A tobacco field rice straw dissolving field progress monitoring method, electronic equipment and storage medium

Abstract

The application provides a tobacco field rice straw field dissolving progress monitoring method, an electronic device and a storage medium, and relates to the field of data processing. The method comprises the following steps: obtaining information of a previous crop of a tobacco field plot according to a first image sequence, obtaining irrigation information of the tobacco field plot according to a second image sequence, and reminding the tobacco field plot that meets a preset condition to dissolve the field according to the information of the previous crop and the irrigation information. The method realizes monitoring of the rice straw field dissolving progress and improves the monitoring efficiency.

Description

Technical Field

[0001] This invention relates to the field of data processing, and in particular to a method, electronic device and storage medium for monitoring the progress of straw thawing in tobacco fields. Background Technology

[0002] Related studies have shown that the fertility of one acre of rice straw is equivalent to 10 kg of urea, 20 kg of superphosphate, and 21 kg of potassium chloride. If it can be used effectively, it can not only solve the pollution problem caused by burning rice straw, but also provide a large amount of organic fertilizer for arable land and reduce the amount of chemical fertilizer used. This is of great significance for creating a resource-saving and green agriculture.

[0003] For tobacco cultivation, "straw dissolution" during the preparation stage is an effective measure to maintain soil fertility, reduce disease occurrence, and improve tobacco quality, playing a significant role in enhancing planting efficiency. The effective implementation of this work will lay a solid foundation for later tobacco production. However, currently, the supervision of "straw dissolution" in tobacco fields mainly relies on manual labor by staff at each tobacco station, resulting in low efficiency. Summary of the Invention

[0004] To address the aforementioned technical problems, the technical solution adopted by this invention is as follows:

[0005] A method for monitoring the progress of rice straw leaching in tobacco fields, the method includes the following steps:

[0006] S1: Obtain the information of the previous crop of the tobacco field plot based on the first image sequence.

[0007] S1 includes the following steps:

[0008] S11: Preprocess the first image sequence to generate the first image to be detected.

[0009] S12: Judge each pixel of the first image to be detected, and divide each pixel in the first image to be detected into rice pixels and non-rice pixels.

[0010] S13: Based on the preset tobacco field plot data, divide the first image to be detected into several sub-images, and generate a list of the first sub-images to be detected, A={A1, A2, ..., A...}. i , ..., A m}, A i Let i be the i-th sub-image in the first list of sub-images to be detected, i = 1, 2, ..., m, where m is the total number of preset plots in the preset tobacco field plot data.

[0011] S14: For each A i Determine the proportion of rice pixels in A i The percentage of all pixels, if the rice pixel is in A iIf the percentage of all pixels is greater than a preset first threshold 'a', then A is considered to be A. i The preceding crop for the corresponding tobacco field was rice; otherwise, it is considered A. i The previous crop of the corresponding tobacco field was not rice.

[0012] S2: Obtain irrigation information for the tobacco field plots based on the second image sequence.

[0013] S2 includes the following steps:

[0014] S21: Preprocess the second image sequence to generate the second image to be detected.

[0015] S22: Judge each pixel of the second image to be detected, and divide each pixel in the second image to be detected into water body pixels and non-water body pixels.

[0016] S23: Divide the second image to be detected into several sub-images based on the preset tobacco field plot data, and generate a list of second sub-images to be detected B={B1, B2, ..., B...} i , ..., B m}, B i Let i be the i-th sub-image in the second image to be detected.

[0017] S24: For each B i Determine the proportion of water pixels in B i The percentage of all pixels, if the water pixels are in B i If the percentage of all pixels is greater than the preset second threshold b, then B is considered to be... i The corresponding tobacco field is currently being flooded; otherwise, it is considered B. i The corresponding tobacco fields were not flooded.

[0018] S3: Based on information about the previous crop and irrigation, provide a field melting reminder for tobacco fields that meet the preset conditions.

[0019] According to another aspect of the present invention, a non-transitory computer-readable storage medium is provided, wherein at least one instruction or at least one program is stored therein, the at least one instruction or the at least one program being loaded and executed by a processor to implement the aforementioned method.

[0020] According to another aspect of the present invention, an electronic device is provided, including a processor and the aforementioned non-transitory computer-readable storage medium.

