An intelligent method and system for processing and analyzing geographical mapping data

Abstract

The present invention relates to an intelligent geographic mapping data processing and analysis method and system, belonging to the field of data processing, including: sequentially preprocessing, data registration, and data fusion of multi-source geographic mapping data to generate a regional standard mapping image; extracting significant features from the regional standard mapping image to obtain a set of local significant mapping images; based on a convolutional neural network, traversing and comparing the set of local significant mapping images with a historical set of local significant mapping images for deviation to output a mapping deviation data set; inputting the mapping deviation data set into a flood spread prediction plug-in to output a flood spread prediction result. Through the present application, the technical problem in the existing method that due to the inability to effectively perform data fusion and feature extraction, the accuracy and efficiency of data processing are insufficient, resulting in poor accuracy of flood spread prediction can be solved, and efficient data fusion and registration can be achieved, achieving the effect of improving the accuracy and reliability of flood spread prediction.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to an intelligent method and system for processing and analyzing geographical mapping data. Background Art

[0002] With the continuous progress of geographical information technology and surveying and mapping equipment, modern geographical surveying and mapping work plays an important role in fields such as disaster monitoring, environmental assessment, and resource management. Especially in flood monitoring and prediction, geographical surveying and mapping data, as basic information, plays a crucial role.

[0003] However, the existing sources of geographical surveying and mapping data are extensive, including satellite remote sensing images, lidar data, meteorological data, ground measurement data, etc. Each data type has its unique characteristics and formats, and there are errors and inconsistencies between the data. Therefore, when processing and analyzing these multi-source data, how to effectively perform data fusion and eliminate errors and contradictions between various types of data remains a difficult point.

[0004] Currently, many traditional surveying and mapping data fusion methods rely on manual correction and simple linear fusion techniques, resulting in the lack of high precision in the results after data fusion, unable to provide consistent and reliable geographical information layers, and affecting subsequent disaster prediction and decision support. Summary of the Invention

[0005] Aiming at the technical problems in the existing geographical surveying and mapping data processing methods, such as the lack of accuracy and efficiency in data processing due to the inability to effectively perform data fusion and feature extraction, resulting in poor accuracy in flood spread prediction, the present invention provides an intelligent method and system for processing and analyzing geographical surveying and mapping data to solve the problems.

[0006] The technical solution of the present invention to solve the above technical problems is as follows:

[0007] In a first aspect, the present invention provides an intelligent method for processing and analyzing geographical surveying and mapping data, including: acquiring multi-source geographical surveying and mapping data of the affected area through various surveying and mapping devices at fixed points; sequentially preprocessing, registering, and fusing the multi-source geographical surveying and mapping data to generate a regional standard surveying and mapping image; extracting significant features from the regional standard surveying and mapping image to obtain a set of local significant surveying and mapping images; based on a convolutional neural network, traversing and comparing the deviation between the set of local significant surveying and mapping images and the historical set of local significant surveying and mapping images of the previous adjacent acquisition node, and outputting a surveying and mapping deviation data set; inputting the surveying and mapping deviation data set into a flood spread prediction plugin to output a flood spread prediction result.

[0008] Second aspect, the present invention provides an intelligent geographic mapping data processing and analysis system, including: a multi-source geographic mapping data acquisition module, configured to acquire multi-source geographic mapping data of the disaster-stricken area by fixed-point acquisition through a variety of mapping devices; a regional standard mapping image generation module, configured to perform preprocessing, data registration, and data fusion on the multi-source geographic mapping data in sequence to generate a regional standard mapping image; a significant feature extraction module, configured to perform significant feature extraction on the regional standard mapping image to obtain a local significant mapping image set; a deviation traversal comparison module, configured to perform deviation traversal comparison between the local significant mapping image set and the historical local significant mapping image set of the previous adjacent acquisition node based on a convolutional neural network, and output a mapping deviation data set; a flood spread prediction module, configured to input the mapping deviation data set into a flood spread prediction plug-in and output a flood spread prediction result.

[0009] Third aspect, the present invention further provides an electronic device, including:

[0010] At least one processor; a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the steps of the method according to any one of the first aspects above.

