A land surveying and mapping method and system based on GIS

Abstract

The present invention discloses a land surveying and mapping method and system based on GIS, which relates to the technical field of land surveying and mapping. The method comprises: uploading the collected remote sensing images to GIS software using a multi-channel transmission method; the GIS software interprets the received remote sensing images using a remote sensing image interpretation model; using a land geographic data prediction model to interpret historical remote sensing image interpretation data, predicting the change trend of various geographic data of the image collection site; drawing a multidimensional map of the image collection site based on the interpretation data of the current remote sensing image and the predicted change trend of the geographic data; and storing the drawn multidimensional map in a private cloud. It can effectively prevent and respond to various security threats and challenges, ensure the security of land surveying and mapping data, improve the quality and efficiency of surveying and mapping services, and provide users with more accurate and reliable surveying and mapping services.

Description

Technical Field

[0001] The present invention relates to the technical field of land surveying and mapping, and in particular to a land surveying and mapping method and system based on GIS. Background Art

[0002] Land surveying and mapping data contains a large amount of land space information, such as national borders, important infrastructure, resource distribution, etc. These data are an important part of national security. Once leaked or tampered with, it will seriously threaten national security. Nowadays, GIS technology has been widely used in the field of land surveying and mapping, including map making, land use planning, resource management, environmental monitoring, urban planning and other aspects. However, in GIS land surveying and mapping, data security is an important issue. If the system security is poor or the manual operation is not standardized, it may lead to data leakage or tampering, thereby causing security risks. Therefore, people in this field urgently need to develop a GIS land surveying and mapping method with guaranteed data security to prevent problems before they happen. Summary of the invention

[0003] The present invention provides a GIS-based land surveying and mapping method, comprising:

[0004] Step 1: Use the multi-channel transmission method to upload the collected remote sensing images to the GIS software;

[0005] Step 2, GIS software uses remote sensing image interpretation model to interpret the received remote sensing images;

[0006] Step 3: Use the national geographic data prediction model to interpret the data based on historical remote sensing images and predict the changing trends of various geographic data in the image collection area;

[0007] Step 4: Draw a multidimensional map of the image collection site based on the interpretation data of the current remote sensing image and the predicted trend of geographic data changes;

[0008] Step 5. Store the drawn multi-dimensional map in the private cloud.

[0009] As described above, a GIS-based land surveying and mapping method, in which the collected remote sensing images are uploaded to the GIS software using a multi-channel transmission method, is specifically divided into the following sub-steps:

[0010] Prepare multiple transmission channels and encrypt each channel individually;

[0011] Use the channel distribution function to distribute remote sensing images to different channels;

[0012] GIS software restores the pixels received from different channels into the original remote sensing images.

[0013] As described above, a GIS-based land surveying and mapping method, in which the GIS software uses a remote sensing image interpretation model to interpret the received remote sensing image, is specifically divided into the following sub-steps:

[0014] Create training data sets based on historical remote sensing images and historical geographic information images;

[0015] Use the training dataset to train the remote sensing image interpretation model;

[0016] The image features of each pixel in the received remote sensing image are extracted, input into the trained remote sensing image interpretation model in sequence, and the interpretation data is output.

[0017] As described above, a GIS-based land surveying and mapping method, in which a training data set is created based on historical remote sensing images and historical geographic information images, is specifically divided into the following sub-steps:

[0018] Extract the image features of each pixel in the historical remote sensing image, and the geographical features represented by each pixel on the historical geographic information image;

[0019] Overlay the layers of historical remote sensing images and geographic information images to obtain feature pairs with spatial correlation;

[0020] The obtained feature pairs are organized into training data sets.

[0021] In the above-mentioned GIS-based land surveying and mapping method, the training process of the land geographic data prediction model is divided into the following sub-steps:

[0022] Create training data sets by combining interpretation data from historical remote sensing images with climate and geological data from the collection sites;

[0023] Use the created training data set to train the national geographic data prediction model;

[0024] Verify the accuracy of the national geographic data prediction model and determine its longest prediction period.

