Mangrove forest extraction method, mangrove forest extraction system and mangrove forest extraction equipment based on self-adaptive threshold value and medium

Abstract

The invention relates to the technical field of mangrove forest extraction. The invention discloses a mangrove forest extraction method, a mangrove forest extraction system, mangrove forest extraction equipment and a medium based on a self-adaptive threshold value, which can improve the mangrove forest area extraction accuracy while simplifying processing steps. The method comprises the following steps: acquiring a multispectral remote sensing image; analyzing and cutting the multispectral remote sensing image to obtain a region-of-interest image; calculating a normalized vegetation index of the image of the region of interest, and detecting the image corresponding to the normalized vegetation index by adopting an Otsu adaptive threshold method to generate a first threshold; generating a vegetation mask based on a first threshold and the normalized vegetation index; calculating a mangrove forest-salt marsh distinguishing index of the image of the region of interest to obtain a mangrove forest-salt marsh distinguishing index image, and generating a mangrove forest-salt marsh mask image and a second threshold value based on the mangrove forest-salt marsh distinguishing index image and the vegetation mask; and obtaining a mangrove forest area based on the mangrove forest-salt marsh mask image, the mangrove forest-salt marsh distinguishing index and a second threshold value.

Description

Technical Field

[0001] The present invention relates to the technical field of mangrove extraction, and more specifically, to a method, system, device and medium for mangrove extraction based on adaptive threshold. Background Art

[0002] In ecological and environmental protection, it is usually necessary to distinguish mangroves from salt marshes in order to better extract mangrove areas for ecological and environmental detection or restoration. Since mangroves and salt marshes have certain similarities in spectral characteristics, traditional mangrove extraction methods often have difficulty effectively distinguishing between mangroves and salt marshes. Specifically, traditional mangrove extraction methods mainly include the following:

[0003] 1) Classification method based on spectral features: Using multispectral or hyperspectral remote sensing data, supervised classification or unsupervised classification algorithms are used to distinguish mangroves from salt marshes to extract mangrove areas. However, this method is highly dependent on ground reference data and is prone to confusion in areas with similar spectral features, resulting in inaccurate extraction of mangrove areas.

[0004] 2) Analysis method based on time series data: Using multi-temporal remote sensing data, different types of vegetation are distinguished by analyzing the temporal variation characteristics of vegetation indices (such as the Normalized Difference Vegetation Index (NDVI)) to extract mangrove areas. However, this method requires a large amount of time series data, which complicates the entire processing process. In addition, this method is affected by cloud cover factors, which affects the accuracy of mangrove area extraction.

[0005] 3) Comprehensive analysis method combined with auxiliary data: Combine auxiliary data such as topography and tides to assist in the identification of mangroves and salt marshes to extract mangrove areas. However, this method requires additional data sources (i.e., auxiliary data), which increases the complexity of data acquisition and processing.

[0006] Therefore, the traditional mangrove extraction method still has many defects that need to be solved. Summary of the invention

[0007] The purpose of the embodiments of the present application is to provide a method, system, device and medium for extracting mangroves based on an adaptive threshold, which can improve the accuracy of mangrove area extraction while simplifying the processing steps. The embodiments of the present application are mainly implemented through the following technical solutions:

[0008] A first aspect of an embodiment of the present application provides a mangrove extraction method based on an adaptive threshold, comprising:

[0009] Acquire multispectral remote sensing images;

[0010] Analyzing and cropping the multispectral remote sensing image to obtain an image of a region of interest;

[0011] Calculating the normalized vegetation index in the image of the region of interest to obtain a normalized vegetation index image, and using the Otsu adaptive threshold method to perform detection processing on the normalized vegetation index image to generate a first threshold;

[0012] comparing the first threshold value with the normalized vegetation index, extracting vegetation areas in the normalized vegetation index image, and generating a vegetation mask;

[0013] Calculating the mangrove-salt marsh discrimination index in the image of the region of interest to obtain a mangrove-salt marsh discrimination index image, and generating a mangrove-salt marsh mask image and a second threshold based on the mangrove-salt marsh discrimination index image and the vegetation mask;

[0014] A mangrove area is obtained based on the mangrove-salt marsh mask image, the mangrove-salt marsh distinction index and the second threshold.

