CN112749597A - Crop area single-yield remote sensing estimation method based on GF1 high-resolution image - Google Patents
Crop area single-yield remote sensing estimation method based on GF1 high-resolution image Download PDFInfo
- Publication number
- CN112749597A CN112749597A CN201911055141.2A CN201911055141A CN112749597A CN 112749597 A CN112749597 A CN 112749597A CN 201911055141 A CN201911055141 A CN 201911055141A CN 112749597 A CN112749597 A CN 112749597A
- Authority
- CN
- China
- Prior art keywords
- crop
- ndvi
- yield
- year
- image
- 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
- 238000000034 method Methods 0.000 title claims abstract description 25
- 239000013598 vector Substances 0.000 claims description 10
- 238000012417 linear regression Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000012937 correction Methods 0.000 claims description 7
- 230000001419 dependent effect Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000011160 research Methods 0.000 claims description 5
- 238000003066 decision tree Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 230000000873 masking effect Effects 0.000 abstract 1
- 241000209140 Triticum Species 0.000 description 21
- 235000021307 Triticum Nutrition 0.000 description 21
- 238000012360 testing method Methods 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 238000013179 statistical model Methods 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
Abstract
The invention discloses a crop area single yield remote sensing estimation method based on GF1 high-resolution images. The method comprises the steps of interpreting and obtaining spatial distribution data of crops for more than four years, masking and obtaining an NDVI index image map of a crop distribution area, rectifying the NDVI index image, collecting the per-unit yield statistical data of target crops in a target area, establishing a crop per-unit yield prediction model, interpreting crop spatial distribution data of years needing to be predicted, selecting an image of a first crop vigorous growth period of the years needing to be predicted, rectifying the NDVI index of the years, predicting the per-unit yield value of the crops and evaluating the accuracy of crop per-unit yield prediction. According to the invention, through the technical idea of correcting the NDVI index value, a technical support is provided for stably and reliably predicting the yield per unit of the crop by using a high-resolution image, and the industrial trend of the current remote sensing yield estimation refinement is met.
Description
Technical Field
The invention belongs to the field of mapping remote sensing, and particularly relates to crop area single-yield remote sensing estimation based on GF1 high-resolution images.
Background
Currently, remote sensing estimation mainly uses the NDVI index of MODIS data as an estimation parameter, and establishes a regression statistical model with the annual yield of crops so as to estimate the yield. The NDVI index generally requires the use of a continuous NDVI index value for several consecutive years over different periods of growth of the crop. Through analyzing and researching the law between NDVI values of different growth periods of crops in consecutive years and crop yield, the optimal NDVI or the combined NDVI of different growth periods of the crops is determined, the optimal regression model is obtained, and the yield is inversely calculated.
With the deep development of the remote sensing industry, the remote sensing monitoring refinement is the trend of the development of the remote sensing technology in the future. The spatial resolution of MODIS is low, and the remote sensing production estimation requirement at the national level or the provincial level can be barely met, but the remote sensing production estimation requirement at the county level or the city level or even the village and town level can not be met at all.
Some experts and scholars have tried to use higher resolution images, such as Landsat, HJ, and SPOT, to perform remote sensing crop estimation with good results. However, their research is often based on selecting ideal regions in more ideal situations. In these areas, high-resolution images meeting quality requirements can be obtained within a fixed time every year, but in the actual estimation process, the temporal resolution of these images with higher spatial resolution often cannot meet the requirements. Only a small number of images may meet the quality requirements throughout the crop growth period, and the annual periods for these quality-meeting images are not the same and are completely irregular. Because the image period is different every year, the growth period of the crops is different, and the vegetation index value of the crops in each year is not well continuous and has the same period contrast. Therefore, when the high-resolution image is used for remote sensing estimation of yield, the annual crop vegetation index value may be greatly different, and a reliable regression statistical model is difficult to establish with the annual crop yield value, so that an accurate crop yield value is predicted.
