Satellite remote sensing image-based shoreline identification method and system

Abstract

The invention relates to the technical field of satellite remote sensing, and discloses a shoreline identification method and system based on a satellite remote sensing image. According to the method and the system, coast satellite remote sensing image data is acquired through a data acquisition module, and a data processing module performs image enhancement and denoising operation according to the acquired image data and sends the processed image to a feature extraction module; the feature extraction module performs coast feature extraction based on the denoised coast satellite remote sensing image and calculates coastline latitude and longitude coordinates, a coastline length, a water body area, a coastline change rate, a terrain slope and a coastline image texture feature, and the machine learning module uses the numerical values as input parameters; a shoreline is identified and shoreline extraction is carried out through a convolutional neural network, a post-processing module carries out post-processing based on the shoreline extracted by a machine learning module and eliminates small pseudo shorelines, and a result display module displays a processed shoreline result in a chart form and generates a report and statistical data of a shoreline identification result.

Description

Technical Field

[0001] The invention relates to the field of satellite remote sensing technology, and in particular to a shoreline recognition method and system based on satellite remote sensing images. Background Art

[0002] Coastline identification is an important task in remote sensing and geographic information systems, especially in the fields of marine management, environmental monitoring and urban planning. The coastline is the boundary of many ecosystems. Accurate coastline identification helps monitor important ecological areas such as wetlands, mangroves and coral reefs. By comparing coastline changes in different time periods, the impact of sea level rise and climate change on coastal areas can be assessed. At the same time, the dynamic changes of the coastline can reveal the impact of floods, coastal erosion and other natural disasters, and provide data support for response and assessment. At the same time, coastline identification can help manage marine resources such as fisheries, minerals and waters to ensure sustainable use. Coastline identification not only has important academic value, but also plays a positive role in environmental protection, resource management, urban construction and public participation.

[0003] Traditional image processing algorithms may not be effective in extracting coastlines, especially when dealing with complex environments. There is no comprehensive analysis of coastal satellite remote sensing image data, calculation of relevant parameters, and extraction of key features for input into machine learning algorithms, resulting in manual intervention and correction still required for coastline identification, which increases costs and workload. Summary of the invention

[0004] 1. Technical issues to be resolved In view of the shortcomings of the prior art, the present invention provides a coastline recognition method and system based on satellite remote sensing images, which has the function of obtaining coastal satellite remote sensing image data through a data acquisition module. The acquired data is transmitted to the data processing module, and the data processing module performs image enhancement and denoising operations according to the image data transmitted by the data acquisition module to obtain an image enhanced coastal satellite remote sensing image Denoising Coastal Satellite Remote Sensing Images The processed image is sent to the feature extraction module. The feature extraction module is based on the denoised coastal satellite remote sensing image. Extract coastal features and calculate the longitude and latitude coordinates of the coastline Length of coastline , water area , shoreline change rate , terrain slope And the texture features of the shoreline image , and transmit the above calculated values ​​to the machine learning module. The machine learning module uses the values ​​transmitted by the feature extraction module as input parameters, identifies the coastline through a convolutional neural network and extracts the coastline. The post-processing module performs post-processing based on the coastline extracted by the machine learning module to eliminate small pseudo coastlines. The result display module displays the processed coastline results in the form of charts and generates a report and statistical data on the coastline identification results. By comprehensively analyzing the coastal satellite remote sensing image data, calculating the relevant parameters and extracting the key features to input into the machine learning algorithm, the coastline can be accurately identified without the need for manual intervention and correction, which reduces the cost and workload, and solves the above problems.

[0005] (II) Technical solution To achieve the above object, the present invention provides the following technical solutions: a shoreline identification system based on satellite remote sensing images, comprising a data acquisition module, a data processing module, a feature extraction module, a machine learning module, a post-processing module and a result display module; The data acquisition module is used to acquire coastal satellite remote sensing image data and transmit the acquired data to the data processing module; The data processing module performs image enhancement and denoising operations according to the image data transmitted by the data acquisition module through an algorithm formula to obtain an image enhanced coastal satellite remote sensing image. Denoising Coastal Satellite Remote Sensing Images , and sending the processed image to the feature extraction module; The feature extraction module is based on denoising coastal satellite remote sensing images Extract coastal features and calculate the longitude and latitude coordinates of the coastline Length of coastline , water area , shoreline change rate , terrain slope And the texture features of the shoreline image , and transmit the above calculated values ​​to the machine learning module; The machine learning module uses the numerical value transmitted by the feature extraction module as an input parameter to identify the shoreline and extract the shoreline through a convolutional neural network; The post-processing module performs post-processing based on the shoreline extracted by the machine learning module, eliminates small pseudo shorelines, and transmits the processed shoreline to the result display module; The result display module displays the processed shoreline results in the form of charts and generates a report and statistical data of the shoreline identification results.

