32 results about "Spatial classification" patented technology

The invention relates to the field of visual processing, and provides a visual classification processing method and device based on large model and multi-modal data fusion. The method comprises the following steps: inputting a to-be-classified input image and a corresponding category text description into a text encoder for multi-level feature extraction to obtain global text features and local text features; performing fine-grained cross-modal alignment on the local visual features and the local text features, calculating association weights between the image regions and the text phrases through a bidirectional cross attention mechanism, and generating aligned intermediate features; splicing and fusing the aligned middle features and the global visual features, and inhibiting background noise in a fusion result and reinforcing discriminative features in the fusion result through a feature mask algorithm in combination with the global text features to obtain multi-modal fusion features; and synchronously inputting the multi-modal fusion features into a multi-space classifier to generate respective classification results, and adaptively outputting an image classification result according to a confidence threshold in combination with a dynamic routing mechanism.

The invention relates to the technical field of urban planning, in particular to a historical and cultural oriented space classification and regeneration method and system. The method comprises the following steps: acquiring historical culture data, and performing multi-modal perception on the historical culture data to obtain historical culture spatial data; performing deep feature extraction on the historical and cultural spatial data to obtain historical and cultural element data; performing spatial semantic map construction on the historical and cultural element data to obtain spatial semantic map data; performing age evolution trajectory classification on the spatial semantic map data to obtain historical and cultural spatial classification data; performing space regeneration generation according to the historical and cultural space classification data to obtain space regeneration data; and acquiring urban planning demand data, and performing spatial regeneration fusion according to the urban planning demand data and the spatial regeneration data to obtain spatial regeneration fusion data. Space regeneration is carried out in combination with city planning, and dynamic balance between historical and cultural protection and modern city development is effectively achieved.

The invention discloses a cultivated land ecological safety comprehensive evaluation method and system based on multi-model coupling. The method comprises the steps that a future multi-source data set of cultivated land to be evaluated in a future time period is set; performing grid division on the cultivated land to be evaluated by adopting a grid calculator in ArcGIS software to obtain a plurality of grid regions, and performing grid division on the future multi-source data set based on the plurality of grid regions to obtain a future multi-source sub-data set of each grid region; and predicting the future multi-source sub-data set of each grid region by adopting the constructed multi-ecological safety comprehensive evaluation function model, the spatial classification method and the constructed ecological safety comprehensive evaluation index calculation formula to obtain an ecological safety comprehensive evaluation index corresponding to each grid region. According to the method, the ecological function of the to-be-evaluated cultivated land in the future scene is simulated by coupling the multi-ecological safety comprehensive evaluation function quantity model, so that systematic evaluation on the cultivated land ecological function of the to-be-evaluated cultivated land in the future scene is realized.

The invention discloses a hyperspectral image classification method, system and device under a cross-scene condition and a medium, and mainly solves the problems that the existing cross-domain feature space is not rich and the classification boundary is not robust, and the scheme comprises the following steps: obtaining source domain data, a source domain label and target domain data; a classification model composed of a Mama flow network and a ViT flow network in parallel is constructed, and the Mama flow network comprises a Mama block, a spectrum SKR block and two spectrum-oriented classifiers and is used for optimizing spectrum classification boundaries; the ViT flow network comprises a self-adaptive dynamic mask, a ViT block, a space SKR block and two space guiding classifiers, and is used for enriching a feature space and optimizing a space classification boundary; inputting the source domain data, the source domain data label and the target domain data into a classification model, and performing iterative training on the classification model; and inputting the target domain data into the trained classification model and outputting a classification result. The method improves the classification capability of the cross-scene hyperspectral image, and can be used for environmental monitoring and landform change prediction.

A mobile object control device for controlling a mobile object capable of moving both on a roadway and in a predetermined region different from the roadway includes a road type recognition unit configured to set a virtual central lane including an assumed course of the mobile object, a virtual right lane located on a right side of the virtual central lane as seen from the mobile object, and a virtual left lane located on a left side of the virtual central lane as seen from the mobile object in an image captured by an external camera configured to perform an imaging process in a movement direction of the mobile object and recognize whether the mobile object is moving on the roadway or in the predetermined region on the basis of results of performing spatial classification processes for the virtual central lane, the virtual right lane, and the virtual left lane and a control unit configured to limit a speed of a case where the mobile object moves on the roadway to a first speed and limit a speed of a case where the mobile object moves in the predetermined region to a second speed lower than the first speed.