In summary, the remote sensing estimated yield can meet certain requirements on a large scale (provincial level or national level), but the fine remote sensing estimated yield on a small scale, namely the county level and the city level, is far from meeting the requirements. However, the whole remote sensing industry, especially the agricultural remote sensing industry, has higher and higher requirements for refinement, and how to stably obtain accurate crop yield by applying a high-resolution image is a technical problem which needs to be solved urgently at present.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a crop area single-yield remote sensing estimation method based on a GF1 high-resolution image.
In order to achieve the purpose, the invention adopts the following technical scheme:
the crop area yield remote sensing estimation method based on the GF1 high-resolution image is characterized by comprising the following steps of:
1) the acquired high-grade first image data is used as a data source, and crop space distribution data of at least four years in a research area are obtained through automatic interpretation by constructing a decision tree classification method;
2) selecting a first-stage crop growth vigorous stage image of each year from the images, and obtaining an NDVI image map of the crop growth vigorous stage of each year by applying an NDVI calculation formula;
3) taking target crop distribution data corresponding to each year as a mask, and performing mask processing on the NDVI images of each year to obtain NDVI index images corresponding to crop distribution;
4) taking the crop distribution NDVI image corresponding to the earliest year in each year as a reference, correcting the NDVI index values of other years by the reference according to the technical idea specified by the histogram to obtain the corrected NDVI image of each year, and calculating to obtain the average value of the NDVI indexes of the crops in each year;
5) acquiring a target area target crop per unit yield statistical value published corresponding to the year through an official channel;
6) establishing a linear regression model between the average NDVI indexes of all the years and the per-unit yield statistic value of the target crop over the years;
7) acquiring distribution data of the predicted year crops and corresponding vigorous period images to obtain crop distribution NDVI images, correcting the NDVI images by taking an NDVI standard value during model construction as a reference, and calculating the average value of the predicted year NDVI of the crops after correcting the NDVI images;
8) substituting the NDVI mean value of the predicted year into the established model to obtain the yield per unit of the crop of the predicted year;
9) and (4) evaluating the accuracy of the crop yield per unit.
Preferably, the step 7) specifically comprises:
71) taking the obtained high-grade first image data as a data source, and automatically interpreting by constructing a decision tree classification method to obtain crop spatial distribution data of the forecast year research area;
72) selecting an image of the first crop growth vigorous period of the predicted year from the images, and applying an NDVI (normalized difference vegetation index) calculation formula to obtain an NDVI image map of the first crop growth vigorous period of the predicted year;
73) applying crop distribution data to perform mask processing on the NDVI image index map to obtain an NDVI index image map of a crop distribution area;
74) counting the NDVI index histogram of the crop distribution area of the earliest year in the predicted year and the step 4), correcting the NDVI index of the predicted year according to the specified thought of the histogram by taking the NDVI index histogram counted in the earliest year as a reference, and acquiring a corrected image of the NDVI index of the crop; and acquiring the average value of the NDVI of the crops in the target area based on the corrected image of the NDVI index of the crops in the predicted year.
Preferably, the image of the data source in step 1) needs to be preprocessed, the preprocessing includes radiometric calibration, atmospheric correction and orthometric correction, and the calculation method of the preprocessing is consistent.
Preferably, the step 9) is specifically: in the process of building and predicting the single-yield model, the year of the crop single-yield data published by a known official channel is selected as the predicted year, the single-yield prediction model is applied to predict the single-yield, and the single-yield prediction model is compared with the crop single-yield data published by the official channel to determine the accuracy of the single-yield prediction model.
Preferably, the data units of the statistical values in the step 5) are unified into kilograms/mu, and the data are used as the dependent variable vector of remote sensing estimation and inversion modeling.
Preferably, the step 6) is specifically: and constructing a linear regression model y which is ax + b by acquiring the target area crop NDVI mean value of each year as an independent variable vector and the official statistical data of the crop yield per unit of the corresponding year as a dependent variable vector, so as to obtain linear regression model parameters and a linear relation between the crop NDVI value and the crop yield per unit.
