CN116091938B - Multisource remote sensing monitoring method for single-cropping rice planting area - Google Patents
Multisource remote sensing monitoring method for single-cropping rice planting area Download PDFInfo
- Publication number
- CN116091938B CN116091938B CN202211704594.5A CN202211704594A CN116091938B CN 116091938 B CN116091938 B CN 116091938B CN 202211704594 A CN202211704594 A CN 202211704594A CN 116091938 B CN116091938 B CN 116091938B
- Authority
- CN
- China
- Prior art keywords
- rice
- index
- remote sensing
- period
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
- G06V10/765—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects using rules for classification or partitioning the feature space
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
Abstract
The application relates to a multisource remote sensing monitoring method for a single-cropping rice planting area, which comprises the following steps: screening the optical remote sensing earth surface reflectivity data and performing cloud removal treatment; preprocessing SAR remote sensing image data of a target year; obtaining rice weather data through field observation; obtaining four-scene multiband images of four weathers; obtaining total 4 standard spectrum curves of the rice in four-scene multiband images in four weathers; obtaining four-scene spectrum similarity images; and identifying the rice by adopting a decision tree classifier to obtain a rice identification result. The beneficial effects of the application are as follows: the application solves the problem that the SAR remote sensing image is distorted due to the influence of the terrain, and can obtain an accurate remote sensing monitoring result of the paddy rice planting area by utilizing a multi-source remote sensing image and spectrum similarity measurement method under the condition of complex terrain.
Description
Technical Field
The application relates to the field of remote sensing image processing, in particular to a multi-source remote sensing monitoring method aiming at a single-cropping rice planting area.
Background
In recent years, the application of remote sensing in agricultural monitoring has made great progress, and the remote sensing has now been developed into an effective and widely used crop monitoring tool. Remote sensing has the advantage of saving time and labor compared to traditional survey-based crop mapping methods. More importantly, it can provide real-time and large-scale simultaneous monitoring of periodic frequencies while maintaining satisfactory accuracy. Two major remote sensing data sources widely used in rice mapping are optical and Synthetic Aperture Radar (SAR) data. Optical telemetry data can be easily correlated with plant photosynthetic parameters such as leaf area index or total primary productivity so they can capture the growth status of crops well. The backscattering strength of the Synthetic Aperture Radar (SAR) is related to factors such as the roughness of the earth surface, complex dielectric constant and the like, and the growth state of rice can be well reflected.
However, the optical remote sensing imaging is easily affected by weather conditions, and in areas with continuous cloudiness, the observed quantity of the optical remote sensing data may be insufficient, such as rice planting areas in south China. Synthetic Aperture Radar (SAR) images have a lot of noise and are distorted by terrain. In addition, the hilly terrain of south China mountain land causes the disruption of paddy fields, and the paddy fields cannot be monitored well by using coarse or medium resolution data of satellite platforms such as MODIS and Landsat satellites. Complicated planting systems, changeable crop weather and highly heterogeneous surface landscapes all increase the difficulty of remote sensing monitoring of the rice planting area.
Disclosure of Invention
The application aims to overcome the defects in the prior art and provides a multi-source remote sensing monitoring method aiming at the single-cropping rice planting area.
