CN117690024A - Integrated remote sensing identification method for paddy fields with multiple planting modes - Google Patents
Integrated remote sensing identification method for paddy fields with multiple planting modes Download PDFInfo
- Publication number
- CN117690024A CN117690024A CN202311737107.XA CN202311737107A CN117690024A CN 117690024 A CN117690024 A CN 117690024A CN 202311737107 A CN202311737107 A CN 202311737107A CN 117690024 A CN117690024 A CN 117690024A
- Authority
- CN
- China
- Prior art keywords
- rice
- data
- remote sensing
- season
- image 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 241000209094 Oryza Species 0.000 claims abstract description 209
- 235000007164 Oryza sativa Nutrition 0.000 claims abstract description 209
- 235000009566 rice Nutrition 0.000 claims abstract description 209
- 238000011160 research Methods 0.000 claims abstract description 17
- 238000007637 random forest analysis Methods 0.000 claims abstract description 11
- 238000012549 training Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims description 16
- 238000001914 filtration Methods 0.000 claims description 12
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 11
- 238000009331 sowing Methods 0.000 claims description 10
- 238000003306 harvesting Methods 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 6
- 239000006185 dispersion Substances 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 3
- 238000010899 nucleation Methods 0.000 claims description 3
- 230000005855 radiation Effects 0.000 claims description 3
- 238000012876 topography Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 7
- 230000004069 differentiation Effects 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000003384 imaging method Methods 0.000 abstract description 2
- 235000013339 cereals Nutrition 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000010198 maturation time Effects 0.000 description 1
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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/36—Applying a local operator, i.e. means to operate on image points situated in the vicinity of a given point; Non-linear local filtering operations, e.g. median filtering
-
- 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
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
- G06V10/449—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters
- G06V10/451—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters with interaction between the filter responses, e.g. cortical complex cells
- G06V10/454—Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]
-
- 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
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- 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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/194—Terrestrial scenes using hyperspectral data, i.e. more or other wavelengths than RGB
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Remote Sensing (AREA)
- Evolutionary Computation (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Nonlinear Science (AREA)
- Computing Systems (AREA)
- Radar Systems Or Details Thereof (AREA)
- Image Processing (AREA)
Abstract
The invention relates to an integrated remote sensing identification method for paddy fields with multiple planting modes, which comprises the following steps: acquiring elevation and gradient image data of a research area and ground object back scattering intensity data of an annual time sequence; collecting sample points of rice and non-rice categories as training samples; obtaining rice weather data; calculating and extracting characteristics based on the ground object backward scattering intensity data of the annual time sequence; acquiring combined multiband characteristic image data; based on multiband characteristic image data and sample points of rice and non-rice categories, a random forest classifier is adopted to identify rice. The beneficial effects of the invention are as follows: the SAR image is used, so that the influence of weather conditions on the imaging quality of the image and the follow-up rice identification monitoring is avoided; in addition, the invention realizes the differentiation of rice and non-rice through statistical characteristics, realizes the differentiation of rice under various planting modes through the climatic characteristics on the basis, and obtains more accurate and fine paddy field remote sensing monitoring results.
Description
Technical Field
The invention relates to the technical field of remote sensing images, in particular to an integrated remote sensing identification method for paddy fields with multiple planting modes.
Background
Timely and accurate mastering of the space-time distribution condition of the rice plays an important role in supporting government to formulate land utilization and grain policy and ensuring sustainable grain supply.
Optical and Synthetic Aperture Radar (SAR) images are commonly used for rice identification. However, effective optical remote sensing data is often limited in cloudy and rainy areas, and only information of rice canopy can be reflected, so that accuracy of rice monitoring is limited. The synthetic aperture radar is not affected by weather, can acquire the back scattering information below the rice canopy, and is favorable for long-term continuous monitoring of rice. The time sequence SAR image has the capability of observing the whole weather period of the rice and capturing the growth state and the weather change of the rice, and can provide identifying remote sensing characteristics for rice identification. However, most of the existing researches are focused on a single rice planting area of a rice planting mode, or different rice planting modes (single-season rice and double-season rice) are usually studied separately, and the integrated identification research of a paddy field in a complex planting mode is less considered, so that the real rice planting condition in a plurality of planting modes is difficult to reflect, and the spatial distribution of the whole rice planting in one area is limited.
Disclosure of Invention
The invention aims at overcoming the defects of the prior art, and provides an integrated remote sensing identification method for paddy fields with multiple planting modes.
