Crop moisture detection method and system
By fusing feature information from multispectral and RGB images for crop canopy moisture detection, the problem of insufficient prediction accuracy in existing technologies is solved, achieving high-precision non-destructive detection and visualization.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- ZHEJIANG UNIV
- Filing Date
- 2024-12-24
- Publication Date
- 2026-04-28
AI Technical Summary
Existing crop canopy moisture detection technologies lack the integration of crop color and texture characteristics, resulting in insufficient prediction accuracy. Furthermore, traditional methods are susceptible to environmental influences and are costly.
By acquiring multispectral orthophotos and RGB orthophotos, farmland areas are extracted and their reflectance, vegetation index, color information, and texture information are fused. Moisture prediction is then performed using machine learning or deep learning algorithms.
It enables accurate and non-destructive detection of crop canopy moisture, improves prediction accuracy and reduces environmental impact, with a prediction error of less than 5%.
Smart Images
Figure CN121933449A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of crop moisture detection, and in particular to a method and system for crop moisture detection. Background Technology
[0002] Water is a key factor affecting crop growth, quality, and yield; water deficit directly impacts crop physiological and biochemical processes and morphological structure. Crop canopy moisture monitoring is crucial for guiding field irrigation and water-saving production. Accurate canopy moisture monitoring helps farmers better manage irrigation and fertilization, optimize crop growing conditions, and improve yield and quality. Furthermore, timely monitoring of crop canopy moisture can prevent pests and diseases, reducing economic losses caused by improper water management.
[0003] Traditional methods for detecting crop canopy moisture include electric drying ovens, low-field nuclear magnetic resonance (NMR) imaging, and vacuum drying. While these methods offer high accuracy, they are susceptible to environmental influences, costly, and can damage samples. With advancements in modern agriculture and the continuous development of UAV remote sensing technology, high-throughput crop growth monitoring methods in the field have also made significant progress. Multispectral remote sensing technology, with its advantages of multi-band, image-spectral integration, and rich spectral information, enables rapid and non-destructive monitoring of crop canopy moisture content. However, existing crop canopy moisture detection technologies often combine data acquired by UAVs and single multispectral cameras for predictive modeling, lacking the fusion of crop color, texture, and other characteristic information, thus requiring improvement in prediction accuracy. Summary of the Invention
[0004] The purpose of this application is to provide a method and system for detecting crop moisture content, which can achieve accurate and non-destructive detection of crop canopy moisture content.
[0005] To achieve the above objectives, this application provides the following solution:
[0006] Firstly, this application provides a method for detecting crop moisture content, including:
[0007] Acquire the multispectral orthophoto and RGB orthophoto of the plot to be inspected, respectively;
[0008] Farmland areas are extracted from the multispectral orthophoto to obtain the first region of interest;
[0009] The farmland area is extracted from the RGB orthophoto to obtain the second region of interest;
[0010] First feature information is extracted from the first region of interest; the first feature information includes the reflectance and vegetation index of each pixel in the first region of interest.
[0011] Extract second feature information from the second region of interest; the second feature information includes the color information and texture information of each pixel in the second region of interest.
[0012] Based on the first feature information and the second feature information, the moisture value of the crop canopy of the plot to be tested is determined.
[0013] Optionally, the multispectral orthophoto and RGB orthophoto of the plot to be detected are acquired, specifically including:
[0014] Multispectral and RGB images of the land parcel to be inspected were acquired using a multispectral camera and an RGB camera, respectively.
[0015] The multispectral image and the RGB image are stitched together to obtain a multispectral orthophoto and an RGB orthophoto.
[0016] Optionally, before stitching together the multispectral image and RGB image of the land parcel to be detected, obtaining the multispectral orthophoto and RGB orthophoto of the land parcel to be detected respectively further includes:
[0017] The multispectral image and the RGB image are corrected respectively.
[0018] Optionally, farmland areas are extracted from the multispectral orthophoto to obtain a first region of interest, specifically including:
[0019] The first region of interest is obtained by manually selecting or cropping the multispectral orthophoto image based on the geographic coordinates of the farmland area.
[0020] Optionally, the farmland area is extracted from the RGB orthophoto to obtain a second region of interest, specifically including:
[0021] The second region of interest is obtained by manually selecting or cropping the RGB orthophoto image based on the geographic coordinates of the farmland area.
