An Automatic Extraction Method and System for the Mildew Range of Winter Wheat at the Maturity Stage

Abstract

The present application provides a method and system for automatically extracting the mildew range of winter wheat at the maturity stage, belonging to the field of image recognition technology. This method realizes the accurate segmentation of the normal wheat area and the wheat disaster area by calculating the mildew remote sensing index of each pixel and combining the threshold segmentation method. Among them, the mildew remote sensing index is constructed by the area method and is defined as the ratio of two areas, namely the first polygon area and the second polygon area. The first polygon area is the sum of the right trapezoid areas enclosed by each band and the coordinate horizontal axis, and the second polygon area is the area enclosed by the maximum surface reflectance, the band with the shortest central wavelength, the band with the longest central wavelength, and the coordinate horizontal axis. Calculating the mildew remote sensing index with the ratio of areas can enhance the index difference between normal wheat and mildewed wheat, which is beneficial to accurately determining the segmentation threshold in the threshold segmentation method, enabling the threshold segmentation method to achieve an overall accuracy similar to that of the traditional machine learning method and improving the stability and convenience of the results.

Description

Technical Field

[0001] This application relates to the field of image recognition technology, and particularly to a method and system for automatically extracting the mildew range of winter wheat at the maturity stage. Background Art

[0002] Currently, remote sensing disaster monitoring and recognition methods based on imaging technology include threshold segmentation, machine learning, deep learning, etc.

[0003] Among them, machine learning methods such as support vector machine (SVM), random forest (RF), etc. have been widely used in the field of remote sensing classification because they can achieve higher classification accuracy than the threshold segmentation method. However, with the complexity and diversity of remote sensing data, machine learning classification algorithms have problems such as complex calculations, high requirements for data processing, and insufficient extraction accuracy in scenarios such as high-dimensional small samples, high-dimensional data imbalance, and feature engineering.

[0004] The idea of the threshold segmentation method is to first calculate the index for measuring the spectral difference of each pixel, and then select the segmentation threshold to classify the pixels, so as to extract the disaster range. Commonly used remote sensing indices include traditional remote sensing indices such as the normalized difference vegetation index (NDVI), EVI index, and HSI (Hue Saturation Intensity) color model. However, when the traditional remote sensing indices are applied to the extraction of the wheat mildew range, the ability to distinguish between wheat mildew and normal wheat is not strong, it is difficult to accurately determine the segmentation threshold, and there is a large gap in the classification result accuracy compared with the classification accuracy of the machine learning method. Moreover, when the threshold segmentation based on the traditional remote sensing index is applied to the remote sensing data with different resolutions in the study area obtained by different types of sensors, there are problems of unstable extraction result accuracy, insufficient adaptability and migration.

[0005] Therefore, an improved technical solution is needed to address the above deficiencies in the prior art. Summary of the Invention

[0006] The purpose of this application is to provide a method and system for automatically extracting the mildew range of winter wheat at the maturity stage to solve or alleviate the problems existing in the above prior art.

[0007] To achieve the above purpose, this application provides the following technical solutions:

[0008] In the first aspect, this application provides a method for calculating a remote sensing index of wheat mildew, including:

[0009] Obtain a multispectral remote sensing image;

[0010] Taking the wavelength as the horizontal axis and the surface reflectance as the vertical axis, plot the surface reflectance curves of the multispectral remote sensing image in multiple bands;

[0011] Calculate the area of the right trapezoid formed by the surface reflectance curve of each band and the horizontal axis of the coordinate according to the interval between the central wavelengths of adjacent bands, and sum them up. Denote the sum result as the area of the first polygon.

[0012] Determine the maximum value of the surface reflectance of all pixels in the multispectral remote sensing image, and calculate the area of the rectangle formed by the maximum value of the surface reflectance, the central wavelength of the first band, the horizontal axis of the coordinate, and the central wavelength of the second band. Denote it as the area of the second polygon. The first band is the band with the shortest central wavelength among multiple bands, and the second band is the band with the longest central wavelength among multiple bands.

[0013] Take the area of the first polygon as the numerator and the area of the second polygon as the denominator, calculate the ratio of the area of the first polygon to the area of the second polygon, and obtain the mildew remote sensing index.

[0014] Combined with the first aspect, in some possible implementation manners, after calculating the ratio of the area of the first polygon to the area of the second polygon with the area of the first polygon as the numerator and the area of the second polygon as the denominator to obtain the mildew remote sensing index, it further includes: assuming that the intervals between the central wavelengths of adjacent bands are equal, simplify the mildew remote sensing index to obtain the simplified mildew remote sensing index.

[0015] Combined with the first aspect, in some possible implementation manners, the multispectral remote sensing image includes but is not limited to: spectral information in the visible light band and the near-infrared band, and the multiple bands include but are not limited to: blue, green, red, and near-infrared bands.

[0016] In a second aspect, this embodiment provides a method for automatically extracting the mildew range at the mature stage of winter wheat by using the method for calculating the wheat mildew remote sensing index provided in any of the above embodiments, including:

[0017] Determine the target cultivated land range.

[0018] Use the method for calculating the wheat mildew remote sensing index provided in any of the above embodiments to calculate the mildew remote sensing index value corresponding to each pixel in the multispectral remote sensing image of the target cultivated land range. Among them, the multispectral remote sensing image contains spectral information of mildewed wheat and normal wheat.

[0019] Based on the mildew remote sensing index value, use an image segmentation method to determine the segmentation threshold.

[0020] According to the segmentation threshold, divide the target cultivated land range into a normal wheat area and a wheat disaster area to extract the wheat disaster range.

[0021] In combination with the second aspect, in some possible implementation manners, based on the mildew remote sensing index value, determining a segmentation threshold using an image segmentation method includes:

[0022] Segmenting the wheat mildew remote sensing index value using multiple candidate image segmentation methods, and determining the segmentation thresholds corresponding to the respective candidate image segmentation methods;

[0023] Using the overall accuracy and the Kappa coefficient as evaluation indicators, validating the segmentation results of the respective candidate image segmentation methods through a confusion matrix to determine the optimal segmentation method; and using the threshold corresponding to the optimal segmentation method as the segmentation threshold.

[0024] In combination with the second aspect, in some possible implementation manners, the multiple candidate image segmentation methods include, but are not limited to: the Otsu threshold segmentation method, the K-means clustering segmentation method, the iterative threshold segmentation method, the maximum entropy segmentation method, and the triangle segmentation method.

[0025] In combination with the second aspect, in some possible implementation manners, the optimal segmentation methods are the Otsu threshold segmentation method and the iterative threshold segmentation method.

