CN116796293A - Method for estimating cotton defoliation process based on unmanned aerial vehicle multispectral inversion leaf area index - Google Patents
Method for estimating cotton defoliation process based on unmanned aerial vehicle multispectral inversion leaf area index Download PDFInfo
- Publication number
- CN116796293A CN116796293A CN202310664798.9A CN202310664798A CN116796293A CN 116796293 A CN116796293 A CN 116796293A CN 202310664798 A CN202310664798 A CN 202310664798A CN 116796293 A CN116796293 A CN 116796293A
- Authority
- CN
- China
- Prior art keywords
- index
- cotton
- leaf area
- nir
- vegetation
- 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
- 229920000742 Cotton Polymers 0.000 title claims abstract description 105
- 230000035613 defoliation Effects 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000008569 process Effects 0.000 title claims abstract description 23
- 238000012417 linear regression Methods 0.000 claims abstract description 18
- 238000002310 reflectometry Methods 0.000 claims abstract description 18
- 230000003595 spectral effect Effects 0.000 claims abstract description 12
- 238000004364 calculation method Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims description 17
- 238000012360 testing method Methods 0.000 claims description 12
- 239000003795 chemical substances by application Substances 0.000 claims description 8
- 230000005070 ripening Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 239000002689 soil Substances 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 235000016709 nutrition Nutrition 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 12
- 238000003306 harvesting Methods 0.000 abstract description 11
- 241000219146 Gossypium Species 0.000 description 76
- 230000008859 change Effects 0.000 description 3
- 239000012535 impurity Substances 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000035558 fertility Effects 0.000 description 2
- 238000005507 spraying Methods 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 240000002024 Gossypium herbaceum Species 0.000 description 1
- 235000004341 Gossypium herbaceum Nutrition 0.000 description 1
- 241000607479 Yersinia pestis Species 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 238000000701 chemical imaging Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention provides a method for estimating a cotton defoliation process based on unmanned aerial vehicle multispectral inversion leaf area indexes, which comprises the steps of obtaining leaf area indexes before and after cotton defoliation in different periods; acquiring multi-spectral image data of cotton fields; preprocessing the cotton multispectral image data to obtain cotton canopy multispectral image reflectivity data; obtaining vegetation indexes of cotton crowns of different cells according to the spectral image reflectivity data through a vegetation index calculation formula; carrying out unitary linear regression modeling and prediction on the vegetation index and the leaf area index according to the leaf area index and the vegetation index; and evaluating a model of the vegetation index and the leaf area index to obtain the vegetation index with highest inversion leaf area index precision. The method provided by the invention can provide references for dynamic monitoring and timely harvesting of defoliation conditions of cotton fields, and provide important theoretical basis and technical support for accurate agricultural management and decision making of regional scale.
Description
Technical Field
The invention belongs to the technical field of crop growth monitoring.
Background
Cotton is an important economic crop in China, is an important material related to national life, and plays an important role in national economy. Harvesting cotton requires a large amount of manual investment, and achieving mechanized harvesting has become a necessary trend in the context of the growing shortage of agricultural labor. In actual agricultural production, a method of spraying defoliation ripening agent is generally adopted to promote the leaves of cotton plants to fall off as soon as possible, so as to improve the operation efficiency of mechanical harvesting and reduce the impurity content of sub-cotton. Traditional methods evaluate cotton defoliation processes in terms of defoliation rate. However, defoliation rate is a relative value, which is complex to investigate. And cotton leaves are large and small, and the single leaf removal rate index represented by the number change is used for representing the cotton leaf removal process, so that the leaf area index representing the leaf area change can be used for representing the leaf removal process of the cotton and can be better fit with the need of cotton harvesting to reduce the impurity content.
The unmanned aerial vehicle plays an important role in crop monitoring, has the characteristics of high efficiency, high resolution, low cost, low risk, high flexibility and the like, and becomes an ideal tool for crop phenotype. Unmanned aerial vehicle images have recently been applied to crop growth monitoring, pest and disease monitoring, and the like. Furthermore, higher resolution images can be obtained compared to satellite and on-board methods, as they are taken at relatively low altitudes. Unmanned aerial vehicle images are of great significance to practical application of developing crop phenotype research.