[0022] Optionally, extracting first feature information from the first region of interest specifically includes:
[0023] Soil background removal is performed on the first region of interest to obtain a crop multispectral orthophoto image;
[0024] For any pixel in the crop multispectral orthophoto image, a first sampling region is defined with the pixel as the center;
[0025] The reflectance of the pixel is determined based on the reflectance of each pixel in each band within the first sampling area;
[0026] The vegetation index of the pixel is calculated based on the reflectance of the pixel.
[0027] Optionally, extracting second feature information from the second region of interest specifically includes:
[0028] Based on the location of the first sampling region in the crop multispectral orthophoto, a second sampling region is determined in the second region of interest;
[0029] The color information of the pixel is determined based on the color information of each pixel in the second sampling area;
[0030] The texture information of the pixel is determined based on the texture information of each pixel in the second sampling area.
[0031] Optionally, soil background removal is performed on the first region of interest, specifically including:
[0032] Calculate the soil-adjusted vegetation index for the first region of interest;
[0033] Based on the soil-adjusted vegetation index, an adaptive threshold segmentation method is used to remove soil background from the first region of interest.
[0034] Optionally, the crop moisture detection method further includes:
[0035] The moisture value of the crop canopy in the plot to be tested is mapped to a given color range and displayed.
[0036] Secondly, this application provides a crop moisture detection system, comprising:
[0037] The data acquisition module is used to acquire the multispectral orthophoto and RGB orthophoto of the plot to be detected, respectively.
[0038] A preprocessing module is used to extract farmland areas from the multispectral orthophoto to obtain a first region of interest, and to extract farmland areas from the RGB orthophoto to obtain a second region of interest;
[0039] The feature extraction module is used to extract first feature information from the first region of interest and second feature information from the second region of interest; the first feature information includes the reflectance and vegetation index of each pixel in the first region of interest; the second feature information includes the color information and texture information of each pixel in the second region of interest.
[0040] The crop moisture detection module is used to determine the moisture value of the crop canopy in the plot to be tested based on the first feature information and the second feature information.
[0041] According to the specific embodiments provided in this application, this application has the following technical effects:
[0042] This application provides a method and system for crop moisture detection. By fusing and analyzing multispectral orthophotos and RGB orthophotos, the reflectance, vegetation index, color information, and texture information of pixels are used as feature information. This solves the problem of low prediction accuracy when using single multispectral data for prediction modeling, and improves the accuracy of crop canopy moisture prediction. Farmland areas are extracted as regions of interest from orthophotos, avoiding the influence of non-farmland images on moisture detection results. Attached Figure Description
[0043] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0044] Figure 1 This is a diagram illustrating the application environment of a crop moisture detection method according to an embodiment of this application.
[0045] Figure 2 This is a flowchart illustrating a crop moisture detection method according to an embodiment of this application;
[0046] Figure 3 This is a schematic diagram of the structure of a crop moisture detection system according to an embodiment of this application;
[0047] Figure 4 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation
[0048] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0049] This application proposes a crop moisture detection method and system that can improve the accuracy of crop canopy moisture prediction and achieve high-precision visualization of crop canopy moisture values. The method has strong generalization and practical application value.
[0050] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.
[0051] The crop moisture detection method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be set up independently, integrated into server 104, or placed in the cloud or on another server. Terminal 102 can send multispectral and RGB images of the plot to be detected to server 104. After receiving the images, server 104 corrects and stitches them to obtain multispectral and RGB orthophotos of the plot. Farmland areas are extracted from these two types of orthophotos, corresponding to first and second regions of interest. First and second feature information are then extracted from these regions of interest, and finally, all feature information is used to obtain the moisture value of the crop canopy of the plot. Server 104 can then feed back the obtained crop canopy moisture value to terminal 102. In addition, in some embodiments, the crop moisture detection method can also be implemented by the server 104 or the terminal 102 alone. For example, the terminal 102 can directly use the multispectral image and RGB image of the plot to be detected to detect crop moisture, or the server 104 can obtain the multispectral image and RGB image of the plot to be detected from the data storage system and perform crop moisture detection on the image to be processed.
[0052] The terminal 102 can be, but is not limited to, various desktop computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. The server 104 can be implemented using a standalone server or a server cluster composed of multiple servers, or it can be a cloud server.
[0053] In one exemplary embodiment, such as Figure 2 As shown, this application proposes a method for detecting crop moisture, including steps 201 to 206. Wherein:
[0054] Step 201: Obtain the multispectral orthophoto and RGB orthophoto of the plot to be detected.