In a first aspect, an integrated remote sensing identification method for a paddy field with multiple planting modes is provided, including:
step 1, collecting digital elevation model data of a research area and preprocessing the data to obtain elevation and gradient image data of the research area;
step 2, collecting annual SAR remote sensing image data and preprocessing the data, and converting the SAR remote sensing image pixel values into actual ground object backscatter intensity to obtain annual time sequence ground object backscatter intensity data;
step 3, collecting sample points of rice and non-rice categories as training samples; the rice comprises single-season early rice, single-season middle rice, single-season late rice and double-season rice; the non-rice includes buildings, natural vegetation, water and dry crops;
step 4, obtaining rice weather data, wherein the rice weather data comprise the date from sowing to mature harvesting of rice;
step 5, calculating and extracting characteristics based on the ground object backward scattering intensity data of the annual time sequence, wherein the characteristics comprise statistical characteristic data and rice object weather parameter characteristic data;
step 6, carrying out wave band superposition on SAR backward scattering intensity data, elevation and gradient image data, statistical characteristic data and rice weather parameter characteristic data to obtain combined multiband characteristic image data;
and 7, identifying the rice by adopting a random forest classifier based on the multiband characteristic image data and the sample points of the rice and non-rice categories.
Preferably, in step 1, the digital elevation model data is elevation image data with resolution not less than 30 m.
Preferably, in step 2, the preprocessing includes:
step 2.1, performing radiation calibration on SAR remote sensing image data, wherein the formula is as follows:
wherein sigma 0 For backscattering coefficient, A i For backscattering back to the antenna per unit time of pixel i, DN i The gray value of pixel i;
step 2.2, filtering SAR remote sensing image data by adopting mean filtering; the convolution kernel used in the mean value filtering is 3×3 in size, the central element value is 1, the surrounding element values are 1, and the convolution kernel is:
step 2.3, doppler topography correction is carried out on SAR remote sensing image data by using elevation data;
step 2.4, performing decibelization on SAR remote sensing image data, and converting the unitless backscattering strength into decibels, wherein the formula is as follows:
σ＝10*log 10 σ 0
wherein sigma 0 Sigma represents the backscattering coefficient after decibelization, and the unit is dB;
and 2.5, performing SG filtering on the earth backscatter intensity data of the annual time sequence after the halving.
Preferably, in step 2.5, the calculation formula is:
in the above, Y j * Is the j-th reconstruction value; c (C) i Is the coefficient of the i-th point in the sliding window; n is the sliding window length, its size equals 2m+1, m is the length of half sliding window, m is set to 3-7.
Preferably, in the step 3, the sample points of the single-season early rice, the single-season middle rice, the single-season late rice, the double-season rice, the building, the natural vegetation, the water body and the dry crop are respectively not less than 100.
Preferably, step 5 includes:
step 5.1, extracting statistical characteristics, wherein the statistical characteristics comprise mean values, median values, polar differences, sum of squares of dispersion, standard deviation and variation coefficients;
step 5.2, extracting rice climatic features including transplanting dates T of early rice, middle rice and late rice TD Date of maturity T MD Growing season length GSL, seeding to transplanting period back scattering coefficient change rate V ST And the change rate V of the backscatter coefficient transplanted to the mature period TM 。
Preferably, in step 5.2, it is assumed that the time-series backscattering coefficient of one pixel in the early rice weather period and the corresponding time are expressed as (d 1 ,σ 1 )，(d 2 ,σ 2 )，…，(d n ,σ n ) Wherein sigma 1 ,…,σ n Is the annual time series backscattering coefficient of the pixel, d 1 ,…,d n Is sigma (sigma) 1 ,…,σ n A corresponding date;
if sigma i ＝min(σ 1 ,…,σ n ) Transplanting date T TD Is d i The method comprises the steps of carrying out a first treatment on the surface of the Wherein the transplanting date T TD The daily sequence of the date corresponding to the minimum value of the pixel backscattering coefficient time sequence curve in one year is represented;
if sigma j ＝max(σ 1 ,…,σ n ) Maturity date T MD Is d j ；
Length of growing season gsl=d j -d i The method comprises the steps of carrying out a first treatment on the surface of the Wherein the growing season length GSL represents a time difference of a maturity date and a transplanting date.
Suppose (d) i1 ,σ i1 ) Sowing date and corresponding backscattering coefficient for rice, (d) i2 ,σ i2 ) The rice transplanting date and the corresponding backscattering coefficient are adopted, and the backscattering coefficient change rate V is sowed to the transplanting period ST ＝(σ i2 -σ i1 )/(d i2 -d i1 )；
Suppose (d) i3 ,σ i3 ) Transplanting the rice to the change rate V of the backscatter coefficient of the mature period for the mature date of the rice and the corresponding backscatter coefficient TM ＝(σ i3 -σ i3 )/(d i2 -d i2 )。
Preferably, the number of decision trees in the random forest algorithm in the step 7 is 50-150.