[0011] Fourth aspect, a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed, it implements the steps of the method according to any one of the first aspects above.

[0012] The beneficial effects of the present invention are: acquiring multi-source geographic mapping data of the disaster-stricken area by fixed-point acquisition through a variety of mapping devices; performing preprocessing, data registration, and data fusion on the multi-source geographic mapping data in sequence to generate a regional standard mapping image; performing significant feature extraction on the regional standard mapping image to obtain a local significant mapping image set; performing deviation traversal comparison between the local significant mapping image set and the historical local significant mapping image set of the previous adjacent acquisition node based on a convolutional neural network, and outputting a mapping deviation data set; inputting the mapping deviation data set into a flood spread prediction plug-in and outputting a flood spread prediction result; which can achieve efficient data fusion and registration, improve the accuracy and efficiency of data processing, and thus achieve the technical effects of improving the accuracy and reliability of flood spread prediction. Description of the Drawings

[0013] Figure 1 It is a schematic flowchart of an intelligent geographic mapping data processing and analysis method provided by the present invention;

[0014] Figure 2Schematic diagram of a structure of an intelligent geographical mapping data processing and analysis system provided by the present invention;

[0015] Figure 3 Schematic diagram of a structure of an electronic device provided by the present invention;

[0016] Figure 4 Schematic diagram of a structure of a computer-readable storage medium provided by the present invention.

[0017] In the drawings, the components represented by the reference numerals are described as follows:

[0018] Multi-source geographical mapping data acquisition module 01, regional standard mapping image generation module 02, significant feature extraction module 03, deviation traversal comparison module 04, flood spread prediction module 05, electronic device 500, memory 510, processor 520, first computer program 511, computer-readable storage medium 600, second computer program 611. Detailed implementation manners

[0019] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present invention.

[0020] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes, and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality of" means two or more, unless otherwise specifically defined.

[0021] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration, or explanation". Any embodiment described as "for example" in the present invention is not necessarily construed as being more preferred or more advantageous than other embodiments. In order for any person skilled in the art to implement and use the present invention, the following description is given. In the following description, details are set forth for the purpose of explanation. It should be understood that those skilled in the art can recognize that the present invention can be implemented without using these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope that conforms to the principles and features disclosed in the present invention.

[0022] Embodiment 1, asFigure 1 As shown in Figure 1 , an embodiment of the present invention provides an intelligent geographic mapping data processing and analysis method, which specifically includes the following steps:

[0023] S100: Through a variety of surveying and mapping devices, fixed-point collection is carried out to obtain multi-source geographic mapping data of the affected area.

[0024] In one embodiment, step S100 of the present application further includes:

[0025] S110: The multi-source geographic mapping data at least includes satellite remote sensing images, ground measurement data, meteorological data, and hydrological data.

[0026] Specifically, through a variety of surveying and mapping devices, fixed-point collection is carried out on the affected area to obtain multi-source geographic mapping data of the affected area. Among them, the multi-source geographic mapping data at least includes satellite remote sensing images, ground measurement data, meteorological data, and hydrological data. Among them, satellite remote sensing images can provide large-scale and high-resolution surface information, especially suitable for the rapid assessment of the affected area. Remote sensing images can help identify water area changes, ground cover conditions (such as farmland, cities, forests, etc.), and disaster traces (such as flood inundation areas, landslides, etc.); ground measurement data mainly includes data measured on-site, such as water level, precipitation, soil humidity, flow velocity, etc. Compared with remote sensing data, ground measurement data has higher accuracy and can provide more detailed and local geographic information; meteorological data includes data such as rainfall, temperature, humidity, wind speed, etc.; hydrological data includes information such as precipitation, surface runoff, groundwater level, and water body evaporation in the basin. By fixed-point collecting multi-source geographic mapping data of the affected area and effectively fusing and processing these data, more accurate disaster monitoring and prediction can be achieved.

[0027] S200: The multi-source geographic mapping data is preprocessed, data registered, and data fused in sequence to generate a regional standard mapping image.