Therefore, the study uses the unmanned aerial vehicle to acquire multispectral data of the cotton canopy, combines the vegetation index with leaf area index data investigated in different time periods before and after defoliation, carries out linear regression modeling prediction, and carries out model evaluation. Provides reference for dynamic monitoring and timely harvesting of defoliation conditions of cotton fields, and provides important theoretical basis and technical support for accurate agricultural management and decision making of regional scale.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems in the related art to some extent.
Therefore, the invention aims to provide a method for estimating the cotton defoliation process based on the unmanned aerial vehicle multispectral inversion leaf area index, which is used for providing references for dynamic monitoring and timely harvesting of cotton field defoliation conditions and providing important theoretical basis and technical support for accurate agricultural management and decision of regional scale.
To achieve the above objective, an embodiment of the first aspect of the present invention provides a method for estimating a cotton defoliation process based on an unmanned aerial vehicle multispectral inversion leaf area index, including:
acquiring leaf area indexes before and after defoliation of cotton in different periods;
acquiring multi-spectral image data of cotton fields; preprocessing the cotton multispectral image data to obtain cotton canopy multispectral image reflectivity data;
obtaining vegetation indexes of cotton crowns of different cells according to the spectral image reflectivity data through a vegetation index calculation formula;
carrying out unitary linear regression modeling and prediction on the vegetation index and the leaf area index according to the leaf area index and the vegetation index;
and evaluating a model of the vegetation index and the leaf area index to obtain the vegetation index with highest inversion leaf area index precision.
In addition, the method for estimating the cotton defoliation process based on the unmanned aerial vehicle multispectral inversion leaf area index according to the embodiment of the invention can also have the following additional technical characteristics:
further, in one embodiment of the present invention, the obtaining leaf area indexes before and after defoliation of cotton at different periods includes:
the leaf area indexes of different communities are obtained before and after cotton defoliation, and defoliation ripening agents Xinsaili are sprayed in preset time.
Further, in one embodiment of the present invention, the acquiring multi-spectral image data of cotton field includes:
by dividing the cotton field area into 2 parts, the leaf area index is measured in the middle 3 rows by the LAI-2200 using the method for measuring leaf area index of row crops in the manual according to LAI-2200 to increase the data volume while reducing variability of the data samples.
Further, in an embodiment of the present invention, the obtaining the vegetation indexes of the cotton crowns of different cells according to the spectral image reflectivity data through a vegetation index calculation formula includes:
normalized difference vegetation index NDVI: (NIR-R)/(NIR+R);
normalized differential red edge vegetation index NDRE: (NIR-RE)/(nir+re);
visible light differential vegetation index VDVI: (2*G-R-B)/(2 x g+r+b);
normalized green red difference index NGRDI: (G-R)/(g+r);
green normalized difference vegetation index GNDVI: (NIR-G)/(NIR+G);
green wide dynamic range vegetation index gwrvi: (0.12 nir-G)/(0.12 nir+g);
simple ratio vegetation index SR: NIR/R;
green ratio vegetation index GRVI: NIR/G;
red-green ratio index RGRI: R/G;
differential vegetation index DVI: NIR-R;
the overgreen index EXG:2*G-R-B;
the redness index EXR:1.4 x r-G;
over-green minus over-red index EXGR: EXG-EXR;
nutritional index VEG: G/(R) a *B (1-a) ),a＝0.667；
Visible atmospheric impedance index VARI: (G-R)/(g+r-B);
red edge soil adjustment vegetation index RESAVI:1.5 x (NIR-RE)/(nir+re+0.5);
improving a soil adjustment vegetation index MSAVI:0.5 (2. NIR+1-sqrt ((2. NIR+1) 2-8 (NIR-R))
Enhanced vegetation index EVI:2.5 x (NIR-R)/(nir+ 6*R-7.5 x b+1);
normalized red index NRI: R/(NIR+RE+R);
wherein, B, G, R, RE, NIR represent blue band, green band, red side band, near infrared band, the central wavelength is respectively: 450nm,560nm,650nm,730nm,850nm.
Further, in an embodiment of the present invention, the modeling and predicting the vegetation index and the leaf area index by using the leaf area index and the vegetation index includes:
dividing a training set and a testing set, and carrying out linear regression modeling on the training set according to the proportion of 7:3;
by determining the coefficient R 2 The performance of the model is evaluated by the root mean square error RMSE and the relative root mean square error R-RMSE, and the best model is selected.
To achieve the above objective, an embodiment of the present invention provides a device for estimating a cotton defoliation process based on an unmanned aerial vehicle multispectral inversion leaf area index, including:
the first acquisition module is used for acquiring leaf area indexes before and after defoliation of cotton in different periods;
the second acquisition module is used for acquiring multi-spectral image data of the cotton field; preprocessing the cotton multispectral image data to obtain cotton canopy multispectral image reflectivity data;
the calculating module is used for obtaining vegetation indexes of the cotton crowns of different cells according to the spectral image reflectivity data through a vegetation index calculating formula;
the construction module is used for carrying out unitary linear regression modeling and prediction on the vegetation index and the leaf area index according to the leaf area index and the vegetation index;
and the evaluation module is used for evaluating the model of the vegetation index and the leaf area index to obtain the vegetation index with highest inversion leaf area index precision.
Further, in an embodiment of the present invention, the first obtaining module is further configured to:
the leaf area indexes of different communities are obtained before and after cotton defoliation, and defoliation ripening agents Xinsaili are sprayed in preset time.
Further, in an embodiment of the present invention, the second obtaining module is further configured to:
by dividing the cotton field area into 2 parts, the leaf area index is measured in the middle 3 rows by the LAI-2200 using the method for measuring leaf area index of row crops in the manual according to LAI-2200 to increase the data volume while reducing variability of the data samples.
Further, in an embodiment of the present invention, the building block is further configured to:
dividing a training set and a testing set, and carrying out linear regression modeling on the training set according to the proportion of 7:3;
by determining the coefficient R 2 The performance of the model is evaluated by the root mean square error RMSE and the relative root mean square error R-RMSE, and the best model is selected.
To achieve the above object, an embodiment of the third aspect of the present invention provides a computer device, which is characterized by comprising a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor implements a method for estimating a cotton defoliation process based on a multispectral inversion leaf area index of an unmanned aerial vehicle as described above when executing the computer program.
According to the method for estimating the cotton defoliation progress based on the unmanned aerial vehicle multispectral inversion leaf area indexes, 19 vegetation indexes which are strong in correlation with the crop leaf area indexes or good in predicted crop leaf area indexes in the literature are selected, modeling prediction is carried out on the 19 vegetation indexes and the leaf area indexes, the optimal vegetation indexes of inversion leaf area indexes before and after defoliation in the later period of cotton fertility are determined, and the defoliation progress of cotton is determined through the inverted leaf area indexes. Provides reference for dynamic monitoring and timely harvesting of defoliation of cotton fields, and provides important theoretical basis and technical support for accurate agricultural management and decision making of regional scale.
Drawings
The foregoing and/or additional aspects and advantages of the invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
fig. 1 is a flow chart of a method for estimating a cotton defoliation process based on an unmanned aerial vehicle multispectral inversion leaf area index according to an embodiment of the invention.
Fig. 2 is a schematic flow chart of a cotton defoliation process estimation device based on unmanned aerial vehicle multispectral inversion leaf area index according to an embodiment of the invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present invention and should not be construed as limiting the invention.
The method for estimating cotton defoliation progress based on the unmanned aerial vehicle multispectral inversion leaf area index is described below with reference to the accompanying drawings.
Fig. 1 is a flow chart of a method for estimating a cotton defoliation process based on an unmanned aerial vehicle multispectral inversion leaf area index according to an embodiment of the invention.
