Geographic information surveying and mapping system based on remote sensing image

Abstract

The invention relates to the technical field of remote sensing images, in particular to a geographic information surveying and mapping system based on remote sensing images, which comprises a first remote sensing image acquisition module for acquiring first-level geographic information; the ground feature marking module processes the first-level geographic information and identifies and marks ground feature features; the map drawing module calculates a danger degree index and an importance index and draws a danger distribution map and an importance map; the safe area site selection module selects an optimal safe area and establishes a rescue site; the unmanned aerial vehicle path planning module plans an optimal path according to node positions, node weights and inter-node distances; the second remote sensing image acquisition module acquires and processes a remote sensing image by using the unmanned aerial vehicle to obtain second-level geographic information; the cloud computing module obtains and processes the geographic information to obtain a geographic information surveying and mapping map; and the geographic information display module displays the geographic information surveying and mapping map. According to the invention, accurate geographic information is mapped for rescue and reconstruction of post-disaster mountainous areas through multi-source satellite remote sensing images and unmanned aerial vehicle remote sensing images.

Description

Technical Field

[0001] The present invention relates to the technical field of remote sensing images, and in particular to a geographic information surveying and mapping system based on remote sensing images. Background Art

[0002] Remote sensing technology obtains information about the earth's surface through long-distance sensors, while geographic information surveying and mapping generates geospatial data through on-site measurement and data processing. The geographic information surveying and mapping system based on remote sensing images combines the advantages of both and can efficiently obtain, process and analyze geospatial data, providing important decision-making and support for reconstruction and rescue after natural disasters.

[0003] In the prior art, for the study of geographic information mapping of natural disasters, for example, the Chinese patent with publication number CN113283802B provides a method for assessing the risk of landslides in complex and dangerous mountainous areas. This method integrates the index factors of various influencing factors through geographic spatial information technology and probability statistical models, calculates the probability of landslide geological action, and finally uses the prediction accuracy curve to test the prediction accuracy of the landslide risk assessment results, which can intuitively reflect the degree of risk of landslide geological disasters in complex and dangerous mountainous areas. The Chinese patent with publication number CN118135408B provides a multi-dimensional survey integrated method, system and medium for geological disasters in mountainous towns. This method obtains remote sensing images, establishes a three-dimensional image model of the geological disaster body and identifies the initial geological disaster body based on the three-dimensional image model; based on the area of ​​the initial geological disaster body, the regional attributes of the current initial geological disaster body are confirmed. The above method integrates the remote sensing sampling and data analysis, and comprehensively considers the frequency of geological survey through the analysis of the geological environment. A Chinese patent with publication number CN116597320A provides a spatiotemporal prediction method for landslide geological disasters suitable for complex mountainous areas. The method first obtains satellite remote sensing images of a large monitoring area, then uses differential interferometry D-InSAR technology to pre-process the remote sensing images of the monitoring area, and then uses image recognition technology to identify landslide risk characteristics in the remote sensing images of the monitoring area to find out the landslide risk areas; after delineating the landslide risk areas in complex mountainous areas, online monitoring of the landslide risk areas is carried out.

[0004] The above patent has certain advantages in geographic information mapping of natural disasters. However, after a natural disaster occurs, geological surveys become more difficult. The terrain in mountainous areas usually contains a variety of dangerous disasters such as landslides, mudslides and fault zones. Satellite remote sensing has difficulty in obtaining clear image data and cannot provide accurate disaster information in a timely manner. Geographic information mapping based on remote sensing images still faces many difficulties and challenges in promoting post-disaster rescue and reconstruction.