[0025] As described above, a GIS-based land surveying and mapping method is described, in which a multi-dimensional map of the image collection area is drawn based on the interpretation data of the current remote sensing image and the predicted trend of geographic data changes, which is specifically divided into the following sub-steps:

[0026] Draw geographic information images in multiple dimensions based on the interpretation data of each pixel in the current remote sensing image;

[0027] Overlay geographic information images of different dimensions and set the base map as the current remote sensing image;

[0028] According to the changing trend of geographic data, frame-interpolation animation is added to geographic information images of different dimensions to create a dynamic evolution effect.

[0029] The present invention also provides a GIS-based land surveying and mapping system, comprising: a multi-channel transmission module, a remote sensing image interpretation module, a geographic change prediction module, a multi-dimensional map drawing module, and a surveying and mapping data storage module;

[0030] Multi-channel transmission module, used to complete data interaction between modules using multi-channel transmission method;

[0031] A remote sensing image interpretation module is used to interpret the received remote sensing images using a remote sensing image interpretation model;

[0032] The geographic change prediction module is used to use the national geographic data prediction model to interpret data based on historical remote sensing images and predict the change trend of various geographic data in the image collection area;

[0033] A multi-dimensional map drawing module is used to draw a multi-dimensional map of the image collection area based on the interpretation data of the current remote sensing image and the predicted trend of geographic data changes;

[0034] The surveying and mapping data storage module is used to store the drawn multi-dimensional maps and the collected surveying and mapping data.

[0035] The beneficial effects achieved by the present invention are as follows: it can effectively prevent and respond to various security threats and challenges, ensure the security of land surveying and mapping data; improve the quality and efficiency of surveying and mapping services, and provide users with more accurate and reliable surveying and mapping services. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0037] Figure 1 This is a flow chart of a GIS-based land surveying and mapping method provided in Example 1 of the present application;

[0038] Figure 2 This is a schematic diagram of a GIS-based land surveying and mapping system provided in Example 2 of the present application. DETAILED DESCRIPTION

[0039] The following is a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0040] Embodiment 1

[0041] like Figure 1 As shown, the first embodiment of the present application provides a land surveying and mapping method based on GIS, including:

[0042] Step S10: uploading the collected remote sensing images to the GIS software using a multi-channel transmission method;

[0043] The multi-channel transmission method refers to transmitting the pixels of the remote sensing image to the GIS software through multiple channels, and each channel is encrypted separately. This can not only shorten the transmission time and reduce the risk of being monitored, but also improve the defense of the transmission channel. Specifically:

[0044] Step S11: prepare multiple transmission channels and perform separate encryption for each channel;

[0045] There are many encryption algorithms available today, and they can be used as needed, as long as the encryption method for each channel is different.

[0046] Step S12: using a channel distribution function to distribute the remote sensing image to different channels;

[0047] Channel Distribution Function It is expressed as: ,in is the i-th pixel of the remote sensing image, % is the modulo operation, is the number of transmission channels, L is an adjustable parameter used to control the offset of channel distribution, Return to The channel number to which the pixel is distributed.

[0048] Step S13: GIS software restores the pixels received by different channels to the original remote sensing image;

[0049] For GIS software, the channel number of the receiving pixel point, the number of transmission channels, and the adjustable parameters are all known quantities. Therefore, the arrangement order of the pixels on the original remote sensing image can be solved according to the channel distribution function, thereby restoring the original remote sensing image.

[0050] Step S20: The GIS software interprets the received remote sensing image using the remote sensing image interpretation model;

[0051] Analyze the spatial relationship and mapping relationship between remote sensing images and geographic information, and interpret the pixels in the remote sensing images as geographic data based on the analysis results. Specifically:

[0052] Step S21: Creating a training data set based on historical remote sensing images and historical geographic information images, which is specifically divided into the following sub-steps:

[0053] Step S211: extracting the image features of each pixel in the historical remote sensing image and the geographical features represented by each pixel on the historical geographical information image;

[0054] Image features include hue features, texture features, spectrum features and shadow features; geographic features include water features, vegetation features, mountain features and land features.