As shown in fig. 1, the method for estimating the cotton defoliation process based on the unmanned aerial vehicle multispectral inversion leaf area index comprises the following steps:
s101: acquiring leaf area indexes before and after defoliation of cotton in different periods;
further, in one embodiment of the invention, obtaining leaf area indexes before and after defoliation of cotton at different times comprises:
the leaf area indexes of different communities are obtained before and after cotton defoliation, and defoliation ripening agents Xinsaili are sprayed in preset time.
S102: acquiring multi-spectral image data of cotton fields; preprocessing the cotton multispectral image data to obtain cotton canopy multispectral image reflectivity data;
further, in one embodiment of the present invention, acquiring cotton field multispectral image data includes:
by dividing the cotton field area into 2 parts, the leaf area index is measured in the middle 3 rows by the LAI-2200 using the method for measuring leaf area index of row crops in the manual according to LAI-2200 to increase the data volume while reducing variability of the data samples.
Specifically, the spatial extent of the test area is first determined and the DJI GS Pro software automatically generates the flight path. Multispectral image acquisition is performed by carrying a multispectral camera on the P4M of the large area, wherein the multispectral camera comprises 1 color sensor for visible light imaging and 5 single sensors for multispectral imaging: valid pixels 208 ten thousand (total pixels 212 ten thousand). The 5 multispectral bands are respectively: blue (B): 450nm + -16 nm; green (G): 560 nm.+ -. 16nm; red (R): 650 nm.+ -. 16nm; red Edge (RE): 730 nm.+ -. 16nm; near Infrared (NIR): 840nm plus or minus 26nm, wherein the flying height is set to be 100m, the flying speed is designed to be 5m/s, the heading overlapping rate is designed to be 80%, the side overlapping rate is designed to be 70%, the unmanned aerial vehicle photographing mode is designed to be a flying spot hovering photographing mode, and other flying parameters are defaults;
before the wave band synthesis, the unmanned aerial vehicle is firstly utilized to carry out radiation correction on the wave band synthesis, the PIX4 DMapplicator is used for carrying out agriculture multispectral image jigsaw, and normalization processing is carried out after the jigsaw to obtain vegetation reflectivity information.
Secondly, acquiring ground parameters: each cell is 9 meters long by 8 meters wide and 1 meter in line spacing, and one cell is divided into 2 parts in order to increase the data volume while reducing variability of data samples. The leaf area index was measured in the middle 3 rows by the LAI-2200 using the method for measuring leaf area index of row crops in manual.
Next, extraction of the spectral index is performed: the region of interest of each cell (a cell is divided into two parts by ground observation, so that each sample is more representative) is drawn in QGIS3.22, the range of the region of interest is the middle 6 rows, and the spectral index value of each cell is extracted by a vegetation index formula.
S103: obtaining vegetation indexes of cotton crowns of different cells according to the spectral image reflectivity data through a vegetation index calculation formula;
further, in one embodiment of the present invention, obtaining vegetation indexes of cotton crowns of different cells according to a vegetation index calculation formula according to spectral image reflectivity data includes:
normalized difference vegetation index NDVI: (NIR-R)/(NIR+R);
normalized differential red edge vegetation index NDRE: (NIR-RE)/(nir+re);
visible light differential vegetation index VDVI: (2*G-R-B)/(2 x g+r+b);
normalized green red difference index NGRDI: (G-R)/(g+r);
green normalized difference vegetation index GNDVI: (NIR-G)/(NIR+G);
green wide dynamic range vegetation index gwrvi: (0.12 nir-G)/(0.12 nir+g);
simple ratio vegetation index SR: NIR/R;
green ratio vegetation index GRVI: NIR/G;
red-green ratio index RGRI: R/G;
differential vegetation index DVI: NIR-R;
the overgreen index EXG:2*G-R-B;
the redness index EXR:1.4 x r-G;
over-green minus over-red index EXGR: EXG-EXR;
nutritional index VEG: G/(R) a *B (1-a) ),a＝0.667；
Visible atmospheric impedance index VARI: (G-R)/(g+r-B);
red edge soil adjustment vegetation index RESAVI:1.5 x (NIR-RE)/(nir+re+0.5);
improving a soil adjustment vegetation index MSAVI:0.5 (2. NIR+1-sqrt ((2. NIR+1) 2-8 (NIR-R))
Enhanced vegetation index EVI:2.5 x (NIR-R)/(nir+ 6*R-7.5 x b+1);
normalized red index NRI: R/(NIR+RE+R);
wherein, B, G, R, RE, NIR represent blue band, green band, red side band, near infrared band, the central wavelength is respectively: 450nm,560nm,650nm,730nm,850nm.