[0015] According to one embodiment of the present application, the step of analyzing and cropping the multispectral remote sensing image to obtain an image of the region of interest includes:

[0016] Performing cloud mask processing on the multispectral remote sensing image to obtain a first image to be processed;

[0017] Performing atmospheric correction processing on the first image to be processed to obtain a second image to be processed;

[0018] The second image to be processed is cropped to obtain the region of interest image.

[0019] According to an embodiment of the present application, the step of using the Otsu adaptive threshold method to detect and process the normalized vegetation index image and generating a first threshold comprises:

[0020] Using the Canny edge detection algorithm of the Otsu adaptive threshold method to detect vegetation edges in the normalized vegetation index image, and generating a first edge image;

[0021] generating a first initial edge buffer based on the first edge image;

[0022] The first initial edge buffer is calculated using the Otsu algorithm of the Otsu adaptive threshold method to obtain the first threshold.

[0023] According to one embodiment of the present application, the step of calculating the mangrove-salt marsh distinction index in the region of interest image includes:

[0024] Acquire the reflectivity of the first band and the reflectivity of the second band of the image of the region of interest;

[0025] A subtraction operation is performed on the reflectivity of the first band and the reflectivity of the second band to obtain the mangrove-salt marsh distinction index.

[0026] According to an embodiment of the present application, the step of generating a mangrove-salt marsh mask image and a second threshold based on the mangrove-salt marsh discrimination index image and the vegetation mask includes:

[0027] Using the vegetation mask to perform mask processing on the mangrove-salt marsh discrimination index image to generate the mangrove-salt marsh mask image;

[0028] Using the Canny edge detection algorithm of the Otsu adaptive threshold method to detect vegetation edges in the mangrove-salt marsh mask image, and generating a second edge image;

[0029] generating a second initial edge buffer based on the second edge image;

[0030] The second initial edge buffer is calculated using the Otsu algorithm of the Otsu adaptive threshold method to obtain the second threshold.

[0031] According to an embodiment of the present application, the step of obtaining the mangrove area based on the mangrove-salt marsh mask image, the mangrove-salt marsh distinction index and the second threshold comprises:

[0032] Determine whether the mangrove-salt marsh discrimination index corresponding to the target pixel in the mangrove-salt marsh mask image is greater than the second threshold corresponding to the target pixel;

[0033] When the mangrove-salt marsh discrimination index corresponding to the target pixel is greater than the second threshold corresponding to the target pixel, dividing the area corresponding to the target pixel into a target area;

[0034] All target areas constitute the mangrove area;

[0035] The target pixel is any pixel in the mangrove-salt marsh mask image.

[0036] According to an embodiment of the present application, the mangrove extraction method based on adaptive threshold further includes:

[0037] A mangrove distribution map is generated based on the mangrove area.

[0038] A second aspect of the embodiment of the present application provides a mangrove extraction system based on an adaptive threshold, comprising:

[0039] A multispectral remote sensing image acquisition module, used for acquiring multispectral remote sensing images;

[0040] An area of ​​interest image acquisition module is used to analyze and crop the multispectral remote sensing image to obtain an area of ​​interest image;

[0041] A first threshold value generating module is used to calculate the normalized vegetation index in the image of the region of interest to obtain a normalized vegetation index image, and use the Otsu adaptive threshold method to detect and process the normalized vegetation index image to generate a first threshold value;

[0042] A vegetation mask generating module, used for comparing the first threshold with the normalized vegetation index, extracting vegetation areas from the normalized vegetation index image, and generating a vegetation mask;

[0043] a second threshold value generating module, configured to calculate the mangrove-salt marsh discrimination index in the image of the region of interest, obtain a mangrove-salt marsh discrimination index image, and generate a mangrove-salt marsh mask image and a second threshold value based on the mangrove-salt marsh discrimination index image and the vegetation mask;

[0044] A mangrove area acquisition module is used to obtain a mangrove area based on the mangrove-salt marsh mask image, the mangrove-salt marsh distinction index and the second threshold.