The invention has the beneficial effects that:
1. technical support is provided for timely and accurately acquiring single yield of county-level crops.
2. The estimation yield is more refined. In the past, MODIS image data are mostly used for estimating yield, the spatial resolution is low, and the method can only be used for estimating yield (unit yield) of crops in provincial or national scales. The invention takes the 16m image data of GF1 as the estimation data source, the spatial resolution is higher, the estimation result (per unit of production) is more precise, and the method can be used for estimating the production (per unit of production) of county-level and even township-level crops.
3. The requirements and tolerances on the temporal resolution of the images are greatly reduced. In the past, crop estimation (yield per unit) is carried out, and usually a multi-period time sequence remote sensing image is needed to carry out vegetation index analysis modeling inversion yield every year, but the method can model estimation (yield per unit) only by an image of a growth vigorous period of a crop every year without the need of the multi-period time sequence image.
4. The estimated yield result (the single yield value) is more stable and more accurate. In the past, crop yield estimation (yield per unit) is usually carried out by directly using an index value calculated by an NDVI formula to carry out analysis modeling and inversion yield, and whether the NDVI index value has deviation or not is not analyzed. However, the invention systematically corrects the NDVI index value, so that the uncertainty of the crop image period and the deviation of the estimated yield result caused by the NDVI systematic error can be better avoided.
Drawings
FIG. 1 is a flow chart of a crop area yield remote sensing estimation method based on GF1 high resolution images according to the present invention;
Detailed Description
In order to make the technical means, creation features, work flow and using method of the present invention easily understood and appreciated, the present invention is further explained below.
(1) Interpretation obtains crop spatial distribution data for at least four years. Acquiring high-resolution first-order 16m image data from a national resource satellite application center and preprocessing the image (radiometric calibration, atmospheric correction and orthorectification, and preprocessing algorithms need to be consistent); obtaining a training sample through field investigation; the target crop key phenological period, various characteristic parameters presented in the remote sensing image and DN values on various wave bands can generate regular changes. Non-target crops can be gradually removed by combining various characteristic parameters and different phenological periods among crops, and planting distribution of the target crops can be extracted with higher precision by combining spectral values of the target crops and a time sequence change rule of combined parameters along with time.
(2) And acquiring an NDVI index image map of the crop distribution area by using a mask. And selecting one image of the crops in the vigorous growth period from the interpretation images selected every year, and then applying an NDVI index calculation formula to obtain an NDVI index image map. And then, applying the crop distribution data of each year, and performing mask processing on the NDVI image index map of the corresponding year to obtain the NDVI index image map of the crop distribution area.
(3) And (5) correcting the NDVI index image. And (3) correcting the NDVI indexes of other years according to the reference by taking the image of the NDVI index of the crop distribution area in the first year of the selected year as the reference. Firstly, NDVI index histograms of crop distribution areas of all years are counted, then the NDVI histograms counted in the first year are used as reference, the NDVI indexes of other years are rectified according to the specified thought of the histograms, and a rectified crop NDVI index image map is obtained. And acquiring a target area crop NDVI mean value based on the corrected crop NDVI index image map, and using the target area crop NDVI mean value as an independent variable vector of subsequent remote sensing estimation inversion modeling.
(4) And collecting the per unit yield statistical data of the target crops in the target area. And acquiring the crop yield per unit statistical data of the target crops in the target area in the corresponding year through a statistical bureau or other official channels, wherein the unit needs to be unified into one kilogram/mu and is used as a dependent variable vector for the subsequent remote sensing yield estimation inversion modeling.
(5) And establishing a crop yield per unit prediction model. A linear regression model y ═ ax + b is constructed by acquiring the average value of NDVI of the target area crops in nearly four years as independent variable vectors and the crop yield per unit statistical data of corresponding years published by the authorities as dependent variable vectors, so as to obtain linear regression model parameters and the linear relation between the crop NDVI value and the crop yield per unit value.