In a second aspect, an integrated remote sensing identification system for a paddy field with multiple planting modes is provided, and the integrated remote sensing identification method for a paddy field with multiple planting modes in any one of the first aspects is performed, and includes:
the first collecting module is used for collecting and preprocessing the digital elevation model data of the research area to obtain the elevation and gradient image data of the research area;
the second collection module is used for collecting annual SAR remote sensing image data and preprocessing the data, converting the SAR remote sensing image pixel values into actual ground object back scattering intensity, and obtaining annual time sequence ground object back scattering intensity data;
the acquisition module is used for acquiring sample points of rice and non-rice categories as training samples; the rice comprises single-season early rice, single-season middle rice, single-season late rice and double-season rice; the non-rice includes buildings, natural vegetation, water and dry crops;
the acquisition module is used for acquiring rice weather data, wherein the rice weather data comprise the date from sowing to mature harvesting of rice;
the computing module is used for computing the ground object backward scattering intensity data of the annual time sequence and extracting features, wherein the features comprise statistical feature data and rice climate parameter feature data;
the superposition module is used for carrying out wave band superposition on SAR backward scattering intensity data, elevation and gradient image data, statistical characteristic data and rice weather parameter characteristic data to obtain combined multiband characteristic image data;
and the identification module is used for identifying the rice by adopting a random forest classifier based on the multiband characteristic image data and the sample points of the rice and non-rice categories.
In a third aspect, a computer readable storage medium is provided, where the computer readable storage medium includes a stored executable program, where when the executable program runs, the device where the computer readable storage medium is located is controlled to execute the integrated remote sensing identification method for a paddy field with multiple planting modes according to any one of the first aspects.
The beneficial effects of the invention are as follows: according to the invention, the influence of weather conditions on the imaging quality of the image and the follow-up rice identification monitoring is avoided by using SAR images; in addition, the invention realizes the differentiation of rice and non-rice through statistical characteristics, and on the basis, the differentiation of single-season early rice, single-season middle rice, single-season late rice and double-season rice under various planting modes is realized through the climatic characteristics, so that more accurate and fine paddy field remote sensing monitoring results are obtained.
Drawings
FIG. 1 is a technical flow diagram of an integrated remote sensing identification method for paddy fields with multiple planting modes;
FIG. 2 is a graph showing a comparison of statistical characteristics of rice and non-rice types in an embodiment of the present invention;
FIG. 3 is a graph showing the characteristic parameter histograms of rice and non-rice according to an embodiment of the present invention;
FIG. 4 is a graph showing the recognition results of single-season early rice, single-season middle rice, single-season late rice and double-season rice in the embodiment of the present invention.
Detailed Description
The invention is further described below with reference to examples. The following examples are presented only to aid in the understanding of the invention. It should be noted that it will be apparent to those skilled in the art that modifications can be made to the present invention without departing from the principles of the invention, and such modifications and adaptations are intended to be within the scope of the invention as defined in the following claims.
Example 1:
the embodiment 1 of the application provides an integrated remote sensing identification method for paddy fields with multiple planting modes, as shown in fig. 1, comprising the following steps:
step 1, collecting digital elevation model data of a research area and preprocessing the data to obtain elevation and gradient image data of the research area;
step 2, collecting annual SAR remote sensing image data and preprocessing the data, and converting the SAR remote sensing image pixel values into actual ground object backscatter intensity to obtain annual time sequence ground object backscatter intensity data;
step 3, collecting sample points of rice and non-rice categories as training samples; the rice comprises single-season early rice, single-season middle rice, single-season late rice and double-season rice; the non-rice includes buildings, natural vegetation, water and dry crops;
step 4, obtaining rice weather data, wherein the rice weather data comprise the date from sowing to mature harvesting of rice;
step 5, calculating and extracting characteristics based on the ground object backward scattering intensity data of the annual time sequence, wherein the characteristics comprise statistical characteristic data and rice object weather parameter characteristic data;
step 6, carrying out wave band superposition on SAR backward scattering intensity data, elevation and gradient image data, statistical characteristic data and rice weather parameter characteristic data to obtain combined multiband characteristic image data;
and 7, identifying the rice by adopting a random forest classifier based on the multiband characteristic image data and the sample points of the rice and non-rice categories.
