixels separated by d pixels in the direction θ have gray levels i and j, respectively, and the elements of the probability can be denoted as P (i, j | d, θ), and when θ and d are determined, the probability is denoted as Pi,jThe order is determined by the gray quantization level of the image. The invention selects the Mean value (Mean) index of the texture to represent the shadow through research and analysisThe textural features of the image. The calculation formula is as follows:
wherein f (i, j | d, θ) represents the probability that a pair of pixels separated by a distance of d pixels in the direction θ have gray scales i and j, respectively, where M ═ N is a gray scale, and M × N represents the scale of the gray scale co-occurrence matrix; θ is typically 0 °, 45 °, 90 °, or 135 °;
(4) constructing a decision tree model and extracting lodging condition information of the corn;
(5) post-processing the result extracted by the model;
(6) and (5) performing precision verification and model parameter adjustment.
Further, in the above method, the image used for extracting the result in step (1) is GF1 WFV image, and the image used for precision verification in step (6) is GF-2 image with a resolution of 0.8 m.
Further preferably, the NDVI, RVI, DVI of step (2)G-BAnd the calculation formula of the SVI vegetation index is as follows:
DVIG-B=ρGreen-ρBlue,
where ρ isNir,ρRed,ρGreen,pBlueRespectively, the spectral reflectivities of the near infrared, red, green and blue bands.
Further preferably, the texture information of the image in step (3) is represented by a texture Mean (Mean) based on a gray-scale co-occurrence matrix, and the calculation formula is as follows:
wherein f (i, j | d, θ) represents the probability that a pair of pixels separated by a distance of d pixels in the direction θ have gray scales i and j, respectively, where M ═ N is a gray scale, and M × N represents the scale of the gray scale co-occurrence matrix; theta is typically 0 deg., 45 deg., 90 deg., or 135 deg..
Further, the step (4) of constructing a decision tree model and extracting the corn lodging condition information comprises the following steps:
s1: removing part of vegetation except water, buildings and corns by using NDVI;
s2: the method is characterized in that lodging corn, paddy rice and non-lodging corn and other vegetation are distinguished by using B2_ Mean, wherein B2_ Mean is Mean value of green band texture.
In the above method, it is further preferable that the constructing of the decision tree model in step (4) and the extracting of the lodging corn distribution information include the following steps,
s1: setting condition T0<NDVI<T1When the condition is false, the pixel is marked as other ground objects, and when the condition is true, the judgment is carried out in S2, wherein NDVI is obtained by calculating the reflectivity of the image according to the red light and the near infrared band, and the threshold value T is used for judging whether the image is a real image or not0And T1Respectively determining according to the distribution and the statistical calculation of the sample data;
s2: set condition B2_ Mean>T2If the condition is false, the step goes to S3 for judgment; if the condition is true, the step of judging in S4 is carried out; b2_ Mean is the key to distinguish between lodging and non-lodging maize, threshold T2The texture data distribution is obtained by statistics of sample texture data;
s3: after S2 is judged to be false, other vegetation, vegetation shadows and the like are removed by using NDVI, RVI and SVI, and the specific steps include setting conditions NDVI>T3,RVI<T4,SVI>T5If the condition is true, the pixel element is the non-lodging corn; wherein the threshold value T3、T4、T5Respectively obtained by sample data distribution and statistics;
s4: after the judgment of S2 is true, DVI is usedG-BEliminating rice, including setting condition DVIG-B<T6When the condition is false, the pixel is marked as rice, and when the condition is true, the pixel is marked as lodging corn; wherein the threshold value T6And determining according to sample data distribution and statistics.
Further, the step (5) performs post-processing on the result extracted through the model, mainly combines speckle noise and non-target ground objects (other ground objects, rice and other vegetation) in the result, and the post-processing mainly comprises filtering, filtering (Sieve) and clustering (column) processing to remove small patches and combine the small patches and the type, so as to obtain grid result data with a regular shape.