(6) Crop spatial distribution data for the year for which the prediction is required is interpreted. Acquiring high-resolution 16m image data from a Chinese resource satellite application center and preprocessing the image (radiometric calibration, atmospheric correction and orthorectification, and preprocessing algorithms need to be consistent); obtaining a training sample through field investigation; the target crop key phenological period, various characteristic parameters presented in the remote sensing image and DN values on various wave bands can generate regular changes. Non-target crops can be gradually removed by combining various characteristic parameters and different phenological periods among crops, and planting distribution of the target crops can be extracted with higher precision by combining spectral values of the target crops and a time sequence change rule of combined parameters along with time.
(7) And selecting the image of the vigorous growth stage of the first-stage crop needing to be predicted for the year. And similarly, an NDVI index image map is obtained by applying an NDVI index calculation formula. And then, applying the crop distribution data to perform mask processing on the NDVI image index map to obtain the NDVI image index map of the crop distribution area.
(8) And (5) correcting the NDVI index of the predicted year. And correcting the NDVI of the predicted year according to the reference by taking the image map of the NDVI of the crop distribution area of the first year as the reference when the yield estimation inversion model is constructed. Firstly, calculating NDVI index histograms of crop distribution areas in a first year during prediction year and construction of an estimated inversion model, then correcting the NDVI indexes of the prediction year by taking the NDVI histograms calculated in the first year as reference according to the specified thought of the histograms, and obtaining a corrected image map of the NDVI indexes of the crops. And acquiring the average value of the NDVI of the crops in the target area based on the corrected image of the NDVI index of the crops in the predicted year.
(9) And predicting the yield per unit of the crops. And substituting the NDVI mean value of the target area crops after deviation correction in the predicted year into the constructed crop yield estimation linear regression model to obtain the predicted crop yield per unit.
(10) And (4) evaluating the accuracy of the crop yield per unit. In the process of building and predicting the single-yield model, the year of certain known crop single-yield data (the crop single-yield data published by an official channel) is set as the predicted year, the single-yield prediction model is applied to predict the single yield, and the single-yield prediction model is compared with the crop single-yield data published by the official channel to determine the accuracy of the single-yield prediction model.
According to the above embodiment, a specific test was conducted with a certain market as a case area, winter wheat as a case crop, and 14, 15, 16, 17, and 18 years as case years.
Selecting GF 116 m remote sensing images of 14 years, 15 years, 16 years, 17 years and 18 years as data sources, wherein the image periods are images of winter wheat in a growth vigorous period. The specific selected image period is shown in table 1.
Based on the remote sensing image data of the 5 years, the wheat distribution data of a certain city and another city for five years are interpreted as the distribution basic data of the test.
TABLE 1 image times of a certain city and another city
Regional unit yield statistical data is collected. And (3) through online query of a certain provincial statistics office, collecting winter wheat regional unit yield data of 14, 15, 16, 17 and 18 years in a certain city and another city as quasi-truth value data of winter wheat unit yields of the certain city and another city, and using the data for training an assessment model and verifying precision.
The single yield estimation result of winter wheat in a certain market is as follows:
(1) conjecture of 18 years in 14, 15, 16 and 17 years
And (3) using the winter wheat quasi-truth value data of 14 years, 15 years, 16 years and 17 years in a certain city as modeling data, and obtaining a relation model between the remote sensing vegetation index and the single yield by using the 18-year winter wheat quasi-truth value data without participating in modeling. The winter wheat yield per unit of 18 years and other years in a certain market is inverted through the relation model, the obtained 18-year estimated yield per unit trend is consistent with the quasi-true value yield per unit trend, the absolute value precision of the yield per unit reaches 98.66%, and the total yield per unit test condition is shown in table 2.