The invention belongs to the field of data processing, and discloses a city update blue-green space dynamic monitoring method based on deep learning, and the method comprises the steps: obtaining a high-resolution remote sensing image, and carrying out the preprocessing of the image, and obtaining the preprocessed image data; the method comprises the following steps: determining a UNetMama model, and carrying out improvement by adopting a ResTv2 backbone network and an ECA attention mechanism to obtain an improved UNetMama model; determining a preset data set, and performing model training and model optimization on the improved UNetMama model according to the preset data set to obtain a blue-green space classification model; inputting the preprocessed image data into a blue-green space classification model, and outputting a blue-green space classification result; and performing post-processing and space transfer metering analysis on a blue-green space classification result to obtain a blue-green space distribution diagram and a blue-green space conversion mulberry-based diagram. The method can effectively improve the recognition precision of the blue-green space, and further effectively reveals the evolvement rule of the ecological space.

The application discloses a kind of based on the cultivated land ecological safety comprehensive evaluation method and system of multi-model coupling, which comprises: setting the future multi-source data set of the cultivated land to be evaluated in future time period;Using the grid calculator in ArcGIS software, the grid division is carried out on the cultivated land to be evaluated, a plurality of grid regions are obtained, and the future multi-source data set is divided into grid based on the plurality of grid regions, to obtain the future multi-source sub-data set of each grid region;Using the multi-ecological safety comprehensive evaluation function quantity model that has been constructed, spatial classification method and the ecological safety comprehensive evaluation index calculation formula that is constructed, the future multi-source sub-data set of each grid region is predicted, to obtain the ecological safety comprehensive evaluation index corresponding to each grid region.The application simulates the ecological function of the cultivated land to be evaluated under future scenario by coupling multi-ecological safety comprehensive evaluation function quantity model, to realize the system evaluation of cultivated land ecological function of the cultivated land to be evaluated under future scenario.

The application discloses a landslide susceptibility comprehensive evaluation method, system, device, medium and product, relates to the technical field of geological disaster prediction, and the method comprises the steps: taking the SBAS-InSAR deformation rate as a dynamic deformation factor, combining a static environmental factor, and constructing an original feature dataset; adopting a recursive feature elimination algorithm, performing importance sorting and iterative elimination on evaluation factors in the original feature dataset, determining an optimal feature subset, training an RFE-RF-XGBoost cascade integrated model; inputting the optimal feature subset corresponding to all grid units in the research area into the trained RFE-RF-XGBoost cascade integrated model, determining a landslide susceptibility spatial classification map, verifying and locally correcting different risk level regions divided in the landslide susceptibility spatial classification map, and determining a landslide susceptibility evaluation result, so that the timeliness and accuracy of the landslide susceptibility evaluation result are improved.

The invention discloses a carbon emission intensity prediction simulation and land utilization management and control method and system, and belongs to the technical field of carbon emission calculation prediction.The method comprises the steps that firstly, multi-source space and statistical data are integrated to establish a basic database, and the carbon emission intensity of all kinds of space is calculated according to land space classification; then, constructing an extended STIRPAT model to screen a core driving factor, and constructing a feature project containing residual, lag and trend features based on the output of the extended STIRPAT model; training an XGBoost machine learning model by adopting a Bayesian optimization algorithm so as to capture a complex nonlinear relationship between the carbon emission intensity and the influence factors; and finally, inputting future scene feature data, generating a territorial space carbon emission intensity distribution map in combination with a PLUS model, and identifying a high-emission hot spot region. According to the method, the problem that the technical progress influence is difficult to quantify and the spatial explicit prediction is difficult to carry out in the prior art is solved, the prediction precision is remarkably improved, and a scientific basis and decision support are provided for regional territorial space planning and low-carbon management and control.

The invention discloses a campus carbon emission prediction and dynamic regulation and control method. The method comprises the steps of data acquisition and preprocessing, feature engineering, static modeling, time sequence prediction, dynamic regulation and control and feedback optimization. The method comprises the following steps: collecting multi-source heterogeneous data such as campus personnel density, equipment use, space classification and meteorology, constructing a regional carbon emission intensity function by using an XGBoost regression model, and capturing a static nonlinear relationship; and learning a historical carbon emission sequence by using an LSTM network, predicting the carbon emission trend in the next 24 hours, and identifying peaks and anomalies. And on the basis of comparison between the prediction result and a threshold value, differential regulation and control strategies for the teaching area, the dormitory area and the canteen area are generated, and equipment control and personnel behavior guidance are executed through the BAS system and the mobile terminal. On-line learning is carried out by using actually measured data and prediction deviation, model parameters are optimized, and a prediction-regulation-feedback closed loop is formed. According to the method, aiming at campus functional area heterogeneity and personnel flow characteristics, high-precision prediction and active intervention are realized, the carbon emission peak value is reduced, the energy efficiency is improved, and sustainable development is supported.