[0028] In one embodiment, step S200 of the present application further includes:

[0029] S210: According to the data preprocessing scheme, noise removal, geometric correction, and data format conversion are carried out on the multi-source geographic mapping data to obtain multi-source processed mapping data; S220: Spatial alignment and error correction are carried out on the multi-source processed mapping data to obtain multi-source standard mapping data; S230: Combining spatial analysis technology, multi-dimensional data fusion is carried out on the multi-source standard mapping data to generate the regional standard mapping image.

[0030] Specifically, according to the data preprocessing scheme, noise removal, geometric correction, and data format conversion are performed on the multi-source geographic mapping data. Among them, various mapping devices are affected by environmental factors, equipment accuracy, etc. when collecting data, resulting in noise in the data. Noise removal is to remove these untrue outliers through techniques such as filtering and smoothing, thereby improving data quality. Since the data collection angles and coordinate systems of different mapping devices are different, geometric correction is required to ensure the spatial alignment of various data, which usually includes geometric transformation of images, such as rotation, scaling, affine transformation, etc., to ensure consistent data coordinates. Different mapping devices may use different file formats and data structures, and format conversion is needed. By converting to a unified format, it is convenient for subsequent analysis and fusion, and multi-source processed mapping data is obtained.

[0031] Next, registration technology is used to perform spatial matching on data from different sources. By setting common reference points or using geometric correction algorithms, ensure that all data is represented in the same coordinate system; further perform error correction on the data, including atmospheric error, terrain error, etc., which can be adjusted through existing error models or adaptive algorithms to improve the accuracy of the data, and obtain multi-source standard mapping data. Then, use spatial analysis algorithms (such as buffer analysis, neighborhood analysis, hot spot analysis, etc.) to deeply analyze the multi-source data to extract useful spatial information (such as change trends, specific features, etc. within the measurement area); combine information from different data sources (such as remote sensing images, meteorological data, ground measurement data, etc.), and use data fusion algorithms (such as weighted average method, principal component analysis, Kalman filter, etc.) to integrate different dimensional information of the data together to generate a comprehensive regional standard mapping image.

[0032] Through noise removal, geometric correction, and error correction, ensure the precise alignment of each source of data, eliminate errors, and improve data accuracy and consistency; through data fusion, data from multiple sources can complement each other, providing more comprehensive and detailed regional mapping information, greatly enhancing the utilization value of the data;

[0033] S300: Extract significant features from the regional standard mapping image to obtain a set of local significant mapping images.

[0034] In one embodiment, step S300 of the present application further includes:

[0035] S310: Input the regional standard surveying and mapping image into a Gaussian pyramid for multi-scale Gaussian downsampling to obtain a multi-scale image set. Among them, the Gaussian pyramid includes a luminance extraction unit, a color extraction unit, and an orientation extraction unit; S320: Calculate the center-surround difference for each image in the multi-scale image set respectively to generate a luminance feature map, a color feature map, and an orientation feature map; S330: Perform an overlay process on the luminance feature map, the color feature map, and the orientation feature map to generate an initial saliency image; S340: Extract the initial saliency image according to an initial saliency feature threshold, set the saliency feature regions that meet the initial saliency feature threshold as local saliency surveying and mapping images, and obtain the local saliency surveying and mapping image set.

[0036] Specifically, a Gaussian pyramid is a structure for multi-scale analysis of images. Usually, by performing Gaussian blur on an image and gradually downsampling it, image levels with different resolutions are generated. Through multi-level image processing, the feature information of the image at different scales can be captured. Among them, the Gaussian pyramid includes a luminance extraction unit, a color extraction unit, and an orientation extraction unit. The luminance extraction unit is used to extract luminance information from the image, and luminance reflects the light and dark changes of the image; the color extraction unit is used to extract color information from the image, and color changes reflect different regional features in the image; the orientation extraction unit is used to extract edge information from the image, and the edge and texture features in the image are captured through orientation changes. Then, input the regional standard surveying and mapping image into the Gaussian pyramid for multi-scale Gaussian downsampling. Through Gaussian downsampling, image levels with different resolutions are obtained, and the details of the image can be analyzed step by step from coarse to fine, capturing the feature information at different scales and obtaining a multi-scale image set.