[0055] A drone equipped with a multispectral camera and an RGB camera was used to acquire multispectral and RGB images of crops in the plot to be inspected at a relative ground altitude of no more than 100m. In an exemplary embodiment, taking corn as an example, a DJI Movavic 3M drone was used to acquire multispectral and RGB images of corn during the tasseling stage of the plot to be inspected, with image resolutions of 2592×1944 and 5280×3956, respectively. The acquired multispectral images included four bands: red, green, near-infrared, and red-edge. The specific drone parameters were set as follows: 70% forward repeatability, 70% lateral repeatability, flight speed of 5m / s, and flight altitude of 50m.
[0056] Using Agisoft Metashape software, geometric and radiometric corrections were performed on the acquired multispectral and RGB images of the site to be inspected. Then, image registration technology was used to stitch the corrected multispectral and RGB images together to obtain the multispectral orthophoto and RGB orthophoto of the site to be inspected.
[0057] Step 202: Extract farmland areas from the multispectral orthophoto to obtain the first region of interest. Specifically, the first region of interest is obtained by manually selecting the farmland area or by cropping the multispectral orthophoto.
[0058] Step 203: Extract farmland areas from the RGB orthophoto to obtain the second region of interest. Specifically, the second region of interest is obtained by manually selecting areas or by cropping the RGB orthophoto based on the geographic coordinates of the farmland areas.
[0059] Step 204: Extract first feature information from the first region of interest. Specifically, the first feature information includes the reflectance and vegetation index of each pixel in the first region of interest.
[0060] Step 205: Extract second feature information from the second region of interest. Specifically, the second feature information includes the color information and texture information of each pixel in the second region of interest.
[0061] In steps 202 to 205 above, the multispectral orthophoto and RGB orthophoto are cropped by manually selecting areas or based on the geographic coordinates of the farmland area to obtain the first region of interest (ROI) and the second ROI. To avoid the influence of soil on the calculation of reflectance and vegetation index, soil background removal is performed on the first ROI to obtain the crop multispectral orthophoto. Specifically, the soil-adjusted vegetation index (SDI) of the first ROI is calculated, and based on the SDI, an adaptive threshold segmentation method is used to remove the soil background from the first ROI. The formula for calculating the SDI of the first ROI is as follows:
[0062]
[0063] Wherein, savi is the soil-adjusted vegetation index of the first region of interest; nir is the average reflectance of all pixels in the near-infrared band within the first region of interest; and r is the average reflectance of all pixels in the red band within the first region of interest.
[0064] After removing the soil background, a first sampling region is defined centered on any pixel in the crop multispectral orthophoto image. The actual ground distance corresponding to the side length of the first sampling region does not exceed 5m. Specifically, a square region with a pixel size of 200×200 is selected as the first sampling region. Considering the ground resolution of the multispectral image of 2.31cm / pixel, the actual ground distance corresponding to the side length of this region is 4.62m. After determining the first sampling region, the geographic coordinates of the first sampling region are obtained based on the pixel coordinates of the four corner points. The geographic coordinates of the first sampling region are then mapped to the second region of interest, and the second sampling region is determined within the second region of interest.
[0065] The average reflectance of all pixels in each band within the first sampling region is taken as the reflectance of the center pixel. Then, the vegetation index of the first sampling region is calculated based on the reflectance of the center pixel and used as the vegetation index of the center pixel. The vegetation index of the first sampling region includes the Normalized Difference Vegetation Index (NDVI), the Green Normalized Difference Vegetation Index (GreenNDE), the Difference Vegetation Index (DVI), the Soil-Adjusted Vegetation Index (SNE), the Green Index, and the Normalized Red Edge Vegetation Index (NRE). The calculation formulas are as follows:
[0066]
[0067] DVI = NIR-G;
[0068]
[0069] Wherein, NDVI is the Normalized Difference Vegetation Index; GNDVI is the Green Normalized Difference Vegetation Index; DVI is the Difference Vegetation Index; SAVI is the Soil-Adjusted Vegetation Index; GI is the Green Index; NDRE is the Normalized Red Edge Vegetation Index; R is the average reflectance of all pixels in the red band of the first sampling area; G is the average reflectance of all pixels in the green band of the first sampling area; NIR is the average reflectance of all pixels in the near-infrared band of the first sampling area; and RE is the average reflectance of all pixels in the red edge band of the first sampling area.