This invention relates to the field of urban planning technology, and more particularly to a historical and cultural-oriented spatial classification and regeneration method and system. The method includes the following steps: acquiring historical and cultural data, and performing multimodal perception on the historical and cultural data to obtain historical and cultural spatial data; extracting deep features from the historical and cultural spatial data to obtain historical and cultural element data; constructing a spatial semantic map from the historical and cultural element data to obtain spatial semantic map data; classifying the spatial semantic map data according to its chronological evolution trajectory to obtain historical and cultural spatial classification data; generating spatial regeneration data based on the historical and cultural spatial classification data to obtain spatial regeneration data; acquiring urban planning demand data, and integrating the urban planning demand data and the spatial regeneration data to obtain integrated spatial regeneration data. This invention combines urban planning with spatial regeneration, effectively achieving a dynamic balance between historical and cultural preservation and modern urban development.

The invention provides an urban rail transit intersection optimization method and device and electronic equipment, and the method comprises the steps: employing a K-means clustering algorithm to carry out the spatial classification of construction environment factors of rail transit line stations, and recognizing the types of stations with different functional features; based on the space classification result of the built environment, a random forest algorithm is adopted to construct a passenger flow prediction model fusing multi-dimensional built environment elements, and the passenger flow volume of the rail transit stations along the line is predicted to obtain a passenger flow prediction result; based on the space classification result and the passenger flow prediction result, constructing a large and small intersection multi-target optimization model fusing the built-up environment factors; and solving the large and small intersection multi-target optimization model by combining a multi-target genetic algorithm to obtain a target optimization scheme of the rail transit. According to the invention, a conversion mechanism from space cognition to operation decision is established, and the problem of poor route optimization effect of urban rail transit in the prior art is solved.

This invention belongs to the field of data processing and discloses a deep learning-based method for dynamic monitoring of blue-green space in urban renewal. The method includes: acquiring high-resolution remote sensing images and preprocessing them to obtain preprocessed image data; determining a UNetMamba model and improving it using a ResTv2 backbone network and ECA attention mechanism to obtain an improved UNetMamba model; determining a preset dataset and training and optimizing the improved UNetMamba model based on the preset dataset to obtain a blue-green space classification model; inputting the preprocessed image data into the blue-green space classification model and outputting the blue-green space classification results; and performing post-processing and spatial transfer econometric analysis on the blue-green space classification results to obtain a blue-green space distribution map and a blue-green space transformation Sankey diagram. This invention can effectively improve the identification accuracy of blue-green space, thereby effectively revealing the evolutionary patterns of ecological space.

The present invention discloses a small-sample cross-domain hyperspectral image classification method based on contrastive learning and subspace, which mainly solves the problems of low utilization rate of embedded feature information, high training cost and low accuracy in conventional methods. The solution includes: obtaining a hyperspectral data set, dividing the source domain and target domain to obtain a training set and a test set; constructing a mapping layer and a feature extractor, using them to extract the embedded features of the source domain and target domain respectively for subspace classification and contrastive learning; constructing a domain discriminator, calculating the total loss of domain discrimination loss, spatial loss and contrast loss of the source domain and target domain; using the training set to iteratively train the feature extractor through backpropagation until the total loss function converges; inputting the test set into the trained feature extractor to obtain the classification result. The present invention improves the discrimination ability and classification accuracy of the classifier, improves the utilization rate of embedded feature information, reduces training cost, and can be used for land feature classification in resource exploration, forest cover and disaster monitoring.

The present specification relates to the field of oil and gas field exploration and development, and relates to a position coding determination method and a geological feature prediction method based on a well logging evaluation large model, the method comprising: identifying a to-be-coded geographical region according to a preset spatial classification rule, and determining a spatial range type to which the to-be-coded geographical region belongs; if the spatial range type is a first spatial range, determining a longitude weight coefficient and a latitude weight coefficient in the first spatial range according to the maximum longitude and latitude and the minimum longitude and latitude in the first spatial range, wherein the first spatial range is a defined spatial range; and calculating the position coding of each point in the first spatial range according to the longitude weight coefficient and the latitude weight coefficient. The present scheme comprehensively considers the elements of geological statistics, and position codes the position information of space, so that the large model based on the oil and gas industry can better consider the spatial correlation of geological information during pre-training, and effectively improve the precision of the oil and gas large model.