S104: carrying out unitary linear regression modeling and prediction on the vegetation index and the leaf area index according to the leaf area index and the vegetation index;
further, in one embodiment of the present invention, the unitary linear regression modeling and prediction of the vegetation index and the leaf area index from the leaf area index and the vegetation index comprises:
dividing a training set and a testing set, and carrying out linear regression modeling on the training set according to the proportion of 7:3;
by determining the coefficient R 2 The performance of the model is evaluated by the root mean square error RMSE and the relative root mean square error R-RMSE, and the best model is selected.
Specifically, a unitary linear regression modeling is performed on the selected vegetation index and leaf area index.
When the model is built, the model is divided into a training set and a testing set, and the ratio of the training set to the testing set is 7:3. By determining the coefficient (R 2 ) The performance of the model was evaluated by Root Mean Square Error (RMSE) and relative root mean square error R-RMSE, and the best model was selected and calculated by performing a linear model regression operation at R4.1.3.
The inversion model at 100m has the highest precision and the vegetation index has the highest inversion precisionFor EVI, MSAVI, followed by DVI and RESAVI. R of EVI and MSAVI in training set 2 0.92, and both RMSE and R-RMSE are 0.30 and 0.12, respectively. In test set EVI, R of MSAVI 2 Each 0.92, the RMSE of evi is 0.28. The RMSE of msavi is 0.29.R-RMSE was 0.12.DVI in training set R 2 0.90, 0.33 for RMSE and 0.13 for R-RMSE, R in the test set 2 0.90, 0.31 for RMSE and 0.13 for R-RMSE. RESAVI in training set R 2 0.88, 0.36 for RMSE and 0.15 for R-RMSE, R in the test set 2 0.90, 0.32 for RMSE and 0.13 for R-RMSE.
S105: and evaluating a model of the vegetation index and the leaf area index to obtain the vegetation index with highest inversion leaf area index precision.
According to the method for estimating the cotton defoliation progress based on the unmanned aerial vehicle multispectral inversion leaf area indexes, 19 vegetation indexes which are strong in correlation with the crop leaf area indexes or good in predicted crop leaf area indexes in the literature are selected, modeling prediction is carried out on the 19 vegetation indexes and the leaf area indexes, the optimal vegetation indexes of inversion leaf area indexes before and after defoliation in the later period of cotton fertility are determined, and the defoliation progress of cotton is determined through the inverted leaf area indexes. Provides reference for dynamic monitoring and timely harvesting of defoliation of cotton fields, and provides important theoretical basis and technical support for accurate agricultural management and decision making of regional scale.
Compared with the conventional defoliation rate description defoliation process, the invention has the advantages that:
leaf area index rather than defoliation rate was redefined as a science describing cotton defoliation process. Traditional methods evaluate cotton defoliation processes in terms of defoliation rate. However, defoliation rate is a relative value, which is complex to investigate. And cotton leaves are large and small, and the single leaf removal rate index represented by the number change is used for representing the leaf removal effect of cotton, so that the cotton leaf harvester can better meet the need of reducing the impurity content of cotton harvesting. The invention provides a linear regression equation for inverting the optimal height of the leaf area index and inverting the leaf area index through researching the multispectral index extracted by the unmanned aerial vehicle before and after spraying defoliation ripening agent on cotton and the measured leaf area index. The unmanned aerial vehicle remote sensing monitoring technology can replace manual large-area and rapid monitoring of cotton leaf area indexes, and provides references for dynamic monitoring and timely harvesting of cotton field defoliation conditions.
In order to realize the embodiment, the invention also provides a device for estimating the cotton defoliation process based on the unmanned aerial vehicle multispectral inversion leaf area index.
Fig. 2 is a schematic structural diagram of a cotton defoliation process estimation device based on unmanned aerial vehicle multispectral inversion leaf area index according to an embodiment of the invention.
As shown in fig. 2, the device for estimating cotton defoliation process based on unmanned aerial vehicle multispectral inversion leaf area index comprises: a first acquisition module 100, a second acquisition module 200, a calculation module 300, a construction module 400, an evaluation module 500, wherein,
the first acquisition module is used for acquiring leaf area indexes before and after defoliation of cotton in different periods;
the second acquisition module is used for acquiring multi-spectral image data of the cotton field; preprocessing the cotton multispectral image data to obtain cotton canopy multispectral image reflectivity data;
the calculating module is used for obtaining vegetation indexes of the cotton crowns of different cells according to the spectral image reflectivity data through a vegetation index calculating formula;
the construction module is used for carrying out unitary linear regression modeling and prediction on the vegetation index and the leaf area index according to the leaf area index and the vegetation index;
and the evaluation module is used for evaluating the model of the vegetation index and the leaf area index to obtain the vegetation index with highest inversion leaf area index precision.
Further, in an embodiment of the present invention, the first obtaining module is further configured to:
the leaf area indexes of different communities are obtained before and after cotton defoliation, and defoliation ripening agents Xinsaili are sprayed in preset time.
Further, in an embodiment of the present invention, the second obtaining module is further configured to:
by dividing the cotton field area into 2 parts, the leaf area index is measured in the middle 3 rows by the LAI-2200 using the method for measuring leaf area index of row crops in the manual according to LAI-2200 to increase the data volume while reducing variability of the data samples.
Further, in one embodiment of the present invention, the building block is further configured to:
dividing a training set and a testing set, and carrying out linear regression modeling on the training set according to the proportion of 7:3;
by determining the coefficient R 2 The performance of the model is evaluated by the root mean square error RMSE and the relative root mean square error R-RMSE, and the best model is selected.
To achieve the above object, an embodiment of the third aspect of the present invention provides a computer device, which is characterized by comprising a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor implements the method for estimating cotton defoliation process based on the multispectral inversion leaf area index of the unmanned aerial vehicle as described above when executing the computer program.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.
Claims (10)
1. A method for estimating cotton defoliation progress based on unmanned aerial vehicle multispectral inversion leaf area index is characterized by comprising the following steps:
acquiring leaf area indexes before and after defoliation of cotton in different periods;
acquiring multi-spectral image data of cotton fields; preprocessing the cotton multispectral image data to obtain cotton canopy multispectral image reflectivity data;
obtaining vegetation indexes of cotton crowns of different cells according to the spectral image reflectivity data through a vegetation index calculation formula;
carrying out unitary linear regression modeling and prediction on the vegetation index and the leaf area index according to the leaf area index and the vegetation index;
and evaluating a model of the vegetation index and the leaf area index to obtain the vegetation index with highest inversion leaf area index precision.
2. The method of claim 1, wherein said obtaining leaf area indices of cotton before and after defoliation at different times comprises:
the leaf area indexes of different communities are obtained before and after cotton defoliation, and defoliation ripening agents Xinsaili are sprayed in preset time.
3. The method of claim 1, wherein the acquiring cotton field multispectral image data comprises:
by dividing the cotton field area into 2 parts, the leaf area index is measured in the middle 3 rows by the LAI-2200 using the method for measuring leaf area index of row crops in the manual according to LAI-2200 to increase the data volume while reducing variability of the data samples.
4. The method of claim 1, wherein the obtaining the vegetation index of the cotton canopy of the different cells according to the spectral image reflectivity data through a vegetation index calculation formula comprises:
normalized difference vegetation index NDVI: (NIR-R)/(NIR+R);
normalized differential red edge vegetation index NDRE: (NIR-RE)/(nir+re);
visible light differential vegetation index VDVI: (2*G-R-B)/(2 x g+r+b);
normalized green red difference index NGRDI: (G-R)/(g+r);
green normalized difference vegetation index GNDVI: (NIR-G)/(NIR+G);
green wide dynamic range vegetation index gwrvi: (0.12 nir-G)/(0.12 nir+g);
simple ratio vegetation index SR: NIR/R;
green ratio vegetation index GRVI: NIR/G;
red-green ratio index RGRI: R/G;
differential vegetation index DVI: NIR-R;
the overgreen index EXG:2*G-R-B;
the redness index EXR:1.4 x r-G;
over-green minus over-red index EXGR: EXG-EXR;
nutritional index VEG: G/(R) a *B (1-a) ),a＝0.667；
Visible atmospheric impedance index VARI: (G-R)/(g+r-B);
red edge soil adjustment vegetation index RESAVI:1.5 x (NIR-RE)/(nir+re+0.5);
improving a soil adjustment vegetation index MSAVI:0.5 x (2 x NIR+1-sqrt ((2 x NIR+1)) 2 -8*(NIR-R)))
Enhanced vegetation index EVI:2.5 x (NIR-R)/(nir+ 6*R-7.5 x b+1);
normalized red index NRI: R/(NIR+RE+R);
wherein, B, G, R, RE, NIR represent blue band, green band, red side band, near infrared band, the central wavelength is respectively: 450nm,560nm,650nm,730nm,850nm.
5. The method of claim 1, wherein the modeling and predicting a unitary linear regression of a vegetation index and a leaf area index from the leaf area index and the vegetation index comprises:
dividing a training set and a testing set, and carrying out linear regression modeling on the training set according to the proportion of 7:3;
by determining the coefficient R 2 The performance of the model is evaluated by the root mean square error RMSE and the relative root mean square error R-RMSE, and the best model is selected.
6. The device for estimating the cotton defoliation process based on the multispectral inversion leaf area index of the unmanned aerial vehicle is characterized by comprising the following modules:
the first acquisition module is used for acquiring leaf area indexes before and after defoliation of cotton in different periods;
the second acquisition module is used for acquiring multi-spectral image data of the cotton field; preprocessing the cotton multispectral image data to obtain cotton canopy multispectral image reflectivity data;
the calculating module is used for obtaining vegetation indexes of the cotton crowns of different cells according to the spectral image reflectivity data through a vegetation index calculating formula;
the construction module is used for carrying out unitary linear regression modeling and prediction on the vegetation index and the leaf area index according to the leaf area index and the vegetation index;
and the evaluation module is used for evaluating the model of the vegetation index and the leaf area index to obtain the vegetation index with highest inversion leaf area index precision.
7. The apparatus of claim 6, wherein the first acquisition module is further configured to:
the leaf area indexes of different communities are obtained before and after cotton defoliation, and defoliation ripening agents Xinsaili are sprayed in preset time.
8. The apparatus of claim 6, wherein the second acquisition module is further configured to:
by dividing the cotton field area into 2 parts, the leaf area index is measured in the middle 3 rows by the LAI-2200 using the method for measuring leaf area index of row crops in the manual according to LAI-2200 to increase the data volume while reducing variability of the data samples.
9. The apparatus of claim 6, wherein the build module is further to:
dividing a training set and a testing set, and carrying out linear regression modeling on the training set according to the proportion of 7:3;
by determining the coefficient R 2 The performance of the model is evaluated by the root mean square error RMSE and the relative root mean square error R-RMSE, and the best model is selected.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of estimating cotton defoliation based on the unmanned aerial vehicle multispectral inversion leaf area index according to any one of claims 1 to 5 when the computer program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310664798.9A CN116796293A (en) | 2023-06-06 | 2023-06-06 | Method for estimating cotton defoliation process based on unmanned aerial vehicle multispectral inversion leaf area index |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310664798.9A CN116796293A (en) | 2023-06-06 | 2023-06-06 | Method for estimating cotton defoliation process based on unmanned aerial vehicle multispectral inversion leaf area index |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116796293A true CN116796293A (en) | 2023-09-22 |
Family
ID=88040811
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310664798.9A Pending CN116796293A (en) | 2023-06-06 | 2023-06-06 | Method for estimating cotton defoliation process based on unmanned aerial vehicle multispectral inversion leaf area index |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116796293A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103766145A (en) * | 2014-02-25 | 2014-05-07 | 山东棉花研究中心 | Rapid indentifying method for disleaving effect before cotton harvesting |
| CN111062251A (en) * | 2020-03-23 | 2020-04-24 | 乔红波 | Monitoring method of farmland cotton aphid pest grade model based on unmanned aerial vehicle imaging |
| CN114998728A (en) * | 2022-05-24 | 2022-09-02 | 中国农业大学 | Method and system for predicting cotton leaf area index by multi-source remote sensing of unmanned aerial vehicle |
-
2023
- 2023-06-06 CN CN202310664798.9A patent/CN116796293A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103766145A (en) * | 2014-02-25 | 2014-05-07 | 山东棉花研究中心 | Rapid indentifying method for disleaving effect before cotton harvesting |
| CN111062251A (en) * | 2020-03-23 | 2020-04-24 | 乔红波 | Monitoring method of farmland cotton aphid pest grade model based on unmanned aerial vehicle imaging |
| CN114998728A (en) * | 2022-05-24 | 2022-09-02 | 中国农业大学 | Method and system for predicting cotton leaf area index by multi-source remote sensing of unmanned aerial vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zheng et al. | Improved estimation of rice aboveground biomass combining textural and spectral analysis of UAV imagery | |
| Liu et al. | Estimating leaf area index using unmanned aerial vehicle data: shallow vs. deep machine learning algorithms | |
| CN110222475B (en) | Method for inverting moisture content of winter wheat plants based on multispectral remote sensing of unmanned aerial vehicle | |
| CN112903600B (en) | Rice nitrogen fertilizer recommendation method based on multispectral image of fixed-wing unmanned aerial vehicle | |
| CN110567891B (en) | Winter wheat canopy chlorophyll estimation system and method | |
| CN108169138B (en) | Rice lodging monitoring method utilizing thermal infrared image | |
| CN111241912A (en) | Multi-vegetation index rice yield estimation method based on machine learning algorithm | |
| JP2006250827A (en) | Analytical method for growth condition of crop | |
| CN111091052A (en) | Corn lodging area extraction system and method based on maximum likelihood method | |
| CN111028096A (en) | System and method for integrating space, air and ground data | |
| CN110658211A (en) | Method for extracting spectral characteristics of cotton canopy of aphid pests in cotton bud period and estimating grade | |
| CN114140695B (en) | Prediction method and system for tea tree nitrogen diagnosis and quality index determination based on unmanned aerial vehicle multispectral remote sensing | |
| CN112986158B (en) | Beet nitrogen nutrition detection method and system based on unmanned aerial vehicle multispectral data | |
| CN116308866B (en) | Rice ear biomass estimation method and system based on canopy reflection spectrum | |
| CN111882242A (en) | Evaluation method of vegetation index in herbage biomass estimation research | |
| CN115372286A (en) | Corn water nitrogen content inversion method based on unmanned aerial vehicle multispectral remote sensing | |
| Kazemi et al. | Evaluation of RGB vegetation indices derived from UAV images for rice crop growth monitoring | |
| CN117292267B (en) | Method and system for estimating rice aboveground biomass in segments based on weather information | |
| CN114549881A (en) | Wheat early stem tiller number estimation method based on regional gradual change vegetation index | |
| CN112345467B (en) | Model for estimating physiological parameters of rice by using remote sensing technology and application thereof | |
| CN116482041B (en) | Rice heading period nondestructive rapid identification method and system based on reflection spectrum | |
| CN117074340A (en) | Wheat nitrogen content measuring and calculating method based on hyperspectral remote sensing image of unmanned aerial vehicle | |
| CN114694020B (en) | Construction method of cotton aphid remote sensing prediction model | |
| CN116796293A (en) | Method for estimating cotton defoliation process based on unmanned aerial vehicle multispectral inversion leaf area index | |
| Liu et al. | Estimating wheat coverage using multispectral images collected by unmanned aerial vehicles and a new sensor |
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 |