[0026] In a third aspect, this embodiment provides a wheat mildew remote sensing index calculation system, including:

[0027] A data acquisition unit configured to acquire a multispectral remote sensing image;

[0028] A curve plotting unit configured to plot the surface reflectance curves of the multispectral remote sensing image in multiple bands with the wavelength as the horizontal axis and the surface reflectance as the vertical axis;

[0029] A first polygon area solving unit configured to calculate the areas of the right trapezoids formed by the surface reflectance curves of the respective bands and the coordinate horizontal axis according to the intervals between the central wavelengths of adjacent bands, and sum them, and record the summation result as the first polygon area;

[0030] A second polygon area solving unit configured to determine the maximum surface reflectance value of all pixels in the multispectral remote sensing image, and calculate the area of the rectangle formed by the maximum surface reflectance value, the central wavelength of the first band, the coordinate horizontal axis, and the central wavelength of the second band, and record it as the second polygon area; the first band is the band with the shortest central wavelength among the multiple bands, and the second band is the band with the longest central wavelength among the multiple bands;

[0031] A ratio calculation unit configured to calculate the ratio of the first polygon area to the second polygon area with the first polygon area as the numerator and the second polygon area as the denominator to obtain the mildew remote sensing index.

[0032] Fourthly, this embodiment provides an automatic extraction system for the mildew range of winter wheat at the mature stage, including:

[0033] A range determination unit configured to determine the target cultivated land range;

[0034] An index calculation unit configured to calculate the mildew remote sensing index value corresponding to each pixel in the multi-spectral remote sensing image of the target cultivated land range by using the wheat mildew remote sensing index calculation method provided in any of the above embodiments; wherein, the multi-spectral remote sensing image contains the spectral information of mildewed wheat and normal wheat;

[0035] A threshold calculation unit configured to determine a segmentation threshold by using an image segmentation method based on the mildew remote sensing index value;

[0036] A disaster-affected area extraction unit configured to segment the target cultivated land range into a normal wheat area and a wheat disaster-affected area according to the segmentation threshold to extract the wheat disaster-affected area range.

[0037] Fifthly, this embodiment provides an electronic device, which includes a memory, and an instruction is stored on the memory. When the instruction is executed on a computer, the computer executes the wheat mildew remote sensing index calculation method provided in any of the above embodiments, or executes the automatic extraction method for the mildew range of winter wheat at the mature stage described in any of the embodiments.

[0038] The technical solution of the embodiment of the present application has the following beneficial effects:

[0039] The present application first provides a method for calculating a wheat mildew remote sensing index. This method constructs the wheat mildew remote sensing index by drawing the surface reflectance curves of spectral remote sensing images in multiple bands and using the area method. The mildew remote sensing index is defined as the ratio of two areas. The first polygon area is the sum of the right trapezoid areas enclosed by each band and the coordinate horizontal axis, and the second polygon area is the area enclosed by the maximum surface reflectance, the band with the shortest central wavelength, the band with the longest central wavelength, and the coordinate horizontal axis. The method of calculating the mildew remote sensing index using the ratio of areas can effectively enhance the index difference between normal wheat and mildewed wheat, which is beneficial to accurately determining the segmentation threshold in the threshold segmentation method. On this basis, the method for automatically extracting the mildew range of winter wheat provided in this embodiment calculates the mildew remote sensing index of each pixel within the target cultivated land range, and combines the threshold segmentation method to accurately segment the normal wheat area and the wheat disaster area through the segmentation threshold. Experimental data shows that the extraction result accuracy of this method for automatically extracting the mildew range of winter wheat can reach an effect similar to the overall accuracy of the machine learning method, and the extraction process is effectively simplified. Moreover, this method has strong applicability to the source and resolution of remote sensing images, and the deviation of the extraction result area for different types and resolutions of remote sensing data is small. Whether using medium-resolution multispectral remote sensing data (such as Sentinel-2 and Landsat 9 satellite data) or high-resolution (such as high-resolution series satellites) multispectral remote sensing data, the extraction accuracy is relatively stable, indicating that this mildew remote sensing index has good generalization ability. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 FIG. is a schematic diagram of the principle of the method for calculating the wheat mildew remote sensing index provided according to some embodiments of the present application.

[0041] Figure 2 FIG. is a grayscale histogram of the mildew remote sensing index provided according to some embodiments of the present application.

[0042] Figure 3 FIG. is a comparison schematic diagram of the segmentation results of different threshold segmentation methods Figure 1

[0043] Figure 4 FIG. is a comparison schematic diagram of the segmentation results of different threshold segmentation methods Figure 2

[0044] Figure 5 FIG. is a comparison schematic diagram of the classification results of the machine learning method and the classification results of the mildew remote sensing index provided in this embodiment.

[0045] Figure 6 FIG. is a schematic diagram of the results of extracting the mildew range using the mildew remote sensing index for different remote sensing data sources Figure 1

[0046] ​​​Figure 7 Schematic diagram of the result of extracting the mildew range from different remote sensing data sources using the mildew remote sensing index Figure 2 。

[0047] Figure 8 Schematic diagram of the result of extracting the mildew range from different regions in the same period using the mildew remote sensing index. Specific implementation manners

[0048] The terms "first", "second", "third", "fourth", etc. in the description and claims of this application and the accompanying drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally further include steps or units not listed, or may optionally further include other steps or units inherent to these processes, methods, products or devices.

[0049] Referring to "embodiments" herein means that the specific features, structures or characteristics described in connection with the embodiments may be included in at least one embodiment of this application. The phrase appears in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein may be combined with other embodiments.

[0050] The embodiments of this application will be described below with reference to the accompanying drawings.

[0051] Embodiment 1

[0052] This embodiment provides a method for calculating the wheat mildew remote sensing index, and the method includes the following steps:

[0053] S1: Obtain multispectral remote sensing images;

[0054] S2: Taking the wavelength as the horizontal axis and the surface reflectance as the vertical axis, draw the surface reflectance curves of the multispectral remote sensing images in multiple bands;

[0055] S3: According to the interval between the central wavelengths of adjacent bands, calculate the area of the right trapezoid formed by the surface reflectance curve of each band and the horizontal axis of the coordinate, and sum them, and record the summation result as the first polygon area;

[0056] S4: Determine the maximum surface reflectance of all pixels in the multispectral remote sensing image, and calculate the area of the rectangle formed by the maximum surface reflectance, the central wavelength of the first band, the horizontal coordinate axis, and the central wavelength of the second band, which is denoted as the second polygon area. The first band is the band with the shortest central wavelength among multiple bands, and the second band is the band with the longest central wavelength among multiple bands.

[0057] S5: Use the first polygon area as the numerator and the second polygon area as the denominator to calculate the ratio of the first polygon area to the second polygon area, obtaining the mildew remote sensing index.

[0058] Considering the accessibility of multispectral remote sensing images and the diversity of data sources, in some embodiments, the multispectral remote sensing image includes, but is not limited to, spectral information in the visible light band and the near-infrared band. The multiple bands include, but are not limited to, the blue, green, red, and near-infrared bands.

[0059] The following refers to Figure 1 to illustrate the principle of the method for calculating the wheat mildew remote sensing index provided in this embodiment.

[0060] Figure 1 shows the comparison of the surface reflectance of normal wheat and mildewed wheat at maturity in multiple spectral bands, and also shows the mean reflectance curves of mildewed wheat and normal wheat. Among them, the X-axis (i.e., the horizontal coordinate axis) is the wavelength, and the Y-axis represents the surface reflectance. Exemplarily, the multiple bands include: blue, green, red, and near-infrared bands. The orange dots represent the surface reflectance of the wheat at a certain pixel position in the multispectral image after mildew, and the green dots represent the surface reflectance of normal wheat. The orange triangle and its dashed line represent the mean reflectance curve of mildewed wheat, and the position of the triangle is the central wavelength position of different bands. The green square and the dashed line represent the mean reflectance curve of normal wheat, and the position of the square is the central wavelength position. Between every two adjacent central wavelengths, the horizontal coordinate axis and the reflectance curve enclose an approximate right trapezoid. From Figure 1 It can be seen that in all bands, the surface reflectance of normal wheat is generally higher than that of mildewed wheat, and with the increase of wavelength, this difference increases, especially obvious in the near-infrared band. On the other hand, with the change of bands and the increase of wavelength, the surface reflectance of mildewed wheat is relatively stable, while the surface reflectance of normal wheat shows an upward trend with the increase of wavelength, especially the reflectance increases significantly in the near-infrared band.

[0061] Analyzing its mechanism, the reasons for the above characteristics are as follows: There are differences in the distribution characteristics between mildewed wheat and normal wheat in the visible and near-infrared wavelength ranges, that is, their spectral reflectance values in these wavelength ranges are different. Specifically, after normal wheat matures, the chlorophyll content decreases, the absorption of blue light and red light decreases, the reflectance increases, showing yellow, the strong absorption in the red wavelength band weakens, and compared with wheat in other periods, there is no obvious trough in its surface reflectance curve. After wheat is mildewed, black spots appear on the surface of the plant due to the growth of mold, and at the same time, the leaves of the wheat plant gradually wither, reducing the reflection of spectral energy in each wavelength band and enhancing the absorption. Therefore, the overall surface reflectance of mildewed wheat is lower than that of normal wheat; as the mold grows and multiplies stably on the wheat plant, affected by the mold, mildewed wheat shows an undifferentiated strong absorption of spectral energy in each wavelength band (even in the near-infrared wavelength band where healthy vegetation has strong reflection), resulting in a lower spectral reflectance and a relatively flat spectral reflectance curve, and the difference between wavelength bands is not obvious.

[0062] Since the spectral characteristics of mildewed wheat are manifested as undifferentiated absorption in each wavelength band and overall low reflectance, which is in contrast to the high reflectance of normal wheat, especially the difference between the high reflectance of normal wheat in the near-infrared wavelength band and the blue wavelength band, while mildewed wheat shows a "flat and low" spectral reflectance curve, the above characteristics can be used as a basis for distinguishing normal wheat from mildewed wheat.

[0063] In this embodiment, based on the above analysis results, a mildew remote sensing index for mature wheat is constructed. The mildew remote sensing index is constructed using the area method and is defined as the ratio of two areas. The area is used to increase the spectral characteristic difference between normal wheat and mildewed wheat, and by comprehensively using the reflectance differences of normal wheat and mildewed wheat in each wavelength band of the multi-spectral image, the multi-spectral image information is fully utilized to enhance the spectral difference between normal wheat and mildewed wheat, making it easier to separate them. After the wheat matures and encounters continuous rainy weather, the surface of the wheat is invaded by mold, and a large amount of mold grows and multiplies, causing a large number of black spots to adhere to the surface of the wheat.

[0064] Furthermore, for the ratio of the two areas of the mildew remote sensing index, the numerator is the area of the first polygon, which is the sum of the right trapezoid areas formed by the adjacent wavelength band values (i.e., reflectance values) of each pixel, the central wavelength interval, and the coordinate axes. The denominator is the area of the second polygon, which is a rectangle formed by the difference between the longest central wavelength and the shortest central wavelength of the spectral reflectance in the multi-band remote sensing image and the maximum surface reflectance. Its function is to provide a standardized scale for calculation by constructing a rectangular frame (i.e., Figure 1 the red dashed frame in the figure) as a reference, so that the index can eliminate the scale difference between wavelength bands and improve the comparability and stability of the index.

[0065] Taking a multispectral remote sensing image including blue, green, red, and near-infrared bands as an example, for a certain pixel, the mildew remote sensing index can be expressed by the following formula:

[0066]

[0067] Where: WMI is the mildew remote sensing index, R blue 、R green 、R red 、R nir are the surface reflectance values of the blue, green, red, and near-infrared bands, λ blue 、λ green 、λ red 、λ nir are the central wavelengths corresponding to the blue, green, red, and near-infrared bands, and R max is the maximum surface reflectance value.

[0068] It should be noted that when the traditional threshold segmentation method is used to extract the affected area of wheat mildew, the remote sensing index is also selected and the index value is obtained through mathematical operations between bands. However, the traditional remote sensing index has weak discrimination ability between wheat mildew and normal wheat:

[0069] Taking NDVI as an example, from the calculation method, only the near-infrared and red bands are considered in the calculation process of NDVI, ignoring the information in other bands. Wheat mildew is often caused by local or systemic changes due to pathogens or other pathological factors. This change is not only reflected in the red and near-infrared bands, but also in other bands such as blue and green. The NDVI index only uses the ratio of the difference between the near-infrared and red bands to the sum of the near-infrared and red bands, resulting in insufficient sensitivity in identifying mildewed wheat, especially in the case of early or mild mildew, which is more difficult to identify comprehensively. Secondly, from the design objective, the design purpose of the NDVI index is to focus on the overall vitality of vegetation, rather than directly used to distinguish the pathological state of vegetation. This results in its ability to measure the growth status and greenness of vegetation more accurately, but its ability to identify details such as whether the vegetation is sick, suffering from diseases or mildew is limited. For example, the decrease in NDVI may be caused only by environmental factors such as reduced vegetation cover or drought, that is, affected by background vegetation or soil, and may not be able to accurately indicate the mildew problem of wheat.

[0070] The Enhanced Vegetation Index (EVI) is another commonly used remote sensing index. It enhances the reflectance difference between the near-infrared and red light, and introduces the blue light band during the calculation process to reduce the influence of atmospheric scattering. However, the main spectral characteristics of mildewed wheat are the overall strong absorption of each band (including the enhanced absorption in the near-infrared band) and the flatness of the spectral reflectance curve. While EVI emphasizes the reflectance difference between the near-infrared and red light, mildewed wheat covered by mold will show lower reflectance in each band (especially in the near-infrared band), making the reflectance difference between the near-infrared and red light not obvious, and the change of EVI value is not significant, thus unable to effectively identify the mildewed situation. Secondly, although the EVI index introduces the blue light band, its role is to suppress the interference of atmospheric aerosol and soil background, and the weight of the blue light band is relatively low, so it cannot effectively capture the spectral characteristics of mildewed wheat.

[0071] The mildew remote sensing index (WMI) constructed in this embodiment makes full use of the characteristic that mildewed wheat strongly absorbs the spectra of each band without difference, resulting in a large difference between its reflectance spectrum and that of normal wheat. And it enhances this difference by the sum of the areas enclosed by the surface reflectance of each band pixel and the coordinate horizontal axis, selects the rectangle formed by the maximum pixel reflectance and the horizontal coordinate axis as the denominator for normalization processing, comprehensively considers the information of each band, and uses the concept of area to enhance the sensitivity of the index to mildewed wheat. In addition, since the mildew remote sensing index (WMI) can obtain the index value only by implementing area calculation, it is simple to apply and intuitive to calculate, without complex data preprocessing and model training, and is convenient for practical application and popularization compared with machine learning methods.

[0072] From the principle of constructing the mildew remote sensing index (WMI), the theoretical maximum value of the mildew remote sensing index (WMI) of wheat is 1, and the minimum value is 0. Since the reflectance of mildewed wheat in each band is less than that of normal wheat, mildewed wheat is closer to the value of 0 on the wheat mildew remote sensing index (WMI), while normal wheat has stronger reflectance to the spectrum and is closer to 1 on the wheat mildew remote sensing index (WMI). Therefore, the closer the wheat mildew remote sensing index (WMI) is to 1, the lower the possibility of wheat mildew, and vice versa, the closer the wheat mildew remote sensing index (WMI) is to 0, the higher the possibility of wheat mildew.

[0073] The experiment on the improvement of the identification effect of mildewed wheat by the mildew remote sensing index (WMI) will be discussed in detail below.

[0074] Since the central wavelengths of each band are used in the Wheat Mildew Index (WMI) for remote sensing, and the central wavelengths are used as scalars in the mildew remote sensing index, the purpose of which is to calculate the area between the crop reflectance and the coordinate axis. The physical quantity actually reflecting whether wheat has mildewed is still the spectral reflectance of wheat. Therefore, in some embodiments, it further includes a step of index simplification, that is, after calculating the ratio of the first polygon area to the second polygon area with the first polygon area as the numerator and the second polygon area as the denominator to obtain the mildew remote sensing index, it further includes: assuming that the intervals between the central wavelengths of adjacent bands are equal, simplifying the mildew remote sensing index to obtain a simplified mildew remote sensing index.

[0075] Taking the multi-spectral remote sensing image including blue, green, red, and near-infrared bands as an example, the expression of the simplified mildew remote sensing index is as follows:

[0076]

[0077] In the formula: WMI1 is the simplified mildew remote sensing index, R blue 、R green 、R red 、R nir are the surface reflectance values of the blue, green, red, and near-infrared bands, and R max is the maximum surface reflectance.

[0078] The above simplification assumes that the intervals between the central wavelengths of each band are equal. By ignoring the differences in the central wavelengths of each band of different remote sensing sensors, the extraction results of the simplified wheat mildew index are similar to those of the non-simplified extraction results, and the overall accuracy difference is only about 1%. However, the simplified mildew remote sensing index no longer requires obtaining the central wavelengths of each original band, reducing the pre-calculation cost and data processing cost during the actual use of the mildew remote sensing index, improving the efficiency of identifying the mildew range of wheat, and making the actual use more simple and convenient.

[0079] Embodiment 2

[0080] This embodiment provides an automatic extraction method for the mildew range at the mature stage of winter wheat using the wheat mildew remote sensing index calculation method provided in any of the above embodiments, including the following steps:

[0081] S101: Determine the target cultivated land range;

[0082] S102: Using the wheat mildew remote sensing index calculation method provided in any of the above embodiments, calculate the mildew remote sensing index values corresponding to each pixel in the multi-spectral remote sensing image of the target cultivated land range; wherein, the multi-spectral remote sensing image contains the spectral information of mildewed wheat and normal wheat;

[0083] S103: Based on the mildew remote sensing index value, use an image segmentation method to determine the segmentation threshold;

[0084] S104: According to the segmentation threshold, divide the target cultivated land area into a normal wheat area and a wheat disaster area to extract the wheat disaster area.

[0085] In the above embodiments, the cultivated land area can be extracted from the multi - spectral remote sensing images of the study area by using GIS technology or remote sensing data processing technology. The non - cultivated land area does not participate in the subsequent operations to reduce the computational workload. The value of the mildew remote sensing index is calculated for each pixel. Through the multi - spectral remote sensing image data, the mildew index value of each pixel is calculated to quantify and distinguish mildewed wheat and normal wheat.

[0086] Among them, the multi - spectral image contains data of multiple bands (such as blue, green, red, near - infrared, etc.), which can capture different spectral reflection characteristics of wheat on the cultivated land. Within the cultivated land area, these bands record the spectral information of wheat at different wavelengths, including the reflectance differences between mildewed wheat and normal wheat.

[0087] A pixel is the smallest unit of a remote sensing image, and each pixel corresponds to a small area on the cultivated land. The reflectance of each pixel at different bands can be used to calculate the value of the mildew remote sensing index.

[0088] Image segmentation is to divide an image into several regions to distinguish regions with different characteristics. By analyzing the distribution of the mildew index value, a segmentation algorithm (such as Otsu method, K - means clustering, etc.) is used to determine a suitable segmentation threshold, which is used to distinguish the normal wheat area and the wheat area affected by mildew.

[0089] Specifically, when the mildew index value of a pixel exceeds the segmentation threshold, it is determined as the disaster area, otherwise it is determined as the normal area. Through the segmentation result, the spatial distribution range of the wheat disaster area can be extracted to quickly and accurately extract the wheat disaster area and achieve automated monitoring.

[0090] Optionally, using an image segmentation method to determine the segmentation threshold based on the mildew remote sensing index value includes:

[0091] Use multiple candidate image segmentation methods to segment the wheat mildew remote sensing index value to determine the segmentation thresholds corresponding to each candidate image segmentation method;

[0092] Taking the overall accuracy and Kappa coefficient as evaluation indicators, verify the segmentation results of each candidate image segmentation method through a confusion matrix to determine the optimal segmentation method; and use the threshold corresponding to the optimal segmentation method as the segmentation threshold.

[0093] Since different segmentation methods perform differently in handling spectral feature differences and noise, by using multiple segmentation methods, the effects of each method in the segmentation of wheat mildew index can be compared. Thus, the segmentation method that can most accurately reflect the mildewed area can be selected, reducing the phenomena of mis-segmentation and missed-segmentation, and improving the accuracy of the final segmentation. At the same time, through the comparison of multiple methods, a method that performs well in various mildew situations can be found, enhancing the robustness of the segmentation under different conditions and making the model more universal.

[0094] The above scheme uses the overall accuracy and Kappa coefficient as evaluation criteria to ensure that the selected segmentation method has good effects. These indicators are based on the confusion matrix, comparing the segmentation results with the true values, reflecting the consistency and accuracy of the classification, avoiding relying solely on subjective judgment, and making the method selection more objective.

[0095] Furthermore, the multiple candidate image segmentation methods include, but are not limited to: Otsu threshold segmentation method, K-means clustering segmentation method, iterative threshold segmentation method, entropy value segmentation method, and triangle segmentation method.

[0096] Furthermore, the optimal segmentation methods are the Otsu threshold segmentation method and the iterative threshold segmentation method.

[0097] The Otsu threshold segmentation method is particularly suitable for binary classification problems, that is, dividing the image into two categories (such as mildewed wheat and normal wheat), while the iterative threshold method can provide good segmentation effects for the mildew recognition task with obvious spectral differences by recursively determining the optimal threshold. Therefore, these two methods perform stably and reliably in the segmentation of wheat mildew.

[0098] To verify the effectiveness of the wheat mildew remote sensing index calculation method and the automatic extraction method for the mildew range in the mature period of winter wheat provided by this application, the following introduces exemplary applications and comparative experiment results.

[0099] In this embodiment, the main wheat production areas with continuous rainy weather during the mature period are selected as the study area. First, multi-spectral image data of the study area are collected by high-resolution (abbreviated as GF) satellites, the spectral characteristics of mildewed wheat and normal wheat are analyzed, the mildew remote sensing index value is calculated, and five segmentation methods such as Otsu threshold and clustering segmentation are used to perform automatic threshold segmentation on normal wheat and mildewed wheat. Secondly, for comparison, this embodiment also uses traditional machine learning classification methods such as random forest (RF) and support vector machine (SVM), and uses the classification samples obtained from the measured data to classify and extract normal wheat and mildewed wheat. Finally, the extraction results of the wheat mildew remote sensing index value are compared and analyzed with the traditional machine learning classification results to verify the feasibility and effectiveness of the provided wheat mildew remote sensing index calculation method and the automatic extraction method for the mildew range in the mature period of winter wheat.

[0100] Specifically, in the experiment, a scene of GF-2 PMS remote sensing image data on June 1, 2023 and a scene of GF-6 remote sensing image on April 18, 2023 were used. The multi-spectral images of GF-2 and GF-6 remote sensing data were preprocessed through radiometric calibration, atmospheric correction, image registration, etc. Since the GF-2 image has higher resolution and spectral information, it was used to calculate the mildew remote sensing index and extract mildewed wheat by machine learning methods.

[0101] When determining the target cultivated land area, in order to make the extraction of mildewed wheat information more accurate, the normalized difference vegetation index (NDVI) was calculated using GF-2 and GF-6 remote sensing images in different periods of the wheat growth stage, and reasonable thresholds were set to extract the information of wheat cultivated land plots, and then the range of mildewed wheat was extracted within the cultivated land area.

[0102] To verify the transferability and stability of the mildew remote sensing index, the experiment also used sensor data of different remote sensing platforms in the same area. Specifically, Sentinel-2 and Landsat-9 remote sensing images on June 1, 2023 were used. The multi-spectral remote sensing image data of Sentinel-2 and Landsat came from Google Earth Engine (GEE), and the data was preprocessed through radiometric calibration, orthorectification, image registration, and atmospheric correction operations.

[0103] After calculating the mildew remote sensing index value, since the mildew remote sensing index expands the difference between mildewed wheat and normal wheat, making the distinguishability between categories further improved, the gray histogram of the mildew remote sensing index can be used to determine the segmentation threshold, as Figure 2 shown, normal wheat and mildewed wheat form two peaks on the gray histogram respectively. Using the gray histogram to assist in determining the segmentation threshold can avoid the influence of subjective factors on the threshold selection.

[0104] To find the optimal segmentation method, five segmentation methods, namely Otsu Threshold Segmentation, K-means Clustering Segmentation, Iterative Threshold Segmentation, Maximum Entropy Segmentation, and Triangle Segmentation, are used to perform binary automatic threshold segmentation on mildewed wheat and normal wheat to obtain the range of mildewed wheat. Among them, the principle of the Otsu threshold segmentation method is to divide the grayscale image into multiple gray levels, calculate the probability of each gray level respectively, and finally calculate and find the gray level corresponding to the maximum between-class variance. This gray level maximizes the difference between the foreground and background of the image, has the best effect of distinguishing the foreground and background, and is simple to calculate, being unaffected by the image brightness and contrast. The K-means clustering segmentation algorithm is based on the Euclidean distance. Points with close distances are grouped into one class, the distance mean is recalculated, and the mean value is selected as the new seed point. The clustering center is continuously iteratively corrected until the criterion function reaches the optimal value to obtain the best segmentation threshold. The basic idea of the iterative threshold segmentation method is to obtain the segmentation threshold by continuously iterating and determining whether the mean of the average gray values of the foreground and background parts is equal to the threshold before iteration or the change in the threshold between the last two iterations is less than the set value. The iterative threshold segmentation method has high practicability and robustness and can effectively handle image segmentation problems in the case of complex and diverse backgrounds. The maximum entropy segmentation algorithm uses the maximum information entropy of the image to distinguish the foreground and background. The triangle segmentation algorithm assumes that there is only one peak in the image gray histogram (unimodal histogram). At this time, only the maximum vertical distance from each point on the histogram to the line connecting the highest point and the leftmost or rightmost point of the gray histogram needs to be found, and the gray value of this point is the segmentation threshold. The triangle threshold segmentation has a good segmentation effect on image types with obvious unimodal gray histograms of images.

[0105] To verify the accuracy of the comparative analysis results, Subregions A and B are selected from the study area for comparison. Five segmentation methods are used for segmentation, and the spatial distribution of their segmentation results is as Figure 3 、 Figure 4As shown in the figure, where (a) is the value of the remote sensing index of wheat mildew (WMI), represented by grayscale value, and (b) is the segmentation result of the Otsu threshold segmentation method (yellow indicates that the recognition result is mildewed wheat, and green indicates that the recognition result is normal wheat, the same below). (c) is the segmentation result of the K-means clustering segmentation method. (d) is the segmentation result of the iterative threshold segmentation method. (e) is the segmentation result of the maximum entropy segmentation method. (f) is the segmentation result of the triangle segmentation method. The overall accuracy and Kappa coefficient are used to evaluate the accuracy of the above five segmentation methods. The overall accuracy of the Otsu threshold segmentation is 93.62%, and the Kappa coefficient is 0.857. The overall accuracy of the K-means clustering algorithm is 93.05%, and the Kappa coefficient is 0.843. The overall accuracy of the iterative threshold segmentation is 93.37%, and the Kappa coefficient is 0.8509. The overall accuracy of the maximum entropy segmentation is 65.53%, and the Kappa coefficient is 0.0506. The overall accuracy of the triangle segmentation is 34.84%, and the Kappa coefficient is 0. Among the five segmentation algorithms, the overall accuracy and Kappa coefficient of the Otsu threshold segmentation method and the iterative threshold segmentation method are relatively high. The overall accuracy of both reaches more than 93%, and the Kappa coefficient reaches more than 0.84. Based on the above results, and considering the problem of simple and efficient calculation at the same time, therefore, the Otsu threshold segmentation method and the iterative threshold segmentation method are determined as the optimal segmentation methods.

[0106] Two classic machine learning classification methods, random forest and support vector machine, are used to extract mildewed wheat in the study area to compare and verify the performance of the proposed remote sensing index of wheat mildew in the extraction of mildewed wheat. In terms of feature selection, in addition to selecting 4 bands of blue, green, red, and near-infrared, 27 kinds of index features are calculated using ENVI software. At the same time, a variety of traditional remote sensing indexes commonly used in existing wheat disease research are referred to, including: Greenness Index (GI), Triangular vegetation Index (TVI), Normalized Pigment Chlorophyll ratio Index (NPCI), Structural Independent Pigment Index (SIPI), Nitrogen Reflectance Index (NRI), and Green Chlorophyll Index (GCI), 6 kinds of remote sensing index features. The Relief F algorithm and the mRMR algorithm are combined to reduce the dimension of the above 37 kinds of features, screen the optimal feature subset for mildewed wheat classification, and finally select the top 5 features with the largest feature weights and input them into the random forest and support vector machine classification models for training, and the training results are used for random forest and support vector machine classification. The classification results are asFigure 5 As shown in the figure, where (a) is the value of the remote sensing index of wheat mildew in the study area, represented by grayscale, (b) is the classification result of the random forest, and (c) is the classification result of the support vector machine. Calculate the overall accuracy and Kappa coefficient for the classification results of the random forest and the support vector machine respectively: The highest overall accuracy of the random forest classification for extracting mildewed wheat is 92.40%, and the Kappa coefficient is 0.8354. The highest overall accuracy of the support vector machine classification for extracting mildewed wheat is 92.40%, and the Kappa coefficient is 0.8354.

[0107] It can be seen that the automatic extraction method for the mildew range of winter wheat proposed in this application, through the combination of the mildew remote sensing index and the threshold segmentation method, can achieve an accuracy level comparable to that of the random forest and the support vector machine classification. Moreover, this method does not require sample collection and a large amount of preprocessing and training processes. Only simple area and ratio calculations are needed to achieve fast and accurate classification using threshold segmentation.

[0108] In terms of the mobility of the remote sensing platform, Figure 6 、 Figure 7Schematic diagram of the results of extracting the mildew range from different remote sensing data sources using the mildew remote sensing index. Among them: (a) is the mildew remote sensing index of Sentinel-2 image (abbreviation: S2); (b) is the segmentation result of the mildew remote sensing index of Sentinel-2 image by Otsu threshold segmentation method; (c) is the segmentation result of the mildew remote sensing index of Sentinel-2 image by iterative threshold segmentation method; (d) is the mildew remote sensing index of Landsat-9 image (abbreviation: L9); (e) is the segmentation result of the mildew remote sensing index of Landsat-9 image by Otsu threshold segmentation method; (f) is the segmentation result of the mildew remote sensing index of Landsat-9 image by iterative threshold segmentation method. The accuracy evaluation of the segmentation results of the wheat mildew remote sensing index of different remote sensing data sources is as follows: The overall accuracy of the segmentation results of the mildew remote sensing index of Sentinel-2 image by Otsu threshold segmentation method and iterative threshold segmentation method is 92.94%, and the Kappa coefficient is 0.8461. The overall accuracy of the segmentation result of the mildew remote sensing index of Landsat-9 image by Otsu threshold segmentation method is 91.40%, and the Kappa coefficient is 0.8151; the overall accuracy of the segmentation result of the mildew remote sensing index of Landsat-9 image by iterative threshold segmentation method is 91.14%, and the Kappa coefficient is 0.8102. The above results show that the wheat mildew remote sensing index proposed in this application has generalization ability and good migration for different remote sensing sensors. For sensor data from different sources, the extraction accuracy of mildewed wheat reaches over 91%, and the Kappa coefficient is above 0.81. At the same time, it also shows that taking the mildew remote sensing index as the segmentation index, the reflectance difference between normal wheat and mildewed wheat is still well retained in medium and high-resolution remote sensing images such as Sentinel-2 and Landsat-9. That is to say, for this index, the difference in spectral reflectance between normal wheat and mildewed wheat is not sensitive to the remote sensing platform and remote sensing sensors, so that the index still has good adaptability and generalization ability for different remote sensing image data sources, greatly expanding the application scenarios of the index, and then it can be realized to monitor the high-frequency wheat mildew situation using various resolution remote sensing images.