[0005] Therefore, a geographic information mapping system based on remote sensing images is proposed. Summary of the invention

[0006] The purpose of the present invention is to provide a geographic information mapping system based on remote sensing images. Through multi-source satellite remote sensing images and unmanned aerial vehicle remote sensing images, a geographic information mapping system with multi-layer display is established, which automatically identifies and marks the features of land objects, draws importance maps and danger distribution maps for post-disaster mountainous areas, designs a safe area site selection module to select the best safe area, uses unmanned aerial vehicle remote sensing images to make up for the lack of accuracy of satellite remote sensing images, and maps accurate geographic information for rescue and reconstruction in post-disaster mountainous areas.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A geographic information surveying and mapping system based on remote sensing images, comprising:

[0009] The first remote sensing image acquisition module is used to acquire and process remote sensing images of post-disaster mountainous areas collected by multi-source satellites to obtain primary geographic information;

[0010] Furthermore, the first remote sensing image acquisition module acquires the remote sensing images of the post-disaster mountainous area acquired by the multi-source satellites, wherein the remote sensing images of the post-disaster mountainous area acquired by the multi-source satellites include different resolutions and bands;

[0011] Performing radiometric calibration, radiometric correction and geometric correction on the post-disaster mountainous area remote sensing images collected by the multi-source satellites to obtain corrected multi-source images;

[0012] The corrected multi-source images are fused through an image registration algorithm to obtain the primary geographic information, and the primary geographic information is uploaded to the cloud computing module.

[0013] A ground object marking module is used to obtain and process the primary geographic information to obtain a first sub-image; classify the first sub-image to obtain ground objects, and mark ground object features of the ground objects;

[0014] Further, the first-level geographic information is segmented to obtain the first sub-image; the first sub-image includes first-level features, second-level features and third-level features, the first-level features include: landslide area, debris flow, barrier lake and fault zone, the second-level features include buildings, roads and bridges, and the third-level features include rivers and vegetation;

[0015] Extracting the features of the first sub-image to obtain a classification feature vector; the classification feature vector includes: soil features, flow texture features, spectral reflectance features, elevation mutation features, geometric shape features and pixel uniformity features;

[0016] The calculation formula of the soil characteristics is:

[0017]

[0018] Where A represents the soil characteristics, χ1 represents the spectral weight coefficient, SW represents the reflectivity of the short-wave infrared band, NI represents the reflectivity of the near-infrared band, χ2 represents the area weight coefficient, S A represents the soil area, S represents the total area of ​​the object, χ3 represents the color weight coefficient, R represents the reflectivity of the red band, G represents the reflectivity of the green band, and B represents the reflectivity of the blue band;

[0019] The calculation formula for the local directional gradient change of the flow texture feature is:

[0020]

[0021] Wherein, T represents the flow texture feature, I x (a, b) represents the horizontal gradient of the ground object sub-image at point (a, b), I y (a, b) represents the vertical gradient of the ground object sub-image at point (a, b), n represents the number of rows, and m represents the number of columns;

[0022] The calculation formula of the elevation mutation feature is:

[0023]

[0024] Wherein, C represents the elevation mutation feature, H represents the elevation, represents the gradient of the elevation in the horizontal direction, Indicates the gradient of the elevation in the vertical direction;

[0025] The calculation formula of the pixel uniformity feature is:

[0026]

[0027] Wherein, Q represents the uniform characteristic of the pixel, N represents the total number of pixels, μ represents the average gray value, and I(c) represents the gray value of the c-th pixel;

[0028] Using a support vector machine algorithm to classify the first sub-image to obtain the ground object;

[0029] marking the features of the features;

[0030] The ground feature is uploaded to the cloud computing module.

[0031] A map drawing module, used to obtain the above-mentioned ground feature, calculate the danger level index and draw a danger distribution map; calculate the importance index and draw an importance map;

[0032] Furthermore, the calculation formula of the importance index is:

[0033]

[0034] Among them, I i represents the importance index of the i-th feature, L e () represents an important function, α e Indicates e The weight coefficient, s e represents the e-th important feature of the i-th feature, and E represents the number of important features;

[0035] Drawing the importance map according to the importance index of the feature;

[0036] The calculation formula of the risk index is:

[0037]

[0038] Among them, D i represents the danger level index of the i-th feature, P g () represents the risk function, β g Indicates z g The weight coefficient, z g represents the g-th danger level feature of the i-th feature, and G represents the number of danger level features;

[0039] Draw the danger distribution map according to the danger level index of the ground feature;

[0040] The importance map and the hazard distribution map are uploaded to the cloud computing module.