[0045] The third aspect of the embodiments of the present application provides a terminal device, including: a processor and a memory, the memory is used to store a computer program, the processor is used to call and run the computer program stored in the memory, and execute the steps of the mangrove extraction method based on adaptive threshold provided in the first aspect of the embodiments of the present application.

[0046] The fourth aspect of the embodiments of the present application provides a computer-readable storage medium, which is used to store a computer program, and the computer program enables a computer to execute the steps of the mangrove extraction method based on adaptive thresholds provided in the first aspect of the embodiments of the present application.

[0047] The beneficial effects of the embodiments of the present application include at least:

[0048] The embodiment of the present application introduces a mangrove-salt marsh differentiation index, and utilizes the spectral difference between mangroves and salt marshes in the short-wave infrared band to improve the ability to distinguish mangroves. Specifically, the embodiment of the present application acquires a multispectral remote sensing image; analyzes and clips the multispectral remote sensing image to obtain an image of a region of interest; calculates the normalized vegetation index in the image of the region of interest to obtain a normalized vegetation index image, and uses the Otsu adaptive threshold method to detect and process the normalized vegetation index image to generate a first threshold; compares the first threshold with the normalized vegetation index, extracts the vegetation area in the normalized vegetation index image, and generates a vegetation mask; calculates the mangrove-salt marsh differentiation index in the image of the region of interest to obtain a mangrove-salt marsh differentiation index image, and generates a mangrove-salt marsh mask image and a second threshold based on the mangrove-salt marsh differentiation index image and the vegetation mask; obtains a mangrove area based on the mangrove-salt marsh mask image, the mangrove-salt marsh differentiation index, and the second threshold. Compared with the prior art, the embodiment of the present application only requires multispectral remote sensing image data, without requiring other ground reference data or a large amount of time series data, and does not require auxiliary data such as terrain and tides to extract mangrove areas. Therefore, the embodiment of the present application can improve the accuracy of mangrove area extraction while simplifying the processing steps. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the conventional technology, the drawings required for use in the embodiments or the conventional technology descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0050] Figure 1 A flowchart of a mangrove extraction method based on an adaptive threshold in some embodiments of the present invention;

[0051] Figure 2 A reference image of the multispectral remote sensing image of the present invention in some embodiments;

[0052] Figure 3 A reference diagram of a mangrove area in some embodiments of the present invention;

[0053] Figure 4 It is a principle block diagram of the mangrove extraction system based on adaptive threshold in some embodiments of the present invention;

[0054] Figure 5 It is a principle block diagram of the terminal device of the present invention in some embodiments. DETAILED DESCRIPTION

[0055] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present application, so the present application is not limited by the specific embodiments disclosed below.

[0056] It should be noted that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0057] The terms "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0058] The terms "comprises," "includes," or any other variations thereof are intended to cover a non-exclusive inclusion, for example, a process, method, system, product, or apparatus that comprises a series of steps or elements is not necessarily limited to those steps or elements explicitly listed but may include other steps or elements not explicitly listed or inherent to such process, method, product, or apparatus.

[0059] Unless otherwise defined, all technical and scientific terms used in the specification of this application have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The term "and / or" used in the specification of this application includes any and all combinations of one or more related listed items.

[0060] The specific implementation of the present application is further described below in conjunction with the accompanying drawings.

[0061] <Mangrove extraction method based on adaptive threshold>

[0062] like Figure 1 FIG. 1 is a flowchart of a method for extracting mangroves based on an adaptive threshold according to the first aspect of the embodiment of the present application. Figure 1 In the method, the mangrove extraction method based on adaptive threshold comprises:

[0063] S1. Acquire multispectral remote sensing images.

[0064] The multispectral remote sensing image is acquired by the Sentinel-2 satellite. The Sentinel-2 satellite is a multispectral remote sensing satellite that can provide images in 13 bands, which cover visible light, near infrared and short-wave infrared bands. The multispectral remote sensing image is composed of images of multiple different bands, each of which has different reflection or radiation characteristics to the ground objects, and thus can provide richer information.

