CN117253140A - Yield estimation method and system based on multi-scale crop full-growth-period agricultural condition - Google Patents
Yield estimation method and system based on multi-scale crop full-growth-period agricultural condition Download PDFInfo
- Publication number
- CN117253140A CN117253140A CN202310855207.6A CN202310855207A CN117253140A CN 117253140 A CN117253140 A CN 117253140A CN 202310855207 A CN202310855207 A CN 202310855207A CN 117253140 A CN117253140 A CN 117253140A
- Authority
- CN
- China
- Prior art keywords
- image
- information
- remote sensing
- agricultural
- estimated
- 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 32
- 238000005192 partition Methods 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 19
- 239000002689 soil Substances 0.000 claims description 30
- 238000012937 correction Methods 0.000 claims description 16
- 238000000605 extraction Methods 0.000 claims description 16
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 238000004519 manufacturing process Methods 0.000 claims description 10
- 230000000694 effects Effects 0.000 claims description 9
- 238000013316 zoning Methods 0.000 claims description 9
- 238000000513 principal component analysis Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 238000012417 linear regression Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 4
- 238000002203 pretreatment Methods 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 description 6
- 238000001914 filtration Methods 0.000 description 4
- 238000012271 agricultural production Methods 0.000 description 3
- 238000001479 atomic absorption spectroscopy Methods 0.000 description 2
- 238000004737 colorimetric analysis Methods 0.000 description 2
- 238000005520 cutting process Methods 0.000 description 2
- 238000013508 migration Methods 0.000 description 2
- 230000005012 migration Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000035558 fertility Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- 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
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- 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
- G06V10/54—Extraction of image or video features relating to texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marine Sciences & Fisheries (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Computing Systems (AREA)
- Mining & Mineral Resources (AREA)
- Artificial Intelligence (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Processing (AREA)
Abstract
The invention provides a multi-scale crop full-growth-period agricultural condition-based yield estimation method and system, wherein the method comprises the following steps: dividing an agricultural ecological partition based on the crop planting space-time consistency and historical agricultural disaster data; acquiring land information, image information, remote sensing data and weather information of an agricultural ecological partition; preprocessing the image information to obtain an estimated image; establishing an image estimated yield model based on the estimated yield image, the land information and the meteorological information, and carrying out image estimated yield on the agricultural ecological subareas based on the image estimated yield model; based on the remote sensing data, a remote sensing estimated yield model is established, and remote sensing estimated yield is carried out on the agricultural ecological partition based on the remote sensing estimated yield model; and obtaining a crop estimated model based on the image estimated model and the remote sensing estimated model.
Description
Technical Field
The invention relates to the technical field of crop growth, in particular to a crop yield estimation method and system based on the full-growth-period agricultural condition of multi-scale crops.
Background
In agricultural production, the estimation of crop yield is not only to estimate yield, but also affects the formulation of agricultural production plan. Therefore, more accurate estimated production information is obtained, and a reference can be provided for agricultural production.
In the past estimated production work, a layer-by-layer statistics and layer-by-layer reporting method is often needed, so that the work efficiency is low, and the information is relatively lagged. With the development of scientific technology, the application of satellite remote sensing makes crop estimation fast and efficient. However, the satellite remote sensing obtains the ground surface instantaneous information and has a certain transit period, so that the remote sensing has the problem of weak continuity and the like. Meanwhile, most of the conventional remote sensing estimation methods are statistical models, and quantitative description on the growth process and yield formation of crops cannot be realized. Therefore, there is a need for a multi-scale estimation method based on total fertility.
Disclosure of Invention
The invention aims to provide a crop yield estimation method and system based on the full growth period of a multi-scale crop, which are characterized in that crop image information is acquired in real time, texture characteristic parameters of the image are extracted, principal component analysis is carried out on the image, a quality estimation model is built, the quality estimation model is corrected by adopting soil information and meteorological factors in consideration of the influence of the soil factors and the meteorological factors on the crop growth, a yield estimation model based on soil, meteorological factors and image information is obtained, and the crop yield data predicted by the image yield estimation model and the crop yield data predicted by the remote sensing yield estimation model are subjected to linear analysis by the historical yields of an agricultural ecological partition, so that the linear relation between the crop yield and the crop yield data predicted by the image yield estimation model and the crop yield data predicted by the remote sensing yield estimation model is obtained.