[0041] The safe area site selection module is used to divide candidate safe areas in the mountainous area after the disaster and select the best safe area to establish a rescue site;

[0042] Further, dividing candidate safety areas according to the hazard distribution map;

[0043] The calculation formula of the site selection objective optimization function is:

[0044]

[0045] Where F represents the site selection target optimization function, γ1 represents I i The weight coefficient, I i represents the importance index of the i-th feature, γ2 represents D i The weight coefficient, D i represents the danger level index of the i-th feature, γ3 represents h i The weight coefficient, h irepresents the elevation of the i-th feature, S represents the location of the candidate safe area, K i represents the node of the i-th feature, dist() represents the distance between the candidate safety area and the i-th feature, γ4 represents M S The weight coefficient, M S represents the area of ​​the candidate safe area, γ5 represents H S The weight coefficient, H S Indicates the maximum height difference of the candidate safety area;

[0046] The formula for the first constraint is:

[0047] dist(S,K i )≥d min ;

[0048] Among them, d min Indicates the minimum distance between the position of the candidate safety area and the primary feature;

[0049] The formula for the second constraint is:

[0050] dist(S,K i )≤d max ;

[0051] Among them, d max Indicates the maximum distance between the candidate safety area and the secondary feature;

[0052] The formula for the third constraint is:

[0053] M S ≥m min ;

[0054] Among them, M S Represents the area of ​​the candidate safe area, m min Indicates the minimum area of ​​the safe area;

[0055] The formula for the fourth constraint is:

[0056] H S ≤h max ;

[0057] Among them, H S represents the maximum height difference of the candidate safety area, h max Indicates the maximum height difference of the safety area;

[0058] The genetic algorithm is used to solve the minimum value of the above objective optimization function and meet all constraints to select the best safety area S * , establish a rescue site.

[0059] The UAV path planning module is used to obtain the ground object, calculate the nodes, node weights and inter-node distances of the ground object, and plan the optimal path according to the nodes, the node weights and the inter-node distances;

[0060] Furthermore, the UAV path planning module includes:

[0061] Calculate the geometric center of the feature to obtain the node;

[0062] The calculation formula of node weight is:

[0063] W i =exp(ω1·f(S i )+ω2·f(I i )+ω3·f(h i )+ω4·f(D i ));

[0064] Among them, W i represents the weight of the i-th node, ω1 represents S i The weight coefficient, S i represents the area of ​​the i-th feature, ω2 represents I i The weight coefficient, I i represents the importance index of the i-th feature, ω3 represents h i The weight coefficient, h i represents the elevation of the i-th feature, ω4 represents D i The weight coefficient, D i represents the danger level index of the i-th feature, and f represents a normalization function;

[0065] ω1, ω2, ω3 and ω4 satisfy ω1+ω2+ω3+ω4=1;

[0066] The calculation formula of comprehensive weight is:

[0067]

[0068] Among them, C pq represents the comprehensive weight, d pq represents the distance between node p and node q, W p represents the weight of the pth node, W q represents the qth node weight, θ represents the adjustment coefficient, which is used to balance the distance between the nodes and the influence of the node weight on the comprehensive weight;

[0069] The optimal path is solved by using the Dijkstra algorithm in combination with the comprehensive weight.

[0070] A second remote sensing image acquisition module is used to obtain the optimal path of the UAV path planning module, collect and process the remote sensing images of the post-disaster mountainous area according to the optimal path, and obtain secondary geographic information;

[0071] Furthermore, the second remote sensing image acquisition module obtains the optimal path of the path planning module, and the UAV traverses the nodes and collects and processes remote sensing images according to the optimal path to obtain the secondary geographic information; and uploads the secondary geographic information to the cloud computing module.