[0065] The multispectral remote sensing image can refer to Figure 2 As shown. Figure 2 In the figure, the black area indicated by number 1 is the salt marsh area, and the gray area indicated by number 2 is the mangrove area.

[0066] S2. Analyze and crop the multispectral remote sensing image to obtain an image of a region of interest.

[0067] Furthermore, the S2 step includes:

[0068] S21. Perform cloud mask processing on the multispectral remote sensing image to obtain a first image to be processed.

[0069] The step S21 can remove the influence of clouds and cloud shadows in the multispectral remote sensing image.

[0070] S22: Perform atmospheric correction processing on the first image to be processed to obtain a second image to be processed.

[0071] The atmospheric correction processing method can be a method based on a physical model, such as a MODTRAN (Moderate Resolution Atmospheric Transmission) model and a 6S atmospheric correction model, wherein the MODTRAN model is an atmospheric transmission model for calculating the transmission and absorption of electromagnetic radiation by the atmosphere; the 6S atmospheric correction model mainly considers the influence of the atmosphere on the scattering and absorption of light, and it simulates the influence of the atmosphere on light and removes these influences from the remote sensing image (i.e., the first image to be processed), so that the obtained image is more accurate and clear. The atmospheric correction processing method can also be an empirical method, such as a dark pixel method and a histogram matching method, etc. Specifically, the dark pixel method is an atmospheric correction method based on a statistical model. Its basic principle is to ignore the atmospheric multiple scattering radiation and the diffuse reflection of adjacent pixels, and use the reflectivity change of dark pixels to calculate the atmospheric path radiation, and then obtain the true reflectivity of the ground object, assuming that there are dark pixel areas, surface Lambertian surface reflection, and uniform atmospheric properties on the remote sensing image to be corrected (that is, the first image to be processed). The atmospheric correction processing method can be determined by those skilled in the art according to actual needs, and this article does not make any further restrictions on this.

[0072] Furthermore, the embodiment of the present application performs atmospheric correction processing on the first image to be processed, converts the digital number (DN) into an apparent reflectivity to obtain the second image to be processed.

[0073] S23: Crop the second image to be processed to obtain the region of interest image.

[0074] The ROI image has a region of interest (ROI). The ROI is a region to be processed that is outlined from the second image to be processed in the form of a square, circle, ellipse, irregular polygon, etc.

[0075] S3, calculating the normalized vegetation index in the image of the region of interest to obtain a normalized vegetation index image, and using the Otsu adaptive threshold method to perform detection processing on the normalized vegetation index image to generate a first threshold.

[0076] The calculation formula of the normalized vegetation index is:

[0077] NDVI=(NI R-Red) / (NI R+Red);

[0078] Among them, NDVI is the normalized vegetation index, NIR is the near infrared band (B8), and Red is the red light band (B4).

[0079] Furthermore, the step of using the Otsu adaptive threshold method to detect and process the normalized vegetation index image and generate a first threshold comprises:

[0080] S31. Using the Canny edge detection algorithm of the Otsu adaptive threshold method to detect vegetation edges in the normalized vegetation index image, a first edge image is generated.

[0081] Furthermore, the step S31 includes:

[0082] S311, converting the normalized vegetation index image into a first grayscale image, and smoothing the first grayscale image using a Gaussian filter to obtain a third image to be processed. The step S311 helps to reduce noise in the normalized vegetation index image.

[0083] S312, using the Sobel operator (also known as the Sobel operator) to calculate the horizontal and vertical gradient values ​​of each pixel in the third image to be processed, and then calculating the gradient amplitude and direction of each pixel to obtain a first gradient amplitude image.

[0084] S313: Perform non-maximum suppression processing on the first gradient amplitude image to obtain a second gradient amplitude image.