[0006] Preferably, the data processing module performs image enhancement operation through an algorithm formula according to the image data transmitted by the data acquisition module to obtain an image enhanced coastal satellite remote sensing image , the image enhancement formula is as follows:

[0007] In the formula, Represents the image enhancement coastal satellite remote sensing image element point, 255 is the pixel enhancement factor, Represents the coastal satellite remote sensing image element points, Indicates the output brightness impact factor, with a value between (0-1).

[0008] Preferably, the data processing module performs image denoising operation according to the image data transmitted by the data acquisition module through an algorithm formula to obtain a denoised coastal satellite remote sensing image. , the image denoising formula is as follows:

[0009] In the formula, represents the denoised coastal satellite remote sensing image, represents image enhanced coastal satellite remote sensing image, Represents the standard deviation of the Gaussian filter, which controls the degree of blur. Represents the half-width of the filter window, which determines the number of nearby points.

[0010] Preferably, the feature extraction module is based on denoised coastal satellite remote sensing images Extract coastal features and calculate the longitude and latitude coordinates of the coastline , the calculation formula is as follows:

[0011]

[0012] In the formula, represents the latitude coordinate, represents the longitude coordinate, , , Represents the coordinates in the spatial rectangular coordinate system. The calculation of longitude and latitude is based on the spherical coordinate system, which converts the three-dimensional coordinates into two-dimensional plane coordinates.

[0013] Preferably, the feature extraction module is based on denoised coastal satellite remote sensing images Extract coastal features and calculate coastline length , the calculation formula is as follows:

[0014] In the formula, Indicates the length of the coastline, the distance of each coastline Calculated by the following formula:

[0015] in, , It is The horizontal and vertical coordinates of the points, , It is The horizontal and vertical coordinates of the points are used to calculate the straight-line distance between two adjacent points using the Euclidean distance formula. Represents the total number of data points.

[0016] Preferably, the feature extraction module is based on denoised coastal satellite remote sensing images Extract coastal features and calculate water area , the calculation formula is as follows:

[0017] In the formula, represents the area of ​​water body, represents the total number of pixels inside the water body identified by image processing technology, Indicates the actual area of ​​each pixel.

[0018] Preferably, the feature extraction module is based on denoised coastal satellite remote sensing images Extract coastal features and calculate the rate of shoreline change , the calculation formula is as follows:

[0019] In the formula, represents the shoreline change rate, represents the length of the shoreline at the first time point, represents the length of the shoreline at the second time point, Indicates the time interval between two time points, obtained through the system timestamp.

[0020] Preferably, the feature extraction module is based on denoised coastal satellite remote sensing images Extract coastal features and calculate terrain slope , the calculation formula is as follows:

[0021] In the formula, represents the terrain slope, Indicates the terrain elevation difference obtained by the system. Indicates the terrain horizontal distance obtained by the system.

[0022] Preferably, the feature extraction module is based on denoised coastal satellite remote sensing images Extract coast features and calculate coastline image texture features , the calculation formula is as follows:

[0023] In the formula, Represents the texture features of the shoreline image, specifically the similarity feature value, Represents the number of gray levels in the image, represents the pixel value of the denoised coastal satellite remote sensing image, Represents a pixel in an image.