[0072] A cloud computing module is used to obtain and process the features of the land object, the hazard distribution map, the importance map, the optimal safety area, the node, the shortest path, the primary geographic information and the secondary geographic information to obtain a geographic information surveying and mapping map;

[0073] Furthermore, the cloud computing module includes:

[0074] A first layer unit, used to store the primary geographic information, the land feature and the secondary geographic information node;

[0075] A second layer unit, used for storing the danger level index and the danger distribution map;

[0076] A third layer unit, used for storing the importance index and the importance map;

[0077] A fourth layer unit, used for storing the positions of the candidate safety area and the optimal safety area;

[0078] A fifth layer unit, used for storing the optimal path;

[0079] The sixth layer unit is used to store the secondary geographic information.

[0080] The geographic information display module is used to display the geographic information surveying and mapping map.

[0081] Furthermore, the geographic information display module includes:

[0082] A first layer display unit is used to receive a click signal from a user, and after receiving the click signal, display the primary geographic information, the land feature and the secondary geographic information node stored in the first layer unit of the cloud computing module;

[0083] A second layer display unit is used to receive the click signal of the user, and display the danger level index and the danger distribution map stored in the second layer unit of the cloud computing module after receiving the click signal;

[0084] a third layer display unit, configured to receive the click signal of the user, and display the importance index and the importance map stored in the third layer unit of the cloud computing module after receiving the click signal;

[0085] a fourth layer display unit, configured to receive the click signal of the user, and display the positions of the candidate safety area and the optimal safety area stored in the fourth layer unit of the cloud computing module after receiving the click signal;

[0086] The fifth layer display unit is used to receive the user's click signal, and display the optimal path stored in the fifth layer unit of the cloud computing module after receiving the click signal.

[0087] Furthermore, the secondary geographic information node is used to receive a click signal from a user, and after receiving the click signal, displays the secondary geographic information stored in the sixth layer unit of the cloud computing module.

[0088] Compared with the prior art, the present invention has the following beneficial effects:

[0089] 1. Fully extract the features of the terrain in the post-disaster mountainous area, including: soil features provide information on surface material composition, color and area, flow texture features provide flow traces of flowing water or debris flow, elevation mutation features are conducive to identifying significant changes in terrain, combined with spectral reflectance features, geometric shape features and pixel uniformity features; construct a classification feature vector, and conduct a multi-dimensional comprehensive analysis of the terrain by combining different types of features to enhance the reliability and accuracy of classification, effectively make up for the shortcomings of a single feature, and improve the accuracy of terrain recognition.

[0090] 2. By calculating the importance index of features by considering factors such as population density and traffic convenience, and drawing importance maps, users can be helped to identify and prioritize important areas and optimize resource allocation; by calculating the danger level of features by considering factors such as feature type, area and elevation, and drawing danger distribution maps, high-risk areas can be visually displayed to help users formulate disaster prevention and mitigation measures and shelter site selection; through the design of importance maps and danger distribution maps, more comprehensive and detailed information on features is provided, which is conducive to rescue and reconstruction in mountainous areas after disasters.

[0091] 3. The design of the safe area site selection model can accurately identify and select low-risk safe areas by comprehensively considering the characteristics of the terrain, the degree of danger, the degree of importance, the terrain and the convenience of transportation, so as to provide reliable shelters for the victims; combining the characteristics of the terrain and the convenience of transportation, scientifically plan the rescue routes to ensure that rescue personnel and materials can reach the disaster-stricken areas quickly and safely, and improve the speed and effectiveness of emergency response; as the disaster situation changes, the model can provide real-time updated data to help decision makers dynamically adjust the rescue and recovery plans and improve the flexibility and effectiveness of emergency response.