TABLE 2A market truth value for a unit yield and an estimated unit yield
(2) Conjecture of 17 years in 14, 15, 16 and 18 years
And (3) using the winter wheat quasi-truth value data of 14 years, 15 years, 16 years and 18 years in a certain city as modeling data, and obtaining a relation model between the remote sensing vegetation index and the single yield by using the winter wheat quasi-truth value data of 17 years without participating in modeling. The winter wheat yield per unit of 17 years and other years in a certain market is inverted through the relation model, the obtained 17-year estimated yield per unit trend is consistent with the quasi-true value yield per unit trend, the absolute value precision of the yield per unit reaches 98.64%, and the total yield per unit test condition is shown in table 3.
TABLE 3 one market truth value and estimated yield
(3) Conjecture of 16 years in 14, 15, 17 and 18 years
And (3) using the winter wheat quasi-truth value data of 14 years, 15 years, 17 years and 18 years in a certain city as modeling data, and obtaining a relation model between the remote sensing vegetation index and the single yield by using the 16-year winter wheat quasi-truth value data without participating in modeling. The winter wheat yield per unit of 16 years and other years in a certain market is inverted through the relation model, the obtained 16-year estimated yield per unit trend is consistent with the quasi-true value yield per unit trend, the absolute value precision of the yield per unit reaches 98.52%, and the total yield per unit test condition is shown in table 4.
TABLE 4 case of a market truth value for a unit yield and an estimated unit yield
(4) Presuming 15 years in 14, 16, 17 and 18 years
And (3) using the winter wheat quasi-truth value data of 14 years, 16 years, 17 years and 18 years in a certain city as modeling data, and obtaining a relation model between the remote sensing vegetation index and the single yield by using the winter wheat quasi-truth value data of 15 years without participating in modeling. The winter wheat yield per unit of 15 years and other years in a certain market is inverted through the relation model, the obtained 15-year estimated yield per unit trend is consistent with the quasi-true value yield per unit trend, the absolute value precision of the yield per unit reaches 99.52%, and the total yield per unit test condition is shown in table 5.
TABLE 5A market truth value and estimated single-yield situation
(5) Presuming 14 years in 15, 16, 17 and 18 years
And (3) taking the winter wheat quasi-truth value data of 15 years, 16 years, 17 years and 18 years in a certain city as modeling data, and obtaining a relation model between the remote sensing vegetation index and the single yield by using the winter wheat quasi-truth value data of 14 years without participating in modeling. The winter wheat yield per unit of 14 years and other years in a certain market is inverted through the relation model, the obtained 14-year estimated yield per unit trend is consistent with the quasi-true value yield per unit trend, the absolute value precision of the yield per unit reaches 97.96%, and the total yield per unit test condition is shown in table 6.
TABLE 6 one market truth value and estimated one-unit yield
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed.
Claims (6)
1. The crop area yield remote sensing estimation method based on the GF1 high-resolution image is characterized by comprising the following steps of:
1) the acquired high-grade first image data is used as a data source, and crop space distribution data of at least four years in a research area are obtained through automatic interpretation by constructing a decision tree classification method;
2) selecting a first-stage crop growth vigorous stage image of each year from the images, and obtaining an NDVI image map of the crop growth vigorous stage of each year by applying an NDVI calculation formula;
3) taking target crop distribution data corresponding to each year as a mask, and performing mask processing on the NDVI images of each year to obtain NDVI index images corresponding to crop distribution;
4) taking the crop distribution NDVI image corresponding to the earliest year in each year as a reference, correcting the NDVI index values of other years by the reference according to the technical idea specified by the histogram to obtain the corrected NDVI image of each year, and calculating to obtain the average value of the NDVI indexes of the crops in each year;
5) acquiring a target area target crop per unit yield statistical value published corresponding to the year through an official channel;
6) establishing a linear regression model between the average NDVI indexes of all the years and the per-unit yield statistic value of the target crop over the years;
7) acquiring distribution data of the predicted year crops and corresponding vigorous period images to obtain crop distribution NDVI images, correcting the NDVI images by taking an NDVI standard value during model construction as a reference, and calculating the average value of the predicted year NDVI of the crops after correcting the NDVI images;
8) substituting the NDVI mean value of the predicted year into the established model to obtain the yield per unit of the crop of the predicted year;
9) and (4) evaluating the accuracy of the crop yield per unit.