[0024] A shoreline recognition method based on satellite remote sensing images comprises the following steps: S1. Obtain coastal satellite remote sensing image data through the data acquisition module and transmit the acquired data to the data processing module; S2, the data processing module performs image enhancement and denoising operations based on the image data transmitted by the data acquisition module through an algorithm formula to obtain an image enhanced coastal satellite remote sensing image Denoising Coastal Satellite Remote Sensing Images , and sending the processed image to the feature extraction module; S3, feature extraction module based on denoising coastal satellite remote sensing images Extract coastal features and calculate the longitude and latitude coordinates of the coastline Length of coastline , water area , shoreline change rate , terrain slope And the texture features of the shoreline image , and transmit the above calculated values ​​to the machine learning module; S4, the machine learning module uses the numerical value transmitted by the feature extraction module as an input parameter to identify the shoreline and extract the shoreline through a convolutional neural network; S5, the post-processing module performs post-processing based on the shoreline extracted by the machine learning module, eliminates small pseudo shorelines, and transmits the processed shoreline to the result display module; S6. The result display module displays the processed shoreline results in the form of charts and generates a report and statistical data of the shoreline identification results.

[0025] Compared with the prior art, the present invention provides a shoreline recognition method and system based on satellite remote sensing images, which has the following beneficial effects: The present invention obtains coastal satellite remote sensing image data through a data acquisition module The acquired data is transmitted to the data processing module, and the data processing module performs image enhancement and denoising operations according to the image data transmitted by the data acquisition module to obtain an image enhanced coastal satellite remote sensing image Denoising Coastal Satellite Remote Sensing Images The processed image is sent to the feature extraction module. The feature extraction module is based on the denoised coastal satellite remote sensing image. Extract coastal features and calculate the longitude and latitude coordinates of the coastline Length of coastline , water area , shoreline change rate , terrain slope And the texture features of the shoreline image , and transmit the above calculated values ​​to the machine learning module. The machine learning module uses the values ​​transmitted by the feature extraction module as input parameters, and uses a convolutional neural network to identify the coastline and extract the coastline. The post-processing module performs post-processing based on the coastline extracted by the machine learning module to eliminate small pseudo coastlines. The result display module displays the processed coastline results in the form of charts and generates a report and statistical data on the coastline identification results. By comprehensively analyzing the coastal satellite remote sensing image data, calculating the relevant parameters and extracting the key features to input into the machine learning algorithm, the coastline can be accurately identified without manual intervention and correction, thereby reducing costs and workload. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a schematic diagram of the system flow of the present invention; Figure 2 It is a schematic diagram of the steps of the method of the present invention. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0028] Traditional image processing algorithms may not be effective in extracting coastlines, especially when dealing with complex environments. There is no comprehensive analysis of coastal satellite remote sensing image data, calculation of relevant parameters and extraction of key features for input into machine learning algorithms, which leads to the need for manual intervention and correction when identifying coastlines, increasing costs and workload. Therefore, a coastline recognition system based on satellite remote sensing images is proposed. Figure 1,The system includes a data acquisition module, a data processing module, a feature extraction module, a machine learning module, a post-processing module and a result display module; The data acquisition module is a key component of the system. It is responsible for collecting remote sensing image data from various ocean satellites. These satellites are usually equipped with a variety of sensors, including optical sensors, radar imagers, and infrared sensors, which can capture information on the earth's surface in different spectral bands. The data acquisition module will first connect to the satellite through the communication interface according to the preset schedule and task requirements, and instruct the satellite to take images or transmit data; After the data transmission is completed, the module will organize the acquired remote sensing images and related auxiliary data, such as timestamps, satellite positions and sensor status, into a structured format, and then transmit them safely and efficiently to the subsequent data processing modules through a dedicated data transmission protocol.

[0029] During this process, the data acquisition module can also work in collaboration with multiple satellites and sensors to achieve multi-temporal and multi-spectral monitoring of specific sea areas. By establishing a real-time monitoring and feedback mechanism, the module can dynamically adjust the data collection plan according to environmental changes or specific needs to ensure that the acquired remote sensing images can timely and accurately reflect the changes in the coastline. The efficient operation of this series of operations provides an important foundation and guarantee for subsequent data processing, analysis and shoreline identification, ensuring the overall performance and reliability of the system. The data processing module performs image enhancement and denoising operations based on the image data transmitted by the data acquisition module through an algorithm formula to obtain an image enhanced coastal satellite remote sensing image. Denoising Coastal Satellite Remote Sensing Images ,in: The image enhancement formula is as follows:

[0030] Through image enhancement technology, more spectral features can be extracted to provide rich information support for remote sensing image analysis. In the formula, Represents the image enhancement coastal satellite remote sensing image element point, 255 is the pixel enhancement factor, Represents the coastal satellite remote sensing image element points, Represents the output brightness impact factor, with a value between (0-1). The enhanced image can show details hidden in the unprocessed image, providing more basis for research and analysis; The image denoising formula is as follows:

[0031] Denoising can reduce random noise in images, improve the overall clarity of images, and show more realistic visual effects. By removing noise, important features in images, such as edges and details, can be made more prominent. In the formula, represents the denoised coastal satellite remote sensing image, represents image enhanced coastal satellite remote sensing image, Represents the standard deviation of the Gaussian filter, which controls the degree of blur. It represents the half-width of the filter window and determines the number of nearby points. In the field of remote sensing, denoising can greatly enhance the accuracy and reliability of subsequent analysis; Feature extraction module based on denoised coastal satellite remote sensing images Extract coastal features and calculate the longitude and latitude coordinates of the coastline Length of coastline , water area , shoreline change rate , terrain slope And the texture features of the shoreline image ; The calculation formula of the longitude and latitude coordinates of the coastline is as follows:

[0032]

[0033] By calculating the longitude and latitude coordinates of the coastline, accurate longitude and latitude information can be provided for the specific location of the coastline, which is convenient for spatial analysis and management. In the formula, represents the latitude coordinate, represents the longitude coordinate, , , Represents coordinates in a spatial rectangular coordinate system. The calculation of longitude and latitude is based on the spherical coordinate system, which converts three-dimensional coordinates into two-dimensional plane coordinates. The calculation of shoreline coordinates is the basis of geographic information systems and remote sensing technology, and supports more complex spatial analysis and data visualization. The formula for calculating the shoreline length is as follows:

[0034] In the formula, Indicates the length of the coastline, the distance of each coastline Calculated by the following formula:

[0035] in, , It is The horizontal and vertical coordinates of the points, , It is The horizontal and vertical coordinates of the points are used to calculate the straight-line distance between two adjacent points using the Euclidean distance formula. Represents the total number of data points; The water body area calculation formula is as follows:

[0036] Shoreline identification usually relies on remote sensing images, and water area calculation can also use these images. Remote sensing technology can provide high-resolution images, which is convenient for accurate shoreline identification. In the formula, represents the area of ​​water body, represents the total number of pixels inside the water body identified by image processing technology, Indicates the actual area of ​​each pixel; The calculation formula of shoreline change rate is as follows:

[0037] The calculation of the rate of shoreline change can assist in studying the impact of climate change on ecosystems, especially in terms of sea level rise and extreme climate events. In the formula, represents the shoreline change rate, represents the length of the shoreline at the first time point, represents the length of the shoreline at the second time point, Indicates the time interval between two time points, obtained through the system timestamp; The terrain slope calculation formula is as follows:

[0038] The shape and characteristics of a shoreline are often influenced by the slope of the surrounding terrain. A steeper slope may result in a straighter shoreline, while a gentler slope may result in a curved or irregular shoreline. represents the terrain slope, Indicates the terrain elevation difference obtained by the system. Indicates the horizontal distance of the terrain obtained by the system. By calculating the slope and combining it with remote sensing technology, it can more effectively monitor shoreline changes and assess the impact of natural and human factors; The calculation formula of shoreline image texture features is as follows:

[0039] In image processing, texture features are a set of features that describe the surface structure and pattern of an image. They can characterize local changes and uniformity in an image. Line regions usually exhibit specific texture features that can be used to distinguish the coastline from the surrounding environment. In the formula, Represents the texture features of the shoreline image, specifically the similarity feature value, Represents the number of gray levels in the image, represents the pixel value of the denoised coastal satellite remote sensing image, Represents the pixel points in the image. The texture features near the coastline are usually related to different materials such as water, beach, rock, etc. The coastline area can be effectively identified and classified using texture features. The machine learning module uses the numerical value transmitted by the feature extraction module as an input parameter to identify the shoreline and extract the shoreline through a convolutional neural network; In order to improve the generalization ability of the model, the convolutional neural network needs to perform data enhancement on the input training data, such as rotation, flipping, scaling and other operations, so as to generate more samples. The convolution layer of the convolutional neural network performs convolution operations on the input image by sliding the convolution kernel to extract local features. In shoreline recognition, these local features can include key information such as edges and textures. Subsequently, downsampling is performed through the pooling layer to reduce the feature dimension while maintaining important features. This process helps to control the complexity of the model and prevent overfitting. After multiple layers of convolution and pooling, the features will be flattened and classified through the fully connected layer. At this stage, the network makes a comprehensive judgment on the extracted features to determine whether they belong to the shoreline area. Finally, the output layer uses the softmax function to calculate the probability distribution of each category, and identifies and extracts the shoreline by determining the category with the highest probability. The post-processing module performs post-processing based on the shorelines extracted by the machine learning module, eliminates small pseudo shorelines, extracts the main shorelines by applying edge detection algorithms, then analyzes the detected edges, removes the edges with smaller or discontinuous sounds, and transmits the processed shorelines to the result display module; See also Figure 2 , a shoreline recognition method based on satellite remote sensing images, comprising the following steps: S1. Obtain coastal satellite remote sensing image data through the data acquisition module and transmit the acquired data to the data processing module; S2, the data processing module performs image enhancement and denoising operations based on the image data transmitted by the data acquisition module through an algorithm formula to obtain an image enhanced coastal satellite remote sensing image Denoising Coastal Satellite Remote Sensing Images , and sending the processed image to the feature extraction module; S3, feature extraction module based on denoising coastal satellite remote sensing images Extract coastal features and calculate the longitude and latitude coordinates of the coastline Length of coastline , water area , shoreline change rate , terrain slope And the texture features of the shoreline image , and transmit the above calculated values ​​to the machine learning module; S4, the machine learning module uses the numerical value transmitted by the feature extraction module as an input parameter to identify the shoreline and extract the shoreline through a convolutional neural network; S5, the post-processing module performs post-processing based on the shoreline extracted by the machine learning module, eliminates small pseudo shorelines, and transmits the processed shoreline to the result display module; S6. The result display module displays the processed shoreline results in the form of charts and generates a report and statistical data of the shoreline identification results.

[0040] By combining the above methods and systems, a comprehensive analysis of coastal satellite remote sensing image data is conducted, relevant parameters are calculated, and key features are extracted and input into the machine learning algorithm to accurately identify the coastline without the need for human intervention and correction, thereby reducing costs and workload.

[0041] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A shoreline recognition system based on satellite remote sensing images, characterized in that: It includes data acquisition module, data processing module, feature extraction module, machine learning module, post-processing module and result display module; The data acquisition module is used to acquire coastal satellite remote sensing image data and transmit the acquired data to the data processing module; The data processing module performs image enhancement and denoising operations according to the image data transmitted by the data acquisition module through an algorithm formula to obtain an image enhanced coastal satellite remote sensing image. Denoising Coastal Satellite Remote Sensing Images , and sending the processed image to the feature extraction module; The feature extraction module is based on denoising coastal satellite remote sensing images Extract coastal features and calculate the longitude and latitude coordinates of the coastline Length of coastline , water area , shoreline change rate , terrain slope And the texture features of the shoreline image , and transmit the above calculated values ​​to the machine learning module; The machine learning module uses the numerical value transmitted by the feature extraction module as an input parameter to identify the shoreline and extract the shoreline through a convolutional neural network; The post-processing module performs post-processing based on the shoreline extracted by the machine learning module, eliminates small pseudo shorelines, and transmits the processed shoreline to the result display module; The result display module displays the processed shoreline results in the form of charts and generates a report and statistical data of the shoreline identification results.

2. The shoreline recognition system based on satellite remote sensing images according to claim 1 is characterized in that: The data processing module performs image enhancement operation according to the image data transmitted by the data acquisition module through an algorithm formula to obtain an image enhanced coastal satellite remote sensing image , the image enhancement formula is as follows: In the formula, Represents the image enhancement coastal satellite remote sensing image element point, 255 is the pixel enhancement factor, Represents the coastal satellite remote sensing image element points, Indicates the output brightness impact factor, with a value between (0-1).