[0085] S314. Set a third threshold and a fourth threshold, divide the pixel points on the second gradient amplitude image into a first strong edge pixel point, a first weak edge pixel point and a first non-edge pixel point based on the third threshold and the fourth threshold, and connect the first strong edge pixel point and the first weak edge pixel point adjacent thereto to form the first edge image.

[0086] The third threshold is a high threshold, and the high threshold is used to determine the first strong edge pixel point. The fourth threshold is a low threshold, and the low threshold is used to determine the first weak edge pixel point connected to the first strong edge pixel point.

[0087] S32: Generate a first initial edge buffer based on the first edge image.

[0088] Further, the step S32 includes:

[0089] S321: Perform dilation processing on the edge detected in the first edge image to obtain a fourth image to be processed. The dilation processing refers to expanding the edge area.

[0090] S322: Perform an erosion operation on the edge detected on the fourth image to be processed to obtain the first initial edge buffer. The erosion operation can remove the over-expanded portion caused by dilation.

[0091] S33: Use the Otsu algorithm of the Otsu adaptive threshold method to calculate the first initial edge buffer to obtain the first threshold.

[0092] S4. Compare the first threshold with the normalized vegetation index, extract vegetation areas from the normalized vegetation index image, and generate a vegetation mask.

[0093] In the embodiment of the present application, in the normalized vegetation index image, all areas where the normalized vegetation index is greater than the first threshold are divided into vegetation areas to generate the vegetation mask.

[0094] S5. Calculate the mangrove-salt marsh discrimination index in the image of the region of interest to obtain a mangrove-salt marsh discrimination index image, and generate a mangrove-salt marsh mask image and a second threshold based on the mangrove-salt marsh discrimination index image and the vegetation mask.

[0095] Furthermore, the step of calculating the mangrove-salt marsh distinction index in the region of interest image includes:

[0096] S51, obtaining a first band reflectivity and a second band reflectivity of the image of the region of interest.

[0097] Specifically, the first band reflectivity is the 7-band reflectivity of the Sentinel-2 satellite, and the second band reflectivity is the 12-band reflectivity of the Sentinel-2 satellite. In other embodiments, the specific bands of the first band reflectivity and the second band reflectivity can be determined by those skilled in the art according to actual needs.

[0098] S52: performing a subtraction operation on the reflectivity of the first waveband and the reflectivity of the second waveband to obtain the mangrove-salt marsh distinction index.

[0099] Furthermore, the calculation formula of the mangrove-salt marsh discrimination index is: MSD I = B7-B12, wherein MSD I is the mangrove-salt marsh discrimination index, B7 represents the 7-band reflectivity of the Sentinel-2 satellite, and B12 represents the 12-band reflectivity of the Sentinel-2 satellite.

[0100] Furthermore, the step of generating a mangrove-salt marsh mask image and a second threshold based on the mangrove-salt marsh discrimination index image and the vegetation mask comprises:

[0101] S53: Use the vegetation mask to perform mask processing on the mangrove-salt marsh discrimination index image to generate the mangrove-salt marsh mask image.

[0102] Specifically, when the vegetation mask performs mask processing on the mangrove-salt marsh discrimination index image, only the mangrove-salt marsh discrimination index of the vegetation area is retained to generate a new MSD I mask image, that is, the mangrove-salt marsh mask image.

[0103] Step S53 can extract the vegetation area corresponding to the mangrove-salt marsh distinction index.

[0104] S54, using the Canny edge detection algorithm of the Otsu adaptive threshold method to detect vegetation edges in the mangrove-salt marsh mask image to generate a second edge image.

[0105] Furthermore, the step S54 includes:

[0106] S541, converting the mangrove-salt marsh mask image into a second grayscale image, and smoothing the second grayscale image using a Gaussian filter to obtain a fifth image to be processed. The step S541 helps to reduce noise in the mangrove-salt marsh mask image.

[0107] S542. Use the Sobel operator (also known as the Sobel operator) to calculate the horizontal and vertical gradient values ​​of each pixel in the fifth image to be processed, and then calculate the gradient amplitude and direction of each pixel to obtain a third gradient amplitude image.

