CN112215169B - Crop plant height and biomass self-adaptive resolving method based on unmanned aerial vehicle passive remote sensing - Google Patents
Crop plant height and biomass self-adaptive resolving method based on unmanned aerial vehicle passive remote sensing Download PDFInfo
- Publication number
- CN112215169B CN112215169B CN202011101682.7A CN202011101682A CN112215169B CN 112215169 B CN112215169 B CN 112215169B CN 202011101682 A CN202011101682 A CN 202011101682A CN 112215169 B CN112215169 B CN 112215169B
- Authority
- CN
- China
- Prior art keywords
- data
- plant height
- digital
- biomass
- crop
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/06—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness for measuring thickness ; e.g. of sheet material
- G01B11/0608—Height gauges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N2021/1793—Remote sensing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/194—Terrestrial scenes using hyperspectral data, i.e. more or other wavelengths than RGB
Abstract
The invention discloses a crop plant height and biomass self-adaptive resolving method based on unmanned aerial vehicle passive remote sensing. Obtaining high precision plant height and biomass estimation results of crops usually requires some spatial auxiliary data, such as a digital surface model DSM of multiple growth periods of crops, a digital ground model DTM of bare soil elevation, a ground control point GCP and a spectrum image. The invention provides four different spatial auxiliary data combinations, one with complete spatial auxiliary data and three with incomplete spatial auxiliary data. The user can collect the necessary spatial assistance data according to cost and accuracy requirements. The invention generates the corresponding crop plant height and biomass estimation scheme in a self-adaptive manner through different data conditions provided by users, and eliminates the uncertainty caused by the deletion of specific species data through data collaborative complementation, thereby obtaining the crop plant height and biomass settlement result with optimal precision through the existing data.
Description
Technical Field
The invention belongs to the field of agricultural automation, particularly relates to a self-adaptive high-precision calculation method for crop plant height and biomass, and particularly relates to a self-adaptive calculation method for crop plant height and biomass based on unmanned aerial vehicle passive remote sensing.
Background
Canopy height and above-ground biomass of crops are two important agronomic traits. In agricultural production, efficient and accurate estimation of plant height and biomass is a prerequisite for monitoring crop growth conditions and for enhancing decision support systems for specific agronomic measures (fertilization, weeding, harvest, etc.) (Zhu et al, 2019). The traditional artificial lossy sampling mode obtains plant height and biomass, the workload is large, the efficiency is low, and the data precision is greatly influenced by subjective factors.
The unmanned aerial vehicle low-altitude remote sensing platform gradually becomes an important means for obtaining crop phenotype information in a field environment because of the advantages of flexibility, suitability for complex farmland environments, high operation efficiency, low cost and the like. The crop height refers to the distance between the root and the top of a plant, a Digital Surface Model (DSM) of the multiple growth periods of the crop and a digital ground model (DTM) representing the bare soil elevation are obtained by an unmanned aerial vehicle carrying a digital camera or a multispectral sensor, and a plant height estimation result with higher precision can be obtained by combining Ground Control Point (GCP). The biomass of the overground part is defined as the total amount of overground organic substances in a unit area, and the method for calculating the vegetation index by using the spectrum image acquired by the unmanned aerial vehicle platform is a commonly used crop biomass prediction method, but the vegetation index is insensitive to the change of the crop growth later stage, so that the biomass prediction precision is reduced. Many studies have demonstrated that high-precision biomass information can be extracted by constructing a three-dimensional model of a crop by means of laser radar or photogrammetry techniques (great et al, 2015, walter et al, 2019), wherein the volume of the crop canopy is obtained by performing three-dimensional spatial integration on the height of the crop canopy in the crop coverage area, which has been shown to be more accurate and stable than spectroscopy.