In a first aspect, a multi-source remote sensing monitoring method for a single-cropping rice planting area is provided, comprising:
step 1, screening optical remote sensing earth surface reflectivity data with the target year and cloud pixel occupancy rate of less than 30% in the previous year and the next year, performing cloud removal processing, and then selecting spectral reflectivity data and calculating a spectral index;
step 2, preprocessing SAR remote sensing image data of a target year, and converting SAR remote sensing image pixel values into backward scattering intensity to obtain earth surface backward scattering intensity data of an annual time sequence;
step 3, obtaining rice physical condition data through field observation, wherein the rice physical condition data comprises time corresponding to a sowing period, a transplanting period, a growing period and a maturing period;
step 4, respectively carrying out mean value synthesis and wave band superposition on spectral reflectance data, spectral index data and back scattering intensity data in a sowing period, a transplanting period, a growing period and a maturing period, and then superposing terrain gradient data to obtain four-scene multiband images in four physical periods;
step 5, selecting sample points of rice and non-rice, and obtaining total 4 standard spectrum curves of the rice in four-scene multiband images in four weathers;
step 6, calculating the spectrum similarity of each pixel in the four-scene multiband image and the rice spectrum curve of the corresponding object weather period to obtain a four-scene spectrum similarity image;
step 7, based on the four-scene spectrum similarity images, rice and non-rice sample points, adopting a decision tree classifier to identify the rice, and obtaining a rice identification result;
and 8, converting the grid-format rice identification result into a vector diagram in the ArcGIS, and counting the rice planting area after adding the area field.
Preferably, in step 1, the cloud removing process includes the following steps:
step 1.1, calculating four initial cloud fraction images based on a blue wave band, a blue-green-red wave band, a near infrared wave band, a second short wave infrared wave band, a green wave band and a first short wave infrared wave band by using a normalization function;
normalization function:
cloudScore1＝normalize(blue，0.1，0.3)
cloudScore2＝normalize(blue+green+red，0.1，0.3)
cloudScore3＝normalize(nir+swir2，0.1，0.3)
cloudScore4＝normalize(green+swir1+swir2，0.1，0.3)
wherein blue represents a blue wave band, green represents a green wave band, red represents a red wave band, nir represents a near infrared wave band, swir1 represents a first short wave infrared wave band, and swir2 represents a second short wave infrared wave band; clodscore 1, clodscore 2, clodscore 3, clodscore 4 represent four initial cloud score images;
step 1.2, taking the minimum value from four initial cloud fraction images to generate a final cloud fraction image for each pixel, and masking off the area with the pixel value larger than 0.3 to obtain a cloud-free area range diagram;
and 1.3, masking the optical remote sensing surface reflectivity data by using the cloud-free regional scope graph to obtain the cloud-free optical remote sensing surface reflectivity data.
Wherein, the pixels with clouscore larger than 0.3 are cloud pixels.
Preferably, in step 1, the spectral reflectance data selected includes red, green, blue, red-edge 1-3, near infrared, short wave infrared 1-2 wave bands.
Preferably, in step 1, the calculated spectral indexes include a ground chlorophyll vegetation index (Ground Chlorophyll Vegetation Index, GCVI), a normalized vegetation index (Normalized Difference Vegetation Index, NDVI), an enhanced vegetation index (Enhanced Vegetation Index, EVI), a topography chlorophyll index (MERIS Terrain Chlorophyll Index, MTCI), a normalized differential red edge index (Normalized Difference Red Edge Index, NDREI), a red edge position (Red Edge Position, REP), a normalized water index (Normalized Difference Water Index, NDWI), a modified normalized differential water index (Modified Normalized Difference Water Index, MNDWI), a surface water index (Land Surface Water Index, LSWI), and a normalized soil index (Normalized Difference Soil Index, NDSI), and the calculated formulas are:
wherein re1 is a first red edge band, re2 is a second red edge band, re3 is a third red edge band, and mir is a mid-infrared band; GCVI is a ground chlorophyll vegetation index, NDVI is a normalized vegetation index, EVI is a normalized vegetation index, MTCI is a topography chlorophyll index, NDREI is a normalized differential red edge index, REP is a red edge position, NDWI is a normalized water index, MNDWI is an improved normalized differential water body index, LSWI is a surface water index, and NDSI is a normalized soil index.
Preferably, in step 2, the surface backscatter intensity data includes two polarized bands: vertical transmission vertical reception and vertical transmission horizontal reception.