[0108] S543: Perform non-maximum suppression processing on the third gradient amplitude image to obtain a fourth gradient amplitude image.

[0109] S544, setting a fifth threshold and a sixth threshold, dividing the pixel points on the fourth gradient amplitude image into second strong edge pixel points, second weak edge pixel points, and second non-edge pixel points based on the fifth threshold and the sixth threshold, and connecting the second strong edge pixel points and the second weak edge pixel points adjacent thereto to form the second edge image.

[0110] The fifth threshold is a high threshold, and the high threshold is used to determine the second strong edge pixel point. The sixth threshold is a low threshold, and the low threshold is used to determine the second weak edge pixel point connected to the second strong edge pixel point.

[0111] S55: Generate a second initial edge buffer based on the second edge image.

[0112] Furthermore, the step S55 includes:

[0113] S551: Perform dilation processing on the edge detected in the second edge image to obtain a sixth image to be processed. The dilation processing refers to enlarging the edge area.

[0114] S552: Perform an erosion operation on the edge detected on the sixth image to be processed to obtain the second initial edge buffer. The erosion operation can remove the over-expanded portion caused by dilation.

[0115] S57: Use the Otsu algorithm of the Otsu adaptive threshold method to calculate the second initial edge buffer to obtain the second threshold.

[0116] It should be understood that the first threshold and the second threshold are the adaptive thresholds.

[0117] In other implementations, the Otsu algorithm may be replaced by Kittler's minimum error threshold method or ISODAT algorithm.

[0118] S6: Based on the mangrove-salt marsh mask image, the mangrove-salt marsh distinction index and the second threshold, obtain a mangrove area. The mangrove area can be referenced to Figure 3 As shown, in Figure 3 In the figure, the black area is the mangrove area.

[0119] Furthermore, the step S6 comprises:

[0120] S61. Determine whether the mangrove-salt marsh distinction index corresponding to the target pixel in the mangrove-salt marsh mask image is greater than the second threshold corresponding to the target pixel.

[0121] S62: When the mangrove-salt marsh distinction index corresponding to the target pixel is greater than the second threshold corresponding to the target pixel, divide the area corresponding to the target pixel into a target area.

[0122] S63. All target areas constitute the mangrove area; wherein the target pixel is any pixel in the mangrove-salt marsh mask image.

[0123] Through the above technical solution, the embodiment of the present application introduces a mangrove-salt marsh differentiation index, which uses the spectral difference between mangroves and salt marshes in the short-wave infrared band to improve the ability to distinguish mangroves. Moreover, compared with the prior art, the embodiment of the present application only requires multi-spectral remote sensing images, without other ground reference data or a large amount of time series data, and does not need to combine auxiliary data such as terrain and tides to extract mangrove areas. Therefore, the embodiment of the present application can improve the accuracy of mangrove area extraction while simplifying the processing steps.

[0124] In addition, the embodiment of the present application adopts a secondary threshold segmentation strategy, first using the normalized vegetation index NDVI to extract the vegetation area, and then using the mangrove-salt marsh differentiation index MSDI to distinguish mangroves in the vegetation area. This strategy can effectively reduce the interference of non-vegetation areas.

[0125] In some embodiments, the mangrove extraction method based on adaptive threshold further includes:

[0126] S7. Generate a mangrove distribution map based on the mangrove area.

[0127] In some embodiments, the mangrove extraction method based on adaptive threshold further includes:

[0128] S8. Verify the mangrove distribution map.

[0129] In the embodiments of the present application, a field survey is conducted on the mangrove distribution map, or high-resolution images are used to verify the accuracy of the mangrove distribution map.

[0130] In the embodiment of the present application, the use of the Canny edge detection algorithm makes the selection of the first threshold and the second threshold more flexible and accurate, and dynamically adjusts the first threshold and the second threshold to adapt to different images and environmental conditions, so as to improve the applicability of the mangrove extraction method based on adaptive threshold.

[0131] The mangrove extraction method based on adaptive threshold proposed in the present application not only has a high degree of automation, reduces manual intervention, and improves processing efficiency, but also has a simple method and a small amount of calculation, and is suitable for large-scale rapid mapping.