[0037] Then, for each image at each scale, calculate the difference between the central region and the surrounding region of the image. Saliency regions usually have larger luminance, color, or orientation differences. The difference between the center and the surrounding reflects the interesting or important parts in the image, generating a luminance feature map, a color feature map, and an orientation feature map. Among them, the luminance feature map highlights the regions with obvious light and dark changes in the image by calculating the difference in luminance changes in the image; the color feature map highlights the regions with significant color changes by calculating the difference in color changes in the image; the orientation feature map highlights the regions with obvious orientation changes by calculating the difference in edge and texture changes in the image. Through this difference calculation, feature maps of luminance, color, and orientation are generated, respectively reflecting the significant changes in the image in terms of luminance, color, and orientation.

[0038] Further, the calculated luminance, color, and orientation feature maps are merged to synthesize various types of feature information. This superposition can integrate information from different feature dimensions, thereby generating a more comprehensive saliency image that identifies all salient regions in the image, resulting in an initial saliency image. Then, an initial saliency feature threshold is set, and the initial saliency feature threshold is used to screen out the most salient part of the initial saliency image. This threshold is usually determined based on the grayscale value or feature intensity value of the image to ensure that only significant regions are extracted; further, the initial saliency image is extracted according to the initial saliency feature threshold, and the salient feature regions that meet the initial saliency feature threshold are set as local salient mapping images, that is, through threshold processing, the eligible salient feature regions are identified and marked as local salient mapping images. Such regions are usually the most prominent and variable parts of the image, representing the most critical geographical information features in the image, resulting in a set of local salient mapping images.

[0039] S400: Based on a convolutional neural network, the set of local salient mapping images is traversed and compared with the historical set of local salient mapping images of the previous adjacent acquisition node for deviation, and a mapping deviation data set is output.

[0040] In one embodiment, step S400 of the present application further includes:

[0041] S410: Construct a deviation comparison model based on a convolutional neural network, where the deviation comparison model includes an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer; S420: Collect and obtain a sample binary salient mapping image set and a sample mapping deviation data set, and use the sample binary salient mapping image as the input and the sample mapping deviation data as the output to perform supervised training on the deviation comparison model to obtain a deviation comparison model that meets the predetermined convergence condition; S430: After mapping and combining the set of local salient mapping images and the historical set of local salient mapping images, input them into the deviation comparison model for deviation traversal comparison, and output the mapping deviation data set.

[0042] Specifically, a deviation comparison model is constructed based on a convolutional neural network (CNN) to compare the deviation between the set of local salient mapping images and the historical set of local salient mapping images. Among them, the deviation comparison model includes an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer. The input layer is used to receive input data, that is, the set of local salient mapping images; the convolutional layer extracts local features in the input image through convolutional operations, and the convolutional layer can capture information such as edges, textures, and shapes in the image; the pooling layer is used to perform dimensionality reduction processing on the convolutional result, reduce the amount of calculation, and retain important features; the fully connected layer is used to flatten and connect the pooled feature data, and learn the relationship between the input data through the weight transfer between multiple neurons; the output layer is used to output the mapping deviation data set.

[0043] Next, collect and obtain a sample binary significant mapping image set and a sample mapping deviation data set, where the sample binary significant mapping image is an image combination containing two significant images; then, using the sample binary significant mapping image set as the input and the sample mapping deviation data as the output, supervise and train the deviation comparison model with the sample binary significant mapping image set and the sample mapping deviation data set, that is, use the sample binary significant mapping image set as the input and the sample mapping deviation data set as the output to train the deviation comparison model. During the training process, by adjusting model parameters (such as convolution kernels, weights, etc.), the model can accurately predict the deviation between the input image and the historical image; during the training process, the loss function of the model will be continuously optimized until the predetermined convergence conditions are met, which usually include minimizing the error or reaching a certain number of training epochs; obtain a deviation comparison model that meets the predetermined convergence conditions.