[0055] Step S212: superimposing the layers of the historical remote sensing image and the geographic information image to obtain feature pairs with spatial correlation;

[0056] The geographic information image is scaled and rotated to make its coordinate ratio consistent with that of the remote sensing image, and the image features and geographic features at the same pixel are extracted to form a feature pair, for example [(0.3, 0.28, 0.72, 0.5), 1.1], where (0.3, 0.28, 0.72, 0.5) are the image features at a certain pixel, and 1.1 is the geographic feature. It should be noted that the superimposed remote sensing image and geographic information image must come from the same collection location and the same collection date to ensure the accuracy of the training data set.

[0057] Step S213: Arrange the obtained feature pairs into a training data set;

[0058] The feature pairs of all pixels in the entire historical remote sensing image are sequentially placed into the training data set.

[0059] Step S22: training the remote sensing image interpretation model using the training data set;

[0060] The image features and geographic features in the training data set are used as input and output pairs, and the remote sensing image interpretation model is supervised for training, so that the model can learn the mapping relationship between image features and geographic features from the data set. The remote sensing image interpretation model is expressed as:

[0061] , where j is the input image feature subscript, ranging from 1 to m, and m is 3. They are the hue eigenvalue, texture eigenvalue and spectrum eigenvalue of the pixel to be interpreted. Represents the shadow feature value of the i-th pixel in the shadow recognition domain of the pixel to be interpreted. Represents the shadow feature value of the i+1th pixel in the shadow recognition domain, i ranges from 1 to -1, is the size of the shadow recognition domain, are the mapping indexes of hue, texture, spectrum and shadow features to geographic features, respectively, and Y1 is the output geographic feature value. The size of the shadow recognition domain is 5 by default, that is, it is centered on the pixel to be interpreted and extends to 5 pixels in the horizontal direction.

[0062] Step S23: extracting the image features of each pixel in the received remote sensing image, inputting them into the trained remote sensing image interpretation model in sequence, and outputting the interpretation data;

[0063] The output interpretation data uses remote sensing image code + pixel coordinates as a unique identifier and is stored in a private cloud to provide data support for subsequent map drawing.

[0064] Step S30: using the national geographic data prediction model to interpret data based on historical remote sensing images and predict the change trend of various geographic data at the image collection site;

[0065] Predicting the changing trend of geographic data can be used in fields such as land planning, land development, environmental monitoring, and disaster management. The land and geographic data prediction model sets a slider selection method for the prediction period. It automatically reads the input set from the private cloud according to the selected period and returns the prediction result. The training process of the land and geographic data prediction model is divided into the following sub-steps:

[0066] Step S31: Create a training data set by combining the interpretation data of historical remote sensing images, as well as the climate data and geological data of the collection site;

[0067] First, two parts are extracted from the interpretation data of historical remote sensing images according to the image acquisition time. The first part is used as input (multiple parts), and the second part is used as output (one part). The time interval in between is used as the prediction period. Then, the climate data and geological data of the image acquisition site are added to the input data as two types of influencing factors to help the model deeply understand the changing patterns of the data and improve the prediction ability. Finally, the input and output pairs are sorted into a large set to form a training data set.

[0068] Step S32: using the created training data set to train the land and geographic data prediction model;

[0069] The national geographic data prediction model is expressed as:

[0070] , where Y2 is the prediction result, C is the prediction period, and T is the length of the input set. The avg() function returns the mean of the expression in brackets when t is 1 to T. represents the climate impact factor with the subscript k1, k1 ranges from 1 to w1, w1 is the number of climate impact factors, represents the geological influence factor with the subscript k2, k2 takes values ​​from 1 to w2, w2 is the number of geological influence factors, D is the general trend parameter of the interpretation data in time series, To interpret the special trend of data in time series, It is the mean of all remote sensing image interpretation data in the input set.

[0071] During the training process, the unknown parameters in the model are continuously adjusted until the MES loss value is minimized.

[0072] Step S33: verifying the accuracy of the national geographic data prediction model and determining its longest prediction period;

[0073] After the model training is completed, the length of the prediction cycle is continuously increased, and the MES loss function is used to verify the accuracy of the model. If the accuracy of the model drops to 95%, the length of the prediction cycle at this time is the longest prediction cycle of the model, which is also the end point of the prediction cycle selection slider.