3. The shoreline recognition system based on satellite remote sensing images according to claim 2 is characterized in that: The data processing module performs image denoising operation according to the image data transmitted by the data acquisition module through an algorithm formula to obtain a denoised coastal satellite remote sensing image. , the image denoising formula is as follows: In the formula, represents the denoised coastal satellite remote sensing image, represents image enhanced coastal satellite remote sensing image, Represents the standard deviation of the Gaussian filter, which controls the degree of blur. Represents the half-width of the filter window, which determines the number of nearby points.

4. The shoreline recognition system based on satellite remote sensing images according to claim 3 is characterized in that: The feature extraction module is based on denoising coastal satellite remote sensing images Extract coastal features and calculate the longitude and latitude coordinates of the coastline , the calculation formula is as follows: In the formula, represents the latitude coordinate, represents the longitude coordinate, , , Represents the coordinates in the spatial rectangular coordinate system. The calculation of longitude and latitude is based on the spherical coordinate system, which converts the three-dimensional coordinates into two-dimensional plane coordinates.

5. The shoreline recognition system based on satellite remote sensing images according to claim 4 is characterized in that: The feature extraction module is based on denoising coastal satellite remote sensing images Extract coastal features and calculate coastline length , the calculation formula is as follows: In the formula, Indicates the length of the coastline, the distance of each coastline Calculated by the following formula: in, , It is The horizontal and vertical coordinates of the points, , It is The horizontal and vertical coordinates of the points are used to calculate the straight-line distance between two adjacent points using the Euclidean distance formula. Represents the total number of data points.

6. The shoreline recognition system based on satellite remote sensing images according to claim 5 is characterized in that: The feature extraction module is based on denoising coastal satellite remote sensing images Extract coastal features and calculate water area , the calculation formula is as follows: In the formula, Represents the area of ​​water body, represents the total number of pixels inside the water body identified by image processing technology, Indicates the actual area of ​​each pixel.

7. The shoreline recognition system based on satellite remote sensing images according to claim 6 is characterized in that: The feature extraction module is based on denoising coastal satellite remote sensing images Extract coastal features and calculate the rate of shoreline change , the calculation formula is as follows: In the formula, represents the shoreline change rate, represents the length of the shoreline at the first time point, represents the length of the shoreline at the second time point, Indicates the time interval between two time points, obtained through the system timestamp.

8. The shoreline recognition system based on satellite remote sensing images according to claim 7 is characterized in that: The feature extraction module is based on denoising coastal satellite remote sensing images Extract coastal features and calculate terrain slope , the calculation formula is as follows: In the formula, represents the terrain slope, Indicates the terrain elevation difference obtained by the system. Indicates the terrain horizontal distance obtained by the system.

9. The shoreline recognition system based on satellite remote sensing images according to claim 8, characterized in that: The feature extraction module is based on denoising coastal satellite remote sensing images Extract coast features and calculate coastline image texture features , the calculation formula is as follows: In the formula, Represents the texture features of the shoreline image, specifically the similarity feature value, Represents the number of gray levels in the image, represents the pixel value of the denoised coastal satellite remote sensing image, Represents a pixel in an image.

10. A shoreline recognition method based on satellite remote sensing images, characterized in that: The following steps are involved: S1. Obtain coastal satellite remote sensing image data through the data acquisition module and transmit the acquired data to the data processing module; S2, the data processing module performs image enhancement and denoising operations based on the image data transmitted by the data acquisition module through an algorithm formula to obtain an image enhanced coastal satellite remote sensing image Denoising Coastal Satellite Remote Sensing Images , and sending the processed image to the feature extraction module; S3, feature extraction module based on denoising coastal satellite remote sensing images Extract coastal features and calculate the longitude and latitude coordinates of the coastline Length of coastline , water area , shoreline change rate , terrain slope And the texture features of the shoreline image , and transmit the above calculated values ​​to the machine learning module; S4, the machine learning module uses the numerical value transmitted by the feature extraction module as an input parameter to identify the shoreline and extract the shoreline through a convolutional neural network; S5, the post-processing module performs post-processing based on the shoreline extracted by the machine learning module, eliminates small pseudo shorelines, and transmits the processed shoreline to the result display module; S6. The result display module displays the processed shoreline results in the form of charts and generates a report and statistical data of the shoreline identification results.

Images