[0044] Finally, map and combine the local significant mapping image set and the historical local significant mapping image set, and use the combined result as input data to input into the deviation comparison model for deviation traversal comparison, and output the mapping deviation data set. Through these technical steps, the accuracy and efficiency of geographic mapping data processing can be significantly improved, providing strong technical support for disaster management and environmental monitoring.

[0045] S500: Input the mapping deviation data set into the flood spread prediction plugin and output the flood spread prediction result.

[0046] In one embodiment, step S500 of the present application further includes:

[0047] S510: Query the historical flood records of the affected area, obtain a sample flood spread data set and multiple sample mapping deviation data sets, and collect the actual flood spread results of different sample flood spread data and different sample mapping deviation data sets after a predetermined time period to obtain a sample flood spread result set, where the flood spread results include the flood expansion speed and the flood expansion direction.

[0048] Specifically, query the historical flood records of the affected area, screen out representative flood events from the historical flood records, and collect and obtain a sample flood spread data set and multiple sample mapping deviation data sets; then collect the actual flood spread results of different sample flood spread data and different sample mapping deviation data sets after a predetermined time period, where the flood spread results include the flood expansion speed and the flood expansion direction, to obtain a sample flood spread result set.

[0049] S520: Use the sample flood spread dataset, multiple sample mapping deviation datasets, and the sample flood spread result set as the training dataset to perform supervised training on the BP neural network until convergence, and obtain the flood spread prediction plugin.

[0050] In one embodiment, step S520 of the present application further includes:

[0051] S521: Divide the training dataset into Q equal parts, and select Q times with replacement to construct the first training set. Iteratively select Q times to obtain Q training sets, where Q is an integer greater than 5; S522: Use the Q training sets to perform supervised training on the BP neural network until convergence to obtain Q flood spread prediction models, and integrally construct the flood spread prediction plugin according to the Q flood spread prediction models. The output of the flood spread prediction plugin is the mode of the outputs of the Q flood spread prediction models.

[0052] Specifically, divide the training dataset into Q equal parts, where Q is an integer greater than 5, and select Q times with replacement from the Q datasets to construct the first training set. Use the same method to iteratively select Q times to obtain Q training sets.

[0053] Further use the Q training sets. With the sample flood spread data and the sample mapping deviation dataset as the input and the sample flood spread result as the output, perform supervised training on the BP neural network respectively. The BP neural network is a common feedforward neural network and is trained based on the backpropagation algorithm. The weights in the network are adjusted by minimizing the prediction error. In the present application, the BP neural network is used for flood spread prediction modeling. Its goal is to predict the output flood spread result (such as the expansion speed and direction) based on the input training data (sample flood spread data and the mapping deviation dataset). The training process is as follows: input the sample data, and obtain the predicted value through the calculations of each layer of the network. Forward propagation is to generate the output of the network after operations such as weights and activation functions on the input signal. Calculate the error by comparing the output predicted by the network with the actual flood spread result. The error usually uses the mean square error. Then use the backpropagation algorithm to update the weights and biases in the network according to the output error. This process calculates the gradient of each weight through the chain rule, adjusts the weights using the gradient descent method, and repeatedly trains using the known sample dataset until the error of the network reaches the predetermined convergence condition. The convergence condition usually means that the error is small enough or the number of training times reaches the maximum limit to obtain Q flood spread prediction models. Then integrally construct the flood spread prediction plugin according to the Q flood spread prediction models. The output of the flood spread prediction plugin is the mode of the outputs of the Q flood spread prediction models.

[0054] S530: Input the mapping deviation data set into the flood spread prediction plug-in to output the flood spread prediction result.

[0055] Specifically, finally input the mapping deviation data set into the flood spread prediction plug-in to output the flood spread prediction result.

[0056] An intelligent geographic mapping data processing and analysis method provided by an embodiment of the present invention has at least the following technical effects:

[0057] Through a variety of mapping devices, multi-source geographic mapping data of the affected area is collected at fixed points; the multi-source geographic mapping data is preprocessed, data registered, and data fused in sequence to generate a regional standard mapping image; significant features of the regional standard mapping image are extracted to obtain a set of local significant mapping images; based on a convolutional neural network, the set of local significant mapping images is traversed and compared with the historical set of local significant mapping images of the previous adjacent acquisition node to output a mapping deviation data set; the mapping deviation data set is input into the flood spread prediction plug-in to output the flood spread prediction result; it can achieve efficient data fusion and registration, improve the accuracy and efficiency of data processing, and thus achieve the technical effect of improving the accuracy and reliability of flood spread prediction.