[0074] Step S40: drawing a multi-dimensional map of the image acquisition location based on the interpretation data of the current remote sensing image and the predicted trend of geographic data changes;

[0075] The geographical data of multiple dimensions, such as water bodies, mountains, vegetation and land, are presented in a single map by overlaying layers, and a dynamic evolution effect is created based on the changing trend of the geographical data. Specifically:

[0076] Step S41: drawing a geographic information image of multiple dimensions according to the interpretation data of each pixel in the current remote sensing image;

[0077] First, separate the different interpretation data and put each interpretation data into a separate layer. Then extract the pixel points whose geographical features are consistent with the current interpretation data from the historical geographic information image, fill them in accordingly, and finally draw a geographic information image in multiple dimensions.

[0078] Step S42: overlaying geographic information images of different dimensions, and setting the base map as the current remote sensing image;

[0079] Step S43: adding interpolation animation to geographic information images of different dimensions according to the changing trend of geographic data to form a dynamic evolution effect;

[0080] Taking water body images as an example, the changing trend of geographic data describes the changing trend of each pixel point of the water body image at the collection site. By adding the interpretation data Y1 of a pixel point on the current water body image to Y1 and multiplying it by the changing trend Y2, we can get the geographic characteristics of the pixel point after a future prediction cycle, recorded as Y3. Y3 is represented on the water body image and filled with pixel points with consistent geographic characteristics in the historical geographic information image. Then, a frame-interpolation animation is added between Y1 and Y3 to form a dynamic evolution effect.

[0081] Step S50: storing the drawn multi-dimensional map in a private cloud;

[0082] Private cloud is a cloud storage instance provided for GIS land surveying and mapping data. It has a strict access control policy and uses multi-channel transmission method for data interaction. Private cloud will monitor user access behavior and only allow data sharing between authorized devices.

[0083] Embodiment 2

[0084] like Figure 2 As shown, the second embodiment of the present application provides a GIS-based land surveying and mapping system, including: a multi-channel transmission module 21, a remote sensing image interpretation module 22, a geographic change prediction module 23, a multi-dimensional map drawing module 24, and a surveying and mapping data storage module 25;

[0085] The multi-channel transmission module 21 is used to complete the data interaction between modules using the multi-channel transmission method; it includes a channel encryption submodule, a channel distribution submodule, and a data restoration submodule;

[0086] The channel encryption submodule is used to create multiple transmission channels and perform separate encryption for each channel;

[0087] There are many encryption algorithms available today, and they can be used as needed, as long as the encryption method for each channel is different.

[0088] A channel distribution submodule is used to distribute the transmission data to different channels using a channel distribution function;

[0089] Taking the transmission of remote sensing images as an example, the channel distribution function It is expressed as: ,in is the i-th pixel of the remote sensing image, % is the modulo operation, is the number of transmission channels, L is an adjustable parameter used to control the offset of channel distribution, Return to The channel number to which the pixel is distributed.

[0090] The data restoration submodule is used to restore the data received from different channels to the original arrangement order;

[0091] Taking the restoration of remote sensing images as an example, the channel number of the receiving pixel point, the number of transmission channels, and the adjustable parameters are all known quantities. Therefore, the arrangement order of the pixels on the original remote sensing image can be solved according to the channel distribution function, thereby restoring the original remote sensing image.

[0092] A remote sensing image interpretation module 22 is used to interpret the received remote sensing image using a remote sensing image interpretation model; it includes a remote sensing image interpretation model training submodule, and input and output submodules;

[0093] The remote sensing image interpretation model training submodule is used to train the remote sensing image interpretation model so that it has the ability to interpret the pixels in the remote sensing image as geographic data;

[0094] The specific training process includes:

[0095] 1. Create training data sets based on historical remote sensing images and historical geographic information images;

[0096] Extract the image features of each pixel in the historical remote sensing image, and the geographical features represented by each pixel on the historical geographic information image;

[0097] Image features include hue features, texture features, spectrum features and shadow features; geographic features include water features, vegetation features, mountain features and land features.

[0098] Overlay the layers of historical remote sensing images and geographic information images to obtain feature pairs with spatial correlation;

[0099] The geographic information image is scaled and rotated to make its coordinate ratio consistent with that of the remote sensing image, and the image features and geographic features at the same pixel are extracted to form a feature pair, for example [(0.3, 0.28, 0.72, 0.5), 1.1], where (0.3, 0.28, 0.72, 0.5) are the image features at a certain pixel, and 1.1 is the geographic feature. It should be noted that the superimposed remote sensing image and geographic information image must come from the same collection location and the same collection date to ensure the accuracy of the training data set.