Further, the precision verification and model parameter adjustment in the step (6) includes randomly generating sample points in a research area, setting the number of the sample points according to the area range and the size, visually interpreting and determining the sample category attribute according to the high-score and medium-resolution images to serve as a verification sample, comparing the remote sensing extraction result with the verification sample, calculating a confusion matrix, obtaining the classification precision, meeting the requirement if the overall classification precision reaches 90% or more, entering the step (4) to readjust the model parameter threshold if the overall classification precision is lower than 90%, and repeating the steps (4) and (5) until the requirement is met.
The invention has the beneficial effects that:
the invention grasps the occurrence range and severity of corn lodging, is the key of disaster diagnosis, timely prevention and control and loss assessment, creatively provides that lodging corn and non-lodging corn can be distinguished by adopting a green band texture Mean value (B2_ Mean), and DVI is constructedG-BThe method does not need to acquire the corn planting area range in advance, can directly use the model to extract the lodging corn from the preprocessed image, uses the data without complex multispectral wave bands, can extract the lodging corn only by the image data containing blue, green, red and near infrared four wave bands, and realizes the quick, accurate and near-infrared extraction of the lodging cornAnd monitoring the distribution condition of the lodging corns.
Drawings
The technical solution of the present application is further explained below with reference to the drawings and the embodiments.
FIG. 1 is a flow chart of remote sensing extraction technology of lodging corn provided by the invention;
FIG. 2 is a GF1 image after lodging of maize in the northeast plain region;
FIG. 3 is a green band texture mean image;
FIG. 4 is a flow chart of a lodging corn and non-lodging corn extraction model;
FIG. 5 is a graph of lodging versus non-lodging corn extraction results;
FIG. 6 is a graph of the results of lodging maize extractions;
fig. 7A and 7B are image comparison graphs of local region lodging corn extraction results, wherein fig. 7A is a GF 19 image of day 6, and fig. 7B is an lodging corn extraction graph.
Detailed Description
In order to better embody the advantages of the present invention and the specific procedures, the present invention is further described below with reference to examples, and it should be noted that the embodiments and features in the embodiments may be combined with each other in the present application without conflict.
Examples
The technical flow chart of the invention is shown in fig. 1, and a part of the area of Ningjiang district of Songyuan city of Jilin province is selected as a research area, GF1 WFV image data is used as a data source, and the image time is 9 months and 6 days in 2020.
The method comprises the following steps: data acquisition and data pre-processing
Downloading GF1 WFV data, wherein the resolution ratio is 16 m, carrying out radiometric calibration, atmospheric correction, orthometric correction and registration on the image data, using the downloaded lodging sentinel 2 data for registration, converting the DN value of the image into reflectivity data after atmospheric correction, and resampling the image to 10 m after preprocessing. The image is cropped according to the study area range, and the cropped study area is shown in fig. 2.
Step two: calculating vegetation index
Blue, green, using GF1 imaging,NDVI, RVI and DVI calculation in red and near infrared bandsG-BAnd SVI vegetation index, the calculation formula is as follows:
DVIG-B=ρGreen-ρBlue
where ρ isRed、ρNir、ρBlue、ρNirRespectively red, green, blue, near infrared band reflectivities, DVIG-BThe index is self-defined and is the difference of the reflectivity of green light and blue light wave bands, and lodging corn and rice can be distinguished.
Step three: calculating texture mean
And calculating mean texture based on the gray level co-occurrence matrix, setting the size of a moving window to be 3 multiplied by 3, setting the transformation quantity of the matrix in the X and Y directions to be 1, and setting the gray level to be 64. Selecting a green light wave band texture Mean value for subsequent model construction according to research analysis, wherein a calculation formula of the texture Mean value (Mean) based on a gray level co-occurrence matrix is as follows:
the resulting green band texture mean image is shown in FIG. 3.