[0058] Embodiment 2, as Figure 2 shown, based on the same inventive concept as the intelligent geographic mapping data processing and analysis method provided in Embodiment 1, an embodiment of the present invention further provides an intelligent geographic mapping data processing and analysis system, including:

[0059] A multi-source geographic mapping data acquisition module 01 for collecting multi-source geographic mapping data of the affected area at fixed points through a variety of mapping devices; a regional standard mapping image generation module 02 for preprocessing, data registering, and data fusing the multi-source geographic mapping data in sequence to generate a regional standard mapping image; a significant feature extraction module 03 for extracting significant features of the regional standard mapping image to obtain a set of local significant mapping images; a deviation traversal comparison module 04 for traversing and comparing the set of local significant mapping images with the historical set of local significant mapping images of the previous adjacent acquisition node based on a convolutional neural network to output a mapping deviation data set; a flood spread prediction module 05 for inputting the mapping deviation data set into the flood spread prediction plug-in to output the flood spread prediction result.

[0060] In one embodiment, the intelligent geographic mapping data processing and analysis system further includes: the multi-source geographic mapping data at least includes satellite remote sensing images, ground measurement data, meteorological data, and hydrological data.

[0061] In one embodiment, the intelligent geographic mapping data processing and analysis system further includes: removing noise, geometrically correcting, and converting the data format of the multi-source geographic mapping data according to a data preprocessing scheme to obtain multi-source processed mapping data; performing spatial alignment and error correction on the multi-source processed mapping data to obtain multi-source standard mapping data; and combining spatial analysis techniques to perform multi-dimensional data fusion on the multi-source standard mapping data to generate the regional standard mapping image.

[0062] In one embodiment, the intelligent geographic mapping data processing and analysis system further includes: inputting the regional standard mapping image into a Gaussian pyramid for multi-scale Gaussian downsampling to obtain a multi-scale image set, where the Gaussian pyramid includes a luminance extraction unit, a color extraction unit, and an orientation extraction unit; calculating the center-surround difference for each image in the multi-scale image set respectively to generate a luminance feature map, a color feature map, and an orientation feature map; performing superposition processing on the luminance feature map, the color feature map, and the orientation feature map to generate an initial saliency image; extracting the initial saliency image according to an initial saliency feature threshold, setting the salient feature regions that meet the initial saliency feature threshold as local salient mapping images, and obtaining the local salient mapping image set.

[0063] In one embodiment, the intelligent geographic mapping data processing and analysis system further includes: constructing a deviation comparison model based on a convolutional neural network, where the deviation comparison model includes an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer; collecting and obtaining a sample binary salient mapping image set and a sample mapping deviation data set, and using the sample binary salient mapping images as inputs and the sample mapping deviation data as outputs to perform supervised training on the deviation comparison model to obtain a deviation comparison model that meets a predetermined convergence condition; after performing mapping combination on the local salient mapping image set and the historical local salient mapping image set, inputting them into the deviation comparison model for deviation traversal comparison, and outputting the mapping deviation data set.

[0064] In one embodiment, the intelligent geographic mapping data processing and analysis system further includes: querying the historical flood records of the disaster-stricken area to obtain a sample flood spread data set and multiple sample mapping deviation data sets, and collecting the actual flood spread results after a predetermined time period for different sample flood spread data and different sample mapping deviation data sets to obtain a sample flood spread result set, where the flood spread result includes the flood expansion speed and the flood expansion direction; using the sample flood spread data set, the multiple sample mapping deviation data sets, and the sample flood spread result set as a training data set to perform supervised training on a BP neural network until convergence to obtain a flood spread prediction plugin; inputting the mapping deviation data set into the flood spread prediction plugin and outputting the flood spread prediction result.