In order to achieve the above purpose, the present invention provides a method for estimating agricultural condition based on full growth period of multi-scale crops, comprising:
s1, dividing an agricultural ecological partition based on crop planting space-time consistency and historical agricultural disaster data;
s2, acquiring land information, image information, remote sensing data and weather information of the agricultural ecological subareas;
s3, preprocessing the image information to obtain an estimated image;
s4, establishing an image estimation model based on the estimation image, the land information and the meteorological information, and carrying out image estimation on the agricultural ecological subareas based on the image estimation model;
s5, establishing a remote sensing yield estimation model based on the remote sensing data, and carrying out remote sensing yield estimation on the agricultural ecological subareas based on the remote sensing yield estimation model;
and S6, obtaining a crop estimated model based on the image estimated model and the remote sensing estimated model.
Optionally, the method of preprocessing includes: color space conversion, component extraction and texture feature parameter extraction;
the color space conversion is used for converting the image information from RGB space to HSI space;
the component extraction is used for extracting the component with the best segmentation effect from H, S, I components;
the texture feature parameter extraction is used for extracting texture feature parameters of the image information.
Optionally, the land information includes: soil K + Content of soil NO 3 - Content, soil pH value and soil water content.
Optionally, the method for obtaining the weather information includes:
determining position information of an area to be estimated, and acquiring the position of a weather station based on the position information;
and selecting two groups of weather stations positioned at two ends of the estimated area as weather estimation stations, and estimating the weather information of the estimated area based on the weather data of the weather estimation stations.
Optionally, the S4 includes:
calculating the texture characteristic parameters by adopting principal component analysis to obtain principal component values of the texture characteristic parameters;
establishing a quality estimation model based on the principal component values by adopting a multiple linear regression method;
and carrying out influence correction on the quality estimation model based on the land information and the meteorological information to obtain the image estimation model.
The invention also provides a multi-scale crop full-growth-period agricultural condition-based yield estimation system, which comprises:
the system comprises a zoning module, an acquisition module, a preprocessing module, an image estimation model module, a remote sensing estimation model module and a crop estimation model module;
the zoning module is used for zoning the agricultural ecology based on the crop planting space-time consistency and the historical agricultural disaster data;
the acquisition module is used for acquiring land information, image information, remote sensing data and meteorological information of the agricultural ecological partition;
the preprocessing module is used for preprocessing the image information to obtain an estimated image;
the image estimation model module is used for establishing an image estimation model based on the estimation image, the land information and the meteorological information and carrying out image estimation on the agricultural ecological subarea based on the image estimation model;
the remote sensing estimated production model module is used for establishing a remote sensing estimated production model based on the remote sensing data and carrying out remote sensing estimated production on the agricultural ecological subareas based on the remote sensing estimated production model;
the crop estimation model module is used for obtaining a crop estimation model based on the image estimation model and the remote sensing estimation model.
Optionally, the method for preprocessing the image information by the preprocessing module includes:
converting the image information from RGB space to HSI space by adopting color space conversion;
extracting the component with the best segmentation effect from the image information H, S, I component of the HSI space;
and extracting texture characteristic parameters of the image information.
Optionally, the acquisition module includes: the device comprises a first acquisition unit, a second acquisition unit, a third acquisition unit and a fourth acquisition unit;
the first acquisition unit is used for acquiring the land information;
the second acquisition unit is used for acquiring the image information;
the third acquisition unit is used for acquiring the land information;
the fourth acquisition unit is used for acquiring the remote sensing information.
Optionally, the image estimation model module includes: the device comprises a calculation unit, a construction unit and a correction unit;
the computing unit is used for computing the texture characteristic parameters by adopting principal component analysis to obtain principal component values of the texture characteristic parameters;
the construction unit is used for constructing a quality estimation model based on the principal component values by adopting a multiple linear regression method;
and the correction unit is used for performing influence correction on the quality estimation model based on the land information and the meteorological information to obtain the image estimation model.
Compared with the prior art, the invention has the beneficial effects that:
the invention can ensure the authenticity and the high efficiency of the data source by collecting the crop image information in real time; the quality prediction model is constructed by extracting texture characteristic parameters of an image and analyzing principal components of the image, the quality prediction model is corrected by adopting soil information and meteorological information in consideration of the influence of the soil factors and the meteorological factors on the crop growth, an estimated yield model based on soil, meteorological and image information is obtained, and the crop yield data predicted by the image estimated yield model and the crop yield data predicted by the remote sensing estimated yield model are subjected to linear analysis by the historical yields of the agricultural ecological partition, so that the linear relation between the crop yield and the crop yield data predicted by the image estimated yield model and the crop yield data predicted by the remote sensing estimated yield model is obtained. The obtained estimated yield data can accurately reflect the actual yield of crops.