Example 2:
based on the embodiment 1, the embodiment 2 of the present application provides an application of the integrated remote sensing identification method for paddy fields with multiple planting modes in the embodiment 1 in reality: the Ningbo city in Zhejiang province is a region with various typical rice planting modes, wherein single-season early rice, single-season middle rice, single-season late rice and double-season rice are planted in the region, the rice planting modes are various, and the planting structure is complex; an integrated remote sensing identification method aiming at paddy fields with multiple planting modes is applied to Ningbo city of Zhejiang province; the Sentinel-1 image was used for monitoring the planting conditions of single season early rice, single season medium rice, single season late rice and double season rice. As shown in fig. 1, the method of the present embodiment includes the steps of:
and step 1, collecting and preprocessing digital elevation model data of the research area to obtain elevation and gradient image data of the research area.
In step 1, the digital elevation model data is elevation image data with resolution not lower than 30 m. In addition, elevation data may be resampled to 10 meters resolution using nearest neighbor methods.
And 2, collecting annual SAR remote sensing image data, preprocessing the data, and converting the SAR remote sensing image pixel values into actual ground object backscatter intensity to obtain annual time sequence ground object backscatter intensity data.
The step 2 comprises the following steps:
step 2.1, performing radiation calibration on SAR remote sensing image data:
in the above, sigma 0 For backscattering coefficient, A i For backscattering back to the antenna per unit time of pixel i, DN i The gray value of pixel i;
step 2.2, filtering SAR remote sensing image data by adopting mean filtering, wherein the size of a convolution kernel used in the mean filtering is 3 multiplied by 3, the value of a central element is 1, the value of surrounding elements is 1, and the convolution kernel is as follows:
step 2.3, doppler topography correction is carried out on SAR remote sensing image data by using elevation data;
step 2.4, performing decibelization on SAR remote sensing image data, and converting the unitless (linear) back scattering intensity into decibels (dB):
σ＝10*log 10 σ 0
in the above, sigma 0 Sigma represents the decibelized backscattering coefficient in dB for the original backscattering coefficient.
Step 2.5, savitzky-Golay filtering is carried out on the annual time series backscattering coefficient data after the halving:
in the above, Y j * Is the j-th reconstruction value; c (C) i Is the coefficient of the i-th point in the sliding window; n is the sliding window length, its size equals 2m+1, m is the length of half the sliding window, m is set to 5.
Step 3, collecting sample points of rice and non-rice categories as training samples; the rice comprises single-season early rice, single-season middle rice, single-season late rice and double-season rice; the non-rice includes buildings, natural vegetation, water and drought crops.
Specifically, rice and non-rice sample points are selected according to field investigation data, unmanned aerial vehicle images and high-resolution Google earth images, wherein the number of sample points of single-season early rice, single-season middle rice, single-season late rice, double-season rice, buildings, natural vegetation, water bodies and dry crops is not less than 100 respectively.
And 4, obtaining rice weather data, wherein the rice weather data comprise the date from sowing to mature harvesting of rice.
For example, the rice climate data is obtained by field observation.
And 5, calculating and extracting characteristics based on the ground object back scattering intensity data of the annual time sequence, wherein the characteristics comprise statistical characteristic data and rice weather parameter characteristic data.
The step 5 comprises the following steps:
step 5.1, as shown in fig. 2, extracting statistical characteristics, wherein the statistical characteristics comprise mean, median, polar error, sum of squares of dispersion, standard deviation and coefficient of variation; the specific formula is as follows:
average value:
median value: media = sigma (n+1)/2 N is an odd number; media = sigma n/2 N is an even number
Extremely bad: range=σ max -σ min
Sum of squares of dispersion:
standard deviation:
coefficient of variation:
where σ is the backscattering coefficient and n is the number of images.
Step 5.2, as shown in FIG. 3, extracting rice climatic features including transplanting dates T of early rice, medium rice and late rice TD Date of maturity T MD Growing season length GSL, seeding to transplanting period back scattering coefficient change rate V ST And the change rate V of the backscatter coefficient transplanted to the mature period TM 。
In step 5.2, it is assumed that the time-series backscattering coefficient of one pixel in the early rice weather period and the corresponding time are expressed as (d 1 ,σ 1 )，(d 2 ,σ 2 )，…，(d n ,σ n ) Wherein sigma 1 ,…,σ n Is the annual time series backscattering coefficient of the pixel, d 1 ,…,d n Is sigma (sigma) 1 ,…,σ n A corresponding date;
if sigma i ＝min(σ 1 ,…,σ n ) Transplanting date T TD Is d i The method comprises the steps of carrying out a first treatment on the surface of the Wherein the transplanting date T TD The daily sequence of the date corresponding to the minimum value of the pixel backscattering coefficient time sequence curve in one year is represented;
if sigma j ＝max(σ 1 ,…,σ n ) Maturity date T MD Is d j ；
Length of growing season gsl=d j -d i The method comprises the steps of carrying out a first treatment on the surface of the Wherein the growing season length GSL represents the date of maturationTime difference of transplanting date.