Preferably, the mean value synthesis in the step 4 refers to a process of obtaining a new image by respectively averaging spectral reflectance data, spectral index data and back scattering intensity data in a sowing period, a transplanting period, a growing period and a maturing period.
Preferably, in step 4, the 1-9 bands of the image after the band superposition are the original spectral reflectance data, the 10-19 bands are the spectral indices, the 20-21 bands are the vertical-emission vertical-reception and vertical-emission horizontal-reception polarized images, and the 22 bands are the gradient images.
Preferably, in step 5, the non-rice plants include buildings, water bodies, grasslands and dry lands; the standard spectrum curve is the mean curve of the spectrum curve of the rice sample points.
Preferably, the calculating of the spectrum similarity image in the step 6 includes the steps of:
step 6.1, calculating Euclidean distance similarity Ed based on sowing-period multiband images and a rice standard spectrum curve:
Ed＝(Ed orig -min)/(max-min)
wherein p and t are respectively defined as a spectrum curve of an unknown class pixel and a standard spectrum curve of rice; n is the number of image bands, min and max are respectively defined as Ed orig Minimum and maximum values of the image;
step 6.2, calculating spectrum related similarity SCS based on the sowing-period multiband image and the rice standard spectrum curve:
wherein μ and σ are defined as the mean and standard deviation of the two spectral curves, respectively;
step 6.3, calculating the spectrum similarity SSV:
and 6.4, repeating the steps 6.1-6.3, and calculating the spectral similarity SSV of the transplanting period, the growing period and the maturing period based on the multiband images of the transplanting period, the growing period and the maturing period and the corresponding rice standard spectral curves.
In a second aspect, a computer storage medium having a computer program stored therein is provided; the computer program when run on a computer causes the computer to execute the multi-source remote sensing monitoring method for single-cropping rice planting area according to any one of the first aspect.
The beneficial effects of the application are as follows: according to the application, through cloud removal processing, the limitation of weather conditions on remote sensing monitoring is reduced, so that enough optical remote sensing data can be obtained; in addition, the problem that the SAR remote sensing image is distorted due to the influence of the terrain is solved, and an accurate rice planting area remote sensing monitoring result can be obtained by utilizing the multi-source remote sensing image and spectrum similarity measurement method under the condition of complex terrain.
Drawings
FIG. 1 is a technical flow diagram of a multi-source remote sensing monitoring method for a single-season rice planting area;
FIG. 2 is a spectrum similarity image of four weathers according to an embodiment of the present application;
FIG. 3 is a graph showing the separability of rice and non-rice on spectral similarity images according to an embodiment of the present application;
FIG. 4 is a graph showing the identification result of single cropping rice according to the embodiment of the present application.
Detailed Description
The application is further described below with reference to examples. The following examples are presented only to aid in the understanding of the application. It should be noted that it will be apparent to those skilled in the art that modifications can be made to the present application without departing from the principles of the application, and such modifications and adaptations are intended to be within the scope of the application as defined in the following claims.
Example 1:
the embodiment 1 of the application provides a multisource remote sensing monitoring method for a single-cropping rice planting area, which is shown in fig. 1 and comprises the following steps:
step 1, screening optical remote sensing earth surface reflectivity data with the target year and cloud pixel occupancy rate of less than 30% in the previous year and the next year, performing cloud removal processing, and then selecting spectral reflectivity data and calculating a spectral index;
step 2, preprocessing SAR remote sensing image data of a target year, and converting pixel values into backward scattering intensity to obtain earth surface backward scattering intensity data of an annual time sequence;
step 3, obtaining rice physical condition data through field observation, wherein the rice physical condition data comprises time corresponding to a sowing period, a transplanting period, a growing period and a maturing period;
step 4, respectively carrying out mean value synthesis and wave band superposition on spectral reflectance data, spectral index data and back scattering intensity data in a sowing period, a transplanting period, a growing period and a maturing period, and then superposing terrain gradient data to obtain four-scene multiband images in four physical periods;
step 5, selecting sample points of rice and non-rice, and obtaining total 4 standard spectrum curves of the rice in four-scene multiband images in four weathers;
step 6, calculating the spectrum similarity of each pixel in the four-scene multiband image and the rice spectrum curve of the corresponding object weather period to obtain a four-scene spectrum similarity image;
step 7, based on the four-scene spectrum similarity images, rice and non-rice sample points, adopting a decision tree classifier to identify the rice, and obtaining a rice identification result;
and 8, converting the grid-format rice identification result into a vector diagram in the ArcGIS, and counting the rice planting area after adding the area field.