The invention relates to the technical field of data processing, and particularly discloses an AI-based air quality prediction method and system, and the method comprises the steps: S1, dividing a preset region into independent grids of a preset size, and setting the information of each grid; s2, extracting influence factors of grid air quality, wherein the influence factors comprise influence factors of spatial change and influence factors of time change; s3, constructing a space classifier based on an artificial neural network algorithm, and capturing the influence of space factors on the air quality; constructing a time classifier based on a convolution LSTM algorithm, and learning time periodic features in the time sequence data; and S4, through a collaborative algorithm, according to results of the space classifier and the time classifier, obtaining gridding air quality data with a time sequence. By adopting the technical scheme of the invention, the air quality prediction accuracy of mountainous regions and river valley cities can be effectively improved.

The invention discloses a topographic relief degree calculation method for hot spring distribution analysis, and the method comprises the steps: determining a target hot spring, obtaining the elevation of a hot spring exposure position in a research area, and collecting a target hot spring water sample for the indoor test analysis of isotopes; obtaining the hydrogen and oxygen stable isotope content of the target hot spring water sample, and inversely calculating the elevation of the supply area according to the elevation effect regression equation; the topographic relief degree of the hot spring is defined, and the topographic relief degree value of the target hot spring is calculated; carrying out statistics on values of all target hot springs in the research area, and dividing the values into low, middle and high classes according to triparties; and a calculation result is integrated with a digital elevation model (DEM) and geological and hydrological maps, so that spatial visualization of the topographic relief degree of the hot spring is realized, and control factors of hot spring distribution are analyzed. According to the method, the relevance between the hot spring and the terrain is quantified, the spatial classification of hot spring distribution and the visual expression of the underground water flowing mode are realized, and a scientific basis is provided for geothermal resource evaluation, underground water flowing mode analysis and hot spring cause research.

The invention relates to the technical field of data processing, and discloses a touch operation accurate identification method and system of a smart bracelet, and the core of the method is to collect capacitance, motion sensing and pressure multi-dimensional data of a bracelet touch screen, establish an analysis time window, extract features of each dimension and complete timestamp alignment and normalization. Constructing a multi-modal feature vector; a time sequence causal judgment result is output through causal test, a joint judgment space is constructed to obtain a space classification judgment result, and a dynamic threshold judgment result is output in combination with a motion intensity dynamic threshold value; and finally, integrating three types of results based on a Bayesian decision theory, outputting a final recognition result, collecting feedback data to optimize model parameters, updating a sample library, and forming a closed-loop recognition mechanism. According to the method, true and false touch control is effectively defined through multi-modal data processing and multi-dimensional judgment, the recognition precision is continuously improved through closed-loop optimization, misoperation is reduced, and the reliability of the intelligent bracelet touch control system is greatly enhanced.

The invention provides a high-resolution city green space classification method and device based on double decoders and a fine segmentation head, equipment and a medium, and relates to the technical field of image classification. The method comprises the following steps: acquiring a high-resolution satellite remote sensing image; preprocessing the satellite remote sensing image to obtain an image training sample and an image test sample; inputting an image test sample into the trained green space classification neural network for processing, and determining a green space classification result; wherein the green space classification neural network is obtained by training the image training sample. According to the embodiment of the invention, the defect of low accuracy of the traditional image classification technology and the deep learning network image classification at the present stage in the prior art is overcome, and large-scale high-resolution satellite city image data can be quickly processed through a classification algorithm for capturing local and global information at the same time; urban green space images are automatically classified in a high-precision mode, and the precision and efficiency of green space classification are remarkably improved.

This invention discloses a blue-green infrastructure mapping and classification method and related apparatus, relating to the field of computer technology. The method includes: generating a new reservoir layer and a first residual water body layer based on original water body layer data, water patch layer data, and point-of-interest layer data; generating a new river layer and a second residual water body layer based on the first residual water body layer and water patch layer data; generating a new lake layer and a new pond layer based on the second residual water body layer and multi-element patch layer data; generating a blue-green space layer based on land cover raster layer data and the above layers; performing land cover type area ratio analysis based on the blue-green space layer using field statistics; performing primary classification using the BGI classification framework based on the land cover type area ratio information; and performing blue-green space classification based on the primary classification results using the BGI classification framework. This invention improves the completeness and feasibility of BGI mapping and classification.