[0092] 4. First, use satellite remote sensing images to quickly present the specific situation of the mountainous area after the disaster, and then use the information provided by satellite remote sensing images to plan the UAV path. The UAV path planning takes into account the distance, elevation, position, importance index, danger index and other influencing factors of the ground objects, and plans the optimal UAV information collection path, which can not only quickly collect important information, but also ensure the endurance of the UAV; using the high accuracy of UAV remote sensing, the second geographic information is set as the sub-information of the first geographic information through the cloud computing module, and the details of the ground objects are presented through the nodes of the display module, which makes up for the lack of accuracy of satellite remote sensing and is conducive to the rescue and reconstruction of the mountainous areas after the disaster. BRIEF DESCRIPTION OF THE DRAWINGS

[0093] Figure 1 A schematic diagram of the structure of a geographic information surveying and mapping system based on remote sensing images provided in Example 1 of the present invention;

[0094] Figure 2 A schematic diagram of the structure of a geographic information display module provided in Example 1 of the present invention;

[0095] Figure 3 A schematic diagram of a second layer display unit provided in Embodiment 1 of the present invention;

[0096] Figure 4 A schematic diagram of a secondary geographic information node provided in Embodiment 1 of the present invention displaying secondary geographic information after receiving a click signal. DETAILED DESCRIPTION

[0097] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0098] Example 1

[0099] like Figure 1The figure shows a schematic diagram of the structure of a geographic information mapping system based on remote sensing images provided by the present invention, which is applied in a post-disaster mountain rescue in a certain southwestern province, and includes:

[0100] The first remote sensing image acquisition module is used to acquire and process remote sensing images of post-disaster mountainous areas collected by multi-source satellites to obtain primary geographic information;

[0101] Furthermore, the first remote sensing image acquisition module acquires the remote sensing images of the post-disaster mountainous area acquired by the multi-source satellites, wherein the remote sensing images of the post-disaster mountainous area acquired by the multi-source satellites include different resolutions and bands;

[0102] Performing radiometric calibration, radiometric correction and geometric correction on the post-disaster mountainous area remote sensing images collected by the multi-source satellites to obtain corrected multi-source images;

[0103] The corrected multi-source images are fused through an image registration algorithm to obtain the primary geographic information, which is then uploaded to the cloud computing module. Data correction eliminates image inconsistencies caused by sensor characteristics, observation conditions, and atmospheric conditions, eliminates geometric distortions caused by terrain, viewing angles, etc., and ensures the accuracy of the spatial position of the image; remote sensing images of different resolutions and bands can provide more information, and through fusion, can fully utilize the advantages of various types of data to provide more comprehensive and detailed geographic information.

[0104] A ground object marking module is used to obtain and process the primary geographic information to obtain a first sub-image; classify the first sub-image to obtain ground objects, and mark ground object features of the ground objects;

[0105] Further, the first-level geographic information is segmented to obtain the first sub-image; the first sub-image includes first-level features, second-level features and third-level features, the first-level features include: landslide area, debris flow, barrier lake and fault zone, the second-level features include buildings, roads and bridges, and the third-level features include rivers and vegetation;

[0106] Extracting the features of the first sub-image to obtain a classification feature vector; the classification feature vector includes: soil features, flow texture features, spectral reflectance features, elevation mutation features, geometric shape features and pixel uniformity features;

[0107] The calculation formula of the soil characteristics is:

[0108]

[0109] Where A represents the soil characteristics, χ1 represents the spectral weight coefficient, SW represents the reflectivity of the short-wave infrared band, NI represents the reflectivity of the near-infrared band, χ2 represents the area weight coefficient, S Arepresents the soil area, S represents the total area of ​​the object, χ3 represents the color weight coefficient, R represents the reflectivity of the red band, G represents the reflectivity of the green band, and B represents the reflectivity of the blue band;

[0110] The calculation formula for the local directional gradient change of the flow texture feature is:

[0111]

[0112] Wherein, T represents the flow texture feature, I x (a, b) represents the horizontal gradient of the ground object sub-image at point (a, b), I y (a, b) represents the vertical gradient of the ground object sub-image at point (a, b), n represents the number of rows, and m represents the number of columns;

[0113] The calculation formula of the elevation mutation feature is:

[0114]

[0115] Wherein, C represents the elevation mutation feature, H represents the elevation, represents the gradient of the elevation in the horizontal direction, Indicates the gradient of the elevation in the vertical direction;

[0116] The calculation formula of the pixel uniformity feature is:

[0117]

[0118] Wherein, Q represents the uniform characteristic of the pixel, N represents the total number of pixels, μ represents the average gray value, and I(c) represents the gray value of the c-th pixel;

[0119] Using a support vector machine algorithm to classify the first sub-image to obtain the ground object;

[0120] marking the features of the features;

[0121] The features of the land objects are uploaded to the cloud computing module. By introducing soil features, flow texture features and elevation mutation features, a comprehensive analysis of multiple features is performed to more accurately identify and mark various types of land objects; different marking colors and labels are assigned to different types of land objects, making the visualization of geographic information more intuitive and convenient for rapid identification and analysis.

[0122] A map drawing module, used to obtain the above-mentioned ground feature, calculate the danger level index and draw a danger distribution map; calculate the importance index and draw an importance map;

[0123] Furthermore, in the map drawing module, the importance index calculation formula is:

[0124]

[0125] Among them, I i Indicates the importance index of the i-th feature, L e () represents an important function, α e Indicates e The weight coefficient, s e represents the e-th important feature of the i-th feature, and E represents the number of important features;

[0126] Table 1. Land feature categories and their importance index

[0127] Feature Type Importance Index Landslide area exp(0.15) mudslide exp(0.13) Fault Zone exp(0.15) building exp(0.67) the way exp(0.45) bridge exp(0.49) river exp(0.30) vegetation exp(0.15)

[0128] For example, the importance of a building is calculated as:

[0129] I=exp(α1·norm(s1)+α2·norm(s2)+α3·norm(s3)+α4·norm(s4)+α5·norm(s5));

[0130] Among them, I represents the importance index of the building, α1 represents the weight coefficient of s1, s1 represents the population density, α2 represents the weight coefficient of s2, s2 represents the distance to transportation facilities, α3 represents the weight coefficient of s3, s3 represents the building area, α4 represents the weight coefficient of s4, s4 represents the use function of the building, α5 represents the weight coefficient of s5, s5 represents the historical and cultural value of the building;

[0131] After calculation, the types of features and their importance indexes in a post-disaster mountain rescue in a southwestern province are shown in Table 1;

[0132] The importance map is drawn according to the importance index of the feature.

[0133] The calculation formula of the danger level index is:

[0134]

[0135] Among them, D i represents the danger index of the i-th feature, P g () represents the risk function, β g Indicates z g The weight coefficient, z g represents the g-th danger level feature of the i-th feature, and G represents the number of danger level features;

[0136] For example, the calculation formula for the hazard index of a landslide area is:

[0137] D=exp(β1·norm(z1)+β2·norm(z2)+β3·norm(z3)+β4·norm(z4)+β5·norm(z5));

[0138] Where D is the landslide danger index, β1 is the weight coefficient of z1, z1 is the slope, β2 is the weight coefficient of z2, z2 is the soil moisture, β3 is the weight coefficient of z3, z3 is the landslide area, β4 is the weight coefficient of z4, z4 is the landslide elevation, β5 is the weight coefficient of z5, z5 is the distance between the landslide and the building;

[0139] After calculation, the types of features and their danger index in a post-disaster mountain rescue in a southwestern province are shown in Table 2;

[0140] The danger distribution map is drawn according to the danger level index of the ground feature.

[0141] The importance map and the danger distribution map are uploaded to the cloud computing module. By calculating the importance index and danger index of the features, and drawing the importance map and danger map, the importance and danger level of each feature are accurately evaluated and displayed, and detailed geographic information analysis is provided to improve the efficiency of emergency response and rescue.