Example 2:
based on the embodiment 1, the embodiment 2 of the application provides an application of the multisource remote sensing monitoring method for the single-cropping rice planting area in the embodiment 1 in reality: the Zhongjiang county and the Zhoujiang county are located in famous mountain city Chongqing cities and are typical single-season rice planting areas, the Zhongjiang county is mainly mountain areas, the topography is complex, the field blocks are broken, and the Zhoujiang county is mainly hilly and flat dam areas; applying a single-cropping rice planting area remote sensing monitoring method to Zhong county and Yangjiang county; single cropping area monitoring was performed using Sentinel-1/2 images. As shown in fig. 1, the method of the present embodiment includes the steps of:
and step 1, screening optical remote sensing earth surface reflectivity data with the target year and cloud pixel occupancy rate of less than 30% in the previous year and the next year, performing cloud removal processing, and then selecting spectral reflectivity data and calculating a spectral index.
The method for performing cloud removal processing on the optical remote sensing surface reflectivity data comprises the following steps of:
step 1.1, calculating four initial cloud fraction images based on a blue wave band, a blue-green-red wave band, a near infrared wave band, a second short wave infrared wave band, a green wave band and a first short wave infrared wave band by using a normalization function;
normalization function:
cloudScore1＝normalize(blue，0.1，0.3)
cloudScore2＝normalize(blue+green+red，0.1，0.3)
cloudScore3＝normalize(nir+swir2，0.1，0.3)
cloudScore4＝normalize(green+swir1+swir2，0.1，0.3)
wherein blue represents a blue wave band, green represents a green wave band, red represents a red wave band, nir represents a near infrared wave band, swir1 represents a first short wave infrared wave band, and swir2 represents a second short wave infrared wave band; clodscore 1, clodscore 2, clodscore 3, clodscore 4 represent four initial cloud score images;
step 1.2, taking the minimum value from four initial cloud fraction images to generate a final cloud fraction image for each pixel, and masking off the area with the pixel value larger than 0.3 to obtain a cloud-free area range diagram;
and 1.3, masking the optical remote sensing surface reflectivity data by using the cloud-free regional scope graph to obtain the cloud-free optical remote sensing surface reflectivity data.
The selected spectral reflectivity data comprise red, green, blue, red edge 1-3, near infrared and short wave infrared 1-2 wave bands;
the calculated spectrum indexes comprise a ground chlorophyll vegetation index, a normalized vegetation index, an enhanced vegetation index, a topography chlorophyll index, a normalized difference red edge index, a red edge position, a normalized water index, an improved normalized difference water body index, a surface water index and a normalized soil index, and the calculation formula is as follows:
wherein re1 is a first red edge band, re2 is a second red edge band, re3 is a third red edge band, and mir is a mid-infrared band; GCVI is a ground chlorophyll vegetation index, NDVI is a normalized vegetation index, EVI is a normalized vegetation index, MTCI is a topography chlorophyll index, NDREI is a normalized differential red edge index, REP is a red edge position, NDWI is a normalized water index, MNDWI is an improved normalized differential water body index, LSWI is a surface water index, and NDSI is a normalized soil index.