The present application is applicable to the field of image processing technology and provides a multispectral image generation method, terminal device, and computer-readable storage medium, including: acquiring a detection image; performing spatial classification based on the spectral similarity of the detection image to determine similar regions; reconstructing a reconstructed multispectral curve for the similar region based on the detection average value of the similar region; and correcting the reconstructed multispectral curve based on the reconstructed multispectral curve of the similar region and the detection image to obtain a target multispectral image of the similar region. By determining similar regions in the detection image and reconstructing the similar regions once to obtain the reconstructed multispectral curve corresponding to the similar regions, the amount of calculation can be effectively reduced. Then, the reconstructed multispectral curve is corrected based on the detection image, effectively improving the accuracy of the generated multispectral image.

This paper proposes a hyperspectral image classification method based on a state-space model, which primarily addresses the poor classification accuracy of existing methods. The solution includes: 1) inputting a hyperspectral image and preprocessing it; 2) using a neighborhood spectral fusion method to eliminate spectral variability, and then using a subspectral scanning method to perceive differences in spectral details and obtain image spectral classification information; 3) constructing a spatial feature extraction network using an SS2D layer, an improved spatial attention mechanism, and multiple residual blocks, and using this network to obtain spatial classification information for the hyperspectral image; 4) obtaining the final classification result by fusing spatial and spectral classification information at the decision layer. This method can reduce the impact of spectral variability within a relatively small range, not neglecting local spectral information while being able to perceive comprehensive spectral information, and simultaneously combining spatial information to effectively improve the classification of hyperspectral images.

The invention provides a photovoltaic power station space classification method and system based on secondary clustering, and the method comprises the steps: obtaining the theoretical power of each photovoltaic power station based on the actual power of each photovoltaic power station and the actual power of a sample machine; based on the theoretical power and installed capacity of each photovoltaic power station, obtaining the maximum clearness index of each photovoltaic power station, and clustering each photovoltaic power station into a plurality of weather categories by using the maximum clearness index; for the photovoltaic power stations in each weather category, performing secondary clustering based on the difference between the theoretical power and the actual power to obtain a final clustering result of the photovoltaic power stations; the weather category to which the photovoltaic power station belongs is determined through the maximum clearness index, and secondary clustering is carried out by using the difference between the theoretical power and the actual power, so that the classification result is more accurate; the classification result can provide a basis for regional level power prediction modeling, a regional level power prediction model is simplified, input data is reduced, and model calculation efficiency is improved.

The application provides a mining area disturbance space identification method, system, computer device and medium, and belongs to the image recognition field, comprising: acquiring remote sensing images of a mining area; performing feature extraction on the remote sensing images to obtain a plurality of coding feature maps of different scales; performing weighted fusion on the plurality of coding feature maps of different scales to obtain a multi-scale fusion feature map; calculating edge gradients of the remote sensing images and the multi-scale fusion feature map respectively, and fusing to obtain a normalized edge feature map; determining an edge attention weight according to the normalized edge feature map, and performing weighted fusion on the edge attention weight and the coding feature map of the corresponding scale to obtain an edge guided feature map; and performing resolution reconstruction on the edge guided feature map to obtain a disturbance space classification image of the mining area. The method improves the accuracy of the mining area disturbance space identification, and meets the fine identification requirement of the disturbance space.

The invention relates to a simplified polarimetric SAR ship refined interpretation method and system based on joint feature space construction. The method comprises the following steps: receiving compact polarization data in a compact polarimetric SAR system through a linear polarization mode and carrying out protocol processing to obtain uniformly represented compact polarization data; extracting polarization characteristic parameters, and constructing a classification joint characteristic space; sVR is introduced to carry out dynamic self-adaptive adjustment on a boundary threshold value of surface scattering and volume scattering, and a combined feature space classification plane after self-adaptive adjustment is used to carry out initial classification on ship targets; and performing iterative clustering on the scattering mechanism by using a GHPSS-Wishart classifier to obtain a refined interpretation result of the ship target. The main work of the simplified polarimetric SAR data is to interpret the structure scattering mechanism of a ship target, fine interpretation can be carried out on different types of ship targets, the type of a ship to which the ship targets belong can be judged through an interpreted image, and the interpretation degree of the ship structure is improved.

In order to solve the technical problem that traditional soil material partitioning methods are difficult to fully express the spatial distribution regularity characteristics of soil materials during spatial partitioning, an embodiment of the present invention provides a spatial classification and partitioning method and system for soil materials, including: establishing a soil material geological reservoir grid model based on soil material exploration test data; judging whether the soil material exploration test data in the grids of the soil material geological reservoir grid model meet the soil material quality technical indicators, and assigning values ​​to each grid in the soil material geological reservoir grid model according to the judgment result to obtain a first assigned soil material model; dividing each grid that meets the soil material quality technical indicators in the first assigned soil material model into several stratigraphic partitions and selecting useful layers from the several stratigraphic partitions; reclassifying each useful layer to obtain a useful layer area; analyzing the spatial position and volume proportion of the spatial classification area in the useful layer area according to the stratigraphic geological characteristics, generalizing the useful layer area, and obtaining the spatial classification and partitioning of soil materials.

The invention discloses a multi-source data-based cultivated land ecological safety comprehensive evaluation method and system. The method comprises the steps of obtaining a historical multi-source data set of a cultivated land to be evaluated in a historical time period; performing grid division on the cultivated land to be evaluated by adopting a grid calculator in ArcGIS software to obtain a plurality of grid regions; performing grid division on the historical multi-source data set based on the plurality of grid regions to obtain a multi-source sub-data set of each grid region; and calculating the multi-source sub-data set of each grid region by adopting an ecological safety comprehensive evaluation function quantity calculation formula set, a space classification method and a constructed ecological safety comprehensive evaluation index calculation formula to obtain an ecological safety comprehensive evaluation index corresponding to each grid region. Through multiple ecological safety comprehensive evaluation functions, ecological safety comprehensive evaluation is performed on the cultivated land, the cultivated land evaluation dimension can be expanded, the evaluation precision can be improved, and the problem that the current industry is lack of a cultivated land ecological safety comprehensive evaluation method is solved.

The present invention discloses a transformer fault diagnosis method and system based on the optimization of sensitive fields reconstructed by photoacoustic signals. Specifically, the method comprises the following steps: first, obtaining a multivariate sequence matrix of signals by monitoring photoacoustic signals of multiple gases in transformer oil samples; second, mapping the multivariate sequence matrix in the form of scattered points in a polar coordinate diagram by the idea of reconstructing sensitive fields; then extracting shallow local features, and clustering the features into multiple mutually exclusive categories, with the center of each category as a visual representation factor to form a visual feature table; finally, realizing the classification of transformer fault diagnosis based on an improved autonomous learning multi-space (ALMMo‑0) classifier. The method of the present invention reconstructs the multivariate photoacoustic signal reflecting the gas concentration into a sensitive field rather than in the form of a concentration threshold or ratio, so as to better reveal the diagnostic features hidden in the signal, and realize deep feature extraction and encoding of the image at the same time, thereby improving the transparency and interpretability of the model, and automatically updating the model parameters by data-driven without the need for manual adjustment of hyperparameters. The method is of great significance for improving the accuracy and practicality of transformer fault diagnosis.

Examples of generating a map for an indoor space are described. In one example, a raw digital representation of the indoor space is obtained and preprocessed by at least one of marking a region-of-interest (ROI) in the raw digital representation and classifying the indoor space into a space-category to obtain a preprocessed representation. Using the preprocessed representation, a skeletal map is generated including indicators to identify elements of the indoor space. Revision inputs are received to modify an erroneous indicator from amongst the multiple indicators. The erroneous indicator is revised to a modified indicator and the modified indicator and unmodified indicators are used to create a modified skeletal map which is usable for localizing a mobile device in the indoor space.

The invention provides an intelligent multi-scale sea-land-air-space global expression method based on a Columbus view, relates to the technical field of geospatial visualization, and realizes unified expression of complex multi-target spatial data through the steps of spatial classification, height conversion and height optimization. According to the method, the spatial height of the earth satellite is divided into user-defined intervals which can be defined by a user, and clear distribution of the multi-target height in the view is achieved by combining the mapping relation and proportional adjustment. In the final rendering process, the target subjected to height processing is fused into a Columbus view in a pseudo three-dimensional mode, the two-dimensional tiling characteristic is reserved, and the space understanding ability is improved. The method is suitable for task planning, remote sensing analysis and military monitoring in a complex multi-target scene, and has the remarkable characteristics of high flexibility, clear expression and strong expansibility.