Step four: constructing a lodging corn extraction model
S1: the value setting condition is 0.72> NDVI > 0.47. When the condition is false, the picture element is marked as another feature, and when the condition is true, the process proceeds to step S2.
S2: the set condition is B2_ Mean > 8.5. When the condition is false, the process proceeds to S3, and when the condition is true, the process proceeds to S4.
S3: the conditions are set to NDVI >0.55, RVI <5.4 and SVI > 0.12. When the condition is false, the pixel is marked as other vegetation, and when the condition is true, the pixel is marked as non-lodging corn;
s4: set the condition as DG-B<0.024. When the condition is false, the pixel is marked as rice, and when the condition is true, the pixel is marked as lodging corn.
The specific extraction process is shown in fig. 4, the extraction results of lodging corn and non-lodging corn are shown in fig. 5, and the extraction results of lodging corn are shown in fig. 6.
Step five: result post-processing, precision verification
The initial extraction result often has speckle noise, and the result has more categories in order to eliminate other ground objects, so after the extraction by using the model, the result needs to be subjected to small speckle elimination and category combination, and the result is subjected to post-processing by using operations such as filtering, small speckle elimination, clustering and the like. And the precision verification uses a randomly generated sample, visual interpretation is carried out by combining the high-resolution image and the medium-resolution image to obtain sample attribute information, and then the sample attribute information is compared with an extraction result to calculate a confusion matrix and a Kappa coefficient so as to obtain the extraction precision.
And continuously adjusting parameters to obtain final model parameters, extracting lodging corns, non-lodging corns and other ground objects by using the model, and verifying the precision of the result after post-processing, wherein the overall precision of the result is 90.33 percent, the Kappa coefficient is 0.8495, the overall precision is higher, and fig. 7 shows that the extraction result of the lodging corns in the local area is compared with an image.
In light of the foregoing description of the preferred embodiments according to the present application, many modifications and variations can be made by the worker skilled in the art without departing from the scope of the present application. The technical scope of the present application is not limited to the contents of the specification, and must be determined according to the scope of the claims.
Claims (10)
1. The remote sensing extraction method of the lodging corn is characterized by comprising the following steps:
(1) acquiring a remote sensing multispectral image after lodging in a research area, extracting an image containing red, green, blue and near-infrared wave bands, and then carrying out radiometric calibration, atmospheric correction, orthorectification and geometric registration on the image;
(2) NDVI, RVI, DVI on the calculated imageG-BSVI vegetation index;
wherein NDVI is a normalized vegetation index, which is the ratio of the difference between the near infrared and red band reflectivities and the sum of the near infrared and red band reflectivities;
DVIG-Bthe difference between the green and blue band reflectivities;
RVI is a ratio vegetation index, which is the ratio of the reflectivity of the near infrared band to the red light band;
SVI is the shadow vegetation index, which is the product of NDVI and the reflectivity of the near infrared band;
(3) calculating texture information of lodging and non-lodging corns, rice and other crops by adopting a gray level co-occurrence matrix (GLCM) based on a statistical analysis method;
(4) constructing a lodging corn extraction model, and extracting lodging distribution information of corn;
(5) post-processing the result extracted by the model;
(6) and (5) performing precision verification and model parameter adjustment.
2. The method of claim 1, wherein the image used for extracting the result in step (1) is GF1 WFV image, and the image used for precision verification in step (6) is GF-2 image with a resolution of 0.8 m.
4. The method according to claim 1, wherein the texture information of the image in step (3) is expressed by a Mean value (Mean) of the texture based on the gray level co-occurrence matrix, and the formula is:
where f (i, j | d, θ) represents the probability that a pair of pixels spaced apart by a distance of d pixels in the direction θ have the gray scales i and j, respectively, where M ═ N is the gray scale level, and M × N represents the scale of the gray scale co-occurrence matrix.