[0065] In one embodiment, the intelligent geographic surveying and mapping data processing and analysis system also includes: dividing the training data set into Q equal parts, selecting Q times with replacement to construct a first training set, iteratively selecting Q times to obtain Q training sets, wherein Q is an integer greater than 5; using the Q training sets, respectively performing supervised training on the BP neural network until convergence to obtain Q flood spread prediction models, and integrating and constructing the flood spread prediction plug-in based on the Q flood spread prediction models, wherein the output of the flood spread prediction plug-in is the mode of the outputs of the Q flood spread prediction models.

[0066] For example 3, please refer to Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 520, and a first computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the first computer program 511, the following steps are implemented: using a variety of surveying and mapping equipment, fixed-point acquisition of multi-source geographic surveying and mapping data of the disaster-stricken area; sequentially preprocessing, data registration, and data fusion of the multi-source geographic surveying and mapping data to generate a regional standard surveying and mapping image; extracting significant features from the regional standard surveying and mapping image to obtain a local significant surveying and mapping image set; based on a convolutional neural network, performing deviation traversal comparison on the local significant surveying and mapping image set and the historical local significant surveying and mapping image set of the previous adjacent acquisition node, and outputting a surveying and mapping deviation data set; inputting the surveying and mapping deviation data set into a flood spread prediction plug-in to output a flood spread prediction result.

[0067] Example 4, please refer to Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 600, on which a second computer program 611 is stored. When the second computer program 611 is executed by the processor, the following steps are implemented: through a variety of surveying and mapping equipment, multi-source geographic surveying and mapping data of the disaster-stricken area are acquired by fixed-point collection; the multi-source geographic surveying and mapping data are preprocessed, data registered and data fused in sequence to generate a regional standard surveying and mapping image; significant features are extracted from the regional standard surveying and mapping image to obtain a local significant surveying and mapping image set; based on a convolutional neural network, the local significant surveying and mapping image set is compared with the historical local significant surveying and mapping image set of the previous adjacent acquisition node through deviation traversal, and a surveying and mapping deviation data set is output; the surveying and mapping deviation data set is input into a flood spread prediction plug-in to output a flood spread prediction result.

[0068] It should be noted that in the above embodiments, each embodiment is described with emphasis. For parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0069] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0070] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for realizing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0071] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that realizes the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0072] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for realizing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0073] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they know the basic inventive concept.

[0074] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and modifications.

Claims

1. An intelligent method for processing and analyzing geographical mapping data, characterized in that, include: Through a variety of surveying and mapping equipment, multi-source geographic surveying and mapping data of the disaster-stricken areas are collected at fixed points; Preprocessing, data registration and data fusion are performed on the multi-source geographic surveying and mapping data in sequence to generate a regional standard surveying and mapping image; Extracting significant features from the standard mapping image of the area to obtain a set of local significant mapping images; Based on a convolutional neural network, the local significant mapping image set is compared with the historical local significant mapping image set of the previous adjacent acquisition node through deviation traversal, and a mapping deviation data set is output; Inputting the surveying and mapping deviation data set into a flood spread prediction plug-in, and outputting a flood spread prediction result; The step of inputting the surveying and mapping deviation data set into the flood spread prediction plug-in and outputting the flood spread prediction result includes: Query the historical flood records of the disaster-stricken area, obtain a sample flood spread data set and multiple sample mapping deviation data sets, and collect the actual flood spread results of different sample flood spread data and different sample mapping deviation data sets after a predetermined time period to obtain a sample flood spread result set, wherein the flood spread results include the flood expansion speed and the flood expansion direction; The sample flood spread data set, multiple sample mapping deviation data sets and sample flood spread result set are used as training data sets to supervise the BP neural network until convergence, thereby obtaining a flood spread prediction plug-in; Inputting the surveying and mapping deviation data set into the flood spread prediction plug-in, and outputting the flood spread prediction result; Wherein, obtaining the flood spread prediction plug-in includes: Divide the training data set into Q equal parts, select Q parts with replacement, construct a first training set, iterate and select Q parts Q times, and obtain Q training sets, where Q is an integer greater than 5; Using the Q training sets, supervised training is performed on the BP neural network until convergence, to obtain Q flood spread prediction models, and the flood spread prediction plug-in is constructed based on the integration of the Q flood spread prediction models, wherein the output of the flood spread prediction plug-in is the mode of the outputs of the Q flood spread prediction models.