[0021] The present invention has at least the following beneficial effects:

[0022] When monitoring the straw thawing situation in tobacco fields, the system first obtains information about the previous crop of the tobacco field based on the first image sequence. Then, it obtains irrigation information for the tobacco field during the second preset time period after the rice harvest based on the second image sequence. Continuous monitoring alerts are then issued for tobacco fields where the previous crop was rice and which are currently being flooded, and straw thawing alerts are issued for tobacco fields where the previous crop was rice and which are not currently being flooded. This eliminates the need for manual monitoring of the straw thawing progress, thereby improving monitoring efficiency. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 A flowchart illustrating the method for monitoring the progress of straw thawing in tobacco fields, as provided in an embodiment of the present invention. Detailed Implementation

[0025] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] Reference Figure 1 The present invention provides a method for monitoring the progress of straw leaching in tobacco fields, comprising the following steps:

[0027] S1: Obtain the information of the previous crop of the tobacco field plot based on the first image sequence.

[0028] Specifically, the first image sequence used in this embodiment was acquired using data from the Sentinel-2 satellite. The Sentinel-2 satellite carries a multispectral instrument (MSI) that can cover 13 spectral bands from visible light to shortwave infrared, with ground resolutions of 10m, 20m and 60m respectively. Other methods of acquiring the first image sequence that are well known to those skilled in the art are also within the scope of protection of this invention, and will not be described in detail here.

[0029] S1 includes the following steps:

[0030] S11: Preprocess the first image sequence to generate the first image to be detected.

[0031] S111: Obtain the first image sequence A 0 .

[0032] S112: Obtain A 0 Images within the first preset time period, A 0 Updated to A 0 ={A 0 1, A 0 2, ..., A 0 r , ..., A 0 s}, A 0 r The first image is taken at the r-th time point in the first image sequence, where r = 1, 2, ..., s, and s is the total number of images in the first image sequence within the first preset time period.

[0033] Specifically, the first preset time period is the period from rice sowing to harvest, which can be set by those skilled in the art and will not be elaborated here.

[0034] Specifically, this embodiment uses the GEE (Google Earth Engine) remote sensing cloud computing platform to complete the data acquisition and processing. Methods for subsequent data processing using other data processing platforms well known to those skilled in the art are all within the protection scope of this invention and will not be described in detail here.

[0035] S113: Based on the preset tobacco field plot data, for each A 0 r Cut and update.

[0036] Specifically, the tobacco field data sets the tobacco field plots in each A... 0 r The position in the middle, when it is necessary to deal with A 0 Each A in 0 r During the cropping process, the tobacco field plots in each A plot are first obtained from the tobacco field plot data. 0 r The location information in the data, and based on the tobacco field plots in each A... 0 r The location information in the data is used to trim the tobacco field plots to form a new A. 0 r Complete the work on A 0 r Update.

[0037] The above refers to A. 0 r Trimming and updating reduced the original A 0r The image located outside the tobacco field block has an impact on the image processing process, thereby reducing the processing workload.

[0038] S114: For each A 0 r Perform outlier removal and set A 0 Median synthesis is performed to generate the first image to be detected.

[0039] Specifically, firstly for each A 0 r Cloud removal processing is performed to reduce the adverse effects of clouds on subsequent image processing. This process utilizes the QA60 band of the image to construct a cloud mask. Other cloud removal methods well-known to those skilled in the art are also within the scope of this invention and will not be elaborated upon here. Subsequently, to reduce noise (outliers) in the image and improve image quality and information extraction, each A... 0 r Outlier removal is performed. Noise removal methods are mainly divided into two categories: spatial domain methods and frequency domain methods. Spatial domain methods filter pixels in the spatial domain of the image to reduce the impact of noise; common methods include mean filtering, median filtering, Lee filtering, and Kuan filtering. Frequency domain methods transform and filter the signal in the frequency domain of the image to eliminate noise components; common methods include Fourier transform, wavelet transform, and singular value decomposition, which will not be elaborated here. Finally, for each A... 0 r Median synthesis is performed to integrate the temporal differences and generate the first image to be detected.

[0040] S12: Judge each pixel of the first image to be detected, and divide each pixel in the first image to be detected into rice pixels and non-rice pixels.

[0041] Specifically, the method for determining whether each pixel in the first image to be detected is a rice pixel or a non-rice pixel is a method well known to those skilled in the art, and will not be described in detail here.

[0042] S13: Based on the preset tobacco field plot data, divide the first image to be detected into several sub-images, and generate a list of the first sub-images to be detected, A={A1, A2, ..., A...}. i , ..., A m}, A i Let i be the i-th sub-image in the first list of sub-images to be detected, i = 1, 2, ..., m, where m is the total number of preset plots in the preset tobacco field plot data.

[0043] Specifically, the tobacco field plot data also includes the location of each preset plot. The first image to be detected is segmented according to the location of each preset plot to generate a list of first sub-images to be detected.

[0044] S14: For each A i Determine the proportion of rice pixels in A i The percentage of all pixels, if the rice pixel is in A i If the percentage of all pixels is greater than a preset first threshold 'a', then A is considered to be A. i The preceding crop for the corresponding tobacco field was rice; otherwise, it is considered A. i The previous crop of the corresponding tobacco field was not rice.

[0045] Specifically, the value of 'a' is determined by those skilled in the art and will not be elaborated here.

[0046] As mentioned above, when it is necessary to determine whether the previous crop of a tobacco field was rice, the A data within the first preset time period is first obtained. 0 , each A 0 r Cropping and updating are performed to reduce the impact of redundant images on image processing. This is followed by cloud removal and outlier removal to improve the image quality of each A. 0 r Image quality is assessed. Median synthesis is then performed to generate the first image to be detected. Each pixel in the first image is then judged to be either a rice pixel or a non-rice pixel. The first image to be detected is then segmented to form a list of sub-images to be detected, and each A in A is further segmented. i The percentage of rice-themed pixels in the total number of pixels is compared with 'a'. If the percentage is greater than 'a', then A is considered to be A. i The preceding crop for the corresponding tobacco field was rice; otherwise, it is considered A. i The previous crop of the corresponding tobacco field was not rice.

[0047] S2: Obtain irrigation information for the tobacco field plots based on the second image sequence.

[0048] S2 includes the following steps:

[0049] S21: Preprocess the second image sequence to generate the second image to be detected.

[0050] Specifically, this embodiment uses Sentinel-1 for the second image sequence. Sentinel-1 is an Earth observation satellite in the European Space Agency's Copernicus Mission (GMES), consisting of two satellites: Sentinel-1A and Sentinel-1B (Sentinel-1B failed in 2021). It carries a C-band synthetic aperture radar and can provide continuous imagery (daytime, nighttime, and various weather conditions), offering both single-polarization and dual-polarization options. ESA uses the raw Sentinel-1 data to generate Level-1 data products, including two data formats: SCL (Single Look Complex) and GRD (Ground Range Detected). The former contains complex numerical and phase information, suitable for interferometry and deformation monitoring, while the latter contains real numerical and intensity information, primarily used for water body extraction and land cover classification.

[0051] S211: Obtain the second image sequence B 0 .

[0052] Specifically, SAR satellite remote sensing data is characterized by its all-weather capability and its immunity to weather and other factors. In addition, SAR satellite remote sensing data has special performance in water body identification (SAR satellites use side-view imaging, and the near-specular reflection of calm water means that very few reflected electromagnetic waves are received by the sensor, resulting in a low backscattering coefficient of the water body, which appears black in the image). This makes water body extraction based on SAR satellite remote sensing data an effective method. Therefore, this embodiment uses Sentinel-1 to acquire the second image sequence. Other methods of acquiring SAR satellite remote sensing data that are well known to those skilled in the art are all within the scope of protection of this invention and will not be described in detail here.

[0053] Specifically, B 0 The imaging mode is IW mode, and the band filtering is VH and VV bands.

[0054] Specifically, radar remote sensing systems commonly use four polarization modes: HH, VV, HV, and VH. HH is used for horizontal transmission and reception, VV is used for vertical transmission and reception, HV is used for horizontal transmission and vertical reception, and VH is used for vertical transmission and horizontal reception.

[0055] S212: Obtain B 0 The image is located within the second preset time period after the rice harvest, and B is... 0 Updated to B 0 ={B 0 1, B 0 2, ..., B 0 g , ..., B 0z}, B 0 g For B 0 The second image taken at the g-th time point, where g = 1, 2, ..., z, and z is the value of B. 0 The total number of images within the second preset time period after rice harvest.

[0056] Specifically, the second preset time period is one month after the rice harvest.

[0057] S213: Based on the preset tobacco field plot data, for each B 0 g Cut and update.

[0058] S214: For each B 0 g Perform outlier removal and add B 0 Median synthesis is performed to generate a second image to be detected.

[0059] Specifically, for B 0 g The processing method is the same as for A. 0 r The processing method is the same, so it will not be repeated here.

[0060] S22: Judge each pixel of the second image to be detected, and divide each pixel in the second image to be detected into water body pixels and non-water body pixels.

[0061] S221: Obtain the water index list D={D1, D2, ..., D2} corresponding to each pixel of the second image to be detected. x , ..., D p}, D x Let x be the water index corresponding to the x-th pixel in the second image to be detected, where x = 1, 2, ..., p, and p is the number of pixels in the second image to be detected.

[0062] Among them, D x =ln(VV) x VH x -arg max y∈（βmin，βmax） ((β) 0 βx<y -β 0 ) 2 +(β) 0 βx>y -β 0 ) 2 ), VV x For the VV polarization image of the x-th pixel, VH xLet be the VH polarization image of the x-th pixel, where y is any value of β between the maximum and minimum values. x Value, β x =ln(VV) x VH x ), β min For all β values ​​in all pixels of the second image to be detected x The minimum value of β max For all β values ​​in all pixels of the second image to be detected x The maximum value.

[0063] β 0 The following condition must be met: β 0 =(∑ x=1 p ln(VV) x VH x )) / p.

[0064] β 0 βx<y For all values ​​of β less than y x The mean.

[0065] β 0 βx>y For all β values ​​greater than y x The mean.

[0066] S222: For each D x If D x >0, then D x The corresponding pixel is water; otherwise, D x The corresponding pixel is a non-water body.

[0067] S23: Divide the second image to be detected into several sub-images based on the preset tobacco field plot data, and generate a list of second sub-images to be detected B={B1, B2, ..., B...} i , ..., B m}, B i Let i be the i-th sub-image in the second image to be detected.

[0068] S24: For each B i Determine the proportion of water pixels in B i The percentage of all pixels, if the water pixels are in B i If the percentage of all pixels is greater than the preset second threshold b, then B is considered to be... i The corresponding tobacco field is currently being flooded; otherwise, it is considered B. i The corresponding tobacco fields were not flooded.

[0069] Specifically, b is to be set by those skilled in the art, and will not be elaborated here.

[0070] S3: Based on information about the previous crop and irrigation, provide a field melting reminder for tobacco fields that meet the preset conditions.

[0071] Specifically, the process of issuing a land leaching warning for tobacco fields that meet preset conditions includes:

[0072] If the previous crop of the i-th plot was rice, and the plot is currently being flooded, then the plot is considered to be in the process of rice straw dissolution, and a continuous monitoring alert will be issued.

[0073] If the previous crop of the i-th plot was rice, and the plot was not flooded, a straw thawing warning will be issued.

[0074] In this embodiment of the invention, when monitoring the straw thawing situation in tobacco fields, the previous crop information of the tobacco field is first obtained based on a first image sequence. Then, irrigation information of the tobacco field during a second preset time period after the rice harvest is obtained based on a second image sequence. Continuous monitoring reminders are then issued for tobacco fields whose previous crop was rice and which are currently being flooded, and straw thawing reminders are issued for tobacco fields whose previous crop was rice and which are not currently being flooded. This eliminates the need for manual monitoring of the straw thawing progress, thereby improving monitoring efficiency.

[0075] Embodiments of the present invention also provide a non-transitory computer-readable storage medium that can be disposed in an electronic device to store at least one instruction or at least one program related to implementing a method in the method embodiments, wherein the at least one instruction or the at least one program is loaded and executed by the processor to implement the method provided in the above embodiments.

[0076] Embodiments of the present invention also provide an electronic device, including a processor and the aforementioned non-transitory computer-readable storage medium.

[0077] While specific embodiments of the invention have been described in detail by way of example, those skilled in the art should understand that the above examples are for illustrative purposes only and are not intended to limit the scope of the invention. Those skilled in the art should also understand that various modifications can be made to the embodiments without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.

Claims

1. A method for monitoring the progress of straw leaching in tobacco fields, characterized in that, The method includes the following steps: S1: Obtain the information on the previous crop of the tobacco field plot based on the first image sequence; S1 includes the following steps: S11: Preprocess the first image sequence to generate the first image to be detected; S12: Judge each pixel of the first image to be detected, and divide each pixel in the first image to be detected into rice pixels and non-rice pixels; S13: Divide the first image to be detected into several sub-images based on the preset tobacco field plot data, and generate a list of the first sub-images to be detected, A={A1, A2, ..., A...} i , ..., A m }, A i Let i be the i-th sub-image in the first list of sub-images to be detected, i = 1, 2, ..., m, where m is the total number of preset plots in the preset tobacco field plot data; S14: For each A i Determine the proportion of rice pixels in A i The percentage of all pixels, if the rice pixel is in A i If the percentage of all pixels is greater than a preset first threshold 'a', then A is considered to be A. i The preceding crop for the corresponding tobacco field was rice; otherwise, it is considered A. i The previous crop of the corresponding tobacco field was not rice; S2: Obtain irrigation information for the tobacco field plots based on the second image sequence; S2 includes the following steps: S21: Preprocess the second image sequence to generate a second image to be detected; wherein, the second image sequence is an image sequence from rice harvest within a second preset time period, the second preset time period being one month after rice harvest; S22: Judge each pixel of the second image to be detected, and divide each pixel of the second image to be detected into water body pixels and non-water body pixels; S23: Divide the second image to be detected into several sub-images based on the preset tobacco field plot data, and generate a list of second sub-images to be detected B={B1, B2, ..., B...} i , ..., B m }, B i This refers to the i-th sub-image in the second list of sub-images to be detected. S24: For each B i Determine the proportion of water pixels in B i The percentage of all pixels, if the water pixels are in B i If the percentage of all pixels is greater than a preset second threshold b, then B is considered to be... i The corresponding tobacco field is currently being flooded; otherwise, it is considered B. i The corresponding tobacco fields were not flooded. S3: Based on information about the previous crop and irrigation, provide a field melting reminder for tobacco fields that meet the preset conditions.