5. The method of claim 1, wherein the step (4) of constructing the decision tree model and extracting the lodging corn and other crops comprises the following steps:
s1: removing vegetation except water, buildings and part of corns by using NDVI;
s2: and distinguishing lodging corn, rice, non-lodging corn and other vegetation by using B2_ Mean, wherein B2_ Mean is a Mean value of green band textures.
6. The method of claim 5, wherein the step (4) of constructing the decision tree model and extracting the corn lodging distribution information comprises the following steps:
s1: setting condition T0<NDVI<T1When the condition is false, the pixel is marked as other ground objects, and when the condition is true, the judgment of S2 is carried out;
s2: set condition B2_ Mean>T2If the condition is false, the step goes to S3 for judgment; if the condition is true, the step goes to S4 for judgment;
s3: setting conditions NDVI>T3,RVI<T4,SVI>T5If the conditions are true, the picture element is the non-lodging corn;
s4: set condition DVIG-B<T6When the condition is false, the pixel is marked as rice, and when the condition is true, the pixel is marked as lodging corn;
wherein, T0、T1、T6All the values are threshold values, and are determined according to the distribution and the statistical calculation of sample data respectively;
T2is a threshold value obtained by the distribution statistics of sample texture data;
T3、T4、T5are threshold values, which are obtained by sample data distribution and statistics, respectively.
7. The method according to claim 1, wherein the step (5) performs post-processing on the result extracted by the model, which is to merge speckle noise and non-target ground objects in the result, and the post-processing includes filtering, filtering (Sieve) and clustering (column) to remove small patches and merge categories, so as to obtain grid result data with a more regular shape.
8. The method according to claim 1, wherein the precision verification and model parameter adjustment in step (6) comprises randomly generating sample points in a research area, comparing the remote sensing extraction results with the sample points, calculating a confusion matrix, and obtaining classification precision, wherein the requirement is met if the overall classification precision reaches 90% or more; if the value is lower than 90%, the model parameter threshold value is readjusted until the requirement is met.
9. The utility model provides a lodging maize remote sensing extraction element which characterized in that includes:
the image acquisition and processing module: the system is used for acquiring remote sensing multispectral images after lodging in a research area, extracting images containing red, green, blue and near-infrared wave bands, and performing radiometric calibration, atmospheric correction, orthorectification and geometric registration on the images;
wherein NDVI is a normalized vegetation index, which is the ratio of the difference between the near infrared and red band reflectivities and the sum of the near infrared and red band reflectivities;
DVIG-Bthe difference between the green and blue band reflectivities;
RVI is a ratio vegetation index, which is the ratio of the reflectivity of the near infrared band to the red light band;
SVI is the shadow vegetation index, which is the product of NDVI and the reflectivity of the near infrared band;
vegetation index calculation module: NDVI, RVI, DVI for calculating imagesG-BSVI vegetation index;
the texture information calculation module: the method is used for calculating texture information of lodging and non-lodging corns, paddy rice and other crops based on a gray level co-occurrence matrix (GLCM) of a statistical analysis method;
the model building module is used for extracting corn lodging distribution information and comprises:
s1: setting condition T0<NDVI<T1When the condition is false, the pixel is marked as other ground objects, and when the condition is true, the judgment of S2 is carried out;
s2: set condition B2_ Mean>T2If the condition is false, the step goes to S3 for judgment; if the condition is true, the step goes to S4 for judgment;
s3: setting conditions NDVI>T3,RVI<T4,SVI>T5If the conditions are true, the picture element is the non-lodging corn;
s4: set condition DVIG-B<T6When the condition is false, the pixel is marked as rice, and when the condition is true, the pixel is marked as lodging corn;
wherein, T0、T1、T6Are all threshold values, respectively according to the distribution of sample data andperforming statistical calculation and determination;
T2is a threshold value obtained by the distribution statistics of sample texture data;
T3、T4、T5all are threshold values, obtained by sample data distribution and statistical analysis, respectively.