[0132] <Mangrove Extraction System Based on Adaptive Threshold>

[0133] like Figure 4 FIG. 1 is a block diagram of a mangrove extraction system based on an adaptive threshold provided in the second aspect of the embodiment of the present application. Figure 4 In the embodiment, the mangrove extraction system 91 based on adaptive threshold comprises:

[0134] A multispectral remote sensing image acquisition module 911 is used to acquire a multispectral remote sensing image;

[0135] An area of ​​interest image acquisition module 912 is used to analyze and crop the multispectral remote sensing image to obtain an area of ​​interest image;

[0136] The first threshold value generating module 913 is used to calculate the normalized vegetation index in the image of the region of interest to obtain a normalized vegetation index image, and use the Otsu adaptive threshold method to detect and process the normalized vegetation index image to generate a first threshold value;

[0137] A vegetation mask generating module 914 is used to compare the first threshold with the normalized vegetation index, extract vegetation areas from the normalized vegetation index image, and generate a vegetation mask;

[0138] A second threshold generation module 915 is used to calculate the mangrove-salt marsh discrimination index in the image of the region of interest, obtain a mangrove-salt marsh discrimination index image, and generate a mangrove-salt marsh mask image and a second threshold based on the mangrove-salt marsh discrimination index image and the vegetation mask;

[0139] The mangrove area acquisition module 916 is used to obtain the mangrove area based on the mangrove-salt marsh mask image, the mangrove-salt marsh distinction index and the second threshold.

[0140] <Terminal Equipment>

[0141] In a third aspect of the embodiments of the present application, a terminal device is provided, wherein the principle block diagram of the terminal device can be as follows: Figure 5 As shown. The terminal device includes a processor, a memory, a network interface, a display screen and a temperature sensor connected via a system bus. The processor is used to provide computing and control capabilities. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the terminal device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a mangrove extraction method based on an adaptive threshold is implemented. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the temperature sensor is pre-set inside the terminal device to detect the operating temperature of the internal device.

[0142] Those skilled in the art will understand that Figure 5 The principle block diagram shown in the figure is only a block diagram of a partial structure related to the scheme of the present invention, and does not constitute a limitation on the terminal device to which the scheme of the present invention is applied. The specific terminal device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0143] In some embodiments, the terminal device includes a processor and a memory, the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the steps of the mangrove extraction method based on adaptive thresholds provided in the first aspect of the above-mentioned embodiment of the present application.

[0144] <Computer Readable Storage Medium>

[0145] The fourth aspect of the embodiments of the present application provides a computer-readable storage medium, which is used to store a computer program, and the computer program enables a computer to execute the steps of the mangrove extraction method based on adaptive thresholds provided in the first aspect of the embodiments of the present application.

[0146] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0147] The technical features of the above embodiments can be combined without changing the basic principles of the present invention. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0148] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the scope of patent protection of the present application shall be subject to the attached claims.

Claims

1. A mangrove extraction method based on adaptive threshold, characterized in that: include: Acquire multispectral remote sensing images; Analyzing and cropping the multispectral remote sensing image to obtain an image of a region of interest; Calculating the normalized vegetation index in the image of the region of interest to obtain a normalized vegetation index image, and using the Otsu adaptive threshold method to perform detection processing on the normalized vegetation index image to generate a first threshold; comparing the first threshold value with the normalized vegetation index, extracting vegetation areas in the normalized vegetation index image, and generating a vegetation mask; Calculating the mangrove-salt marsh discrimination index in the image of the region of interest to obtain a mangrove-salt marsh discrimination index image, and generating a mangrove-salt marsh mask image and a second threshold based on the mangrove-salt marsh discrimination index image and the vegetation mask; A mangrove area is obtained based on the mangrove-salt marsh mask image, the mangrove-salt marsh distinction index and the second threshold.