2. The remote crop area yield estimation method based on GF1 high resolution images according to claim 1, wherein the step 7) comprises:
71) taking the obtained high-grade first image data as a data source, and automatically interpreting by constructing a decision tree classification method to obtain crop spatial distribution data of the forecast year research area;
72) selecting an image of the first crop growth vigorous period of the predicted year from the images, and applying an NDVI (normalized difference vegetation index) calculation formula to obtain an NDVI image map of the first crop growth vigorous period of the predicted year;
73) applying crop distribution data to perform mask processing on the NDVI image index map to obtain an NDVI index image map of a crop distribution area;
74) counting the NDVI index histogram of the crop distribution area of the earliest year in the predicted year and the step 4), correcting the NDVI index of the predicted year according to the specified thought of the histogram by taking the NDVI index histogram counted in the earliest year as a reference, and acquiring a corrected image of the NDVI index of the crop; and acquiring the average value of the NDVI of the crops in the target area based on the corrected image of the NDVI index of the crops in the predicted year.
3. The GF1 high-resolution image-based crop area yield remote sensing estimation method according to claim 1, wherein the image of the data source in step 1) is further preprocessed, the preprocessing includes radiometric calibration, atmospheric correction and ortho correction, and the calculation method of the preprocessing is consistent.
4. The remote crop area yield estimation method based on GF1 high resolution images according to claim 1, wherein the step 9) is specifically: in the process of building and predicting the single-yield model, the year of the crop single-yield data published by a known official channel is selected as the predicted year, the single-yield prediction model is applied to predict the single-yield, and the single-yield prediction model is compared with the crop single-yield data published by the official channel to determine the accuracy of the single-yield prediction model.
5. The remote crop area yield remote sensing estimation method based on GF1 high resolution images according to claim 1, wherein the data units of the statistics value in step 5) are unified into kg/mu, and the data is used as a dependent variable vector of remote sensing estimation inversion modeling.
6. The remote crop area yield estimation method based on GF1 high resolution images according to claim 1, wherein the step 6) is specifically: and constructing a linear regression model y which is ax + b by acquiring the target area crop NDVI mean value of each year as an independent variable vector and the official statistical data of the crop yield per unit of the corresponding year as a dependent variable vector, so as to obtain linear regression model parameters and a linear relation between the crop NDVI value and the crop yield per unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911055141.2A CN112749597A (en) | 2019-10-31 | 2019-10-31 | Crop area single-yield remote sensing estimation method based on GF1 high-resolution image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911055141.2A CN112749597A (en) | 2019-10-31 | 2019-10-31 | Crop area single-yield remote sensing estimation method based on GF1 high-resolution image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112749597A true CN112749597A (en) | 2021-05-04 |
Family
ID=75644636
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911055141.2A Pending CN112749597A (en) | 2019-10-31 | 2019-10-31 | Crop area single-yield remote sensing estimation method based on GF1 high-resolution image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112749597A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107527014A (en) * | 2017-07-20 | 2017-12-29 | 武汉珈和科技有限公司 | Crops planting area RS statistics scheme of sample survey design method at county level |
| CN108982369A (en) * | 2018-04-28 | 2018-12-11 | 中国农业大学 | Merge the plot scale crop condition monitoring method of GF-1WFV and MODIS data |
