CN116188793A - Astragalus sinicus planting area monitoring method based on satellite remote sensing image - Google Patents
Astragalus sinicus planting area monitoring method based on satellite remote sensing image Download PDFInfo
- Publication number
- CN116188793A CN116188793A CN202211396518.2A CN202211396518A CN116188793A CN 116188793 A CN116188793 A CN 116188793A CN 202211396518 A CN202211396518 A CN 202211396518A CN 116188793 A CN116188793 A CN 116188793A
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- research area
- time phase
- sensing image
- vegetation index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/42—Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation
- G06V10/422—Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation for representing the structure of the pattern or shape of an object therefor
-
- 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
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a method for monitoring the planting area of astragalus sinicus based on satellite remote sensing images, which comprises the following steps: acquiring multi-temporal remote sensing images of a research area and longitude and latitude data of actual measurement sample points of all crops on the ground within the range of the research area; preprocessing the multi-temporal remote sensing image of the research area to obtain the remote sensing image of the research area; carrying out optimal characteristic combination analysis on remote sensing images of all research areas to determine an optimal time phase; selecting the most suitable time phase remote sensing image of the research area according to the most suitable time phase; training the random forest classification model by taking pixels of all crop actual measurement sample points on the ground in the research area on the most suitable time phase remote sensing image of the research area as training samples to obtain a trained random forest classification model; inputting the remote sensing images of the research area to be monitored into a trained random forest classification model to obtain a classification result of the remote sensing images of the astragalus sinicus in the research area; and obtaining the planting area of the astragalus sinicus according to the classification result of the astragalus sinicus remote sensing images in the research area.
Description
Technical Field
The invention belongs to the technical field of remote sensing monitoring, and particularly relates to a method for monitoring a planting area of astragalus sinicus based on satellite remote sensing images.
Background
The Chinese milk vetch is a green manure crop mainly planted and utilized in the rice area of China, the planted Chinese milk vetch has the functions of improving the physical and chemical properties of soil, increasing the quantity and diversity of soil microorganisms and improving the soil fertility, and the planting mode of the Chinese milk vetch and rice rotation is adopted, so that the Chinese milk vetch has important significance for protecting the ecological environment of farmlands and promoting the sustainable development of agriculture, and is an important measure of land culture for traditional agriculture. Along with the continuous expansion of the planting scale of the milk vetch in the rice area, the research and the solution of a series of problems such as space distribution, dynamic change and the like of the milk vetch planting are becoming urgent.
The traditional investigation method of the crop planting area is a statistical investigation method, and the statistical investigation method relies on collecting and reporting data layer by layer after field investigation to obtain the crop planting area, but the investigation method has the limitations of time and labor waste and larger influence of subjective factors, and cannot be widely used.
Disclosure of Invention
The invention aims to: in order to solve the problems of time and labor waste and uncertainty of statistical data in the existing investigation method for acquiring data such as the planting area of the astragalus sinicus, the invention provides a satellite remote sensing image-based method for monitoring the planting area of the astragalus sinicus.
The technical scheme is as follows: a method for monitoring a planting area of Astragalus sinicus based on satellite remote sensing images comprises the following steps:
step 1: acquiring multi-temporal remote sensing images of a research area and longitude and latitude data of actual measurement sample points of all crops on the ground within the range of the research area; the actual measurement sample points of all crops on the ground in the research area range comprise actual measurement sample points of milk vetch on the ground in the research area range and actual measurement sample points of other crops on the ground in the same season in the research area range;
step 2: preprocessing the multi-temporal remote sensing image of the research area to obtain the remote sensing image of the research area;
step 3: performing optimal feature combination analysis on the remote sensing images of all the research areas to obtain optimal feature combinations of each time phase, and determining the optimal time phase and the optimal feature combinations;
step 4: selecting the most suitable time phase remote sensing image of the research area according to the most suitable time phase;
step 5: training the random forest classification model by taking the optimal characteristic combination of pixels on the remote sensing image of all crop actual measurement sample points on the ground in the research area in the most suitable time phase of the research area as a training sample to obtain a trained random forest classification model;
step 6: inputting the remote sensing images of the research area to be monitored into a trained random forest classification model to obtain crop classification results of the research area, and extracting the astragalus sinicus remote sensing image classification results of the research area;
step 7: and outputting the classification result of the astragalus membranaceus remote sensing images in the research area as a vectorization file, and carrying out area statistics on the vectorization file by utilizing GIS software to obtain the planting area of the astragalus membranaceus.
Further, the remote sensing image of each time phase of the research area comprises satellite remote sensing images of the key growth period of the ground milk vetch in the range of the research area.
Further, the preprocessing of the multi-temporal remote sensing image of the research area specifically includes:
the remote sensing image of each time phase is preprocessed as follows:
s210: resampling each wave band image of the remote sensing image of each time phase to obtain an image with the resolution of 10 m;
s220: unifying the images with the resolution of 10m by adopting Gaussian-Kelvin projection to obtain unified remote sensing images;
s230: and cutting and embedding the unified remote sensing image according to the range of the research area to obtain the remote sensing image of the research area in the time phase.
Further, the step 3 specifically includes:
the remote sensing image of the research area of each time phase is operated as follows:
s310: according to longitude and latitude data of all crop actual measurement sampling points on the ground in the research area, extracting pixels on a research area remote sensing image of all crop actual measurement sampling points on the ground in the research area in the current time phase, and acquiring reflectivity values of the pixels in each wave band;
s320: calculating by utilizing a wave band to obtain a normalized vegetation index, a green wave band normalized vegetation index, a specific vegetation index, a green wave band specific vegetation index, a near infrared and red wave band specific vegetation index, a red-green wave band specific vegetation index, a red-red wave band specific vegetation index, a green wave band atmospheric resistance vegetation index, a conversion vegetation index, a soil regulation vegetation index, a difference vegetation index, a reciprocal difference vegetation index, an enhanced vegetation index, a land water index, a conversion difference vegetation index, an optimized soil regulation vegetation index, a nonlinear vegetation index and an improved nonlinear vegetation index of pixels on a remote sensing image of a research area in a current time phase of all crop actual measurement sample points on the ground within the research area;
s330: taking the reflectivity value obtained in the step S310 and each index obtained in the step S320 as characteristic parameters, and constructing an initial characteristic parameter data set;
s340: the importance of each characteristic difference parameter is obtained by calculating the root mean square error reduction value of each characteristic parameter, and the larger the root mean square error reduction value is, the larger the importance is; deleting the characteristic parameter with the minimum root mean square error reduction value of the characteristic parameter, and updating the characteristic parameter data set; inputting the updated characteristic parameter data set into a random forest classifier, and calculating the overall classification accuracy of the random forest classifier;
s350: repeatedly executing S340 until the feature parameter data set is an empty set, at this time, taking a group of feature parameters with the largest overall classification precision as the best feature combination of the time phase, and recording the overall classification precision as the maximum overall classification precision of the current time phase;
comparing the maximum value of the overall classification precision of each time phase, taking the time phase with the highest overall classification precision as the most suitable time phase, taking the best feature combination corresponding to the most suitable time phase as the most suitable feature combination, and taking the feature parameter corresponding to the most suitable time phase as the best feature combination.
Furthermore, the multi-temporal remote sensing image of the research area is a remote sensing image obtained by observing the same research area at different times by using a middle-high resolution remote sensing satellite with a red-edge band.
The beneficial effects are that: aiming at the defects of the existing method for reporting the field investigation statistics of the planting area of the milk vetch, the invention searches and establishes the remote sensing identification characteristics and the proper time phase of the distinguishability of the milk vetch by utilizing the medium-high resolution satellite data with the red band, performs the distribution extraction and the area statistics of the milk vetch, and improves the monitoring efficiency and the objectivity of the planting area of the milk vetch.
Drawings
FIG. 1 is a flow chart of an embodiment of the present invention;
fig. 2 shows the result of remote sensing monitoring of milk vetch in the test area.
Detailed Description
The technical scheme of the invention is further described with reference to the accompanying drawings and the embodiments.
Example 1:
the technical scheme of the invention is described by taking the monitoring of the planting area of the astragalus sinicus based on the second satellite remote sensing image of the sentinel as an example, wherein the second satellite remote sensing image of the sentinel is a medium-high resolution satellite image with a red-edge wave band. As shown in fig. 1, it mainly comprises the following steps:
step 1: the data acquisition mainly comprises the following steps: downloading sentinel second LEVEL-2A data covering the range of the research area and the growth period of the milk vetch from an European space agency data center, wherein the sentinel second LEVEL-2A data is a reflectivity image after radiation correction, atmospheric correction, orthographic correction and geometric correction treatment; the sentinel second LEVEL-2A data in the growth period of the milk vetch is a multi-temporal remote sensing image containing the key growth period of the milk vetch in the current year; and acquiring longitude and latitude data of all crop actual measurement sampling points on the ground in the research area by using a high-precision GPS, wherein the actual measurement sampling points comprise longitude and latitude data of current-year ground astragalus sinicus sampling points in the research area and longitude and latitude data of other main crop sampling points in the same season, and the current year is the year corresponding to the data.
Step 2: preprocessing the data of the second sentinel LEVEL-2A in the growth period of the milk vetch obtained in the step 1 mainly comprises the following steps: leading in a sentinel second LEVEL-2A data in a milk vetch growing period, and resampling images of each wave band into images with 10m resolution; the remote sensing image is projected by Gaussian-Kelvin uniformly; and cutting and embedding the remote sensing image by utilizing the boundary of the research area to obtain the remote sensing image of the multi-temporal research area.
Step 3: and carrying out optimal feature combination analysis on the remote sensing images of the multi-time-phase research area to obtain optimal feature combination of each time phase, and determining the optimal time phase. The method specifically comprises the following steps:
s310: and extracting pixels of all crop sample points actually measured on the ground on a remote sensing image of the current time phase research area according to longitude and latitude data of all crop actually measured sample points on the ground in the range of the research area, and obtaining reflectivity values of the pixels in each wave band. Since the sentinel second LEVEL-2A data itself is a reflectivity image after a series of processing, the value corresponding to the pixel is the reflectivity value. The extracted pixels are specific pixels which are directly matched to the satellite images according to longitude and latitude data of the actual measurement sample points.
S320: extracting normalized vegetation index (NDVI) of pixels of all crop sample points actually measured on the ground on a remote sensing image of a current time phase research area by utilizing wave band calculation GREEN ) Normalized vegetation index in green band (GNDVI), ratio Vegetation Index (RVI), ratio vegetation index in green band (RVI) GREEN ) Vegetation index (SR) of near infrared to red edge band ratio NIR/RE ) Ratio vegetation index (SR) RED/GREEN ) Vegetation index (SR) of red-to-red edge band ratio RED/RE ) Green band atmospheric impedance vegetation index (VARI) GREEN ) A Transformed Vegetation Index (TVI), a soil regulated vegetation index (SAVI), a Differential Vegetation Index (DVI), a reciprocal differential vegetation index (DDVI), an Enhanced Vegetation Index (EVI), a land water index (LSWI), a Transformed Differential Vegetation Index (TDVI), an optimized soil regulated vegetation index (OSAVI), a non-linear vegetation index (NLI), and an improved non-linear vegetation index (MNLI).
DVI＝ρ NIR -ρ RED (11)
Wherein ρ is NIR 、ρ RED 、ρ GREEN 、ρ BLUE 、ρ SWIR 、ρ RE Respectively near infrared band reflectivity, red band reflectivity, green band reflectivity, blue light reflectivity, short wave infrared and red side reflectivity.
S330: and taking the reflectivity of each wave band and various vegetation index values of all crop samples actually measured on the ground as a characteristic parameter data set, estimating the importance of the characteristic parameters by utilizing a scikit-learn software package of python, calculating to obtain root mean square error reduction values (Increase in Mean Square Error, incMSE) of each characteristic parameter by using a feature_import parameter, wherein the larger the IncMSE value is, the more important the representative characteristic is, sorting the root mean square error reduction values of the characteristic parameters according to descending order, and deleting the characteristic parameter with the minimum root mean square error reduction value of the characteristic parameter to obtain a new characteristic parameter data set.
Inputting a new characteristic parameter data set into a random forest classifier, wherein each sample point has a plurality of characteristic parameters, inputting the characteristic parameters and corresponding categories (such as milk vetch, rice, rape and the like) into the random forest classifier, and judging the category of the sample point according to the numerical distribution condition of the characteristic parameters by the random forest classifier; the Overall classification Accuracy (OA) of the random forest classifier is calculated, and the OA is calculated through a result after classification of the random forest classifier, namely an confusion matrix. Deleting the characteristic parameter with the minimum root mean square error reduction value in the current characteristic parameter data set through importance estimation to form a new characteristic parameter data set, and then bringing the new characteristic parameter data set into a random forest classifier to calculate the overall classification precision; repeating the above process until 1 feature is remained finally, and carrying into the classifier to obtain an OA; all the OAs are obtained, and the maximum OA is obtained by comparing all the OAs, wherein the maximum OA corresponds to the optimal feature combination.
Wherein n is the number of samples, x kk To classify the number of samples consistent with the actual type.
S340: and sequentially carrying out optimal feature combination analysis on all the remote sensing images, and comparing the overall classification precision of each time phase, wherein the time phase with the highest overall classification precision is determined to be the most suitable time phase.
Step 4: and (3) selecting the remote sensing image of the most suitable time phase of the research area for classification preparation according to the most suitable time phase determined in the step (3). Training the random forest classifier by taking the optimal characteristic combination of pixels on the remote sensing image of all crop sample points actually measured on the ground in the most suitable time phase of the research area as a training sample to obtain a trained random forest classifier; and inputting the second satellite remote sensing image of the guard in the research area to be monitored into a trained random forest classifier for crop classification, and obtaining a astragalus membranaceus remote sensing image classification result.
Step 5: and outputting the classification result of the astragalus membranaceus remote sensing image as a astragalus membranaceus vectorization file in the research area, and carrying out area statistics on the astragalus membranaceus vectorization file in the research area by utilizing GIS software to obtain the planting area of the astragalus membranaceus in the research area.
Example 2:
the technical scheme of the invention is described by taking a test area in the north of the Liuhe area of Nanjing as an example. The method specifically comprises the following steps:
step 1: and acquiring 497 ground actual measurement sample points of crops in 3 months 2020 to 5 months 2020, wherein the test area, the 4-scene sentry second image and the 4-month crops in the north of the Liuhe region of Nanjing are positioned, and the crop categories comprise wheat, rape, milk vetch and leisure cultivated land. Table 1 shows a list of 4-scene sentinel second remote sensing images.
Table 1 4 Jing Shaobing No. two remote sensing image list
| Numbering device | Sensor for detecting a position of a body | Phase of |
| 1 | S2A/ |
2020, 3 months and 7 |
| 2 | S2A/ |
2020, 3 months and 17 |
| 3 | S2A/ |
2020, 4 months and 26 |
| 4 | S2B/MSI | 2020, 5 and 21 days |
Step 2: resampling each wave band image of the 4-time-phase sentinel second-number image into an image with the resolution of 10m, uniformly converting the image into Gaussian-Ke-Lv projection, and cutting out a remote sensing image of the test area according to the range of the test area.
Step 3: extracting reflectivity (ρ) of each wave band (except 10 th wave band) of pixels in the sentinel images of all crop ground actual measurement sample points in 4 time phases 1 、ρ 2 、ρ 3 、ρ 4 、ρ 5 、ρ 6 、ρ 7 、ρ 8 、ρ 8A 、ρ 9 、ρ 11 、ρ 12 ) Vegetation index NDVI, NDVI GREEN 、RVI、RVI GREEN 、SR NIR/RE 、SR RED/GREEN 、SR RED/RE 、VARI GREEN TVI, SAVI, DVI, DDVI, EVI, LSWI, TDVI, OSAVI, NLI and MNLI.
And (3) carrying out optimal characteristic combination analysis on the remote sensing images of the research areas in 4 time phases, and determining the optimal time phases and the corresponding optimal characteristic combinations (see table 2).
Table 2 test zone best remote sensing feature-time phase combination
Step 4: taking the optimal characteristic combination of pixels of all crop sample points actually measured on the ground on a sentinel second remote sensing image of month 26 in 2020 as a training sample, and training the random forest classifier to obtain a trained random forest classifier; and inputting the second satellite remote sensing image of the guard II in the research area to be monitored into a trained random forest classifier for crop classification, extracting a milk vetch classification result as shown in fig. 2, and outputting the result as a shp format.
Step 5: and calculating and obtaining the planting area of the milk vetch in the test area based on ARCGIS software.
Claims (5)
1. A method for monitoring the planting area of Astragalus sinicus based on satellite remote sensing images is characterized by comprising the following steps: the method comprises the following steps:
step 1: acquiring multi-temporal remote sensing images of a research area and longitude and latitude data of actual measurement sample points of all crops on the ground within the range of the research area; the actual measurement sample points of all crops on the ground in the research area range comprise actual measurement sample points of milk vetch on the ground in the research area range and actual measurement sample points of other crops on the ground in the same season in the research area range;
step 2: preprocessing the multi-temporal remote sensing image of the research area to obtain the remote sensing image of the research area;
step 3: carrying out optimal feature combination analysis on remote sensing images of all research areas, and determining an optimal time phase and an optimal feature combination;
step 4: selecting the most suitable time phase remote sensing image of the research area according to the most suitable time phase;
step 5: training the random forest classification model by taking the optimal characteristic combination of pixels on the remote sensing image of all crop actual measurement sample points on the ground in the research area in the most suitable time phase of the research area as a training sample to obtain a trained random forest classification model;
step 6: inputting the remote sensing images of the research area to be monitored into a trained random forest classification model to obtain a crop classification result of the research area, and extracting a astragalus sinicus remote sensing image classification result of the research area from the crop classification result;
step 7: and outputting the classification result of the astragalus membranaceus remote sensing images in the research area as a vectorization file, and carrying out area statistics on the vectorization file by utilizing GIS software to obtain the planting area of the astragalus membranaceus.
2. The method for monitoring the planting area of astragalus sinicus based on satellite remote sensing images according to claim 1, wherein the method comprises the following steps of: the remote sensing image of each time phase of the research area comprises satellite remote sensing images of the key growth period of the ground milk vetch in the range of the research area.
3. The method for monitoring the planting area of astragalus sinicus based on satellite remote sensing images according to claim 2, wherein the method comprises the following steps of: the pretreatment of the multi-temporal remote sensing image of the research area specifically comprises the following steps:
the remote sensing image of each time phase is preprocessed as follows:
s210: resampling each wave band image of the remote sensing image of each time phase to obtain an image with the resolution of 10 m;
s220: unifying the images with the resolution of 10m by adopting Gaussian-Kelvin projection to obtain unified remote sensing images;
s230: and cutting and embedding the unified remote sensing image according to the range of the research area to obtain the remote sensing image of the research area in the time phase.
4. The method for monitoring the planting area of astragalus sinicus based on satellite remote sensing images according to claim 3, wherein the method comprises the following steps of: the step 3 specifically comprises the following steps:
the remote sensing image of the research area of each time phase is operated as follows:
s310: according to longitude and latitude data of all crop actual measurement sampling points on the ground in the research area, extracting pixels on a research area remote sensing image of all crop actual measurement sampling points on the ground in the research area in the current time phase, and acquiring reflectivity values of the pixels in each wave band;
s320: calculating by utilizing a wave band to obtain a normalized vegetation index, a green wave band normalized vegetation index, a specific vegetation index, a green wave band specific vegetation index, a near infrared and red wave band specific vegetation index, a red-green wave band specific vegetation index, a red-red wave band specific vegetation index, a green wave band atmospheric resistance vegetation index, a conversion vegetation index, a soil regulation vegetation index, a difference vegetation index, a reciprocal difference vegetation index, an enhanced vegetation index, a land water index, a conversion difference vegetation index, an optimized soil regulation vegetation index, a nonlinear vegetation index and an improved nonlinear vegetation index of pixels on a remote sensing image of a research area in a current time phase of all crop actual measurement sample points on the ground within the research area;
s330: taking the reflectivity value obtained in the step S310 and each index obtained in the step S320 as characteristic parameters, and constructing an initial characteristic parameter data set;
s340: the importance of each characteristic difference parameter is obtained by calculating the root mean square error reduction value of each characteristic parameter; deleting the characteristic parameter with the minimum root mean square error reduction value of the characteristic parameter, and updating the characteristic parameter data set; inputting the updated characteristic parameter data set into a random forest classifier, and calculating the overall classification accuracy of the random forest classifier;
s350: repeatedly executing S340 until the feature parameter data set is an empty set, at this time, taking a group of feature parameters with the largest overall classification precision as the best feature combination of the time phase, and recording the overall classification precision as the maximum overall classification precision of the current time phase;
comparing the maximum value of the overall classification precision of each time phase, taking the time phase with the highest overall classification precision as the most suitable time phase, and taking the characteristic parameter of the most suitable time phase as the best characteristic combination.
5. The method for monitoring the planting area of astragalus sinicus based on satellite remote sensing images according to claim 1, wherein the method comprises the following steps of: the multi-temporal remote sensing image of the research area is obtained by observing the same research area at different times by using a middle-high resolution remote sensing satellite with a red-edge wave band.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211396518.2A CN116188793A (en) | 2022-11-09 | 2022-11-09 | Astragalus sinicus planting area monitoring method based on satellite remote sensing image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211396518.2A CN116188793A (en) | 2022-11-09 | 2022-11-09 | Astragalus sinicus planting area monitoring method based on satellite remote sensing image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116188793A true CN116188793A (en) | 2023-05-30 |
Family
ID=86446858
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211396518.2A Pending CN116188793A (en) | 2022-11-09 | 2022-11-09 | Astragalus sinicus planting area monitoring method based on satellite remote sensing image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116188793A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116935238A (en) * | 2023-07-07 | 2023-10-24 | 滁州学院 | Forest disturbance monitoring method, system, equipment and medium based on deep learning |
| CN117218531A (en) * | 2023-09-08 | 2023-12-12 | 国家海洋局南海规划与环境研究院 | Sea-land ecological staggered zone mangrove plant overground carbon reserve estimation method |
| CN117475325A (en) * | 2023-11-16 | 2024-01-30 | 中国科学院东北地理与农业生态研究所 | Automatic film-covered farmland information extraction method based on remote sensing image |
-
2022
- 2022-11-09 CN CN202211396518.2A patent/CN116188793A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116935238A (en) * | 2023-07-07 | 2023-10-24 | 滁州学院 | Forest disturbance monitoring method, system, equipment and medium based on deep learning |
| CN116935238B (en) * | 2023-07-07 | 2024-02-23 | 滁州学院 | Forest disturbance monitoring method, system, equipment and medium based on deep learning |
| CN117218531A (en) * | 2023-09-08 | 2023-12-12 | 国家海洋局南海规划与环境研究院 | Sea-land ecological staggered zone mangrove plant overground carbon reserve estimation method |
| CN117475325A (en) * | 2023-11-16 | 2024-01-30 | 中国科学院东北地理与农业生态研究所 | Automatic film-covered farmland information extraction method based on remote sensing image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108921885B (en) | Method for jointly inverting forest aboveground biomass by integrating three types of data sources | |
| CN106600434B (en) | Crop growth remote sensing monitoring method based on crop model and assimilation technology | |
| CN116188793A (en) | Astragalus sinicus planting area monitoring method based on satellite remote sensing image | |
| CN105740759B (en) | Semilate rice information decision tree classification approach based on feature extraction in multi-temporal data | |
| CN114821362B (en) | Multi-source data-based rice planting area extraction method | |
| CN111898503B (en) | Crop identification method and system based on cloud coverage remote sensing image and deep learning | |
| CN107527014A (en) | Crops planting area RS statistics scheme of sample survey design method at county level | |
| CN115481368B (en) | Vegetation coverage estimation method based on full remote sensing machine learning | |
| CN112836575B (en) | Multi-time-sequence image rice yield estimation method based on crop weather period | |
| Cao et al. | Mapping paddy rice using Landsat time series data in the Ganfu Plain irrigation system, Southern China, from 1988− 2017 | |
| CN109977991A (en) | Forest resourceies acquisition method based on high definition satellite remote sensing | |
| CN114120132A (en) | Crop yield estimation method and device combining meteorological remote sensing and red-edge wave band remote sensing | |
| CN112215090A (en) | Remote sensing rice mapping method integrating phenological knowledge and application thereof | |
| Li et al. | Mapping rice cropping systems using Landsat-derived renormalized index of normalized difference vegetation index (RNDVI) in the Poyang Lake Region, China | |
| CN114782840A (en) | Real-time wheat phenological period classification method based on unmanned aerial vehicle RGB images | |
| CN107437262B (en) | Crop planting area early warning method and system | |
| CN113408700A (en) | Convolutional neural network soil alkaline hydrolysis nitrogen analysis model construction system and method | |
| CN115880577A (en) | Remote sensing technology-based dynamic monitoring method for autumn soil preparation progress of cultivated land | |
| WO2023131949A1 (en) | A versatile crop yield estimator | |
| CN115909063A (en) | Medium-resolution rice extraction method and system | |
| CN115527108A (en) | Method for rapidly identifying water and soil loss artificial disturbance plots based on multi-temporal Sentinel-2 | |
| CN105974091B (en) | The remote sensing and quantizing detection method of hayashishita herbosa litter richness | |
| CN113408701A (en) | Convolutional neural network soil organic matter analysis model construction system and method | |
| CN112733780A (en) | System and method for constructing soil available phosphorus analysis model based on satellite images | |
| CN113435574A (en) | Convolutional neural network soil quick-acting potassium analysis model construction system and 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 |