2. The method for extracting mangroves based on adaptive threshold according to claim 1, characterized in that: The step of analyzing and clipping the multispectral remote sensing image to obtain an image of the region of interest comprises: Performing cloud mask processing on the multispectral remote sensing image to obtain a first image to be processed; Performing atmospheric correction processing on the first image to be processed to obtain a second image to be processed; The second image to be processed is cropped to obtain the region of interest image.

3. The method for extracting mangroves based on adaptive threshold according to claim 1, characterized in that: The step of using the Otsu adaptive threshold method to detect and process the normalized vegetation index image and generate a first threshold comprises: Using the Canny edge detection algorithm of the Otsu adaptive threshold method to detect vegetation edges in the normalized vegetation index image, and generating a first edge image; generating a first initial edge buffer based on the first edge image; The first initial edge buffer is calculated using the Otsu algorithm of the Otsu adaptive threshold method to obtain the first threshold.

4. The method for extracting mangroves based on adaptive threshold according to claim 1, characterized in that: The step of calculating the mangrove-salt marsh distinction index in the region of interest image comprises: Acquire the reflectivity of the first band and the reflectivity of the second band of the image of the region of interest; A subtraction operation is performed on the reflectivity of the first band and the reflectivity of the second band to obtain the mangrove-salt marsh distinction index.

5. The method for extracting mangroves based on adaptive threshold according to claim 1, characterized in that: The step of generating a mangrove-salt marsh mask image and a second threshold based on the mangrove-salt marsh discrimination index image and the vegetation mask comprises: Using the vegetation mask to perform mask processing on the mangrove-salt marsh discrimination index image to generate the mangrove-salt marsh mask image; Using the Canny edge detection algorithm of the Otsu adaptive threshold method to detect vegetation edges in the mangrove-salt marsh mask image, and generating a second edge image; generating a second initial edge buffer based on the second edge image; The second initial edge buffer is calculated using the Otsu algorithm of the Otsu adaptive threshold method to obtain the second threshold.

6. The method for extracting mangroves based on adaptive threshold according to claim 1, characterized in that: The step of obtaining the mangrove area based on the mangrove-salt marsh mask image, the mangrove-salt marsh distinction index and the second threshold comprises: Determine whether the mangrove-salt marsh discrimination index corresponding to the target pixel in the mangrove-salt marsh mask image is greater than the second threshold corresponding to the target pixel; When the mangrove-salt marsh discrimination index corresponding to the target pixel is greater than the second threshold corresponding to the target pixel, dividing the area corresponding to the target pixel into a target area; All target areas constitute the mangrove area; The target pixel is any pixel in the mangrove-salt marsh mask image.

7. The method for extracting mangroves based on adaptive threshold according to claim 6, characterized in that: The mangrove extraction method based on adaptive threshold also includes: A mangrove distribution map is generated based on the mangrove area.

8. A mangrove extraction system based on adaptive threshold, characterized in that: include: A multispectral remote sensing image acquisition module, used for acquiring multispectral remote sensing images; An area of ​​interest image acquisition module is used to analyze and crop the multispectral remote sensing image to obtain an area of ​​interest image; A first threshold value generating module is used to calculate the normalized vegetation index in the image of the region of interest to obtain a normalized vegetation index image, and use the Otsu adaptive threshold method to detect and process the normalized vegetation index image to generate a first threshold value; A vegetation mask generating module, used for comparing the first threshold with the normalized vegetation index, extracting vegetation areas from the normalized vegetation index image, and generating a vegetation mask; a second threshold value generating module, configured to calculate the mangrove-salt marsh discrimination index in the image of the region of interest, obtain a mangrove-salt marsh discrimination index image, and generate a mangrove-salt marsh mask image and a second threshold value based on the mangrove-salt marsh discrimination index image and the vegetation mask; A mangrove area acquisition module is used to obtain a mangrove area based on the mangrove-salt marsh mask image, the mangrove-salt marsh distinction index and the second threshold.

9. A terminal device, characterized in that: include: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory to execute the steps of the mangrove extraction method based on adaptive threshold as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that Used to store a computer program, wherein the computer program enables a computer to execute the steps of the mangrove extraction method based on adaptive threshold as described in any one of claims 1 to 7.

Images