A model extraction result post module: the system is used for filtering, filtering and clustering speckle noise and non-target ground objects in the model extraction result to remove small patches and combine the small patches and the types to obtain grid result data with a regular shape;
the precision verification and model parameter adjustment module comprises: the method is used for comparing the remote sensing extraction result with sample points randomly generated in a research area, calculating a confusion matrix, solving the classification precision, meeting the requirement if the overall classification precision reaches 90% or more, and readjusting the model parameter threshold value if the overall classification precision is lower than 90% until the requirement is met.
10. The apparatus of claim 9, wherein the vegetation index calculation module is NDVI, RVI, DVIG-BAnd the calculation formula of the SVI vegetation index is as follows:
DVIG-B=ρGreen-ρBlue,
where ρ isNir,ρRed,ρGreen,pBlueSpectral reflectances in the near-infrared, red, green, and blue bands, respectively;
the texture information of the image in the texture information calculation module is expressed by a texture Mean (Mean) based on a gray level co-occurrence matrix, and the calculation formula is as follows:
where f (i, j | d, θ) represents the probability that a pair of pixels spaced apart by a distance of d pixels in the direction θ have the gray scales i and j, respectively, where M ═ N is the gray scale level, and M × N represents the scale of the gray scale co-occurrence matrix.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011441317.0A CN112766036A (en) | 2020-12-08 | 2020-12-08 | Remote sensing extraction method and device for lodging corn |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011441317.0A CN112766036A (en) | 2020-12-08 | 2020-12-08 | Remote sensing extraction method and device for lodging corn |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112766036A true CN112766036A (en) | 2021-05-07 |
Family
ID=75693614
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011441317.0A Pending CN112766036A (en) | 2020-12-08 | 2020-12-08 | Remote sensing extraction method and device for lodging corn |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112766036A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113538559A (en) * | 2021-07-02 | 2021-10-22 | 宁波大学 | Extraction method of offshore aquaculture raft extraction index based on hyperspectral remote sensing image |
CN114076955A (en) * | 2021-09-27 | 2022-02-22 | 农业农村部规划设计研究院 | Method for identifying lodging corn based on high-score first satellite data |
CN114519721A (en) * | 2022-02-16 | 2022-05-20 | 广东皓行科技有限公司 | Crop lodging identification method, device and equipment based on remote sensing image |
CN115775354A (en) * | 2023-02-10 | 2023-03-10 | 天地信息网络研究院(安徽)有限公司 | Grouting period rice outcrop extraction method based on fusion remote sensing index |
CN117233123A (en) * | 2023-09-13 | 2023-12-15 | 宁波大学 | Large-scale remote sensing monitoring method and device for bacterial leaf blight of rice based on sentinel No. 2 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109344892A (en) * | 2018-09-21 | 2019-02-15 | 北京航空航天大学 | A kind of lodging index extracting method based on Multi-source Information Fusion |
CN111091052A (en) * | 2019-11-07 | 2020-05-01 | 中国农业大学 | Corn lodging area extraction system and method based on maximum likelihood method |
US20200141877A1 (en) * | 2018-11-06 | 2020-05-07 | Nanjing Agricultural University | Method for estimating aboveground biomass of rice based on multi-spectral images of unmanned aerial vehicle |
CN111860150A (en) * | 2020-06-11 | 2020-10-30 | 中科禾信遥感科技(苏州)有限公司 | Lodging rice identification method and device based on remote sensing image |
-
2020
- 2020-12-08 CN CN202011441317.0A patent/CN112766036A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109344892A (en) * | 2018-09-21 | 2019-02-15 | 北京航空航天大学 | A kind of lodging index extracting method based on Multi-source Information Fusion |
US20200141877A1 (en) * | 2018-11-06 | 2020-05-07 | Nanjing Agricultural University | Method for estimating aboveground biomass of rice based on multi-spectral images of unmanned aerial vehicle |