Drawings
For a clearer description of the technical solutions of the present invention, the drawings that are required to be used in the embodiments are briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that, without inventive effort, other drawings may be obtained by those skilled in the art according to the drawings:
fig. 1 is a schematic flow chart of an estimation method based on the full-growth-period agricultural condition of a multi-scale crop according to an embodiment of the invention.
Detailed Description
For a better understanding of the technical features, objects and effects of the invention, the invention will be described in more detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the present invention. It should be noted that these drawings are in a very simplified form and use non-precise ratios for convenience and clarity in assisting in describing the present invention.
While the invention has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Example 1
As shown in fig. 1, a flow chart of a method for estimating agricultural conditions during whole growth period of a multi-scale crop according to this embodiment includes:
s1, dividing an agricultural ecological partition based on crop planting space-time consistency and historical agricultural disaster data;
because the limited ground samples exist in the county crop yield prediction, the regional migration precision of the yield estimation algorithm cannot meet the precise agricultural requirements of county, and therefore the space-time consistency agricultural ecological subareas taking counties as units are further defined according to the space-time consistency of crop agricultural planting and the historical agricultural disaster data.
S2, acquiring land information, image information, remote sensing data and weather information of the agricultural ecological subareas;
in this embodiment, the land data includes: soil K + Content of soil NO 3 - Content, soil PH, soil moisture content, and the like. Wherein, soil K + The content is measured by atomic absorption spectrometry; soil NO 3 - The content is obtained by colorimetric method; the PH value of the soil is obtained by adopting a potential method; the water content of the soil is measured by neutron instrument.
The image information is collected by the drone or camera. In order to have the same image acquisition conditions for the same region to be estimated, image information is acquired simultaneously for different divided regions.
Remote sensing data is obtained through a professional website.
The method for obtaining the weather information comprises the following steps:
determining position information of an area to be estimated, and acquiring the position of a weather station based on the position information;
two groups of weather stations which are positioned at two ends of the area with estimated yield and have the nearest distance are selected as weather estimation stations, and a linear expression is constructed for the two weather estimation stations by adopting a linear analysis method based on the distance based on weather data of the weather estimation stations. And acquiring weather information of the region to be estimated based on the distance between the region to be estimated and the weather estimation station. The weather information includes: temperature, humidity, etc.
S3, preprocessing the image information to obtain an estimated image;
in this embodiment, the pretreatment method includes: color space conversion, component extraction, and texture feature parameter extraction.
Wherein the color space conversion is used for converting the image information from RGB space to HSI space; the conversion method comprises the following steps:
for simplicity of the formula, a parameter θ is introduced, and the calculation formula is as follows:
component extraction is used for extracting the component with the best segmentation effect from H, S, I components;
in this embodiment, H, I, S component values of the image information are obtained, image cutting is performed on each component by using a fuzzy C-means clustering algorithm, and finally, the results of the images under each component are compared, and the component with the best effect is extracted.
The texture feature parameter extraction is used for extracting texture feature parameters of image information.
In this embodiment, the texture feature parameters include: mean, standard deviation, smoothness, third order moment, consistency, and entropy.
S4, establishing an image estimated yield model based on the estimated yield image, the land information and the meteorological information, and carrying out image estimated yield on the agricultural ecological partition based on the image estimated yield model;
specifically, the principal component analysis is adopted to calculate the texture characteristic parameters, so as to obtain principal component values of the texture characteristic parameters;
establishing a quality estimation model based on the principal component values by adopting a multiple linear regression method;
and carrying out influence correction on the quality estimation model based on the land information and the meteorological information to obtain an image estimation model.
S5, establishing a remote sensing estimated yield model based on the remote sensing data, and carrying out remote sensing estimated yield on the agricultural ecological partition based on the remote sensing estimated yield model;
specifically, firstly, collecting leaf area index and other data of agricultural ecological partition crops; and downloading the original remote sensing data of the agricultural ecological partition through a professional website, and performing geometric correction on the original remote sensing data.
And then, carrying out data correction on the original remote sensing data by a Savitzky-Golay filtering method.
Based on the collected leaf area and the meteorological information, a WOFOST model is coupled by adopting a set Kalman filtering assimilation algorithm, and a remote sensing estimated yield model is obtained to predict crop yield of the agricultural ecological partition.