Step 2, preprocessing SAR remote sensing image data of a target year, and converting pixel values into backward scattering intensity to obtain earth surface backward scattering intensity data of an annual time sequence;
the surface backscatter intensity data includes two polarized bands, vertical transmission vertical reception (VV) and vertical transmission horizontal reception (VH).
Step 3, obtaining rice physical condition data through field observation, wherein the rice physical condition data comprises time corresponding to a sowing period, a transplanting period, a growing period and a maturing period;
step 4, respectively carrying out mean value synthesis and wave band superposition on spectral reflectance data, spectral index data and back scattering intensity data in a sowing period, a transplanting period, a growing period and a maturing period, and then superposing terrain gradient data, as shown in fig. 2, to obtain four-view multiband images in four weathers;
the mean value synthesis is a process of obtaining a new image by respectively averaging spectral reflectance data in a sowing period, a transplanting period, a growing period and a maturing period, and carrying out mean value synthesis on the spectral index data and the back scattering intensity data;
the 1-9 bands of the image after band superposition are the original spectral reflectance data, the 10-19 bands are the spectral indices, the 20-21 bands are the VV and VH polarized images, and the 22 bands are the slope images.
Step 5, selecting sample points of rice and non-rice, and obtaining total 4 standard spectrum curves of the rice in four-scene multiband images in four weathers;
the number of rice sample points is 75, and non-rice includes building, water body, forest grass land and dry land, and the number of sample points is 75.
Step 6, calculating the spectrum similarity of each pixel in the four-scene multiband image and the rice spectrum curve of the corresponding object weather period to obtain a four-scene spectrum similarity image;
calculating the spectrum similarity image comprises the following steps:
step 6.1, calculating Euclidean distance similarity Ed based on sowing-period multiband images and a rice standard spectrum curve:
Ed＝(Ed orig -min)/(max-min)
wherein p and t are defined as the spectral curve of the unknown class pixel and the standard spectral curve of rice, respectively. n is the number of image bands, min and max are respectively defined as Ed orig Minimum and maximum values of the image.
Step 6.2, calculating spectrum related similarity SCS based on the sowing-period multiband image and the rice standard spectrum curve:
where μ and σ are defined as the mean and standard deviation of the two spectral curves, respectively.
Step 6.3, calculating the spectrum similarity SSV:
and 6.4, repeating the steps 6.1-6.3, and calculating the spectral similarity SSV of the transplanting period, the growing period and the maturing period based on the multiband images of the transplanting period, the growing period and the maturing period and the corresponding rice standard spectral curves as shown in figure 3.
And 7, identifying the rice by adopting a decision tree classifier based on the four-scene spectrum similarity image, the rice and the non-rice sample points, and obtaining a rice identification result as shown in fig. 4.
And 8, converting the grid-format rice identification result into a vector diagram in the ArcGIS, and counting the rice planting area after adding the area field.
Claims (10)
1. A multisource remote sensing monitoring method for a single-cropping rice planting area is characterized by comprising the following steps of:
step 1, screening optical remote sensing earth surface reflectivity data with the target year and cloud pixel occupancy rate of less than 30% in the previous year and the next year, performing cloud removal processing, and then selecting spectral reflectivity data and calculating a spectral index;
step 2, preprocessing SAR remote sensing image data of a target year, and converting SAR remote sensing image pixel values into backward scattering intensity to obtain earth surface backward scattering intensity data of an annual time sequence;
step 3, obtaining rice physical condition data through field observation, wherein the rice physical condition data comprises time corresponding to a sowing period, a transplanting period, a growing period and a maturing period;
step 4, respectively carrying out mean value synthesis and wave band superposition on spectral reflectance data, spectral index data and back scattering intensity data in a sowing period, a transplanting period, a growing period and a maturing period, and then superposing terrain gradient data to obtain four-scene multiband images in four physical periods;
step 5, selecting sample points of rice and non-rice, and obtaining total 4 standard spectrum curves of the rice in four-scene multiband images in four weathers;
step 6, calculating the spectrum similarity of each pixel in the four-scene multiband image and the rice spectrum curve of the corresponding object weather period to obtain a four-scene spectrum similarity image;
step 7, based on the four-scene spectrum similarity images, rice and non-rice sample points, adopting a decision tree classifier to identify the rice, and obtaining a rice identification result;
and 8, converting the grid-format rice identification result into a vector diagram in the ArcGIS, and counting the rice planting area after adding the area field.