CN111091052A (en) * | 2019-11-07 | 2020-05-01 | 中国农业大学 | Corn lodging area extraction system and method based on maximum likelihood method |
CN111860150A (en) * | 2020-06-11 | 2020-10-30 | 中科禾信遥感科技(苏州)有限公司 | Lodging rice identification method and device based on remote sensing image |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113538559A (en) * | 2021-07-02 | 2021-10-22 | 宁波大学 | Extraction method of offshore aquaculture raft extraction index based on hyperspectral remote sensing image |
CN114076955A (en) * | 2021-09-27 | 2022-02-22 | 农业农村部规划设计研究院 | Method for identifying lodging corn based on high-score first satellite data |
CN114519721A (en) * | 2022-02-16 | 2022-05-20 | 广东皓行科技有限公司 | Crop lodging identification method, device and equipment based on remote sensing image |
CN115775354A (en) * | 2023-02-10 | 2023-03-10 | 天地信息网络研究院(安徽)有限公司 | Grouting period rice outcrop extraction method based on fusion remote sensing index |
CN115775354B (en) * | 2023-02-10 | 2023-04-25 | 天地信息网络研究院(安徽)有限公司 | Grouting period rice harvest-stop extraction method based on fusion of remote sensing indexes |
CN117233123A (en) * | 2023-09-13 | 2023-12-15 | 宁波大学 | Large-scale remote sensing monitoring method and device for bacterial leaf blight of rice based on sentinel No. 2 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112766036A (en) | Remote sensing extraction method and device for lodging corn | |
CN110287944B (en) | Crop pest monitoring method based on multispectral remote sensing image of deep learning | |
Solano et al. | A methodology based on GEOBIA and WorldView-3 imagery to derive vegetation indices at tree crown detail in olive orchards | |
Meneguzzo et al. | Mapping trees outside forests using high-resolution aerial imagery: a comparison of pixel-and object-based classification approaches | |
CN107480706A (en) | A kind of seed production corn field remote sensing recognition method and device | |
Zhang et al. | Robust hyperspectral vision-based classification for multi-season weed mapping | |
CN113033670B (en) | Rice planting area extraction method based on Sentinel-2A/B data | |
CN108458978B (en) | Sensitive waveband and waveband combination optimal tree species multispectral remote sensing identification method | |
WO2001033505A2 (en) | Multi-variable model for identifying crop response zones in a field | |
CN110363246B (en) | Fusion method of vegetation index NDVI with high space-time resolution | |
CN108764284B (en) | Classification and denoising method and system for high-resolution image of dead pine | |
CN111091052A (en) | Corn lodging area extraction system and method based on maximum likelihood method | |
CN111860150B (en) | Lodging rice identification method and device based on remote sensing image | |
CN114049564B (en) | Pine wood nematode disease level prediction model construction method based on hyperspectral remote sensing image | |
Ippoliti‐Ramilo et al. | Landsat‐5 Thematic Mapper data for pre‐planting crop area evaluation in tropical countries | |
Wenting et al. | Detecting maize leaf water status by using digital RGB images | |
Ji et al. | In-field automatic detection of maize tassels using computer vision | |
CN115546636A (en) | Vegetation restoration monitoring method after geological disaster based on high-resolution remote sensing image | |
CN110189043B (en) | Usable land resource analysis system based on high-score satellite remote sensing data | |
CN114581768A (en) | Crop lodging unmanned aerial vehicle monitoring method and device | |
CN116543316B (en) | Method for identifying turf in paddy field by utilizing multi-time-phase high-resolution satellite image | |
CN116824384A (en) | Soybean identification method based on standard curve | |
Yang et al. | Cotton hail disaster classification based on drone multispectral images at the flowering and boll stage | |
CN111007013A (en) | Crop rotation fallow remote sensing monitoring method and device for northeast cold region | |
Mueller-Warrant et al. | Remote sensing classification of grass seed cropping practices in western Oregon |
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 |