[0100] Arrange the obtained feature pairs into a training data set;

[0101] The feature pairs of all pixels in the entire historical remote sensing image are sequentially placed into the training data set.

[0102] 2. Use the training data set to train the remote sensing image interpretation model;

[0103] The image features and geographic features in the training data set are used as input and output pairs, and the remote sensing image interpretation model is supervised for training, so that the model can learn the mapping relationship between image features and geographic features from the data set. The remote sensing image interpretation model is expressed as:

[0104] , where j is the input image feature subscript, ranging from 1 to m, and m is 3. They are the hue eigenvalue, texture eigenvalue and spectrum eigenvalue of the pixel to be interpreted. Represents the shadow feature value of the i-th pixel in the shadow recognition domain of the pixel to be interpreted. Represents the shadow feature value of the i+1th pixel in the shadow recognition domain, i ranges from 1 to -1, is the size of the shadow recognition domain, are the mapping indexes of hue, texture, spectrum and shadow features to geographic features, respectively, and Y1 is the output geographic feature value. The size of the shadow recognition domain is 5 by default, that is, it is centered on the pixel to be interpreted and extends to 5 pixels in the horizontal direction.

[0105] The input and output submodule is used to interpret the currently acquired remote sensing images using the trained remote sensing image interpretation model;

[0106] Extract the image features of each pixel in the remote sensing image, input them into the trained remote sensing image interpretation model in turn, and output the interpretation data;

[0107] The output interpretation data uses remote sensing image code + pixel coordinates as a unique identifier and is stored in a private cloud to provide data support for subsequent map drawing.

[0108] The geographic change prediction module 23 is used to use the national geographic data prediction model to interpret the data of historical remote sensing images and predict the change trend of various geographic data in the image collection area;

[0109] The training process of the national geographic data prediction model includes:

[0110] 1. Create a training data set by combining the interpretation data of historical remote sensing images with the climate data and geological data of the collection site;

[0111] First, two parts are extracted from the interpretation data of historical remote sensing images according to the image acquisition time. The first part is used as input (multiple parts), and the second part is used as output (one part). The time interval in between is used as the prediction period. Then, the climate data and geological data of the image acquisition site are added to the input data as two types of influencing factors to help the model deeply understand the changing patterns of the data and improve the prediction ability. Finally, the input and output pairs are sorted into a large set to form a training data set.

[0112] 2. Use the created training data set to train the national geographic data prediction model;

[0113] The national geographic data prediction model is expressed as:

[0114] , where Y2 is the prediction result, C is the prediction period, and T is the length of the input set. The avg() function returns the mean of the expression in brackets when t is 1 to T. represents the climate impact factor with the subscript k1, k1 ranges from 1 to w1, w1 is the number of climate impact factors, represents the geological influence factor with the subscript k2, k2 takes values ​​from 1 to w2, w2 is the number of geological influence factors, D is the general trend parameter of the interpretation data in time series, To interpret the special trend of data in time series, It is the mean of all remote sensing image interpretation data in the input set.

[0115] During the training process, the unknown parameters in the model are continuously adjusted until the MES loss value is minimized.

[0116] 3. Verify the accuracy of the national geographic data prediction model and determine its longest prediction period;

[0117] After the model training is completed, the length of the prediction cycle is continuously increased, and the MES loss function is used to verify the accuracy of the model. If the accuracy of the model drops to 95%, the length of the prediction cycle at this time is the longest prediction cycle of the model, which is also the end point of the prediction cycle selection slider.

[0118] The multi-dimensional map drawing module 24 is used to draw a multi-dimensional map of the image collection area based on the interpretation data of the current remote sensing image and the predicted trend of geographic data changes; it includes a multi-dimensional geographic information image generation submodule, a geographic information image overlay submodule, and a geographic change evolution submodule;

[0119] The multi-dimensional geographic information image generation submodule is used to draw a multi-dimensional geographic information image based on the interpretation data of each pixel in the current remote sensing image;

[0120] First, separate the different interpretation data and put each interpretation data into a separate layer. Then extract the pixel points whose geographical features are consistent with the current interpretation data from the historical geographic information image, fill them in accordingly, and finally draw a geographic information image in multiple dimensions.