[0070] The average DN value of all pixels in each channel within the second sampling region is calculated and used as the color information of the center pixel. Then, the RGB orthophoto of the second sampling region is converted to a grayscale image. Based on the gray-level co-occurrence matrix, the texture information of the second sampling region is obtained and used as the texture information of the center pixel. The obtained texture information includes contrast, homogeneity, energy, entropy, and correlation.
[0071] The above feature extraction method is applied to each pixel in the crop multispectral orthophoto image to obtain the reflectance and vegetation index of each pixel in the first region of interest as the first feature information; and to obtain the color and texture information of each pixel in the second region of interest as the second feature information.
[0072] Step 206: Determine the moisture value of the crop canopy of the plot to be tested based on the first feature information and the second feature information.
[0073] All features extracted in steps 204 and 205 are input into the moisture detection model to determine the moisture value of the crop canopy in the plot to be detected. Specifically, the moisture detection model is a moisture regression model pre-trained using machine learning or deep learning algorithms.
[0074] This application, by implementing steps 201 to 206 above, accurately predicts canopy moisture values based on multispectral and RGB images acquired by UAV remote sensing, fusing the spectral and color texture features of the crop canopy with a prediction error of less than 5%. This achieves accurate, non-destructive detection and end-to-end analysis of crop canopy moisture content. Furthermore, this application comprehensively considers the feature information of the surrounding area for each pixel in the multispectral image, exhibiting strong generalization ability and performing refined moisture prediction for the crop canopy corresponding to each pixel.
[0075] In another exemplary embodiment of this application, in order to achieve high-precision visualization of crop canopy moisture at the pixel level, such as Figure 2 As shown, after step 206 above, the method may further include:
[0076] Step 207: Map the moisture value of the crop canopy of the plot to be tested to a given color range and display it.
[0077] Using the matplotlib library, the moisture values of the crop canopy in the plot under test are mapped onto a red-blue gradient color bar, with low moisture values represented by red and high moisture values by blue. This completes the visualization of crop canopy moisture in the plot under test.
[0078] This application also provides an application scenario in which the above-described crop moisture detection method is applied. Specifically, the crop moisture detection method provided in this embodiment can be applied in an agricultural production management scenario. The agricultural production management scenario includes a target farmland identification step, a moisture detection and analysis step, and a production management guidance step. When optimizing an agricultural production management plan, the target farmland to be optimized is first identified. Then, the moisture value of the crops in the target farmland is detected and analyzed through the moisture detection and analysis step. Finally, based on the moisture value analysis results, guidance on the production management of the target farmland is provided through the production management guidance step. The crop moisture detection method provided in this embodiment belongs to the moisture detection and analysis step. Specifically, after identifying the target farmland, multispectral orthophotos and RGB orthophotos of the target farmland are acquired to detect the crop moisture content.
[0079] Based on the same inventive concept, this application also provides a crop moisture detection system for implementing the crop moisture detection method described above. The solution provided by this system is similar to the implementation described in the above method; therefore, the specific limitations of the one or more crop moisture detection system embodiments provided below can be found in the limitations of the crop moisture detection method described above, and will not be repeated here.
[0080] In one exemplary embodiment, such as Figure 3 As shown, this application also proposes a crop moisture detection system, which includes: a data acquisition module 301, a preprocessing module 302, a feature extraction module 303, and a crop moisture detection module 304. The data acquisition module 301 includes an image acquisition unit, an image correction unit, and an image stitching unit, used to acquire multispectral orthophotos and RGB orthophotos of the plot to be detected, respectively. The preprocessing module 302 is used to extract farmland areas as a first region of interest from the multispectral orthophotos and as a second region of interest from the RGB orthophotos. The feature extraction module 303 includes a soil background removal unit and a feature extraction unit, used to extract first feature information from the first region of interest and second feature information from the second region of interest. Specifically, the first feature information includes the reflectance and vegetation index of each pixel in the first region of interest, and the second feature information includes the color and texture information of each pixel in the second region of interest. The crop moisture detection module 304 is used to determine the moisture value of the crop canopy of the plot to be detected based on the first and second feature information.
[0081] In another exemplary embodiment of this application, in order to achieve high-precision visualization of crop canopy moisture at the pixel level, such as Figure 3 As shown, the crop moisture detection system may also include:
[0082] The visualization module 305 is used to map the moisture value of the crop canopy of the plot to be detected to a given color range and display it.