[0142] Table 2. Land feature categories and their hazard index

[0143] Feature Type Danger level index Landslide area exp(0.60) mudslide exp(0.72) Fault Zone exp(0.63) building exp(0.47) the way exp(0.35) bridge exp(0.49) river exp(0.58) vegetation exp(0.37)

[0144] The safe area site selection module is used to divide candidate safe areas in the mountainous area after the disaster and select the best safe area to establish a rescue site;

[0145] Further, dividing candidate safety areas according to the hazard distribution map;

[0146] The calculation formula of the site selection objective optimization function is:

[0147]

[0148] Where F represents the site selection target optimization function, γ1 represents I i The weight coefficient, I i represents the importance index of the i-th feature, γ2 represents D i The weight coefficient, D i represents the danger level index of the i-th feature, γ3 represents h i The weight coefficient, h i represents the elevation of the i-th feature, S represents the location of the candidate safe area, K irepresents the node of the i-th feature, dist() represents the distance between the candidate safety area and the i-th feature, γ4 represents M S The weight coefficient, M S represents the area of ​​the candidate safe area, γ5 represents H S The weight coefficient, H S Indicates the maximum height difference of the candidate safety area;

[0149] The formula for the first constraint is:

[0150] dist(S,K i )≥d min ;

[0151] Among them, d min Indicates the minimum distance between the position of the candidate safety area and the primary feature;

[0152] The formula for the second constraint is:

[0153] dist(S,K i )≤d max ;

[0154] Among them, d max Indicates the maximum distance between the candidate safety area and the secondary feature;

[0155] The formula for the third constraint is:

[0156] M S ≥m min ;

[0157] Among them, M S Represents the area of ​​the candidate safe area, m min Indicates the minimum area of ​​the safe area;

[0158] The formula for the fourth constraint is:

[0159] H S ≤h max ;

[0160] Among them, H S represents the maximum height difference of the candidate safety area, h max Indicates the maximum height difference of the safety area;

[0161] The genetic algorithm is used to solve the minimum value of the above objective optimization function and meet all constraints to select the best safety area S *, establish rescue sites. The site selection target optimization function takes into account many factors such as the importance index of the features, the danger index, the elevation and the distance, and performs comprehensive optimization through weight parameters, avoiding high-risk areas while ensuring proximity to important features and transportation facilities, improving disaster resistance and emergency response capabilities, and ensuring that the selected safe areas meet the requirements in all aspects.

[0162] The UAV path planning module is used to obtain the ground object, calculate the nodes, node weights and inter-node distances of the ground object, and plan the optimal path according to the nodes, the node weights and the inter-node distances;

[0163] Furthermore, the UAV path planning module includes:

[0164] Calculate the geometric center of the feature to obtain the node;

[0165] The calculation formula of node weight is:

[0166] W i =exp(ω1·f(S i )+ω2·f(I i )+ω3·f(h i )+ω4·f(D i ));

[0167] Among them, W i represents the weight of the i-th node, ω1 represents S i The weight coefficient, S i represents the area of ​​the i-th feature, ω2 represents I i The weight coefficient, I i represents the importance index of the i-th feature, ω3 represents h i The weight coefficient, h i represents the elevation of the i-th feature, ω4 represents D i The weight coefficient, D i represents the danger level index of the i-th feature, and f represents a normalization function;

[0168] ω1, ω2, ω3 and ω4 satisfy ω1+ω2+ω3+ω4=1;

[0169] The calculation formula of comprehensive weight is:

[0170]

[0171] Among them, C pq represents the comprehensive weight, d pq represents the distance between node p and node q, W p represents the weight of the pth node, W qrepresents the qth node weight, θ represents the adjustment coefficient, which is used to balance the distance between the nodes and the influence of the node weight on the comprehensive weight;

[0172] Table 3. Node weights

[0173] node area Importance Index Elevation Danger level index Node Weight N1 6000 0.8 150 0.6 0.80 N2 5000 0.6 120 0.7 0.71 N3 5500 0.7 130 0.5 0.69

[0174] There are three nodes as shown in Table 3. After the calculation formula of the node weight, the node weights of nodes N1, N2 and N3 are 0.80, 0.71 and 0.69 respectively.