[0121] The geographic information image overlay submodule is used to overlay geographic information images of different dimensions, and the base map is set as the current remote sensing image;

[0122] The geographic change evolution submodule is used to add interpolation animation to geographic information images of different dimensions according to the change trend of geographic data to form a dynamic evolution effect;

[0123] Taking water body images as an example, the changing trend of geographic data describes the changing trend of each pixel point of the water body image at the collection site. By adding the interpretation data Y1 of a pixel point on the current water body image to Y1 and multiplying it by the changing trend Y2, we can get the geographic characteristics of the pixel point after a future prediction cycle, recorded as Y3. Y3 is represented on the water body image and filled with pixel points with consistent geographic characteristics in the historical geographic information image. Then, frame-interpolation animation is added between Y1 and Y3 to form a dynamic evolution effect.

[0124] The surveying and mapping data storage module 25 is used to store the drawn multi-dimensional map and the collected surveying and mapping data;

[0125] The storage module uses a private cloud as a storage unit and has a strict access control policy. Data interaction uses a multi-channel transmission method. The private cloud monitors the user's access behavior and only allows data sharing between authorized devices.

[0126] Corresponding to the above embodiment, an embodiment of the present invention provides a computer storage medium, including: at least one memory and at least one processor;

[0127] The memory is used to store one or more program instructions;

[0128] The processor is used to run one or more program instructions to execute a GIS-based land surveying and mapping method.

[0129] Corresponding to the above-mentioned embodiment, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer storage medium contains one or more program instructions, and the one or more program instructions are used by a processor to execute a GIS-based land surveying and mapping method.

[0130] The embodiment disclosed in the present invention provides a computer-readable storage medium, in which computer program instructions are stored. When the computer program instructions are executed on a computer, the computer executes the above-mentioned GIS-based land surveying and mapping method.

[0131] In the embodiment of the present invention, the processor may be an integrated circuit chip having the ability to process signals. The processor may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0132] The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present invention can be directly embodied as a hardware decoding processor for execution, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The processor reads the information in the storage medium and completes the steps of the above method in combination with its hardware.

[0133] The storage medium may be a memory, which may be, for example, a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memory.

[0134] Among them, the non-volatile memory can be a read-only memory (ROM), a programmable ROM (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory.

[0135] The volatile memory may be a random access memory (RAM) which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDRSDRAM), enhanced synchronous DRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus DRAM (DRRAM).

[0136] The storage media described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memory.

[0137] Those skilled in the art will appreciate that in one or more of the above examples, the functions described in the present invention can be implemented using a combination of hardware and software. When software is used, the corresponding functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any media that facilitates the transmission of computer programs from one place to another. Storage media can be any available media that can be accessed by general or special-purpose computers.

[0138] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solution of the present invention should be included in the scope of protection of the present invention.

Claims

1. A GIS-based land surveying and mapping method, characterized in that: include: Step 1: Use the multi-channel transmission method to upload the collected remote sensing images to the GIS software, which is divided into the following sub-steps: Prepare multiple transmission channels and encrypt each channel separately to ensure that the encryption method of each channel is different; Use the channel distribution function to distribute remote sensing images to different channels. It is expressed as: ,in is the i-th pixel of the remote sensing image, % is the modulo operation, is the number of transmission channels, L is an adjustable parameter used to control the offset of channel distribution, Return to The channel number of the pixel distribution; GIS software restores the pixels received by different channels to the original remote sensing images; Step 2, GIS software uses remote sensing image interpretation model to interpret the received remote sensing images; Step 3: Use the national geographic data prediction model to interpret the data based on historical remote sensing images and predict the changing trends of various geographic data in the image collection area. The training process of the national geographic data prediction model is divided into the following sub-steps: Combine the interpretation data of historical remote sensing images, as well as the climate data and geological data of the collection site to create a training data set; first, extract two parts from the interpretation data of historical remote sensing images according to the image collection time, with the first part as input and the second part as output, and the time interval in between as the prediction period, then add the climate data and geological data of the image collection site to the input data as two types of influencing factors, and finally organize the input and output pairs into a large set to form a training data set; Use the created training data set to train the national land geographic data prediction model, which is expressed as: , where Y2 is the prediction result, C is the prediction period, and T is the length of the input set. The avg() function returns the mean of the expression in brackets when t is 1 to T. represents the climate impact factor with the subscript k1, k1 ranges from 1 to w1, w1 is the number of climate impact factors, represents the geological influence factor with the subscript k2, k2 takes values ​​from 1 to w2, w2 is the number of geological influence factors, D is the general trend parameter of the interpretation data in time series, To interpret the special trend of data in time series, It is the mean of all remote sensing image interpretation data in the input set; Verify the accuracy of the national geographic data prediction model and determine its longest prediction period; Step 4: Draw a multidimensional map of the image collection site based on the interpretation data of the current remote sensing image and the predicted trend of geographic data changes; Step 5. Store the drawn multi-dimensional map in the private cloud.