[0083] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 4 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores crop moisture detection data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network. When executed by the processor, the computer program implements a crop moisture detection method.
[0084] Those skilled in the art will understand that Figure 4 The structures shown are merely block diagrams of some structures related to the present application and do not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.
[0085] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.
[0086] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.
[0087] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.
[0088] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).
[0089] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.
[0090] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0091] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.
Claims
1. A method for detecting crop moisture content, characterized in that, The crop moisture detection method includes: Acquire the multispectral orthophoto and RGB orthophoto of the plot to be inspected, respectively; Farmland areas are extracted from the multispectral orthophoto to obtain the first region of interest; The farmland area is extracted from the RGB orthophoto to obtain the second region of interest; First feature information is extracted from the first region of interest; the first feature information includes the reflectance and vegetation index of each pixel in the first region of interest. Extract second feature information from the second region of interest; the second feature information includes the color information and texture information of each pixel in the second region of interest. Based on the first feature information and the second feature information, the moisture value of the crop canopy of the plot to be tested is determined.
2. The crop moisture detection method according to claim 1, characterized in that, Acquire the multispectral orthophoto and RGB orthophoto of the plot to be inspected, respectively, including: Multispectral and RGB images of the land parcel to be inspected were acquired using a multispectral camera and an RGB camera, respectively. The multispectral image and the RGB image are stitched together to obtain a multispectral orthophoto and an RGB orthophoto.
3. The crop moisture detection method according to claim 2, characterized in that, Before stitching together the multispectral image and RGB image of the land parcel to be detected, obtaining the multispectral orthophoto and RGB orthophoto of the land parcel to be detected respectively also includes: The multispectral image and the RGB image are corrected respectively.
4. The crop moisture detection method according to claim 1, characterized in that, Extracting farmland areas from the multispectral orthophoto image yields a first region of interest, specifically including: The first region of interest is obtained by manually selecting or cropping the multispectral orthophoto image based on the geographic coordinates of the farmland area.
5. The crop moisture detection method according to claim 4, characterized in that, The farmland area is extracted from the RGB orthophoto to obtain a second region of interest, specifically including: The second region of interest is obtained by manually selecting or cropping the RGB orthophoto image based on the geographic coordinates of the farmland area.
6. The crop moisture detection method according to claim 1, characterized in that, Extracting first feature information from the first region of interest specifically includes: Soil background removal is performed on the first region of interest to obtain a crop multispectral orthophoto image; For any pixel in the crop multispectral orthophoto image, a first sampling region is defined with the pixel as the center; The reflectance of the pixel is determined based on the reflectance of each pixel in each band within the first sampling area; The vegetation index of the pixel is calculated based on the reflectance of the pixel.
7. The crop moisture detection method according to claim 6, characterized in that, Extracting second feature information from the second region of interest specifically includes: Based on the location of the first sampling region in the crop multispectral orthophoto, a second sampling region is determined in the second region of interest; The color information of the pixel is determined based on the color information of each pixel in the second sampling area; The texture information of the pixel is determined based on the texture information of each pixel in the second sampling area.
8. The crop moisture detection method according to claim 6, characterized in that, Soil background removal is performed on the first region of interest, specifically including: Calculate the soil-adjusted vegetation index for the first region of interest; Based on the soil-adjusted vegetation index, an adaptive threshold segmentation method is used to remove soil background from the first region of interest.
9. The crop moisture detection method according to claim 1, characterized in that, The crop moisture detection method also includes: The moisture value of the crop canopy in the plot to be tested is mapped to a given color range and displayed.
10. A crop moisture detection system, characterized in that, The crop moisture detection system includes: The data acquisition module is used to acquire the multispectral orthophoto and RGB orthophoto of the plot to be detected, respectively. A preprocessing module is used to extract farmland areas from the multispectral orthophoto to obtain a first region of interest, and to extract farmland areas from the RGB orthophoto to obtain a second region of interest; The feature extraction module is used to extract first feature information from the first region of interest and second feature information from the second region of interest; the first feature information includes the reflectance and vegetation index of each pixel in the first region of interest; the second feature information includes the color information and texture information of each pixel in the second region of interest. The crop moisture detection module is used to determine the moisture value of the crop canopy in the plot to be tested based on the first feature information and the second feature information.