2. The multi-source remote sensing monitoring method for single-cropping rice planting area according to claim 1, wherein in step 1, the cloud removal process comprises the steps of:
step 1.1, calculating four initial cloud fraction images based on a blue wave band, a blue-green-red wave band, a near infrared wave band, a second short wave infrared wave band, a green wave band and a first short wave infrared wave band by using a normalization function;
normalization function:
cloudScore1＝normaiize(blue,0.1,0.3)
cloudScore2＝normaiize(blue+green+red,0.1,0.3)
cloudScore3＝normaiize(nir+swir2,0.1,0.3)
cloudScore4＝normallze(green+swir1+swir2,0.1,0.3)
wherein blue represents a blue wave band, green represents a green wave band, red represents a red wave band, nir represents a near infrared wave band, swir1 represents a first short wave infrared wave band, and swir2 represents a second short wave infrared wave band; clodscore 1, clodscore 2, clodscore 3, clodscore 4 represent four initial cloud score images;
step 1.2, taking the minimum value from four initial cloud fraction images to generate a final cloud fraction image for each pixel, and masking off the area with the pixel value larger than 0.3 to obtain a cloud-free area range diagram;
and 1.3, masking the optical remote sensing surface reflectivity data by using the cloud-free regional scope graph to obtain the cloud-free optical remote sensing surface reflectivity data.
3. The method for multi-source remote sensing monitoring of single-cropping rice according to claim 2, wherein in step 1, the selected spectral reflectance data comprises red, green, blue, red-edge 1-3, near infrared, short wave infrared 1-2 bands.
4. The method of claim 3, wherein in step 1, the calculated spectral indexes include a ground chlorophyll vegetation index, a normalized vegetation index, an enhanced vegetation index, a topography chlorophyll index, a normalized differential red edge index, a red edge position, a normalized water index, an improved normalized differential water index, a surface water index, and a normalized soil index, and the calculation formula is:
wherein re1 is a first red edge band, re2 is a second red edge band, re3 is a third red edge band, and mir is a mid-infrared band; GCVI is a ground chlorophyll vegetation index, NDVI is a normalized vegetation index, EVI is an enhanced vegetation index, MTCI is a topography chlorophyll index, NDREI is a normalized differential red edge index, REP is a red edge position, NDWI is a normalized water index, MNDWI is an improved normalized differential water body index, LSWI is a surface water index, and NDSI is a normalized soil index.
5. The method of claim 4, wherein in step 2, the surface backscatter intensity data comprises two polarized bands: vertical transmission vertical reception and vertical transmission horizontal reception.
6. The multi-source remote sensing monitoring method for single-cropping rice planting areas according to claim 5, wherein the mean value synthesis in step 4 is a process of obtaining new images by averaging spectral reflectance data, spectral index data and back scattering intensity data at a sowing period, a transplanting period, a growing period and a maturing period, respectively.
7. The method of claim 6, wherein in the step 4, 1-9 bands of the image after the band superposition are the original spectral reflectance data, 10-19 bands are the spectral index, 20-21 bands are the vertical emission vertical reception and the vertical emission horizontal reception polarized image, and 22 bands are the gradient image.
8. The method for multi-source remote sensing monitoring of single-cropping rice planting areas according to claim 7, wherein in step 5, the non-rice comprises buildings, bodies of water, woodland and dry land; the standard spectrum curve is the mean curve of the spectrum curve of the rice sample points.