When a digital camera or a multispectral sensor is carried by an unmanned aerial vehicle platform to obtain the plant height and the biomass of crops, some space auxiliary data is usually needed to complete the resolving of two phenotypic characteristics, such as a digital surface model, a digital ground model, a ground control point and a spectrum image. However, the cost and accuracy requirements for crop phenotype extraction may vary from scientific research to scientific research or actual agricultural production, and thus the choice of spatial assistance data may vary. Currently, there is no study on the spatial-assisted data selection for the unmanned aerial vehicle platform to acquire plant height and biomass phenotype, and a solution under data deficiency is proposed. The patent aims at four common data condition combinations, one contains complete space auxiliary data, and the other is incomplete space auxiliary data. The requirement for highly accurate phenotypic estimation means that the completeness of data acquisition needs to be guaranteed, and thus the data collection cost will also increase; and when the requirement on the precision is relatively low, the cost can be reduced by reducing the collection of data. Therefore, before estimating the plant height and the biomass, a user can acquire necessary space auxiliary data according to the requirements of cost and precision, the method generates a corresponding crop plant height and biomass acquisition scheme in a self-adaptive manner through different data provided by the user, and eliminates uncertainty caused by specific species data deletion through data collaborative complementation, so that the existing data is used for acquiring the crop plant height and biomass settlement results with optimal precision.
Disclosure of Invention
Technical problem to be solved
In order to solve the problem of the balance of precision and cost when the unmanned aerial vehicle platform obtains the plant height and the biomass, the invention provides a crop plant height and biomass self-adaptive calculating method based on unmanned aerial vehicle passive remote sensing, and the optimal calculation of the plant height and the biomass of crops under different existing data conditions is realized.
(II) technical scheme
The invention provides a crop plant height and biomass self-adaptive resolving method based on unmanned aerial vehicle passive remote sensing, which is used for solving the technical problem.
A crop plant height and biomass self-adaptive resolving method based on unmanned aerial vehicle passive remote sensing is used for generating an optimal crop plant height and biomass resolving scheme under different data conditions and is characterized in that,
before calculating the plant height and biomass of the crops, four basic data conditions are provided for a user in advance, and the user can make a selection according to the actual situation:
a first data condition, a user has a digital surface model DSM, a digital ground model DTM, a ground control point GCP and a spectral image;
a second data condition, user possesses digital surface model DSM, ground control point GCP and spectrum image;
under a third data condition, a user has a digital surface model DSM, a digital ground model DTM and a spectral image;
a fourth data condition, wherein the user has a digital surface model DSM and a spectral image;
aiming at the estimation of the plant height and the biomass of the crops, the first data condition is a complete data condition, and the latter three conditions have data deletion; and (3) generating a corresponding scheme in a self-adaptive manner according to the data conditions actually selected by the user, eliminating uncertainty caused by data deletion of a specific variety through data collaborative complementation, then performing calculation on the plant height and the biomass of the crop, and finally obtaining the estimation result of the plant height and the biomass of the high-precision crop.
More specifically, the combination of different data conditions comprises four kinds of data in total, wherein the digital surface model DSM represents the crop elevation data covered by crops, and the first-stage or multi-stage data is an image format file; the digital ground model DTM represents bare soil elevation data without crop coverage, and the first-stage data is an image format file; the ground control point GCP records the spatial position information of the field control points, and first-stage data are text format files; the spectral image is a visible light image or a multispectral image, one or more phases of data.
More specifically, under the first data condition, the digital surface model DSM and the digital ground model DTM are registered by importing the same set of ground control point GCP when generating data, so that the conventional plant height extraction algorithm is directly executed, and the plant height result of the crop can be obtained by subtracting the digital ground model DTM from the digital surface model DSM.
More specifically, under the second data condition, the digital ground model DTM is absent, and the spectral image of the crop is used for assisting in extracting the bare soil data as the digital ground model DTM; before bare soil data is extracted, a user needs to judge whether the area of bare soil in a field in a spectral image is large or small;
aiming at the condition of a large number of bare soil areas, two algorithms are provided for users to select, and soil identification and extraction are carried out; the first method is a spectral index method, after a normalized difference index NDI is calculated through a spectral image, a soil region is obtained through division by using an Otsu method, the soil region is used as a mask to extract a soil part of a digital surface model DSM in a corresponding period, then an inverse distance weight interpolation method IDW is used for carrying out interpolation on the soil part to obtain a complete digital ground model DTM, and finally the digital surface model DSM is subjected to subtraction with the digital ground model DTM extracted before to obtain the plant height of a crop; the second method is a deep learning method, a trained convolutional neural network model is adopted to carry out soil identification on a spectral image to obtain a soil area of the spectral image, then an inverse distance weight interpolation method IDW is used for carrying out interpolation on extracted soil to obtain a complete digital ground model DTM, and finally a digital surface model DSM is combined to obtain the plant height of crops;
aiming at the condition of few bare soil areas, sufficient data is difficult to provide for interpolation, a user needs to manually select the bare soil areas around the field after inputting an optical spectrum image, the elevations of the areas are obtained through a digital surface model DSM, the average value of the elevations is counted to be used as a digital ground model DTM, and finally the difference between the digital surface model DSM and the elevations is obtained to obtain the plant height of crops.