Suppose (d) i1 ,σ i1 ) Sowing date and corresponding backscattering coefficient for rice, (d) i2 ,σ i2 ) The rice transplanting date and the corresponding backscattering coefficient are adopted, and the backscattering coefficient change rate V is sowed to the transplanting period ST ＝(σ i2 -σ i1 )/(d i2 -d i1 )；
Suppose (d) i3 ,σ i3 ) Transplanting the rice to the change rate V of the backscatter coefficient of the mature period for the mature date of the rice and the corresponding backscatter coefficient TM ＝(σ i3 -σ i3 )/(d i2 -d i2 )。
And step 6, performing wave band superposition on SAR backward scattering intensity data, elevation and gradient image data, statistical characteristic data and rice weather parameter characteristic data to obtain combined multiband characteristic image data.
Step 7, as shown in fig. 4, based on the multiband characteristic image data, the sample points of the rice (single-season early rice, single-season middle rice, single-season late rice and double-season rice) and the non-rice (building, natural vegetation, water body and dry crops) categories, the random forest classifier is adopted to identify the rice.
Specifically, the number of decision trees in the random forest algorithm in the step 7 is 50-150, and most preferably 100.
In this embodiment, the same or similar parts as those in embodiment 1 may be referred to each other, and will not be described in detail in this application.
Example 3:
on the basis of embodiments 1 and 2, embodiment 3 of the present application provides an integrated remote sensing identification system for paddy fields with multiple planting modes, including:
the first collecting module is used for collecting and preprocessing the digital elevation model data of the research area to obtain the elevation and gradient image data of the research area;
the second collection module is used for collecting annual SAR remote sensing image data and preprocessing the data, converting the SAR remote sensing image pixel values into actual ground object back scattering intensity, and obtaining annual time sequence ground object back scattering intensity data;
the acquisition module is used for acquiring sample points of rice and non-rice categories as training samples; the rice comprises single-season early rice, single-season middle rice, single-season late rice and double-season rice; the non-rice includes buildings, natural vegetation, water and dry crops;
the acquisition module is used for acquiring rice weather data, wherein the rice weather data comprise the date from sowing to mature harvesting of rice;
the computing module is used for computing and extracting characteristics based on the ground object backward scattering intensity data of the annual time sequence, wherein the characteristics comprise statistical characteristic data and rice weather parameter characteristic data;
the superposition module is used for carrying out wave band superposition on SAR backward scattering intensity data, elevation and gradient image data, statistical characteristic data and rice weather parameter characteristic data to obtain combined multiband characteristic image data;
and the identification module is used for identifying the rice by adopting a random forest classifier based on the multiband characteristic image data and the sample points of the rice and non-rice categories.
Specifically, the system provided in this embodiment is a system corresponding to the method provided in embodiment 1, so that the portions in this embodiment that are the same as or similar to those in embodiment 1 may be referred to each other, and will not be described in detail in this application.
Claims (10)
1. An integrated remote sensing identification method for paddy fields with multiple planting modes is characterized by comprising the following steps:
step 1, collecting digital elevation model data of a research area and preprocessing the data to obtain elevation and gradient image data of the research area;
step 2, collecting annual SAR remote sensing image data and preprocessing the data, and converting the SAR remote sensing image pixel values into actual ground object backscatter intensity to obtain annual time sequence ground object backscatter intensity data;
step 3, collecting sample points of rice and non-rice categories as training samples; the rice comprises single-season early rice, single-season middle rice, single-season late rice and double-season rice; the non-rice includes buildings, natural vegetation, water and dry crops;
step 4, obtaining rice weather data, wherein the rice weather data comprise the date from sowing to mature harvesting of rice;
step 5, calculating and extracting characteristics based on the ground object backward scattering intensity data of the annual time sequence, wherein the characteristics comprise statistical characteristic data and rice object weather parameter characteristic data;
step 6, carrying out wave band superposition on SAR backward scattering intensity data, elevation and gradient image data, statistical characteristic data and rice weather parameter characteristic data to obtain combined multiband characteristic image data;
and 7, identifying the rice by adopting a random forest classifier based on the multiband characteristic image data and the sample points of the rice and non-rice categories.
2. The integrated remote sensing identification method for paddy fields with multiple planting modes according to claim 1, wherein in the step 1, the digital elevation model data is elevation image data with resolution not lower than 30 meters.
3. The integrated remote sensing identification method for paddy fields with multiple planting modes according to claim 2, wherein in step 2, the preprocessing includes:
step 2.1, performing radiation calibration on SAR remote sensing image data, wherein the formula is as follows:
wherein sigma 0 For backscattering coefficient, A i For backscattering back to the antenna per unit time of pixel i, DN i The gray value of pixel i;
step 2.2, filtering SAR remote sensing image data by adopting mean filtering, wherein the size of a convolution kernel used in the mean filtering is 3 multiplied by 3, the value of a central element is 1, the value of surrounding elements is 1, and the convolution kernel is as follows:
step 2.3, doppler topography correction is carried out on SAR remote sensing image data by using ALOS elevation data;
step 2.4, performing decibelization on SAR remote sensing image data, and converting the unitless backscattering strength into decibels, wherein the formula is as follows:
σ＝10*log 10 σ 0
wherein sigma 0 Sigma represents the backscattering coefficient after decibelization, and the unit is dB;
and 2.5, performing SG filtering on the earth backscatter intensity data of the annual time sequence after the halving.
4. The integrated remote sensing identification method for paddy fields with multiple planting modes according to claim 3, wherein in the step 2.5, a calculation formula is as follows:
in the above, Y j * Is the j-th reconstruction value; c (C) i Is the coefficient of the i-th point in the sliding window; n is the sliding window length, its size equals 2m+1, m is the length of half sliding window, m is set to 3-7.
5. The integrated remote sensing identification method for paddy fields with multiple planting modes according to claim 4, wherein in the step 3, the number of sample points of single-season early rice, single-season middle rice, single-season late rice, double-season rice, buildings, natural vegetation, water bodies and dry crops is not less than 100 respectively.
6. The integrated remote sensing identification method for paddy fields in multiple planting modes according to claim 5, wherein step 5 comprises:
step 5.1, extracting statistical characteristics, wherein the statistical characteristics comprise mean values, median values, polar differences, sum of squares of dispersion, standard deviation and variation coefficients;
step 5.2, extracting rice climatic features including transplanting dates T of early rice, middle rice and late rice TD Date of maturity T MD Length CSL of growing season and change rate V of back scattering coefficient from seeding to transplanting period ST And the change rate V of the backscatter coefficient transplanted to the mature period TM 。
7. The integrated remote sensing identification method for multi-planting pattern paddy fields according to claim 6, wherein in step 5.2, it is assumed that the time series backscattering coefficient and corresponding time of one pixel in early rice weather period are expressed as (d) 1 ,σ 1 )，(d 2 ,σ 2 )，…，(d n ,σ n ) Wherein sigma 1 ,…,σ n Is the annual time series backscattering coefficient of the pixel, i 1 ,…,d n Is sigma (sigma) 1 ,…,σ n A corresponding date;
if sigma i ＝min(σ 1 ,…,σ n ) Transplanting date T TD Is d i The method comprises the steps of carrying out a first treatment on the surface of the Wherein the transplanting date T TD The daily sequence of the date corresponding to the minimum value of the pixel backscattering coefficient time sequence curve in one year is represented;
if sigma j ＝max(σ 1 ,…,σ n ) Maturity date T MD Is d j ；
Length of growing season gsl=d j -d i The method comprises the steps of carrying out a first treatment on the surface of the Wherein the growing season length GSL represents a time difference of a maturity date and a transplanting date.
Suppose (d) i1 ,σ i1 ) Sowing date and corresponding backscattering coefficient for rice, (d) i2 ,σ i2 ) The rice transplanting date and the corresponding backscattering coefficient are adopted, and the backscattering coefficient change rate V is sowed to the transplanting period ST ＝(σ i2 -σ i1 )/(d i2 -d i1 )；
Suppose (d) i3 ,σ i3 ) Transplanting the rice to the change rate V of the backscatter coefficient of the mature period for the mature date of the rice and the corresponding backscatter coefficient TM ＝(σ i3 -σ i3 )/(d i2 -d i2 )。
8. The integrated remote sensing identification method for paddy fields with multiple planting modes according to claim 6, wherein the number of decision trees in the random forest algorithm in the step 7 is 50-150.
9. An integrated remote sensing identification system for a multi-planting-mode paddy field, for performing the integrated remote sensing identification method for a multi-planting-mode paddy field according to any one of claims 1 to 8, comprising:
the first collecting module is used for collecting and preprocessing the digital elevation model data of the research area to obtain the elevation and gradient image data of the research area;
the second collection module is used for collecting annual SAR remote sensing image data and preprocessing the data, converting the SAR remote sensing image pixel values into actual ground object back scattering intensity, and obtaining annual time sequence ground object back scattering intensity data;
the acquisition module is used for acquiring sample points of rice and non-rice categories as training samples; the rice comprises single-season early rice, single-season middle rice, single-season late rice and double-season rice; the non-rice includes buildings, natural vegetation, water and dry crops;
the acquisition module is used for acquiring rice weather data, wherein the rice weather data comprise the date from sowing to mature harvesting of rice;
the computing module is used for computing and extracting characteristics based on the ground object backward scattering intensity data of the annual time sequence, wherein the characteristics comprise statistical characteristic data and rice weather parameter characteristic data;
the superposition module is used for carrying out wave band superposition on SAR backward scattering intensity data, elevation and gradient image data, statistical characteristic data and rice weather parameter characteristic data to obtain combined multiband characteristic image data;
and the identification module is used for identifying the rice by adopting a random forest classifier based on the multiband characteristic image data and the sample points of the rice and non-rice categories.
10. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored executable program, wherein the executable program when run controls a device in which the computer readable storage medium is located to execute the integrated remote sensing identification method for a paddy field with multiple planting modes according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311737107.XA CN117690024B (en) | 2023-12-18 | 2023-12-18 | Integrated remote sensing identification method for paddy fields with multiple planting modes |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311737107.XA CN117690024B (en) | 2023-12-18 | 2023-12-18 | Integrated remote sensing identification method for paddy fields with multiple planting modes |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117690024A true CN117690024A (en) | 2024-03-12 |
| CN117690024B CN117690024B (en) | 2024-06-14 |
Family
ID=90128130
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311737107.XA Active CN117690024B (en) | 2023-12-18 | 2023-12-18 | Integrated remote sensing identification method for paddy fields with multiple planting modes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117690024B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117975293A (en) * | 2024-03-28 | 2024-05-03 | 四川汉盛源科技有限公司 | Extraction method for rice planting area in multiple cloud and fog areas |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011080944A1 (en) * | 2009-12-28 | 2011-07-07 | 株式会社パスコ | Rice crop status tracking system, rice crop status tracking method, rice crop status tracking program |
| CN106529451A (en) * | 2016-10-28 | 2017-03-22 | 山东省农业可持续发展研究所 | Winter wheat-summer corn planting mode remote sensing identification method |
| CN111142106A (en) * | 2020-02-26 | 2020-05-12 | 北京师范大学 | Automatic rice identification method based on synthetic aperture radar time sequence data |
| CN113009485A (en) * | 2021-03-10 | 2021-06-22 | 安徽皖南烟叶有限责任公司 | Remote sensing tobacco field identification method based on improved vegetation index |
| WO2021258359A1 (en) * | 2020-06-24 | 2021-12-30 | 深圳市大疆创新科技有限公司 | Method and apparatus for determining crop planting information, and computer storage medium |
| 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 |
| CN115223059A (en) * | 2022-08-31 | 2022-10-21 | 自然资源部第三航测遥感院 | Multi-cloud-fog-area crop planting mode extraction method based on multi-element remote sensing image |
| CN115861844A (en) * | 2022-12-27 | 2023-03-28 | 中科禾信遥感科技（苏州）有限公司 | Rice early-stage remote sensing identification method based on planting probability |
| WO2023109652A1 (en) * | 2021-12-14 | 2023-06-22 | 深圳先进技术研究院 | Rice planting extraction and multiple-cropping index monitoring method and system, and terminal and storage medium |
-
2023
- 2023-12-18 CN CN202311737107.XA patent/CN117690024B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011080944A1 (en) * | 2009-12-28 | 2011-07-07 | 株式会社パスコ | Rice crop status tracking system, rice crop status tracking method, rice crop status tracking program |