9. The method of claim 8, wherein calculating the spectral similarity image in step 6 comprises the steps of:
step 6.1, calculating Euclidean distance similarity Ed based on sowing-period multiband images and a rice standard spectrum curve:
Ed＝(Ed orig -min)/(max-min)
wherein p and t are respectively defined as a spectrum curve of an unknown class pixel and a standard spectrum curve of rice; n is the number of image bands, min and max are respectively defined as Ed orig Minimum and maximum values of the image;
step 6.2, calculating spectrum related similarity SCS based on the sowing-period multiband image and the rice standard spectrum curve:
wherein μ and σ are defined as the mean and standard deviation of the two spectral curves, respectively;
step 6.3, calculating the spectrum similarity SSV:
and 6.4, repeating the steps 6.1-6.3, and calculating the spectral similarity SSV of the transplanting period, the growing period and the maturing period based on the multiband images of the transplanting period, the growing period and the maturing period and the corresponding rice standard spectral curves.
10. A computer storage medium, wherein a computer program is stored in the computer storage medium; the computer program, when run on a computer, causes the computer to perform the multi-source remote sensing monitoring method for single-season rice planting areas of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211704594.5A CN116091938B (en) | 2022-12-29 | 2022-12-29 | Multisource remote sensing monitoring method for single-cropping rice planting area |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211704594.5A CN116091938B (en) | 2022-12-29 | 2022-12-29 | Multisource remote sensing monitoring method for single-cropping rice planting area |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116091938A CN116091938A (en) | 2023-05-09 |
| CN116091938B true CN116091938B (en) | 2023-08-18 |
Family
ID=86209637
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211704594.5A Active CN116091938B (en) | 2022-12-29 | 2022-12-29 | Multisource remote sensing monitoring method for single-cropping rice planting area |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116091938B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116597157B (en) * | 2023-07-11 | 2023-09-26 | 中国科学院地理科学与资源研究所 | Plant climate extraction method and device based on characteristic spectrum change |
| CN116563720B (en) * | 2023-07-12 | 2023-10-03 | 华中师范大学 | Single-double-season rice sample automatic generation method for cooperative optical-microwave physical characteristics |
| CN117576572A (en) * | 2024-01-16 | 2024-02-20 | 杭州稻道农业科技有限公司 | Comprehensive planting and raising paddy rice planting coverage extraction method, device and medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112435292A (en) * | 2020-12-18 | 2021-03-02 | 太原理工大学 | Rice planting area extraction method based on remote sensing image |
| CN113033670A (en) * | 2021-03-29 | 2021-06-25 | 华南农业大学 | Method for extracting rice planting area based on Sentinel-2A/B data |
| CN113505635A (en) * | 2021-05-24 | 2021-10-15 | 中国农业大学 | Method and device for identifying winter wheat and garlic mixed planting area based on optics and radar |
| CN114387516A (en) * | 2022-01-07 | 2022-04-22 | 宁波大学 | Single-season rice SAR (synthetic aperture radar) identification method for small and medium-sized fields in complex terrain environment |
| CN114998742A (en) * | 2022-06-16 | 2022-09-02 | 天津市生态环境科学研究院(天津市环境规划院、天津市低碳发展研究中心) | Method for quickly identifying and extracting rice planting area in single-season rice planting area |
| WO2022214039A1 (en) * | 2021-04-07 | 2022-10-13 | 中国农业大学 | Remote sensing identification method for agricultural planting structure |
-
2022
- 2022-12-29 CN CN202211704594.5A patent/CN116091938B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112435292A (en) * | 2020-12-18 | 2021-03-02 | 太原理工大学 | Rice planting area extraction method based on remote sensing image |
| CN113033670A (en) * | 2021-03-29 | 2021-06-25 | 华南农业大学 | Method for extracting rice planting area based on Sentinel-2A/B data |
| WO2022214039A1 (en) * | 2021-04-07 | 2022-10-13 | 中国农业大学 | Remote sensing identification method for agricultural planting structure |