More specifically, under the third data condition, if a ground control point GCP is absent, a proper number of feature points need to be manually selected from the spectral image, the spatial position information of the feature points is acquired and used as the ground control point GCP, and the feature points are exported to a text format file; when a user generates a digital ground model (DTM) and other time-period Digital Surface Models (DSMs), the ground control point information is imported to align all the Digital Surface Models (DSMs) with the digital ground model (DTM) in spatial positions, and finally, a crop plant height result is obtained according to a conventional plant height extraction algorithm under the condition of complete data.
More specifically, under the fourth data condition, both the digital terrestrial model DTM and the ground control point GCP are absent; firstly, manually selecting a characteristic point in a spectral image to obtain a ground control point GCP; generating a digital ground model (DTM) and a Digital Surface Model (DSM) by using the ground control point; and then, according to the resolving step under the second data condition, after the digital ground model DTM is obtained, the plant height is obtained by combining the digital surface model DSM.
More specifically, biomass estimation under all four data conditions was based on crop plant height results; after the plant height is obtained, calculating a normalized difference index NDI through a spectral image, dividing the NDI image by using an Otsu method to obtain crop coverage, and counting the accumulation of the plant height in the crop coverage area to obtain a crop canopy volume model CVM, namely the crop biomass.
More particularly, the method is suitable for the plant height and biomass acquisition of conventional crops in a field environment.
(III) advantageous effects
The invention provides a crop height and biomass self-adaptive calculation method based on unmanned aerial vehicle passive remote sensing based on technical accumulation and research and development of an inventor in the field for years, and the method realizes the optimal calculation of the crop height and biomass based on the unmanned aerial vehicle passive remote sensing and obtained for different data conditions. Compared with the prior art, the method has the following technical advantages: (1) The provided four data conditions cover the most common data acquisition conditions of the plant height and biomass of the crop obtained by the unmanned aerial vehicle through passive remote sensing, the method is widely suitable for variable practical application scenes, and the efficiency of scheme making and solution execution is greatly improved; (2) The optimal plant height and biomass calculation method can be generated in a self-adaptive manner under the condition of limited data provided by a user, the high-precision and low-cost crop phenotype extraction is realized, and the maximization of user benefits is met.
Drawings
Fig. 1 is a diagram of a convolutional neural network structure for identifying soil regions in the present invention.
FIG. 2 is a schematic diagram of crop biomass estimation according to the present invention (first data condition is taken as an example).
Detailed Description
The invention provides a crop plant height and biomass self-adaptive resolving method based on unmanned aerial vehicle passive remote sensing, aiming at solving the technical problem.
A crop plant height and biomass self-adaptive resolving method based on unmanned aerial vehicle passive remote sensing is used for generating an optimal crop plant height and biomass resolving scheme under different data conditions and is characterized in that,
before calculating the plant height and biomass of the crops, four basic data conditions are provided for a user in advance, and the user can make a selection according to the actual situation:
under a first data condition, a user has a digital surface model DSM, a digital ground model DTM, a ground control point GCP and a spectrum image;
a second data condition, wherein the user has a digital surface model DSM, a ground control point GCP and a spectral image;
under a third data condition, a user has a digital surface model DSM, a digital ground model DTM and a spectral image;
a fourth data condition, wherein the user has a digital surface model DSM and a spectral image;
aiming at the estimation of the plant height and the biomass of the crops, the first data condition is a complete data condition, and the latter three conditions have data deletion; and (3) generating a corresponding scheme in a self-adaptive manner according to the data conditions actually selected by the user, eliminating uncertainty caused by data deletion of a specific variety through data collaborative complementation, then performing calculation on the plant height and the biomass of the crop, and finally obtaining the estimation result of the plant height and the biomass of the high-precision crop.
More specifically, the combination of different data conditions comprises four kinds of data in total, wherein the digital surface model DSM represents the crop elevation data covered by crops, and the first-stage or multi-stage data is an image format file; the digital ground model DTM represents bare soil elevation data without crop coverage, and the first-stage data is an image format file; the ground control point GCP records the spatial position information of the field control points, and first-stage data are text format files; the spectral image is a visible light image or a multispectral image, one or more phases of data.
More specifically, under the first data condition, the digital surface model DSM and the digital ground model DTM are registered through the ground control point GCP when data generation is performed, so that a conventional plant height extraction algorithm is directly performed, and a crop plant height result can be obtained by subtracting the digital ground model DTM from the digital surface model DSM.
More specifically, under the second data condition, the digital ground model DTM is lacked, and the spectral image of the crop is used for assisting in extracting the bare soil data to serve as the digital ground model DTM; before bare soil data is extracted, a user needs to judge whether the area of bare soil in a field in a spectral image is large or small;
aiming at the condition of a large number of bare soil areas, two algorithms are provided for users to select, and soil identification and extraction are carried out; the first method is a spectral index method, after a normalized difference index NDI is calculated through a spectral image, a soil area is obtained by using an Otsu method through segmentation, the soil area is used as a mask to extract a soil part of a digital surface model DSM in a corresponding period, then an inverse distance weight interpolation method IDW is used for carrying out interpolation on the soil part to obtain a complete digital ground model DTM, and finally the difference between the digital surface model DSM and the digital ground model DTM extracted before is used for obtaining the plant height of crops; the second method is a deep learning method, a trained convolutional neural network model is adopted to carry out soil recognition on a spectral image, the structure of the network model is shown in figure 1, a soil area of the spectral image is obtained, then an inverse distance weight interpolation method IDW is used for carrying out interpolation on extracted soil to obtain a complete digital ground model DTM, and finally a digital surface model DSM is combined to obtain the plant height of crops;
aiming at the condition of few bare soil areas, sufficient data is difficult to provide for interpolation, a user needs to manually select the bare soil areas around the field after inputting an optical spectrum image, the elevations of the areas are obtained through a digital surface model DSM, the average value of the elevations is counted to be used as a digital ground model DTM, and finally the difference between the digital surface model DSM and the elevations is obtained to obtain the plant height of crops.
More specifically, under the third data condition, if a ground control point GCP is absent, a proper number of feature points need to be manually selected from the spectral image, the spatial position information of the feature points is acquired and used as the ground control point GCP, and the feature points are exported to a text format file; when a user generates a digital ground model (DTM) and other time-period Digital Surface Models (DSMs), the ground control point information is imported to align all the Digital Surface Models (DSMs) with the digital ground model (DTM) in spatial positions, and finally, a crop plant height result is obtained according to a conventional plant height extraction algorithm under the condition of complete data.
More specifically, under the fourth data condition, both the digital terrestrial model DTM and the ground control point GCP are absent; firstly, manually selecting a characteristic point in a spectral image to obtain a ground control point GCP; generating a digital ground model (DTM) and a Digital Surface Model (DSM) by using the ground control point; and then, according to the resolving step under the second data condition, obtaining a digital ground model (DTM), and finally calculating to obtain a crop plant height result.
More specifically, biomass estimation under all four data conditions was based on crop plant height results; after the plant height is obtained, calculating a normalized difference index NDI through a spectral image, dividing the NDI image by using an Otsu method to obtain crop coverage, and counting the accumulation of the plant height in the crop coverage area to obtain a crop canopy volume model CVM, namely crop biomass, wherein the specific biomass estimation flow is shown in figure 2.
More particularly, the method is suitable for the plant height and biomass acquisition of conventional crops in a field environment.
The rape is taken as a specific application object, and spatial auxiliary data is provided according to four data conditions to estimate the plant height and biomass of the crops, wherein the rape data provided under the data condition 2 belongs to the condition of few bare soil areas, and the following results are obtained. Data Condition 1 has complete spatial auxiliary data, and has highest precision and lowest error, wherein plant height and biomass determining coefficient R 2 0.897 and 0.834 respectively, and absolute errors RMSE of 0.035m and 0.762kg/m respectively 2 The relative errors RE were 8.8% and 16.6%, respectively. The prediction precision of the plant height and the biomass under the other three data deletion conditions is relatively poor in complete data result, but the determination coefficient R 2 All are maintained at above 0.7, the absolute error of plant height is below 0.05m, and the absolute error of biomass is 0.9kg/m 2 The following.
TABLE 1 estimation of plant height and Biomass under four data conditions
The specific embodiments described in this application are merely illustrative of the spirit of the invention. Various modifications or additions may be made to the described embodiments or alternatives may be employed by those skilled in the art without departing from the spirit or ambit of the invention as defined in the appended claims.
Claims (4)
1. A crop plant height and biomass self-adaptive resolving method based on unmanned aerial vehicle passive remote sensing is used for generating an optimal crop plant height and biomass resolving scheme under different data conditions and is characterized in that,
before calculating the plant height and biomass of the crops, four basic data conditions are provided for a user in advance, and the user can make a selection according to the actual situation:
a first data condition, a user has a digital surface model DSM, a digital ground model DTM, a ground control point GCP and a spectral image;
a second data condition, wherein the user has a digital surface model DSM, a ground control point GCP and a spectral image;
under a third data condition, a user has a digital surface model DSM, a digital ground model DTM and a spectral image;
a fourth data condition, the user having a digital surface model, DSM, and a spectral image;
aiming at the estimation of the plant height and the biomass of the crops, the first data condition is a complete data condition, and the latter three conditions have data deletion; generating a corresponding solution in a self-adaptive manner according to data conditions actually selected by a user, eliminating uncertainty caused by data deletion of specific species through data collaborative complementation, then performing calculation of the plant height and biomass of the crops, and finally obtaining estimation results of the plant height and the biomass of the high-precision crops;
under the first data condition, the digital surface model DSM and the digital ground model DTM are registered by leading in the same set of ground control point GCP when data are generated, so that a conventional plant height extraction algorithm is directly executed, and a plant height result of crops can be obtained by subtracting the digital ground model DTM from the digital surface model DSM;
under the second data condition, the digital ground model DTM is absent, and the spectrum image is used for assisting in extracting bare soil data to serve as the digital ground model DTM; before bare soil data is extracted, a user needs to judge whether the area of bare soil in a field in a spectral image is large or small; aiming at the condition of a large number of bare soil areas, two algorithms are provided for users to select, and soil identification and extraction are carried out; the first method is a spectral index method, after a normalized difference index NDI is calculated through a spectral image, a soil area is obtained by using an Otsu method through segmentation, the soil area is used as a mask to extract a soil part of a digital surface model DSM in a corresponding period, then an inverse distance weight interpolation method IDW is used for carrying out interpolation on the soil part to obtain a complete digital ground model DTM, and finally the digital surface model DSM and the extracted digital ground model DTM are subjected to difference to obtain the plant height of a crop; the second method is a deep learning method, a trained convolutional neural network model is adopted to carry out soil identification on a spectral image to obtain a soil area in the spectral image, then an inverse distance weight interpolation method IDW is used for carrying out interpolation on extracted soil to obtain a complete digital ground model DTM, and finally a digital surface model DSM is combined to obtain the plant height of crops; aiming at the condition of few bare soil areas, sufficient data is difficult to provide for interpolation, a user needs to manually select the bare soil areas around the field after inputting an optical spectrum image, the elevations of the areas are obtained through a Digital Surface Model (DSM), the average value of the elevations is counted to be used as a digital ground model (DTM), and finally the difference between the elevations and the Digital Surface Model (DSM) is carried out to obtain the plant height of crops;
under the third data condition, if a ground control point GCP is lacked, a proper number of characteristic points need to be manually selected from the spectrum image, the spatial position information of the characteristic points is obtained and is used as the ground control point GCP, and the characteristic points are exported to be a text format file; when a user generates a digital ground model (DTM) and other time-period Digital Surface Models (DSMs), importing the ground control point information to align all the Digital Surface Models (DSMs) with the digital ground model (DTM) in a spatial position, and finally acquiring a crop plant height result according to a conventional plant height extraction algorithm under the condition of complete data;
under the fourth data condition, the digital ground model DTM and the ground control point GCP are not available; firstly, manually selecting a characteristic point in a spectral image to obtain a ground control point GCP; generating a digital ground model (DTM) and a Digital Surface Model (DSM) by using the ground control point; and then, according to the resolving step under the second data condition, after the digital ground model DTM is obtained, the plant height is obtained by combining the digital surface model DSM.
2. The crop plant height and biomass self-adaptive resolving method based on unmanned aerial vehicle passive remote sensing according to claim 1, characterized in that: the combination of different data conditions comprises four kinds of data in total, wherein the digital surface model DSM represents the crop elevation data covered by crops, and the first-stage or multi-stage data is an image format file; the digital ground model DTM represents bare soil elevation data without crop coverage, and the first-stage data is an image format file; the ground control point GCP records the spatial position information of the field control points, and first-stage data are text format files; the spectral image is a visible light image or a multispectral image, one or more phases of data.
3. The crop plant height and biomass self-adaptive resolving method based on unmanned aerial vehicle passive remote sensing according to claim 1, characterized in that: biomass estimation under all four data conditions is performed based on crop plant height results; after the plant height is obtained, calculating a normalized difference index NDI through a spectral image, dividing the NDI image by using an Otsu method to obtain crop coverage, and counting the accumulation of the plant height in the crop coverage area to obtain a crop canopy volume model CVM, namely the crop biomass.
4. The crop height and biomass adaptive resolving method based on unmanned aerial vehicle passive remote sensing according to any one of claims 1 to 3, characterized in that: it is suitable for obtaining the plant height and biomass of conventional crops in a field environment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011101682.7A CN112215169B (en) | 2020-10-10 | 2020-10-10 | Crop plant height and biomass self-adaptive resolving method based on unmanned aerial vehicle passive remote sensing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011101682.7A CN112215169B (en) | 2020-10-10 | 2020-10-10 | Crop plant height and biomass self-adaptive resolving method based on unmanned aerial vehicle passive remote sensing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112215169A CN112215169A (en) | 2021-01-12 |
| CN112215169B true CN112215169B (en) | 2022-11-08 |
Family
ID=74054255
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011101682.7A Active CN112215169B (en) | 2020-10-10 | 2020-10-10 | Crop plant height and biomass self-adaptive resolving method based on unmanned aerial vehicle passive remote sensing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112215169B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022173383A1 (en) * | 2021-02-11 | 2022-08-18 | Saengprachatanarug Khwantri | Method for determining height of crop covered soil surface from sea level through use of aerial photographs |
| CN116229289A (en) * | 2022-12-13 | 2023-06-06 | 河南省农业科学院农业经济与信息研究所 | Unmanned aerial vehicle-based winter wheat biomass rapid and high-precision estimation method |
| CN117274359B (en) * | 2023-10-13 | 2024-04-19 | 扬州大学 | Plant height measuring and calculating method and system for crop group |
| CN117456364B (en) * | 2023-11-09 | 2024-04-26 | 中国农业科学院农业信息研究所 | Grassland biomass estimation method and system based on SfM and grassland height factors |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130015278A (en) * | 2011-08-03 | 2013-02-14 | 솔트웨어 주식회사 | The system for monitoring plant and method using the same |
| CN104180754A (en) * | 2014-07-28 | 2014-12-03 | 南京林业大学 | Inversion method for biophysical property of forest based on LiDAR comprehensive waveform model |
| CN106643529A (en) * | 2016-09-30 | 2017-05-10 | 中国科学院、水利部成都山地灾害与环境研究所 | Rapid measuring method for growing height of agricultural crops in mountainous areas based on unmanned aerial vehicle photographed image |
| CN109084690A (en) * | 2018-10-31 | 2018-12-25 | 杨凌禾讯遥感科技有限公司 | Crop plant height calculation method based on unmanned plane visual remote sensing |
| CN109376579A (en) * | 2018-08-29 | 2019-02-22 | 浙江农林大学 | The prediction technique of ginkgo crown biomass based on unmanned plane orthograph picture |
| EP3467702A1 (en) * | 2017-10-04 | 2019-04-10 | Kws Saat Se | Method and system for performing data analysis for plant phenotyping |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110148116A (en) * | 2019-04-12 | 2019-08-20 | 深圳大学 | A kind of forest biomass evaluation method and its system |
-
2020
- 2020-10-10 CN CN202011101682.7A patent/CN112215169B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130015278A (en) * | 2011-08-03 | 2013-02-14 | 솔트웨어 주식회사 | The system for monitoring plant and method using the same |
| CN104180754A (en) * | 2014-07-28 | 2014-12-03 | 南京林业大学 | Inversion method for biophysical property of forest based on LiDAR comprehensive waveform model |
| CN106643529A (en) * | 2016-09-30 | 2017-05-10 | 中国科学院、水利部成都山地灾害与环境研究所 | Rapid measuring method for growing height of agricultural crops in mountainous areas based on unmanned aerial vehicle photographed image |
| EP3467702A1 (en) * | 2017-10-04 | 2019-04-10 | Kws Saat Se | Method and system for performing data analysis for plant phenotyping |
| CN109376579A (en) * | 2018-08-29 | 2019-02-22 | 浙江农林大学 | The prediction technique of ginkgo crown biomass based on unmanned plane orthograph picture |
| CN109084690A (en) * | 2018-10-31 | 2018-12-25 | 杨凌禾讯遥感科技有限公司 | Crop plant height calculation method based on unmanned plane visual remote sensing |
Non-Patent Citations (1)
| Title |
|---|
| Estimation of Winter Wheat Above-Ground Biomass Using Unmanned Aerial Vehicle-Based Snapshot Hyperspectral Sensor and Crop Height Improved Models;Jibo Yue 等;《Remote Sensing》;20170710;第9卷(第7期);1-19 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112215169A (en) | 2021-01-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112215169B (en) | Crop plant height and biomass self-adaptive resolving method based on unmanned aerial vehicle passive remote sensing | |
| CN109884664B (en) | Optical microwave collaborative inversion method and system for urban overground biomass | |
| CN108921885B (en) | Method for jointly inverting forest aboveground biomass by integrating three types of data sources | |
| Xiao et al. | Use of general regression neural networks for generating the GLASS leaf area index product from time-series MODIS surface reflectance | |
| CN110414738B (en) | Crop yield prediction method and system | |
| CN113221765B (en) | Vegetation phenological period extraction method based on digital camera image effective pixels | |
| Swinfield et al. | Imaging spectroscopy reveals the effects of topography and logging on the leaf chemistry of tropical forest canopy trees | |
| Stone et al. | Determining an optimal model for processing lidar data at the plot level: results for a Pinus radiata plantation in New South Wales, Australia | |
| Solvin et al. | Use of UAV photogrammetric data in forest genetic trials: measuring tree height, growth, and phenology in Norway spruce (Picea abies L. Karst.) | |
| CN109211791B (en) | Crop growth monitoring method and system | |
| CN108981616B (en) | Method for inverting effective leaf area index of artificial forest by unmanned aerial vehicle laser radar | |
| Sun et al. | Extracting distribution and expansion of rubber plantations from Landsat imagery using the C5. 0 decision tree method | |
| Xu et al. | Estimation of secondary forest parameters by integrating image and point cloud-based metrics acquired from unmanned aerial vehicle | |
| CN113205014B (en) | Time sequence data farmland extraction method based on image sharpening | |
| Pätzig et al. | Allometric relationships for selected macrophytes of kettle holes in northeast Germany as a basis for efficient biomass estimation using unmanned aerial systems (UAS) | |
| CN117036061B (en) | Intelligent solution providing method and system for intelligent agricultural insurance | |
| Chen et al. | An integrated GIS tool for automatic forest inventory estimates of Pinus radiata from LiDAR data | |
| CN116403048B (en) | Crop growth estimation model construction method based on multi-mode data fusion | |
| Gautam et al. | Estimation of forest carbon using Lidar-Assisted Multi-source Programme (LAMP) in Nepal | |
| Sevillano Marco et al. | Improvement of existing and development of future Copernicus land monitoring products–the ECOLASS project | |
| CN112700347A (en) | Method and device for generating crop height growth curve and storage medium | |
| CN112700346A (en) | Crop height determination method and device, storage medium and equipment | |
| Jin et al. | UAV-RGB-image-based aboveground biomass equation for planted forest in semi-arid Inner Mongolia, China | |
| Noordermeer | Large-area forest productivity estimation using bitemporal data from airborne laser scanning and digital aerial photogrammetry | |
| CN114220028B (en) | Rare tree species identification method based on unmanned aerial vehicle hyperspectral image and machine learning algorithm model research and development |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |