A vegetation classification method and device

Abstract

The present invention discloses a vegetation classification method and apparatus, comprising: preprocessing a remote sensing image of a target area to obtain a target image; determining a buffer zone based on the remote sensing image of the target area; collecting pixel information in the buffer zone and determining a target segmentation threshold based on the pixel information; and classifying the target image based on the target segmentation threshold to obtain a vegetation area. In the present invention, the target segmentation threshold is a bisection axis corresponding to the maximum inter-class variance, determined based on a target processing mode and the pixel information. The target processing mode is a mode in which the bisection axis is iteratively processed by increasing the step size by one. This target segmentation threshold determination method is suitable for threshold segmentation of planar floating-point data, avoiding compression of high-precision floating-point data and improving vegetation classification accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a vegetation classification method and device. Background Art

[0002] Since vegetation can bring various values ​​such as economic value and environmental value, how to accurately identify vegetation has become the focus of current attention.

[0003] Currently, vegetation information is typically identified and extracted based on the spectral characteristics of ground objects. This primarily exploits the fact that different objects reflect or absorb different wavelengths of visible light. These methods include single-band thresholding, spectral relationship methods, and exponential model methods. All three rely heavily on threshold segmentation and are classified as threshold classification methods. Vegetation and non-vegetation classification based on the vegetation index model also relies heavily on threshold selection, and the quality of the threshold selection method directly affects the accuracy of the final vegetation classification. Common threshold selection methods include manual experience selection, histogram analysis, Otsu's method, and adaptive thresholding. Manual experience selection relies heavily on empirical judgment and is difficult to automate. Histogram analysis is only applicable to binary images with clear contrast between foreground and background colors. Adaptive thresholding is typically used for localized image threshold optimization and is often used to address challenges in threshold selection caused by uneven illumination distribution. The Otsu method only supports RGB color brightness values, such as {0, 1, 2, …, 255}, making it inapplicable to remote sensing images, which are typically floating-point data.

[0004] It can be seen that the existing threshold selection method cannot be applied to all application scenarios, which reduces the accuracy of vegetation classification. Summary of the Invention

[0005] In order to solve the above problems, the present invention provides a vegetation classification method and device, which improves the accuracy of vegetation classification.

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] A vegetation classification method comprising:

[0008] Preprocessing the acquired remote sensing image of the target area to obtain a target image;

[0009] determining a buffer zone based on remote sensing images of the target area;

[0010] Counting pixel information of the buffer zone and determining a target segmentation threshold based on the pixel information, wherein the target segmentation threshold is a bisection axis corresponding to a maximum inter-class variance determined according to a target processing mode and the pixel information, wherein the target processing mode is a mode of iteratively processing the bisection axis by increasing a step size;

[0011] The target image is classified based on the target segmentation threshold to obtain a vegetation area.

[0012] Optionally, preprocessing the acquired remote sensing image of the target area to obtain the target image includes:

[0013] Screening the acquired remote sensing image of the target area to obtain a first image;

[0014] removing cirrus clouds from the first image, and extracting the median of the first image after the cirrus clouds are removed;

[0015] synthesizing the first image after removing cirrus clouds based on the median to obtain a synthesized image, and performing band calculation according to a vegetation index model to obtain a normalized vegetation index;

[0016] A target image corresponding to the normalized vegetation index is determined in the synthetic image.

[0017] Optionally, determining the buffer zone based on the remote sensing image of the target area includes:

[0018] Performing edge detection on the remote sensing image of the target area to obtain edge pixels;

[0019] Pixel dilation is performed on each edge pixel to obtain a buffer zone.

[0020] Optionally, the counting of pixel information of the buffer zone and determining a target segmentation threshold based on the pixel information includes:

[0021] Processing the vegetation index data of the buffer zone to obtain a one-dimensional ordered array;

[0022] Performing statistics on corresponding pixel information in the one-dimensional ordered data to obtain minimum and maximum values;

[0023] Determining a bisection axis based on a preset step size and the minimum value;

[0024] Classifying the one-dimensional ordered data based on the bipartite axis and determining the probability of a point falling into each classification;

[0025] The inter-class variance is obtained according to the probability calculation, and a step size is added to the bipartite axis to obtain a new bipartite axis, and the inter-class variance is determined by the new bipartite axis until the bipartite axis is no greater than the maximum value and the iteration is stopped;

[0026] The bipartite axis corresponding to the maximum inter-class variance is determined as the target segmentation threshold.

[0027] Optionally, the method further includes:

[0028] The target image is rendered based on the color features corresponding to the vegetation area to obtain a rendered image.

[0029] A vegetation classification device, comprising:

[0030] A preprocessing unit, used for preprocessing the acquired remote sensing image of the target area to obtain a target image;

[0031] A first determining unit is configured to determine a buffer zone based on a remote sensing image of the target area;

[0032] a second determining unit, configured to collect pixel information of the buffer zone and determine a target segmentation threshold based on the pixel information, wherein the target segmentation threshold is a bisection axis corresponding to a maximum inter-class variance determined according to a target processing mode and the pixel information, wherein the target processing mode is a mode of iteratively processing the bisection axis by increasing a step size;

[0033] The classification unit is used to classify the target image based on the target segmentation threshold to obtain a vegetation area.

[0034] Optionally, the pre-processing unit includes:

[0035] a screening subunit, configured to screen the acquired remote sensing image of the target area to obtain a first image;

[0036] an extraction subunit, configured to remove cirrus clouds from the first image and extract a median of the first image after the cirrus clouds are removed;

[0037] a calculation subunit, configured to synthesize the first image after removing cirrus clouds based on the median to obtain a synthetic image, and perform band calculation according to a vegetation index model to obtain a normalized vegetation index;

[0038] The first determining subunit is configured to determine a target image corresponding to the normalized vegetation index in the synthetic image.

[0039] Optionally, the first determining unit includes:

[0040] A detection subunit, configured to perform edge detection on the remote sensing image of the target area to obtain edge pixels;

[0041] The expansion processing subunit is used to perform pixel expansion on each edge pixel to obtain a buffer zone.

[0042] Optionally, the second determining unit is specifically configured to:

[0043] Processing the vegetation index data of the buffer zone to obtain a one-dimensional ordered array;

[0044] Performing statistics on corresponding pixel information in the one-dimensional ordered data to obtain minimum and maximum values;

[0045] Determining a bisection axis based on a preset step size and the minimum value;

[0046] Classifying the one-dimensional ordered data based on the bipartite axis and determining the probability of a point falling into each classification;

[0047] The inter-class variance is obtained according to the probability calculation, and a step size is added to the bipartite axis to obtain a new bipartite axis, and the inter-class variance is determined by the new bipartite axis until the bipartite axis is no greater than the maximum value and the iteration is stopped;

[0048] The bipartite axis corresponding to the maximum inter-class variance is determined as the target segmentation threshold.

[0049] Optionally, the device further comprises:

[0050] A rendering unit is used to render the target image based on the color features corresponding to the vegetation area to obtain a rendered image.

[0051] Compared to the prior art, the present invention provides a vegetation classification method and apparatus, comprising: preprocessing a remote sensing image of a target area to obtain a target image; determining a buffer zone based on the remote sensing image of the target area; collecting pixel information in the buffer zone and determining a target segmentation threshold based on the pixel information; and classifying the target image based on the target segmentation threshold to obtain a vegetation area. In the present invention, the target segmentation threshold is the bisection axis corresponding to the maximum inter-class variance, determined based on a target processing mode and the pixel information. The target processing mode is an iterative processing mode in which the bisection axis is incremented by one step. This target segmentation threshold determination method is suitable for threshold segmentation of planar floating-point data, avoiding compression of high-precision floating-point data and improving vegetation classification accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0053] Figure 1 A schematic diagram of a process flow of a vegetation classification method provided by an embodiment of the present invention;

[0054] Figure 2 A schematic diagram of a flow chart of a method for determining a target segmentation threshold provided by an embodiment of the present invention;

[0055] Figure 3 A schematic diagram of a process for extracting vegetation from remote sensing images provided by an embodiment of the present invention;

[0056] Figure 4 A schematic structural diagram of a vegetation classification device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0057] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0058] The terms "first," "second," and the like in the specification, claims, and accompanying drawings of the present invention are used to distinguish between different items, not to describe a specific order. Furthermore, the terms "including," "having," and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements and may include steps or elements that are not listed.

[0059] In an embodiment of the present invention, a vegetation classification method is provided. Figure 1 , the method may include the following steps:

[0060] S101 , preprocessing the acquired remote sensing image of the target area to obtain a target image.

[0061] The target area refers to an area where vegetation classification is required, for example, a designated area to be classified. When acquiring remote sensing images corresponding to the target area, remote sensing images of the target area can be acquired using remote sensing image data in an open source remote sensing image database.

[0062] In order to improve the processing accuracy, the remote sensing image of the target area can be preprocessed. This can be to remove interference data or images, or to extract key information therein. In one implementation of the embodiment of the present invention, the remote sensing image of the target area is preprocessed to obtain a target image, including: screening the remote sensing image of the target area to obtain a first image; removing cirrus clouds from the first image, and extracting the median of the first image after removing the cirrus clouds; synthesizing the first image after removing the cirrus clouds based on the median to obtain a synthetic image, and performing band calculation according to a vegetation index model to obtain a normalized vegetation index; and determining a target image corresponding to the normalized vegetation index in the synthetic image.

[0063] When acquiring the first image, a quality assessment can be performed to select images that meet the processing requirements. A cloud removal algorithm can then be used to remove cirrus clouds from the target area. Normalized Difference Vegetation Index (NDVI): Due to the composition of plant leaf cells, plants have high reflectivity in the near-infrared band and strong absorptivity in the red band. The vegetation index is a model that can extract vegetation based on the ratio between these bands. NDVI is used to monitor vegetation growth, vegetation cover, and eliminate some radiation errors. NDVI can reflect background influences of the plant canopy, such as soil, wet ground, snow, dead leaves, and roughness, and is related to vegetation cover.

[0064] S102: Determine a buffer zone based on the remote sensing image of the target area.

[0065] The corresponding buffer spacing can be set based on the control resolution of the vegetation index, and then the corresponding buffer is determined based on the buffer spacing. Alternatively, edge detection can be performed on the remote sensing image of the target area to obtain edge pixels; and pixel expansion is performed on each of the edge pixels to obtain a buffer. In this embodiment, in order to remove the influence of other irrelevant background objects in the area on the results, the Canny edge detection algorithm is used, and on this basis, the pixels are expanded one by one according to a certain proportion to obtain a buffer, so that the global threshold segmentation algorithm OTSU (Otsu method) can concentrate the target on the edge part, thereby improving the accuracy of threshold segmentation. Among them, the edge detection algorithm is a common algorithm for extracting image features in image processing and computer vision. It detects the edge contour line of the target area in the image based on the characteristic that the image gradient can obtain a maximum value at the edge pixel point.

[0066] S103: Count pixel information of the buffer zone, and determine a target segmentation threshold based on the pixel information.

[0067] The method for determining the target segmentation threshold in the embodiment of the present invention can be applied to the processing of planar floating-point data. This is primarily achieved through a modified Otsu method, also known as the maximum between-class variance method (OTSU). The Otsu method uses statistical learning to calculate pixel grayscale values ​​and select a threshold to segment an image into a target and foreground.

[0068] Specifically, the target segmentation threshold is a bisection axis corresponding to the maximum inter-class variance determined according to a target processing mode and the pixel information, wherein the target processing mode is a mode of iteratively processing the bisection axis by increasing a step size.

[0069] In one implementation of an embodiment of the present invention, the counting of pixel information of the buffer zone and determining the target segmentation threshold based on the pixel information include: processing the vegetation index data of the buffer zone to obtain a one-dimensional ordered array; counting the corresponding pixel information in the one-dimensional ordered data to obtain a minimum value and a maximum value; determining a bipartite axis based on a preset step size and the minimum value; classifying the one-dimensional ordered data based on the bipartite axis to determine the probability of points falling into each category; calculating the inter-class variance according to the probability, adding a step size to the bipartite axis to obtain a new bipartite axis, and determining the inter-class variance with the new bipartite axis, and stopping the iteration until the bipartite axis is no greater than the maximum value; determining the bipartite axis corresponding to the maximum inter-class variance as the target segmentation threshold.

[0070] S104: Classify the target image based on the target segmentation threshold to obtain a vegetation area.

[0071] After determining the target segmentation threshold, binary image classification can be performed to identify vegetation areas. To facilitate visualization, the target image can be rendered based on the color characteristics corresponding to the vegetation areas to produce a rendered image. The resulting vegetation selection is then overlaid on a true-color composite image to visually display the classification results.

[0072] The present invention provides a vegetation classification method, comprising: preprocessing a remote sensing image of a target area to obtain a target image; determining a buffer zone based on the remote sensing image of the target area; collecting pixel information in the buffer zone and determining a target segmentation threshold based on the pixel information; and classifying the target image based on the target segmentation threshold to obtain a vegetation area. In the present invention, the target segmentation threshold is a bisection axis corresponding to a maximum inter-class variance, determined based on a target processing mode and the pixel information, wherein the target processing mode is a mode in which the bisection axis is iteratively processed by increasing the step size by one. This target segmentation threshold determination method is suitable for threshold segmentation of planar floating-point data, avoids compression of high-precision floating-point data, and improves vegetation classification accuracy.

[0073] See also Figure 2 , which is a flow chart of a method for determining a target segmentation threshold provided by an embodiment of the present application. First, the vegetation index data of the edge buffer is read into the memory as an array and sorted to obtain a one-dimensional ordered array.

[0074] Then, determine the minimum and maximum values in the one-dimensional ordered array. For example, denote the minimum and maximum values in the array as min and max respectively. Set the step size step according to the target accuracy. Then the i-th binary axis is pivot(i) = min + (i + 1) * step. Divide the array into two categories with the binary axis pivot as the axis, denoted as Class1 (min < Class1 <= pivot) and Class2 (pivot < Class2 <= max) respectively. Count the number of points falling into Class1 and Class2 as the probabilities p1 and p2, and calculate the means of the two categories denoted as mean1 and mean2. After derivation, substitute them into the between-class variance formula δ , ,

[0078] , ,

[0077] ,

[0081] ,

[0080] , ,

[0079] , i = p1 * p2 * (mean1 - mean2) 2 . Store the between-class variance in the hash table map[pivot] = between-class variance.

[0075] On the basis of the above, increase the binary axis by one step size, that is, i = i + 1. Determine whether this binary axis is less than or equal to the maximum value max. If it is satisfied, continue the above operation with the new binary axis. If not, the iteration ends. In the hash table, determine the binary axis corresponding to the maximum between-class variance as the target segmentation threshold.

[0076] See Figure 3 , which is a schematic flowchart of a method for extracting vegetation from remote sensing images provided by an embodiment of the present invention. It includes:

[0077] Data preprocessing: Obtain remote sensing images of a specified area through an open-source remote sensing image database, evaluate the quality of the images and select the images that meet the conditions, use a cloud removal algorithm to remove cirrus clouds in the regional images, take the median of each image, synthesize the images and perform band calculations according to the vegetation index model to obtain the NDVI (Normalized Difference Vegetation Index) result.

[0078] Generate a buffer: In order to remove the influence of other irrelevant background features in the area on the results, use the Canny algorithm for edge detection, and on this basis, expand each pixel by a certain ratio to obtain a buffer, so that the global threshold segmentation algorithm OTSU can concentrate the target on the edge part, thereby improving the accuracy of threshold segmentation.

[0079] Threshold segmentation: On the basis of the above edge buffer, count the pixel information, and calculate the optimal segmentation threshold according to the improved OTSU algorithm.

[0080] Visualization: Perform binary processing on the image with the selected threshold to obtain the vegetation area, overlay the obtained vegetation selection on the true color composite image, and visually display the classification results.

[0081] This invention is based on an improved Otsu method using a threshold segmentation method based on the difference index. This method avoids the need to compress high-precision floating-point data, significantly improving segmentation accuracy. Furthermore, the method offers real-time performance, high accuracy, speed, and convenience, while also achieving full automation. It can be applied in agricultural credit scenarios, saving the labor and material costs of traditional manual land surveying and effectively shortening loan application cycles.

[0082] In another embodiment of the present invention, a vegetation classification device is provided. Figure 4 ,include:

[0083] A preprocessing unit 401 is used to preprocess the acquired remote sensing image of the target area to obtain a target image;

[0084] A first determining unit 402 is configured to determine a buffer zone based on a remote sensing image of the target area;

[0085] A second determining unit 403 is configured to collect pixel information of the buffer and determine a target segmentation threshold based on the pixel information, wherein the target segmentation threshold is a bisection axis corresponding to a maximum inter-class variance determined according to a target processing mode and the pixel information, wherein the target processing mode is a mode of iteratively processing the bisection axis by increasing a step size;

[0086] The classification unit 404 is configured to perform classification processing on the target image based on the target segmentation threshold to obtain a vegetation area.

[0087] An embodiment of the present invention provides a vegetation classification device, comprising: a preprocessing unit that preprocesses an acquired remote sensing image of a target area to obtain a target image; a first determination unit that determines a buffer zone based on the remote sensing image of the target area; a second determination unit that counts pixel information in the buffer zone and determines a target segmentation threshold based on the pixel information; and a classification unit that classifies the target image based on the target segmentation threshold to obtain a vegetation area. In the present invention, the target segmentation threshold is a bisection axis corresponding to the maximum inter-class variance determined based on a target processing mode and the pixel information, wherein the target processing mode is a mode in which the bisection axis is iteratively processed by increasing a step size. This method for determining the target segmentation threshold is suitable for threshold segmentation of planar floating-point data, avoids compressing high-precision floating-point data, and improves vegetation classification accuracy.

[0088] Optionally, the pre-processing unit includes:

[0089] a screening subunit, configured to screen the acquired remote sensing image of the target area to obtain a first image;

[0090] an extraction subunit, configured to remove cirrus clouds from the first image and extract a median of the first image after the cirrus clouds are removed;

[0091] a calculation subunit, configured to synthesize the first image after removing cirrus clouds based on the median to obtain a synthetic image, and perform band calculation according to a vegetation index model to obtain a normalized vegetation index;

[0092] The first determining subunit is configured to determine a target image corresponding to the normalized vegetation index in the synthetic image.

[0093] Optionally, the first determining unit includes:

[0094] A detection subunit, configured to perform edge detection on the remote sensing image of the target area to obtain edge pixels;

[0095] The expansion processing subunit is used to perform pixel expansion on each edge pixel to obtain a buffer zone.

[0096] Optionally, the second determining unit is specifically configured to:

[0097] Processing the vegetation index data of the buffer zone to obtain a one-dimensional ordered array;

[0098] Performing statistics on corresponding pixel information in the one-dimensional ordered data to obtain minimum and maximum values;

[0099] Determining a bisection axis based on a preset step size and the minimum value;

[0100] Classifying the one-dimensional ordered data based on the bipartite axis and determining the probability of a point falling into each classification;

[0101] The inter-class variance is obtained according to the probability calculation, and a step size is added to the bipartite axis to obtain a new bipartite axis, and the inter-class variance is determined by the new bipartite axis until the bipartite axis is no greater than the maximum value and the iteration is stopped;

[0102] The bipartite axis corresponding to the maximum inter-class variance is determined as the target segmentation threshold.

[0103] Optionally, the device further comprises:

[0104] A rendering unit is used to render the target image based on the color features corresponding to the vegetation area to obtain a rendered image.

[0105] Based on the foregoing embodiments, embodiments of the present application provide a computer-readable storage medium storing one or more programs, which can be executed by one or more processors to implement the steps of any of the above vegetation classification methods.

[0106] An embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the steps of the vegetation classification method are implemented when the processor executes the program.

[0107] It should be noted that the above-mentioned processor or CPU can be at least one of an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a central processing unit (CPU), a controller, a microcontroller, and a microprocessor. It is understandable that the electronic device that implements the above-mentioned processor function can also be other electronic devices, which are not specifically limited in the embodiments of the present application.

[0108] It should be noted that the above-mentioned computer storage medium / memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory (Flash Memory), a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); it can also be various terminals including one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc.

[0109] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0110] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0111] In addition, the functional units in the embodiments of the present application can all be integrated into one processing module, or each unit can be a separate unit, or two or more units can be integrated into one unit; the above-mentioned integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional units. It can be understood by ordinary technicians in this field that all or part of the steps of the above-mentioned method embodiments can be completed by hardware related to program instructions, and the above-mentioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiments; and the above-mentioned storage medium includes: mobile storage devices, read-only memory (ROM), random access memory (RAM), disks or optical disks, etc. Various media that can store program codes.

[0112] The methods disclosed in the several method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0113] The features disclosed in the several product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0114] The features disclosed in the several method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0115] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0116] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0117] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A vegetation classification method, characterized in that: include: Preprocessing the acquired remote sensing image of the target area to obtain a target image; Performing edge detection on the remote sensing image of the target area to obtain edge pixels, and performing pixel expansion on each edge pixel to obtain a buffer zone; Counting pixel information of the buffer zone and determining a target segmentation threshold based on the pixel information, wherein the target segmentation threshold is a bisection axis corresponding to a maximum inter-class variance determined according to a target processing mode and the pixel information, wherein the target processing mode is a mode of iteratively processing the bisection axis by increasing a step size; Classify the target image based on the target segmentation threshold to obtain a vegetation area; The counting of pixel information of the buffer zone and determining a target segmentation threshold based on the pixel information includes: Processing the vegetation index data of the buffer zone to obtain a one-dimensional ordered array; Counting the corresponding pixel information in the one-dimensional ordered array to obtain the minimum and maximum values; Determining a bisection axis based on a preset step size and the minimum value; Classifying the one-dimensional ordered array based on the bipartite axis and determining the probability of a point falling into each classification; The inter-class variance is obtained according to the probability calculation, and a step size is added to the bipartite axis to obtain a new bipartite axis, and the inter-class variance is determined by the new bipartite axis until the bipartite axis is no greater than the maximum value and the iteration is stopped; Determine the bipartite axis corresponding to the maximum value of the inter-class variance as the target segmentation threshold; The method for determining the target segmentation threshold is applicable to the threshold segmentation of planar floating-point data.

2. The method according to claim 1, characterized in that The preprocessing of the acquired remote sensing image of the target area to obtain the target image includes: Screening the acquired remote sensing image of the target area to obtain a first image; removing cirrus clouds from the first image, and extracting the median of the first image after the cirrus clouds are removed; synthesizing the first image after removing cirrus clouds based on the median to obtain a synthesized image, and performing band calculation according to a vegetation index model to obtain a normalized vegetation index; A target image corresponding to the normalized vegetation index is determined in the synthetic image.

3. The method according to claim 1, characterized in that The method further comprises: The target image is rendered based on the color features corresponding to the vegetation area to obtain a rendered image.

4. A vegetation classification device, characterized in that: include: A preprocessing unit, used for preprocessing the acquired remote sensing image of the target area to obtain a target image; A first determining unit is configured to perform edge detection on the remote sensing image of the target area to obtain edge pixels, and perform pixel expansion on each edge pixel to obtain a buffer zone; a second determining unit, configured to collect pixel information of the buffer zone and determine a target segmentation threshold based on the pixel information, wherein the target segmentation threshold is a bisection axis corresponding to a maximum inter-class variance determined according to a target processing mode and the pixel information, wherein the target processing mode is a mode of iteratively processing the bisection axis by increasing a step size; a classification unit, configured to classify the target image based on the target segmentation threshold to obtain a vegetation area; The second determining unit is specifically configured to: Processing the vegetation index data of the buffer zone to obtain a one-dimensional ordered array; Counting the corresponding pixel information in the one-dimensional ordered array to obtain the minimum and maximum values; Determining a bisection axis based on a preset step size and the minimum value; Classifying the one-dimensional ordered array based on the bipartite axis and determining the probability of a point falling into each classification; The inter-class variance is obtained according to the probability calculation, and a step size is added to the bipartite axis to obtain a new bipartite axis, and the inter-class variance is determined by the new bipartite axis until the bipartite axis is no greater than the maximum value and the iteration is stopped; Determine the bipartite axis corresponding to the maximum value of the inter-class variance as the target segmentation threshold; The method for determining the target segmentation threshold is applicable to the threshold segmentation of planar floating-point data.

5. The device according to claim 4, characterized in that The pre-processing unit comprises: a screening subunit, configured to screen the acquired remote sensing image of the target area to obtain a first image; an extraction subunit, configured to remove cirrus clouds from the first image and extract a median of the first image after the cirrus clouds are removed; a calculation subunit, configured to synthesize the first image after removing cirrus clouds based on the median to obtain a synthetic image, and perform band calculation according to a vegetation index model to obtain a normalized vegetation index; The first determining subunit is configured to determine a target image corresponding to the normalized vegetation index in the synthetic image.

6. The device according to claim 4, characterized in that The device further comprises: A rendering unit is used to render the target image based on the color features corresponding to the vegetation area to obtain a rendered image.

Images