And S6, obtaining a crop estimated model based on the image estimated model and the remote sensing estimated model.
And carrying out linear analysis on the crop yield data predicted by the image estimation model and the crop yield data predicted by the remote sensing estimation model through the historical yields of the agricultural ecological partition to obtain a linear relation between the crop yield and the crop yield data predicted by the image estimation model and the crop yield data predicted by the remote sensing estimation model, and taking the linear relation as an estimation model.
Example two
The embodiment provides an estimation system based on the agricultural condition of the multi-scale crops in the whole growth period, comprising:
the system comprises a zoning module, an acquisition module, a preprocessing module, an image estimation model module, a remote sensing estimation model module and a crop estimation model module;
the zoning module is used for zoning the agricultural ecology based on the crop planting space-time consistency and the historical agricultural disaster data;
because the limited ground samples exist in the county crop yield prediction, the regional migration precision of the yield estimation algorithm cannot meet the precise agricultural requirements of the county, and therefore the regional division module further determines the space-time consistency agricultural ecological subareas taking the county as a unit according to the space-time consistency of crop agricultural planting and the historical agricultural disaster data.
The acquisition module is used for acquiring land information, image information, remote sensing data and meteorological information of the agricultural ecological subareas;
in this embodiment, the acquisition module includes: the device comprises a first acquisition unit, a second acquisition unit, a third acquisition unit and a fourth acquisition unit; the first acquisition unit is used for acquiring land information; the second acquisition unit is used for acquiring image information; the third acquisition unit is used for acquiring land information; the fourth acquisition unit is used for acquiring remote sensing information.
Wherein, the land data includes: soil K + Content of soil NO 3 - Content, soil PH, soil moisture content, and the like. Wherein, soil K + The content is measured by atomic absorption spectrometry; soil NO 3 - The content is obtained by colorimetric method; the PH value of the soil is obtained by adopting a potential method; the water content of the soil is measured by neutron instrument.
The image information is collected by the drone or camera. In order to have the same image acquisition conditions for the same region to be estimated, image information is acquired simultaneously for different divided regions.
Remote sensing data is obtained through a professional website.
The method for obtaining the weather information comprises the following steps:
determining position information of an area to be estimated, and acquiring the position of a weather station based on the position information;
two groups of weather stations which are positioned at two ends of the area with estimated yield and have the nearest distance are selected as weather estimation stations, and a linear expression is constructed for the two weather estimation stations by adopting a linear analysis method based on the distance based on weather data of the weather estimation stations. And acquiring weather information of the region to be estimated based on the distance between the region to be estimated and the weather estimation station. The weather information includes: temperature, humidity, etc.
The preprocessing module is used for preprocessing the image information to obtain an estimated image;
in this embodiment, the method for preprocessing by the preprocessing module includes: color space conversion, component extraction, and texture feature parameter extraction.
Wherein the color space conversion is used for converting the image information from RGB space to HSI space; the conversion method comprises the following steps:
for simplicity of the formula, a parameter θ is introduced, and the calculation formula is as follows:
component extraction is used for extracting the component with the best segmentation effect from H, S, I components;
in this embodiment, H, I, S component values of the image information are obtained, image cutting is performed on each component by using a fuzzy C-means clustering algorithm, and finally, the results of the images under each component are compared, and the component with the best effect is extracted.
The texture feature parameter extraction is used for extracting texture feature parameters of image information.
In this embodiment, the texture feature parameters include: mean, standard deviation, smoothness, third order moment, consistency, and entropy.
The image estimation model module is used for establishing an image estimation model based on the estimation image, the land information and the meteorological information and carrying out image estimation on the agricultural ecological subareas based on the image estimation model;
in this embodiment, the image estimation model module includes: the device comprises a calculation unit, a construction unit and a correction unit;
the computing unit is used for computing the texture characteristic parameters by adopting principal component analysis to obtain principal component values of the texture characteristic parameters;
the construction unit is used for constructing a quality estimation model based on the principal component values by adopting a multiple linear regression method;
the correction unit is used for performing influence correction on the quality estimation model based on the land information and the meteorological information to obtain an image estimation model.
The remote sensing yield estimation model module is used for establishing a remote sensing yield estimation model based on the remote sensing data and carrying out remote sensing yield estimation on the agricultural ecological partition based on the remote sensing yield estimation model;
specifically, firstly, collecting leaf area index and other data of agricultural ecological partition crops; and downloading the original remote sensing data of the agricultural ecological partition through a professional website, and performing geometric correction on the original remote sensing data.