2. The method according to claim 1, characterized in that, Preprocessing the first image sequence to generate the first image to be detected includes the following steps: S111: Obtain the first image sequence A 0 ; S112: Obtain A 0 Images within the first preset time period, A 0 Updated to A 0 ={A 0 1, A 0 2, ..., A 0 r , ..., A 0 s }, A 0 r The first image is taken at the r-th time point in the first image sequence, where r = 1, 2, ..., s, and s is the total number of images in the first image sequence within the first preset time period. S113: Based on the preset tobacco field plot data, for each A 0 r Cut and update; S114: For each A 0 r Perform outlier removal and set A 0 Median synthesis is performed to generate the first image to be detected.

3. The method according to claim 1, characterized in that, Preprocessing the second image sequence to generate the second image to be detected includes the following steps; S211: Obtain the second image sequence B 0 ; S212: Obtain B 0 The image is located within the second preset time period after the rice harvest, and B is... 0 Updated to B 0 ={B 0 1, B 0 2, ..., B 0 g , ..., B 0 z }, B 0 g For B 0 The second image taken at the g-th time point, where g = 1, 2, ..., z, and z is the value of B. 0 The total number of images within the second preset time period after rice harvest; S213: Based on the preset tobacco field plot data, for each B 0 g Cut and update; S214: For each B 0 g Perform outlier removal and add B 0 Median synthesis is performed to generate a second image to be detected.

4. The method according to claim 1, characterized in that, The process of judging each pixel in the second image to be detected includes the following steps: S221: Obtain the water index list D={D1, D2, ..., D2} corresponding to each pixel of the second image to be detected. x , ..., D p }, D x Let x be the water index corresponding to the x-th pixel in the second image to be detected, where x = 1, 2, ..., p, and p is the number of pixels in the second image to be detected. Among them, D x =ln(VV) x *VH x -arg max y∈（βmin，βmax） ((β) 0 βx<y -β 0 ) 2 +(β) 0 βx>y -β 0 ) 2 ), VV x For the VV polarization image of the x-th pixel, VH x Let be the VH polarization image of the x-th pixel, where y is a value between β and β. min and β max Any β between x Value, β x =ln(VV) x *VH x ), β min For all β values ​​in all pixels of the second image to be detected x The minimum value of β max For all β values ​​in all pixels of the second image to be detected x The maximum value, β 0 The following condition must be met: β 0 =(∑ x=1 p ln(VV) x *VH x )) / p, β 0 βx<y For all values ​​of β less than y x The mean; β 0 βx>y For all β values ​​greater than y x The mean; S222: For each D x If D x >0, then D x The corresponding pixel is water; otherwise, D x The corresponding pixel is a non-water body.

5. The method according to claim 1, characterized in that, The provision of field leaching reminders for tobacco fields that meet preset conditions includes: If the previous crop of the i-th plot was rice, and the plot is currently being flooded, a continuous monitoring alert will be issued. If the previous crop of the i-th plot was rice, and the plot was not flooded, a straw thawing warning will be issued.

6. The method according to claim 3, characterized in that, The imaging mode of the second image sequence is IW mode, and the band filtering is two bands: VH and VV.

7. The method according to claim 2, characterized in that, The first preset time period is from rice sowing to harvest.

8. The method according to claim 3, characterized in that, The second preset time period is one month after the rice harvest.

9. A non-transitory computer-readable storage medium, wherein the storage medium stores at least one instruction or at least one program segment, characterized in that, The at least one instruction or the at least one program segment is loaded and executed by the processor to implement the method as described in any one of claims 1-8.

10. An electronic device, characterized in that, Includes a processor and the non-transitory computer-readable storage medium as described in claim 9.

Images