| CN113505635A (en) * | 2021-05-24 | 2021-10-15 | 中国农业大学 | Method and device for identifying winter wheat and garlic mixed planting area based on optics and radar |
| CN114387516A (en) * | 2022-01-07 | 2022-04-22 | 宁波大学 | Single-season rice SAR (synthetic aperture radar) identification method for small and medium-sized fields in complex terrain environment |
| CN114998742A (en) * | 2022-06-16 | 2022-09-02 | 天津市生态环境科学研究院(天津市环境规划院、天津市低碳发展研究中心) | Method for quickly identifying and extracting rice planting area in single-season rice planting area |
Non-Patent Citations (1)
| Title |
|---|
| Rice Planting Area Identification Based on Multi-Temporal Sentinel-1 SAR Images and an Attention U-Net Model;Xiaoshuang Ma,et al;《remote sensing》;正文第1-19页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116091938A (en) | 2023-05-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116091938B (en) | Multisource remote sensing monitoring method for single-cropping rice planting area | |
| Lu et al. | A decision-tree classifier for extracting transparent plastic-mulched landcover from Landsat-5 TM images | |
| CN113033670B (en) | Rice planting area extraction method based on Sentinel-2A/B data | |
| CN113009485A (en) | Remote sensing tobacco field identification method based on improved vegetation index | |
| CN114998742B (en) | Method for rapidly identifying and extracting rice planting area of single-cropping rice region | |
| CN111209871B (en) | Rape planting land remote sensing automatic identification method based on optical satellite image | |
| CN113221806B (en) | Cloud platform fusion multi-source satellite image and tea tree phenological period based automatic tea garden identification method | |
| CN112711989A (en) | Corn straw coverage estimation method based on radar remote sensing and optical remote sensing | |
| CN114778483A (en) | Method for correcting terrain shadow of remote sensing image near-infrared wave band for monitoring mountainous region | |
| CN114387516B (en) | Single-season rice SAR (synthetic aperture radar) identification method for small and medium-sized fields in complex terrain environment | |
| CN113869370A (en) | Tree species refined classification method based on deep learning algorithm and time sequence sentinel image | |
| Darmawan et al. | The potential scattering model for oil palm phenology based on spaceborne X-, C-, and L-band polarimetric SAR imaging | |
| Nguyen et al. | Mapping Land use/land cover using a combination of Radar Sentinel-1A and Sentinel-2A optical images | |
| Nguyen et al. | Rice-planted area extraction by time series analysis of ENVISAT ASAR WS data using a phenology-based classification approach: A case study for Red River Delta, Vietnam | |
| Venkatesan et al. | Multi-temporal feature extraction for precise maize area mapping using time-series Sentinel 1A SAR data | |
| CN109446965B (en) | Automatic tobacco field identification method based on unmanned aerial vehicle data | |
| CN111723712A (en) | Method and system for extracting mulching film information based on radar remote sensing data and object-oriented mulching film information | |
| Mirelva et al. | Application of Sentinel-1 Data for Classifying Croplands Using Google Earth Engine. | |
| CN115063690A (en) | Vegetation classification method based on NDVI (normalized difference vegetation index) time sequence characteristics | |
| Jiang et al. | An automatic rice mapping method based on constrained feature matching exploiting Sentinel-1 data for arbitrary length time series | |
| CN111783625A (en) | Rapid extraction method for information of water-impermeable surface of plain river network area | |
| CN109918826A (en) | A kind of rice yield estimation method based on crucial phenological period multi-source vegetation parameter | |
| Bouhennache et al. | Using landsat images for urban change detection, a case study in Algiers town | |
| CN117911783A (en) | Young rubber plantation identification method based on multi-source remote sensing | |
| CN114332628B (en) | Ginger rapid remote sensing extraction method based on typical physical condition and film network characteristics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |