Unmanned aerial vehicle remote sensing monitoring method for cotton defoliation and ripening process feedback

Abstract

The invention relates to an unmanned aerial vehicle remote sensing monitoring method for cotton defoliation and ripening process feedback. The method comprises the following steps: step 1, establishing a reference model according to historical data; step 2, data acquisition: utilizing an unmanned aerial vehicle to carry a spectrum camera to acquire spectrum data of the cotton field; and step 3, data processing: importing the collected cotton field spectral data into the reference model for comparison. According to the technical scheme, the benchmark model based on the spectral information is constructed as a reference, the spectral information is obtained at the same collection time interval in the cotton defoliation and ripening acceleration process, a plurality of comparison points in the benchmark model are compared one by one, the difference between the current process and the historical process can be reflected, and the pesticide application condition is adjusted according to the difference.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural informatization, and specifically relates to an unmanned aerial vehicle remote sensing monitoring method for feedback on the process of cotton defoliation and ripening promotion. Background Art

[0002] Cotton defoliation and ripening promotion is a key link in cotton production. Usually, the method of spraying defoliation and ripening agents is adopted to prompt 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 unginned cotton.

[0003] Traditional methods rely on manual observation and empirical judgment, and have problems such as low efficiency and poor accuracy. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide an unmanned aerial vehicle remote sensing monitoring method for feedback on the process of cotton defoliation and ripening promotion, so as to solve the problems that the existing technology relies on manual observation and empirical judgment and has low efficiency and poor accuracy.

[0005] The present invention is realized through the following technical solutions:

[0006] An unmanned aerial vehicle remote sensing monitoring method for feedback on the process of cotton defoliation and ripening promotion, including the following steps:

[0007] Step 1: Establish a benchmark model according to historical data;

[0008] Step 2: Data collection, using an unmanned aerial vehicle equipped with a spectral camera to collect spectral data of a cotton field;

[0009] Step 3: Data processing, importing the collected spectral data of the cotton field into the benchmark model for comparison.

[0010] Further defined, the construction method of the benchmark model is:

[0011] During the process of cotton leaves turning from green to yellow, cotton leaves are collected according to the time process, and spectral data of the cotton leaves are collected using a spectral camera;

[0012] Among them, the collected cotton leaves are of the same variety, and the collection interval is 2 - 3 days;

[0013] The specific collection method is to take the upper, middle, and lower layers on the same plant, collect the same number of cotton leaves in each layer, then collect spectral data for each cotton leaf, calculate its spectral index, and then take the average value to obtain the benchmark spectral value;

[0014] Finally, a number of benchmark values are sorted in sequence according to the time line to form a benchmark model, and a number of benchmark parameters form a number of comparison points in the benchmark model.

[0015] Further defined, the specific method of data collection is:

[0016] Formulate flight plans based on cotton field area and terrain, and collect spectra from cotton fields;

[0017] The collection interval is 2 to 3 days, and the collection method is to collect multiple times on the flight path of the UAV, and then take the average value to obtain comparative spectral data.

[0018] It is further defined that the spectral camera is a hyperspectral camera, the data collected by the camera is hyperspectral data, and the calculation formula of the reference spectral value and the comparison spectral value is:

[0019]

[0020] Where:

[0021] R Red is: reflectivity of the red band;

[0022] R Green is: reflectivity of green band;

[0023] R Blue is: reflectivity of the blue band;

[0024] Among them, the lower the GI value, the lower the greenness of the vegetation and the higher the degree of yellowing.

[0025] It is further defined that the processing method of the comparative spectral data is:

[0026] The hyperspectral camera carried by the drone is used to capture spectral information in the range of 400-1000nm, and the collected data is stored in the drone’s local storage device and wirelessly transmitted to the cloud for storage;

[0027] The collected data is called from the drone’s local storage device or the cloud, and radiation correction, atmospheric correction, geometric correction and data dimension reduction are performed on it in turn, and then feature extraction is performed on it.

[0028] It is further defined that the spectral camera is a hyperspectral camera, the data collected by the camera is hyperspectral data, and the calculation formula of the reference spectral value and the comparison spectral value is:

[0029]

[0030] Where:

[0031] R NIR is: reflectivity of green band;

[0032] R Red is: reflectivity of the red band;

[0033] Among them, the lower the NDVI value, the worse the vegetation health.

[0034] Further defined, the processing method of the comparative spectral data is as follows:

[0035] Use the multispectral camera carried by the drone to capture the spectral information in the blue, green, red, red edge and near-infrared bands, store the collected data in the local storage device of the drone, and transmit it wirelessly to the cloud for storage;

[0036] Call the collected data in the local storage device or the cloud of the drone, perform radiometric correction, atmospheric correction, geometric correction and data fusion on it in sequence, and then perform feature extraction on it.

[0037] A method for remotely sensing and monitoring the process of cotton defoliation and ripening promotion by drone. According to the cotton field area and terrain, a flight plan is formulated, and a hyperspectral camera carried by the drone is used to collect the spectrum of the cotton field to obtain the spectral information of the cotton field;

[0038] Generate a cotton field color index map according to the spectral information and the cotton field map synthesis.

[0039] Further defined, the spectral acquisition interval is 2 to 3 days, and multiple color index maps are produced according to the time line.

[0040] Further defined, the processing method of the spectral information is as follows:

[0041] Use remote sensing data processing software to read the multispectral data, calculate the NDVI value of each pixel, and generate an NDVI value index map;

[0042] Then map and generate a color NDVI value index map in the remote sensing data processing software, that is, a color index map, and finally output the image.

[0043] The beneficial effects of the present invention are as follows:

[0044] The method for remotely sensing and monitoring the process of cotton defoliation and ripening promotion by drone constructs a reference model based on spectral information as a reference. During the process of cotton defoliation and ripening promotion, spectral information is obtained at the same acquisition time interval, and multiple comparison points in the reference model are compared one by one, which can reflect the gap between the current process and the historical process, and adjust the application of pesticides according to the gap.

[0045] Other advantages, objectives and features of the present invention will be described to some extent in the subsequent specification, and to some extent, will be obvious to those skilled in the art based on the study of the following text, or can be taught from the practice of the present invention. The objectives and other advantages of the present invention can be realized and obtained through the following specification. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1It is the reference model architecture diagram of Embodiment 1 of the present invention;

[0047] Figure 2 It is the architecture diagram of the spectral information processing method of Embodiment 1 of the present invention;

[0048] Figure 3 It is the architecture diagram of the spectral information processing method of Embodiment 2 of the present invention;

[0049] Figure 4 It is the architecture diagram of Embodiment 3 of the present invention; Detailed implementation manners

[0050] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Usually, the components of the embodiments of the present invention described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations.

[0051] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed present invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0052] It should be noted that: similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0053] In the above description of the present invention, it should be noted that the orientation or positional relationship indicated by terms such as "one side", "the other side", etc. is based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the present invention is usually placed during use. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus cannot be construed as a limitation of the present invention. In addition, terms such as "first", "second", etc. are only used for distinguishing descriptions and cannot be construed as indicating or implying relative importance.

[0054] In addition, terms such as "the same" do not mean that the components must be absolutely the same, but there may be slight differences. The term "vertical" only means that the positional relationship between components is more vertical relative to "parallel", and does not mean that the structure must be completely vertical, but can be slightly inclined.

[0055] Embodiment 1

[0056] The present invention provides a technical solution: a method for remotely sensing and monitoring of a cotton defoliation and ripening process feedback by an unmanned aerial vehicle, comprising the following steps:

[0057] Step 1, establish a benchmark model according to historical data;

[0058] Step 2, data collection, using an unmanned aerial vehicle equipped with a spectral camera to collect spectral data of a cotton field;

[0059] Step 3, data processing, importing the collected spectral data of the cotton field into the benchmark model for comparison.

[0060] The construction method of the benchmark model is as follows:

[0061] During the process of cotton leaves turning from green to yellow, collect cotton leaves according to the time process, and use a spectral camera to collect the spectra of the cotton leaves;

[0062] Among them, the collected cotton leaves are of the same variety, and the collection interval is 2 to 3 days;

[0063] The specific collection method is to take the upper, middle, and lower layers on the same plant, collect the same number of cotton leaves on each layer, then collect the spectra of each cotton leaf, calculate its spectral index, and then take the average value to obtain the benchmark spectral value;

[0064] Finally, arrange a number of benchmark values in sequence according to the time line to form a benchmark model, and a number of benchmark parameters form a number of comparison points in the benchmark model.

[0065] The specific method for data collection is as follows:

[0066] Formulate a flight plan according to the area and terrain of the cotton field, and collect the spectra of the cotton field;

[0067] Among them, the collection interval is 2 to 3 days, and the collection method is to conduct multiple collections on the flight path of the unmanned aerial vehicle, and then take the average value to obtain the comparison spectral data.

[0068] The spectral camera is a hyperspectral camera, and the data collected by it is hyperspectral data. The calculation formulas for the benchmark spectral value and the comparison spectral value are:

[0069]

[0070] In the formula:

[0071] R Red is: the reflectance of the red band;

[0072] R Green is: the reflectance of the green band;

[0073] R Blue is: the reflectance of the blue band;

[0074] Among them, the lower the GI value, the lower the green degree of the vegetation and the higher the yellowing degree.

[0075] Use the hyperspectral camera carried by the drone to capture spectral information in the range of 400 - 1000 nm, store the collected data in the local storage device of the drone, and transmit it wirelessly to the cloud for storage;

[0076] Call the collected data in the local storage device of the drone or in the cloud, and perform the following operations on it in sequence:

[0077] Radiometric correction, eliminate the influence of sensor error and illumination conditions, and convert the original data into reflectance data;

[0078] Atmospheric correction, eliminate the influence of atmospheric scattering and absorption, and obtain the true surface reflectance;

[0079] Geometric correction, correct image distortion, and ensure that the image is aligned with the geographic coordinates;

[0080] Data dimensionality reduction, use methods such as principal component analysis (PCA) or linear discriminant analysis (LDA) to reduce the data dimension and improve the processing efficiency;

[0081] Then perform feature extraction on it, and extract spectral features (such as absorption peaks, reflectance curves);

[0082] By constructing a reference model based on spectral information as a reference, during the process of defoliating and ripening cotton, obtain spectral information at the same acquisition time interval, and compare it one by one with multiple comparison points in the reference model, which can reflect the gap between the current process and the historical process, and adjust the application of pesticides according to the gap.

[0083] Example Two

[0084] The difference from Example One is that the spectral camera is a hyperspectral camera, the data it collects is hyperspectral data, and the calculation formulas for the reference spectral value and the comparison spectral value are:

[0085]

[0086] In the formula:

[0087] R NIR is the reflectance of the green band;

[0088] R Red is the reflectance of the red band;

[0089] Among them, the lower the NDVI value, the worse the health status of the vegetation.

[0090] The processing method of the comparison spectral data is:

[0091] Use the multispectral camera carried by the UAV to capture spectral information in the blue, green, red, red-edge, and near-infrared bands, store the collected data in the local storage device of the UAV, and wirelessly transmit it to the cloud for storage;

[0092] Call the collected data in the local storage device of the UAV or in the cloud, and perform the following operations on it in sequence:

[0093] Radiometric correction to eliminate the influence of sensor errors and lighting conditions, and convert the original data into reflectance data;

[0094] Atmospheric correction to eliminate the influence of atmospheric scattering and absorption, and obtain the true surface reflectance;

[0095] Geometric correction to correct image distortion and ensure that the image is aligned with the geographic coordinates;

[0096] Data fusion to fuse multispectral data with other data sources (such as hyperspectral data, meteorological data) to improve data utilization;

[0097] Then perform feature extraction on it to extract spectral features (such as NDVI).

[0098] Example 3

[0099] A UAV remote sensing monitoring method for feedback on the defoliation and ripening process of cotton. A flight plan is formulated according to the cotton field area and terrain, and a hyperspectral camera is carried by the UAV to collect spectral information of the cotton field;

[0100] Generate a cotton field color index map based on the spectral information and the cotton field map synthesis.

[0101] The spectral acquisition interval is 2 to 3 days, and multiple color index maps are produced according to the time line.

[0102] The processing method of the spectral information is as follows:

[0103] Use remote sensing data processing software (such as ENVI, ArcGIS, or the GDAL library of Python) to read the multispectral data.

[0104] Calculate the NDVI value of each pixel to generate an NDVI index map.

[0105] Color mapping:

[0106] Define the color gradient and map the NDVI value to the color space.

[0107] For example:

[0108] Low NDVI value (healthy green vegetation): dark green.

[0109] Medium NDVI value (yellowing vegetation): Yellow.

[0110] High NDVI value (severely yellowing or senescent vegetation): Orange or red.

[0111] Use the color mapping tool in the software (such as ColorMapping in ENVI or the Matplotlib library in Python) to generate a color NDVI index map.

[0112] Image output:

[0113] Save the generated NDVI index map as an image file (such as GeoTIFF or PNG format).

[0114] Generating a color vegetation index map through the NDVI index can visually display the change from green to yellow during the defoliation and ripening process of cotton. Combining time series analysis and visualization tools can provide important data support for precision agriculture management.

[0115] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the purpose and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A method for remotely sensing and monitoring cotton defoliation and ripening process by using an unmanned aerial vehicle, characterized in that: It includes the following steps: Step 1: Establish a benchmark model based on historical data; Step 2: Data collection. Use a drone equipped with a spectral camera to collect spectral data of the cotton field; Step 3: Data processing. Import the collected spectral data of the cotton field into the benchmark model for comparison.

2. The UAV remote sensing monitoring method for the feedback of the cotton defoliation and ripening process according to claim 1, wherein: The construction method of the benchmark model is as follows: During the process of cotton leaves turning from green to yellow, collect cotton leaves according to the time process, and use a spectral camera to collect the spectra of the cotton leaves; Among them, the collected cotton leaves are of the same variety, and the collection interval is 2 - 3 days; The specific collection method is to take the upper, middle, and lower layers on the same plant, with the same number of cotton leaves collected in each layer. Then, collect the spectra of each cotton leaf, calculate its spectral index, and then take the average value to obtain the benchmark spectral value; Finally, sort a number of benchmark values in sequence according to the time line to form a benchmark model, and a number of benchmark parameters form a number of comparison points in the benchmark model.

3. The UAV remote sensing monitoring method for the feedback of the cotton defoliation and ripening process according to claim 1, characterized in that: The specific method of data collection is as follows: Formulate a flight plan according to the area and terrain of the cotton field, and conduct spectral collection on the cotton field; Among them, the collection interval is 2 - 3 days, and the collection method is to conduct multiple collections on the flight path of the drone, and then take the average value to obtain the comparison spectral data.

4. The UAV remote sensing monitoring method for the feedback of the cotton defoliation and ripening process according to claim 2 or 3, characterized in that: The spectral camera is a hyperspectral camera, and the data it collects is hyperspectral data. The calculation formulas for the benchmark spectral value and the comparison spectral value are: In the formula: R Red is: the reflectance of the red band; R Green is: the reflectance of the green band; R Blue is: the reflectance in the blue band; Among them, the lower the GI value, the lower the green degree of the vegetation and the higher the yellowing degree.

5. The method for remotely sensing and monitoring drones for feedback on the cotton defoliation and ripening process according to claim 4, characterized in that: The processing method of the comparison spectral data is: Use the hyperspectral camera carried by the drone to capture spectral information in the range of 400 - 1000 nm, store the collected data in the local storage device of the drone, and transmit it wirelessly to the cloud for storage; Call the collected data in the local storage device or the cloud of the drone, perform radiometric correction, atmospheric correction, geometric correction, and data dimensionality reduction on it in sequence, and then perform feature extraction on it.

6. The UAV remote sensing monitoring method for the feedback of the cotton defoliation and ripening process according to claim 2 or 3, characterized in that: The spectral camera is a hyperspectral camera, and the data it collects is hyperspectral data. The calculation formulas for the benchmark spectral value and the comparison spectral value are: In the formula: R NIR is: the reflectance of the green band; R Red is: the reflectance of the red band; Among them, the lower the NDVI value, the worse the health status of the vegetation.

7. The UAV remote sensing monitoring method for the feedback of the cotton defoliation and ripening process according to claim 6, wherein: The processing method of the comparison spectral data is: Use the multispectral camera carried by the drone to capture spectral information in the blue, green, red, red edge, and near-infrared bands, store the collected data in the local storage device of the drone, and transmit it wirelessly to the cloud for storage; Call the collected data in the local storage device or the cloud of the drone, perform radiometric correction, atmospheric correction, geometric correction, and data fusion on it in sequence, and then perform feature extraction on it.

8. A method for remotely sensing and monitoring of a cotton defoliation and ripening process feedback by an unmanned aerial vehicle, characterized in that: Formulate a flight plan according to the area and terrain of the cotton field, use a drone equipped with a hyperspectral camera to conduct spectral collection on the cotton field, and obtain the spectral information of the cotton field; Generate a cotton field color index map according to the synthesis of the spectral information and the cotton field map.

9. The method for remotely sensing and monitoring of a cotton defoliation and ripening acceleration process feedback according to claim 8, characterized in that: The spectral collection interval is 2 - 3 days, and multiple color index maps are produced according to the time line.

10. The UAV remote sensing monitoring method for feedback of cotton defoliation and ripening acceleration process according to claim 8 or 9, characterized in that: The processing method of the spectral information is: Use remote sensing data processing software to read the multispectral data, calculate the NDVI value of each pixel, and generate an NDVI value index map; Then, it is mapped in the remote sensing data processing software to generate a color NDVI value index map, that is, a color index map, and finally the image is output.

Images