| CN108985260A (en) * | 2018-08-06 | 2018-12-11 | 航天恒星科技有限公司 | A kind of remote sensing and meteorological integrated rice yield estimation method |
| CN109509112A (en) * | 2018-10-31 | 2019-03-22 | 武汉珈和科技有限公司 | Global soybean and main maize area yield assessment method and system based on MODIS NDVI |
| CN109829234A (en) * | 2019-01-30 | 2019-05-31 | 北京师范大学 | A kind of across scale Dynamic High-accuracy crop condition monitoring and yield estimation method based on high-definition remote sensing data and crop modeling |
-
2019
- 2019-10-31 CN CN201911055141.2A patent/CN112749597A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107527014A (en) * | 2017-07-20 | 2017-12-29 | 武汉珈和科技有限公司 | Crops planting area RS statistics scheme of sample survey design method at county level |
| CN108982369A (en) * | 2018-04-28 | 2018-12-11 | 中国农业大学 | Merge the plot scale crop condition monitoring method of GF-1WFV and MODIS data |
| CN108985260A (en) * | 2018-08-06 | 2018-12-11 | 航天恒星科技有限公司 | A kind of remote sensing and meteorological integrated rice yield estimation method |
| CN109509112A (en) * | 2018-10-31 | 2019-03-22 | 武汉珈和科技有限公司 | Global soybean and main maize area yield assessment method and system based on MODIS NDVI |
| CN109829234A (en) * | 2019-01-30 | 2019-05-31 | 北京师范大学 | A kind of across scale Dynamic High-accuracy crop condition monitoring and yield estimation method based on high-definition remote sensing data and crop modeling |
Non-Patent Citations (3)
| Title |
|---|
| 唐泽艳;魏永亮;: "绿潮卫星遥感监测技术应用研究", 遥感信息, no. 03, pages 3 * |
| 祝国祥;: "林地资源管理中像元二分模型定向定量分析探究", 林业调查规划, no. 05 * |
| 郝建亭;杨武年;李玉霞;郝建园;: "基于FLAASH的多光谱影像大气校正应用研究", 遥感信息, no. 03 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108241905B (en) | Method for predicting soil and/or plant condition | |
| CN108985260B (en) | Remote sensing and meteorological integrated rice yield estimation method | |
| CN110751019B (en) | High-resolution image crop automatic extraction method and device based on deep learning | |
| CN109597968B (en) | SMT big data-based solder paste printing performance influence factor analysis method | |
| Wayte et al. | An effective harvest strategy using improved catch-curves | |
| CN102495005A (en) | Method for diagnosing crop water deficit through hyperspectral image technology | |
| CN111126662A (en) | Irrigation decision making method, device, server and medium based on big data | |
| CN107895136B (en) | Coal mine area identification method and system | |
| CN113723541B (en) | Slope displacement prediction method based on hybrid intelligent algorithm | |
| CN111814866A (en) | Disease and pest early warning method and device, computer equipment and storage medium | |
| CN108763673B (en) | Land use change driving force screening method and device based on LASSO regression | |
| CN101446828A (en) | Nonlinear process quality prediction method | |
| CN112749597A (en) | Crop area single-yield remote sensing estimation method based on GF1 high-resolution image | |
| CN111177495A (en) | Method for intelligently identifying data content and generating corresponding industry report | |
| CN114625781A (en) | Commodity housing value-based batch evaluation method | |
| KR20210069987A (en) | Crop growth diagnosis system and method using image | |
| US20230005084A1 (en) | Method and system for dynamically predicting deoxynivalenol content of wheat at harvest | |
| CN110569277A (en) | Method and system for automatically identifying and classifying configuration data information | |
| CN117540327B (en) | Enterprise environment autonomous management data acquisition and processing system | |
| CN113642834B (en) | Task importance evaluation method and system based on task attribute priority mapping | |
| CN117390008B (en) | Method and device for processing measurement data of multi-type observation instrument | |
| CN117274825B (en) | Crop yield evaluation method and system based on remote sensing technology | |
| CN117253140A (en) | Yield estimation method and system based on multi-scale crop full-growth-period agricultural condition | |
| CN117520910A (en) | Method and system for predicting user satisfaction in business handling system | |
| CN112712397A (en) | Service internet optimization management method based on service population evolution prediction model |
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 |