[0109] In terms of the migration in different study areas, Figure 8Schematic diagram of the result of extracting the mildew range in different regions during the same period using the mildew remote sensing index. Among them, (a) shows the values of the wheat mildew remote sensing index (WMI), represented by grayscale values, (b) shows the Otsu threshold segmentation result, and (c) shows the result of the iterative threshold segmentation method. Based on the high-resolution satellite image No. 2 of different regions during the same period, the mildew situation of wheat was monitored. The overall accuracy of extracting mildewed wheat by Otsu threshold segmentation was 91.76%, and the Kappa coefficient was 0.8285. The overall accuracy of extracting by iterative threshold segmentation was 91.91%, and the Kappa coefficient was 0.8320. Generally speaking, the extraction results of the wheat mildew index in different regions are very close, with the overall accuracy above 91% and the Kappa coefficient above 0.82. The results show that the spectral reflectance difference between mildewed wheat and normal wheat is universal, and this difference can be captured by remote sensing sensors with little influence from geographical factors. Furthermore, it shows that the wheat mildew remote sensing index constructed based on the spectral difference between normal wheat and mildewed wheat in this application has good applicability in different regions.

[0110] In summary, in this application, by analyzing the spectral differences between mildewed wheat and normal wheat, the wheat mildew remote sensing index was constructed using the area method to enhance the spectral differences between normal wheat and mildewed wheat, and then multiple segmentation methods were used to achieve the automatic segmentation of mildewed wheat. The experimental results show that the extraction results based on the wheat mildew remote sensing index are similar to the overall accuracy of the extraction results of traditional random forest and SVM classification methods, but the extraction process is greatly simplified. Moreover, the wheat mildew remote sensing index has good transferability to different remote sensing sensor data, and the extraction result accuracy is more stable, with good applicability and generalization ability.

[0111] Embodiment 3

[0112] This embodiment provides a wheat mildew remote sensing index calculation system, including:

[0113] A data acquisition unit configured to acquire multispectral remote sensing images;

[0114] A curve plotting unit configured to plot the surface reflectance curves of the multispectral remote sensing images in multiple bands with the wavelength as the horizontal axis and the surface reflectance as the vertical axis;

[0115] A first polygon area solving unit configured to calculate the areas of the right trapezoids formed by the surface reflectance curves of each band and the coordinate horizontal axis according to the intervals between the central wavelengths of adjacent bands, sum them, and record the summation result as the first polygon area;

[0116] The second polygon area calculation unit is configured to determine the maximum surface reflectance of all pixels in the multispectral remote sensing image, and calculate the area of the rectangle formed by the maximum surface reflectance, the central wavelength of the first band, the horizontal coordinate axis, and the central wavelength of the second band, which is denoted as the second polygon area; the first band is the band with the shortest central wavelength among multiple bands, and the second band is the band with the longest central wavelength among multiple bands;

[0117] The ratio calculation unit is configured to calculate the ratio of the first polygon area to the second polygon area, with the first polygon area as the numerator and the second polygon area as the denominator, to obtain the mildew remote sensing index.

[0118] The wheat mildew remote sensing index calculation system provided in this embodiment can implement the processes and steps of the wheat mildew remote sensing index calculation method provided in any of the above embodiments, and achieve the same technical effects, which will not be elaborated here one by one.

[0119] Embodiment 4

[0120] This embodiment provides an automatic extraction system for the mildew range of winter wheat at maturity, including:

[0121] The range determination unit is configured to determine the target cultivated land range;

[0122] The index calculation unit is configured to calculate the mildew remote sensing index value corresponding to each pixel in the multispectral remote sensing image of the target cultivated land range by using the wheat mildew remote sensing index calculation method provided in any of the above embodiments; wherein, the multispectral remote sensing image contains the spectral information of mildewed wheat and normal wheat;

[0123] The threshold calculation unit is configured to determine the segmentation threshold by using an image segmentation method based on the mildew remote sensing index value;

[0124] The disaster-affected area extraction unit is configured to divide the target cultivated land range into a normal wheat area and a wheat disaster-affected area according to the segmentation threshold, so as to extract the wheat disaster-affected area.

[0125] The automatic extraction system for the mildew range of winter wheat at maturity provided in this embodiment can implement the processes and steps of the automatic extraction method for the mildew range of winter wheat at maturity provided in any of the above embodiments, and achieve the same technical effects, which will not be elaborated here one by one.

[0126] Embodiment 5

[0127] This embodiment provides an electronic device, which includes a memory, and an instruction is stored on the memory. When the instruction is executed on a computer, the computer is caused to execute the wheat mildew remote sensing index calculation method provided in any of the above embodiments, or execute the automatic extraction method for the mildew range of winter wheat at maturity provided in any of the above embodiments.

[0128] For the electronic device according to the embodiment of the present application, the electronic device may be, but is not limited to, mobile terminals such as mobile phones, tablet computers, handheld computers, personal digital assistants (PDAs), etc., smart home devices such as smart TVs, smart cameras, etc., wearable devices such as smart bracelets, smart watches, smart glasses, or other computer devices such as desktop computers, laptop computers, notebook computers, ultra-mobile personal computers (UMPCs), netbooks, smart screens, etc.

[0129] The electronic device may include one or more of the following components: a processor, a computer-readable storage medium (memory), a communication interface, and a communication bus. Among them, the memory may be connected to the processor through the bus. The bus can transfer data between the processor and the memory. The bus can be divided into an address bus, a data bus, a control bus, etc.

[0130] The processor may include one or more processing cores. The processor can connect various parts within the entire electronic device using various interfaces and circuits. By running or executing instructions, programs, code sets, or instruction sets stored in the memory, and by invoking the data stored in the memory, it can perform various functions of the electronic device and process data. Exemplarily, the processor may include an application processor (AP), a modem processor, a CPU, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a field-programmable gate array (FPGA), a programmable logic array (PLA), and / or a neural-network processing unit (NPU), etc. Among them, the CPU mainly processes the operating system, user interface, and application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed; the NPU is used to implement artificial intelligence (AI) functions; the modem is used to process wireless communication. Different processing units can be independent devices or integrated in one or more processors. For example, the multiple processing units shown above are all integrated in one SoC, or the AP is a separate semiconductor chip and other processing units are integrated in one SoC. This application does not make any limitations in this regard.

[0131] The memory may include a random access memory (RAM), may also include a read-only memory (ROM), and may further include a non-transitory computer-readable storage medium. The memory can be used to store instructions, programs, code, code sets, or instruction sets. The memory may include a program storage area and a data storage area. Among them, the program storage area can store instructions for implementing the operating system, instructions for at least one function, such as a three-dimensional rough fracture non-linear flow field simulation method, a three-dimensional rough fracture long-term corrosion mechanism analysis method, etc.; the data storage area can store the data created according to the use of the electronic device, such as the input data for flow field simulation, etc.

[0132] In addition, those skilled in the art can understand that the structure of the electronic device shown in the above drawings does not limit the electronic device. The electronic device may include more or fewer components than shown in the drawings, or combine certain components, or have different component arrangements. For example, the electronic device also includes components such as a microphone, a speaker, a radio frequency circuit, a sensor, an audio circuit, a power supply, and a Bluetooth module, which will not be elaborated here.

[0133] The above are only the preferred embodiments of the present application and are not used to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for calculating wheat mildew remote sensing index, characterized in that: include: Acquire multispectral remote sensing images; With wavelength as the horizontal axis and surface reflectivity as the vertical axis, plotting the surface reflectivity curve of the multispectral remote sensing image in multiple bands; According to the interval between the central wavelengths of adjacent bands, the area of ​​the right-angled trapezoid formed by the surface reflectance curve of each band and the horizontal axis of the coordinate is calculated, and the sum is calculated, and the sum result is recorded as the first polygon area; Determine the maximum value of the surface reflectance of all pixels in the multispectral remote sensing image, and calculate the area of ​​a rectangle enclosed by the maximum value of the surface reflectance, the central wavelength of the first band, the horizontal axis of the coordinate, and the central wavelength of the second band, and record it as the second polygonal area; the first band is the band with the shortest central wavelength among the multiple bands, and the second band is the band with the longest central wavelength among the multiple bands; The ratio of the area of ​​the first polygon to the area of ​​the second polygon is calculated with the area of ​​the first polygon as the numerator and the area of ​​the second polygon as the denominator to obtain the mildew remote sensing index.

2. The method for calculating the wheat mildew remote sensing index according to claim 1, characterized in that: After calculating the ratio of the area of ​​the first polygon to the area of ​​the second polygon with the area of ​​the first polygon as the numerator and the area of ​​the second polygon as the denominator to obtain the mildew remote sensing index, the method further includes: assuming that the intervals between the central wavelengths of adjacent bands are equal, simplifying the mildew remote sensing index to obtain a simplified mildew remote sensing index.

3. The method for calculating the wheat mildew remote sensing index according to claim 1, characterized in that: The multispectral remote sensing image includes but is not limited to: spectral information of visible light band and near infrared band, and the multiple bands include but are not limited to: blue, green, red, and near infrared bands.

4. A method for automatically extracting the mildew range of winter wheat at maturity using the wheat mildew remote sensing index calculation method according to any one of claims 1 to 3, characterized in that: include: Determine the scope of target cultivated land; The method for calculating the wheat mildew remote sensing index according to any one of claims 1 to 3 is used to calculate the mildew remote sensing index value corresponding to each pixel in the multispectral remote sensing image of the target cultivated land range; wherein the multispectral remote sensing image contains spectral information of mildewed wheat and normal wheat; Based on the mildew remote sensing index value, a segmentation threshold is determined using an image segmentation method; According to the segmentation threshold, the target cultivated land range is segmented into normal wheat areas and wheat disaster-affected areas to extract the wheat disaster-affected area.

5. The method for automatically extracting the mildew range of winter wheat at maturity stage according to claim 4, characterized in that: Based on the mildew remote sensing index value, an image segmentation method is used to determine a segmentation threshold, including: Use multiple candidate image segmentation methods to segment the wheat mildew remote sensing index value, and determine the segmentation threshold value corresponding to each candidate image segmentation method; The overall accuracy and Kappa coefficient are used as evaluation indicators, and the segmentation results of each candidate image segmentation method are verified through the confusion matrix to determine the optimal segmentation method; and the threshold corresponding to the optimal segmentation method is used as the segmentation threshold.

6. The method for automatically extracting the mildew range of winter wheat at maturity according to claim 5, characterized in that: The multiple image segmentation methods to be selected include but are not limited to: Otsu threshold segmentation method, K-means clustering segmentation method, iterative threshold segmentation method, maximum entropy segmentation method and triangular segmentation method.

7. The method for automatically extracting the mildew range of winter wheat at maturity stage according to claim 6, characterized in that: The optimal segmentation methods are Otsu threshold segmentation method and iterative threshold segmentation method.

8. A wheat mildew remote sensing index calculation system, characterized in that: include: a data acquisition unit configured to acquire multispectral remote sensing images; A curve drawing unit is configured to draw a surface reflectance curve of the multispectral remote sensing image in multiple bands with wavelength as the horizontal axis and surface reflectance as the vertical axis; A first polygon area solving unit is configured to calculate the area of ​​a right-angled trapezoid formed by the surface reflectance curve of each band and the horizontal axis of the coordinate according to the interval between the central wavelengths of adjacent bands, and sum them up, and record the summation result as the first polygon area; The second polygon area solving unit is configured to determine the maximum surface reflectance of all pixels in the multispectral remote sensing image, and calculate the area of ​​a rectangle enclosed by the maximum surface reflectance, the central wavelength of the first band, the horizontal axis of the coordinate, and the central wavelength of the second band, which is recorded as the second polygon area; the first band is the band with the shortest central wavelength among the multiple bands, and the second band is the band with the longest central wavelength among the multiple bands; The ratio calculation unit is configured to calculate the ratio of the first polygon area to the second polygon area with the first polygon area as the numerator and the second polygon area as the denominator to obtain the mildew remote sensing index.

9. An automatic extraction system for the mildew range of winter wheat at maturity, characterized in that: include: a range determination unit configured to determine a range of target cultivated land; An index calculation unit is configured to calculate the mildew remote sensing index value corresponding to each pixel in the multispectral remote sensing image of the target cultivated land range by using the wheat mildew remote sensing index calculation method according to any one of claims 1 to 3; wherein the multispectral remote sensing image contains spectral information of mildewed wheat and normal wheat; A threshold calculation unit configured to determine a segmentation threshold using an image segmentation method based on the mildew remote sensing index value; The disaster-affected extraction unit is configured to segment the target cultivated land range into normal wheat areas and wheat-affected areas according to the segmentation threshold, so as to extract the wheat-affected area.

10. An electronic device, comprising a memory, characterized in that: The memory stores instructions which, when executed on a computer, cause the computer to execute the method for calculating the wheat mildew remote sensing index according to any one of claims 1 to 3, or the method for automatically extracting the mildew range of winter wheat at maturity according to any one of claims 4 to 7.

Images