2. The GIS-based land surveying and mapping method according to claim 1, characterized in that: GIS software uses remote sensing image interpretation models to interpret received remote sensing images, which is divided into the following sub-steps: Create training data sets based on historical remote sensing images and historical geographic information images; Use the training dataset to train the remote sensing image interpretation model; The image features of each pixel in the received remote sensing image are extracted, input into the trained remote sensing image interpretation model in sequence, and the interpretation data is output.

3. The GIS-based land surveying and mapping method according to claim 2, characterized in that: Creating a training dataset based on historical remote sensing images and historical geographic information images is divided into the following sub-steps: Extract the image features of each pixel in the historical remote sensing image, and the geographical features represented by each pixel on the historical geographic information image; Overlay the layers of historical remote sensing images and geographic information images to obtain feature pairs with spatial correlation; The obtained feature pairs are organized into training data sets.

4. The GIS-based land surveying and mapping method according to claim 1, characterized in that: Based on the interpretation data of the current remote sensing image and the predicted trend of geographic data changes, a multidimensional map of the image collection area is drawn. The specific steps are as follows: Draw geographic information images in multiple dimensions based on the interpretation data of each pixel in the current remote sensing image; Overlay geographic information images of different dimensions and set the base map as the current remote sensing image; According to the changing trend of geographic data, frame-interpolation animation is added to geographic information images of different dimensions to create a dynamic evolution effect.

5. A GIS-based land surveying and mapping system for executing a GIS-based land surveying and mapping method as claimed in any one of claims 1 to 4, characterized in that: include: Multi-channel transmission module, remote sensing image interpretation module, geographic change prediction module, multi-dimensional map drawing module, surveying and mapping data storage module; Multi-channel transmission module, used to complete data interaction between modules using multi-channel transmission method; A remote sensing image interpretation module is used to interpret the received remote sensing images using a remote sensing image interpretation model; The geographic change prediction module is used to use the national geographic data prediction model to interpret data based on historical remote sensing images and predict the change trend of various geographic data in the image collection area; A multi-dimensional map drawing module is used to draw a multi-dimensional map of the image collection area based on the interpretation data of the current remote sensing image and the predicted trend of geographic data changes; The surveying and mapping data storage module is used to store the drawn multi-dimensional maps and the collected surveying and mapping data.

6. The GIS-based land surveying and mapping system according to claim 5, characterized in that: The multi-channel transmission module includes a channel encryption submodule, a channel distribution submodule, and a data restoration submodule; The channel encryption submodule is used to create multiple transmission channels and perform separate encryption for each channel; A channel distribution submodule is used to distribute the transmission data to different channels using a channel distribution function; The data restoration submodule is used to restore the data received from different channels to the original arrangement order.

7. The GIS-based land surveying and mapping system according to claim 5, characterized in that: The remote sensing image interpretation module includes a remote sensing image interpretation model training submodule, an input and output submodule; The remote sensing image interpretation model training submodule is used to train the remote sensing image interpretation model so that it has the ability to interpret the pixels in the remote sensing image as geographic data; The input and output submodules are used to interpret the currently acquired remote sensing images using the trained remote sensing image interpretation model.

Images