| CN106529451A (en) * | 2016-10-28 | 2017-03-22 | 山东省农业可持续发展研究所 | Winter wheat-summer corn planting mode remote sensing identification method |
| CN111142106A (en) * | 2020-02-26 | 2020-05-12 | 北京师范大学 | Automatic rice identification method based on synthetic aperture radar time sequence data |
| WO2021258359A1 (en) * | 2020-06-24 | 2021-12-30 | 深圳市大疆创新科技有限公司 | Method and apparatus for determining crop planting information, and computer storage medium |
| CN113009485A (en) * | 2021-03-10 | 2021-06-22 | 安徽皖南烟叶有限责任公司 | Remote sensing tobacco field identification method based on improved vegetation index |
| WO2023109652A1 (en) * | 2021-12-14 | 2023-06-22 | 深圳先进技术研究院 | Rice planting extraction and multiple-cropping index monitoring method and system, and terminal and storage medium |
| 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 |
| CN115223059A (en) * | 2022-08-31 | 2022-10-21 | 自然资源部第三航测遥感院 | Multi-cloud-fog-area crop planting mode extraction method based on multi-element remote sensing image |
| CN115861844A (en) * | 2022-12-27 | 2023-03-28 | 中科禾信遥感科技（苏州）有限公司 | Rice early-stage remote sensing identification method based on planting probability |
Non-Patent Citations (1)
| Title |
|---|
| 黄翀;许照鑫;张晨晨;李贺;刘庆生;杨振坤;刘高焕;: "基于Sentinel-1数据时序特征的热带地区水稻种植结构提取方法", 农业工程学报, no. 09, 8 May 2020 (2020-05-08) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117975293A (en) * | 2024-03-28 | 2024-05-03 | 四川汉盛源科技有限公司 | Extraction method for rice planting area in multiple cloud and fog areas |
| CN117975293B (en) * | 2024-03-28 | 2024-06-04 | 四川汉盛源科技有限公司 | Extraction method for rice planting area in multiple cloud and fog areas |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117690024B (en) | 2024-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Brook et al. | A smart multiple spatial and temporal resolution system to support precision agriculture from satellite images: Proof of concept on Aglianico vineyard | |
| Phung et al. | Monitoring rice growth status in the Mekong Delta, Vietnam using multitemporal Sentinel-1 data | |
| Shihua et al. | Monitoring paddy rice phenology using time series MODIS data over Jiangxi Province, China | |
| Son et al. | A phenological object-based approach for rice crop classification using time-series Sentinel-1 Synthetic Aperture Radar (SAR) data in Taiwan | |
| CN106372592B (en) | A kind of winter wheat planting area calculation method based on winter wheat area index | |
| US8478003B2 (en) | Vegetation growth condition analysis method, recording medium on which program is recorded, and vegetation growth condition analyzer | |
| Wang et al. | Characterizing L-band scattering of paddy rice in southeast China with radiative transfer model and multitemporal ALOS/PALSAR imagery | |
| CN113505635B (en) | Winter wheat and garlic mixed seed area identification method and device based on optics and radar | |
| CN114387516B (en) | Single-season rice SAR (synthetic aperture radar) identification method for small and medium-sized fields in complex terrain environment | |
| Sharifi | Estimation of biophysical parameters in wheat crops in Golestan province using ultra-high resolution images | |
| CN110348314B (en) | Method and system for monitoring vegetation growth by using multi-source remote sensing data | |
| CN117690024B (en) | Integrated remote sensing identification method for paddy fields with multiple planting modes | |
| Pang et al. | Pixel-level rice planting information monitoring in Fujin City based on time-series SAR imagery | |
| Zhou et al. | Wheat phenology detection with the methodology of classification based on the time-series UAV images | |
| CN112836725A (en) | Weak supervision LSTM recurrent neural network rice field identification method based on time sequence remote sensing data | |
| Park | Estimating plant water stress and evapotranspiration using very-high-resolution (VHR) UAV imagery | |
| Li et al. | BRDF effect on the estimation of canopy chlorophyll content in paddy rice from UAV-based hyperspectral imagery | |
| CN116452359A (en) | Comprehensive evaluation method for winter wheat growth vigor | |
| KR20240046375A (en) | Automatically classification method on land use of agricultural land by using multispectral sensor of UAV | |
| CN109141371B (en) | Winter wheat disaster identification method, device and equipment | |
| Zheng et al. | Using high spatial and temporal resolution data blended from SPOT-5 and MODIS to map biomass of summer maize | |
| Sofue et al. | Estimation of normal rice yield considering heading stage based on observation data and satellite imagery | |
| Verma et al. | Knowledge based classifier based on backscattering coefficient for monitoring the crop growth analysis using multi-temporal images of space-borne synthetic aperture radar (SAR) sensors | |
| Shen et al. | Hidden Markov Models for corn progress percents estimation in multivariate time series | |
| CN114724024B (en) | Cloud computing platform and life cycle based double-season crop planting boundary automatic extraction method |
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 |