2. The intelligent geographic mapping data processing and analysis method according to claim 1, wherein The multi-source geographic surveying and mapping data at least include satellite remote sensing images, ground measurement data, meteorological data and hydrological data.

3. An intelligent geographic mapping data processing and analysis method according to claim 2, characterized in that, Preprocessing, data registration and data fusion are performed on the multi-source geographic surveying and mapping data in sequence to generate a regional standard surveying and mapping image, including: According to the data preprocessing scheme, the multi-source geographic surveying and mapping data are subjected to noise removal, geometric correction and data format conversion to obtain multi-source processed surveying and mapping data; Performing spatial alignment and error correction on the multi-source processed surveying and mapping data to obtain multi-source standard surveying and mapping data; Combined with spatial analysis technology, multi-dimensional data fusion is performed on the multi-source standard surveying and mapping data to generate the regional standard surveying and mapping image.

4. An intelligent geographic mapping data processing and analysis method according to claim 1, characterized in that Extracting significant features from the regional standard mapping image to obtain a local significant mapping image set includes: Inputting the regional standard surveying and mapping image into a Gaussian pyramid for multi-scale Gaussian downsampling to obtain a multi-scale image set, wherein the Gaussian pyramid includes a brightness extraction unit, a color extraction unit and a direction extraction unit; Perform center-surround difference calculations on the multi-scale image sets respectively to generate luminance feature maps, color feature maps, and orientation feature maps; Perform superposition processing on the luminance feature maps, color feature maps, and orientation feature maps to generate an initial saliency image; Extract the initial saliency image according to the initial saliency feature threshold, set the saliency feature regions that meet the initial saliency feature threshold as local saliency mapping images, and obtain the local saliency mapping image set.

5. An intelligent geographic mapping data processing and analysis method according to claim 1, characterized in that, Based on a convolutional neural network, perform deviation traversal comparison between the local saliency mapping image set and the historical local saliency mapping image set of the previous adjacent acquisition node, and output a mapping deviation data set, including: Construct a deviation comparison model based on a convolutional neural network, where the deviation comparison model includes an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer; Collect and obtain a sample binary saliency mapping image set and a sample mapping deviation data set, and use the sample binary saliency mapping images as inputs and the sample mapping deviation data as outputs to perform supervised training on the deviation comparison model to obtain a deviation comparison model that meets the predetermined convergence conditions; After performing mapping combination on the local saliency mapping image set and the historical local saliency mapping image set, input them into the deviation comparison model for deviation traversal comparison, and output the mapping deviation data set.

6. An intelligent geographic mapping data processing and analysis system, characterized in that, Steps for implementing the intelligent geographic mapping data processing and analysis method according to any one of claims 1 to 5, including: A multi-source geographic mapping data acquisition module, configured to acquire multi-source geographic mapping data of the disaster area at fixed points through a variety of mapping devices; A regional standard mapping image generation module, configured to perform preprocessing, data registration, and data fusion on the multi-source geographic mapping data in sequence to generate a regional standard mapping image; A saliency feature extraction module, configured to perform saliency feature extraction on the regional standard mapping image to obtain a local saliency mapping image set; A deviation traversal comparison module, configured to perform deviation traversal comparison between the local saliency mapping image set and the historical local saliency mapping image set of the previous adjacent acquisition node based on a convolutional neural network, and output a mapping deviation data set; A flood spread prediction module, configured to input the mapping deviation data set into a flood spread prediction plug-in and output a flood spread prediction result.

7. An electronic device, characterized in that, Including: A memory, configured to store computer software programs; A processor, configured to read and execute the computer software programs, and further implement the steps of the intelligent geographic mapping data processing and analysis method according to any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium, characterized in that, The computer software programs are stored in the storage medium, and when the computer software programs are executed by the processor, the steps of the intelligent geographic mapping data processing and analysis method according to any one of claims 1 to 5 are implemented.

Images