And then, carrying out data correction on the original remote sensing data by a Savitzky-Golay filtering method.
Based on the collected leaf area and the meteorological information, a WOFOST model is coupled by adopting a set Kalman filtering assimilation algorithm, and a remote sensing estimated yield model is obtained to predict crop yield of the agricultural ecological partition.
The crop estimation model module is used for obtaining a crop estimation model based on the image estimation model and the remote sensing estimation model.
Specifically, through the historical yields of the agricultural ecological subareas, the crop yield data predicted by the image estimation model and the crop yield data predicted by the remote sensing estimation model are subjected to linear analysis, and the linear relation between the crop yield and the crop yield data predicted by the image estimation model and the crop yield data predicted by the remote sensing estimation model is obtained to serve as an estimation model.
The above embodiments are merely illustrative of the preferred embodiments of the present invention, and the scope of the present invention is not limited thereto, but various modifications and improvements made by those skilled in the art to which the present invention pertains are made without departing from the spirit of the present invention, and all modifications and improvements fall within the scope of the present invention as defined in the appended claims.
Claims (9)
1. An estimation method based on the agricultural condition of the multi-scale crops in the whole growth period is characterized by comprising the following steps:
s1, dividing an agricultural ecological partition based on crop planting space-time consistency and historical agricultural disaster data;
s2, acquiring land information, image information, remote sensing data and weather information of the agricultural ecological subareas;
s3, preprocessing the image information to obtain an estimated image;
s4, establishing an image estimation model based on the estimation image, the land information and the meteorological information, and carrying out image estimation on the agricultural ecological subareas based on the image estimation model;
s5, establishing a remote sensing yield estimation model based on the remote sensing data, and carrying out remote sensing yield estimation on the agricultural ecological subareas based on the remote sensing yield estimation model;
and S6, obtaining a crop estimated model based on the image estimated model and the remote sensing estimated model.
2. A method of assessing a full-life agricultural condition of a multi-scale crop according to claim 1, wherein the method of pre-treatment comprises: color space conversion, component extraction and texture feature parameter extraction;
the color space conversion is used for converting the image information from RGB space to HSI space;
the component extraction is used for extracting the component with the best segmentation effect from H, S, I components;
the texture feature parameter extraction is used for extracting texture feature parameters of the image information.
3. The method for estimating agricultural conditions during full-life of a multi-scale crop according to claim 1, wherein the land information comprises: soil K + Content of soil NO 3 - Content, soil pH value and soil water content.
4. The method for estimating agricultural conditions during full-life of a multi-scale crop according to claim 1, wherein the method for obtaining the weather information comprises:
determining position information of an area to be estimated, and acquiring the position of a weather station based on the position information;
and selecting two groups of weather stations positioned at two ends of the estimated area as weather estimation stations, and estimating the weather information of the estimated area based on the weather data of the weather estimation stations.
5. A method for estimating agricultural conditions during full-life of a multi-scale crop according to claim 2, wherein S4 comprises:
calculating the texture characteristic parameters by adopting principal component analysis to obtain principal component values of the texture characteristic parameters;
establishing a quality estimation model based on the principal component values by adopting a multiple linear regression method;
and carrying out influence correction on the quality estimation model based on the land information and the meteorological information to obtain the image estimation model.
6. An estimation system based on the agricultural condition of the multi-scale crops in the whole growth period is characterized by comprising:
the system comprises a zoning module, an acquisition module, a preprocessing module, an image estimation model module, a remote sensing estimation model module and a crop estimation model module;
the zoning module is used for zoning the agricultural ecology based on the crop planting space-time consistency and the historical agricultural disaster data;
the acquisition module is used for acquiring land information, image information, remote sensing data and meteorological information of the agricultural ecological partition;
the preprocessing module is used for preprocessing the image information to obtain an estimated image;
the image estimation model module is used for establishing an image estimation model based on the estimation image, the land information and the meteorological information and carrying out image estimation on the agricultural ecological subarea based on the image estimation model;
the remote sensing estimated production model module is used for establishing a remote sensing estimated production model based on the remote sensing data and carrying out remote sensing estimated production on the agricultural ecological subareas based on the remote sensing estimated production model;
the crop estimation model module is used for obtaining a crop estimation model based on the image estimation model and the remote sensing estimation model.
7. The system for estimating agricultural conditions during full-life of a crop with multiple scales according to claim 6, wherein the preprocessing module preprocesses the image information by:
converting the image information from RGB space to HSI space by adopting color space conversion;
extracting the component with the best segmentation effect from the image information H, S, I component of the HSI space;
and extracting texture characteristic parameters of the image information.
8. The system for estimating agricultural conditions during full-life of a multi-scale crop according to claim 6, wherein the acquisition module comprises: the device comprises a first acquisition unit, a second acquisition unit, a third acquisition unit and a fourth acquisition unit;
the first acquisition unit is used for acquiring the land information;
the second acquisition unit is used for acquiring the image information;
the third acquisition unit is used for acquiring the land information;
the fourth acquisition unit is used for acquiring the remote sensing information.
9. The system for estimating agricultural conditions during full-life of a multi-scale crop according to claim 7, wherein the image estimation model module comprises: the device comprises a calculation unit, a construction unit and a correction unit;
the computing unit is used for computing the texture characteristic parameters by adopting principal component analysis to obtain principal component values of the texture characteristic parameters;
the construction unit is used for constructing a quality estimation model based on the principal component values by adopting a multiple linear regression method;
and the correction unit is used for performing influence correction on the quality estimation model based on the land information and the meteorological information to obtain the image estimation model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310855207.6A CN117253140A (en) | 2023-07-12 | 2023-07-12 | Yield estimation method and system based on multi-scale crop full-growth-period agricultural condition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310855207.6A CN117253140A (en) | 2023-07-12 | 2023-07-12 | Yield estimation method and system based on multi-scale crop full-growth-period agricultural condition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117253140A true CN117253140A (en) | 2023-12-19 |
Family
ID=89125395
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310855207.6A Pending CN117253140A (en) | 2023-07-12 | 2023-07-12 | Yield estimation method and system based on multi-scale crop full-growth-period agricultural condition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117253140A (en) |
-
2023
- 2023-07-12 CN CN202310855207.6A patent/CN117253140A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111368736B (en) | Rice refined estimation method based on SAR and optical remote sensing data | |
| CN113040034B (en) | Water-saving irrigation control system and control method | |
| CN108984803B (en) | Method and system for spatializing crop yield | |
| CN111126662B (en) | Irrigation decision making method, device, server and medium based on big data | |
| CN112348812B (en) | Forest stand age information measurement method and device | |
| CN112749627A (en) | Method and device for dynamically monitoring tobacco based on multi-source remote sensing image | |
| CN115481368B (en) | Vegetation coverage estimation method based on full remote sensing machine learning | |
| CN112183428A (en) | Wheat planting area segmentation and yield prediction method | |
| CN111751376B (en) | Rice nitrogen nutrition estimation method based on canopy image feature derivation | |
| CN111721714B (en) | Soil water content estimation method based on multi-source optical remote sensing data | |
| CN113553697B (en) | Long-time-sequence multi-source data-based vegetation disturbance analysis method for coal mining | |
| CN113591631A (en) | Crop yield estimation method based on multi-source data | |
| CN112858632A (en) | Grassland drought monitoring method comprehensively considering temperature and water stress | |
| GB2620469A (en) | Spatial prediction and evaluation method of soil organic matter content based on partition algorithm | |
| CN114140695B (en) | Prediction method and system for tea tree nitrogen diagnosis and quality index determination based on unmanned aerial vehicle multispectral remote sensing | |
| CN116863341B (en) | Crop classification and identification method and system based on time sequence satellite remote sensing image | |
| CN116403048B (en) | Crop growth estimation model construction method based on multi-mode data fusion | |
| CN117253140A (en) | Yield estimation method and system based on multi-scale crop full-growth-period agricultural condition | |
| Ayub et al. | Wheat Crop Field and Yield Prediction using Remote Sensing and Machine Learning | |
| CN116011881A (en) | Black soil farmland productivity evaluation method and system based on pixel scale | |
| CN115661674A (en) | Crop irrigation information extraction method based on multisource satellite soil humidity data | |
| CN115713691A (en) | Pixel-level electric power popularity estimation method and device based on noctilucent remote sensing | |
| CN114283344A (en) | Automatic real-time monitoring method and system for forest ecological hydrological process | |
| Sayad et al. | Crop management using Big Data | |
| CN114611271A (en) | Snow water equivalent grid data modeling and analyzing method considering spatial heterogeneity |
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 |