[0175] Table 4. Comprehensive weights

[0176] Node pair (i,j) distance Node weight i Node weight j Comprehensive weight (N1, N2) 200 0.80 0.71 150.45 (N1, N3) 250 0.80 0.69 200.50 (N2, N3) 150 0.71 0.69 125.35

[0177] The comprehensive weights are shown in Table 4. After calculating the comprehensive weights, the Dijkstra algorithm is used to solve the optimal path. The node weight calculation formula takes into account multiple factors such as area, importance index, elevation and danger index to ensure that the weight of each node is accurately reflected; by calculating the comprehensive weights, combined with the distance and weights between nodes, the path cost from one node to another can be more accurately evaluated, ensuring that the path planning is more accurate and reasonable, improving the efficiency and effectiveness of UAV mission execution, reducing energy consumption and time costs, and improving disaster resistance and emergency response capabilities.

[0178] A second remote sensing image acquisition module is used to obtain the optimal path of the UAV path planning module, collect and process the remote sensing images of the post-disaster mountainous area according to the optimal path, and obtain secondary geographic information;

[0179] Furthermore, the second remote sensing image acquisition module obtains the optimal path of the path planning module, and the UAV traverses the nodes and collects and processes remote sensing images according to the optimal path to obtain the secondary geographic information, which includes high-precision topographic maps, contour maps, and landform types generated by digital elevation models; and uploads the secondary geographic information to the cloud computing module. By obtaining the optimal path through the second remote sensing image acquisition module, the UAV can efficiently traverse each node to ensure coverage of important areas and high-risk areas, and improve the efficiency and quality of data collection; the UAV uploads the secondary geographic information to the cloud computing module in real time to ensure that the latest information in the mountainous area after the disaster can be obtained and processed in a timely manner, providing timely and accurate data support for decision-making; the data accuracy of disaster area monitoring is improved through UAV remote sensing data, helping to accurately assess the impact and losses of disasters.

[0180] A cloud computing module is used to obtain and process the features of the land object, the hazard distribution map, the importance map, the optimal safety area, the node, the shortest path, the primary geographic information and the secondary geographic information to obtain a geographic information surveying and mapping map;

[0181] Furthermore, the cloud computing module includes:

[0182] A first layer unit, used to store the primary geographic information, the land feature and the secondary geographic information node;

[0183] A second layer unit, used for storing the danger level index and the danger distribution map;

[0184] A third layer unit, used for storing the importance index and the importance map;

[0185] A fourth layer unit, used for storing the positions of the candidate safety area and the optimal safety area;

[0186] A fifth layer unit, used for storing the optimal path;

[0187] The sixth layer unit is used to store the secondary geographic information;

[0188] The geographic information surveying and mapping map is obtained. Through the multiple layer units of the cloud computing module, various geographic information data can be integrated and centrally managed, which facilitates the unified storage and call of data and improves data management efficiency.

[0189] Geographic information display module such as Figure 2 As shown, it is used to display the geographic information surveying and mapping map.

[0190] Furthermore, the geographic information display module includes:

[0191] The first layer display unit is used to receive a click signal from a user, and after receiving the click signal, the first-level geographic information, the features of the objects and the second-level geographic information nodes stored in the first layer unit of the cloud computing module are displayed, and the display effect is as follows: Figure 2 As shown;

[0192] The second layer display unit is used to receive the user's click signal, and after receiving the click signal, display the ground feature danger level index and the danger distribution map stored in the second layer unit of the cloud computing module, and the display effect is as follows: Figure 3 As shown;

[0193] A third layer display unit, used to receive the click signal of the user, and display the land feature importance index and the importance map stored in the third layer unit of the cloud computing module after receiving the click signal;

[0194] a fourth layer display unit, configured to receive the click signal of the user, and display the candidate safety area and the optimal safety area position stored in the fourth layer unit of the cloud computing module after receiving the click signal;

[0195] The fifth layer display unit is used to receive the user's click signal, and after receiving the click signal, display the optimal path stored in the fifth layer unit of the cloud computing module. By displaying geographic information in layers, rescuers can choose to view different geographic information layers as needed. The interface is simple and clear, and rescuers can quickly understand and analyze the situation in the disaster area.

[0196] Furthermore, the secondary geographic information node in the first layer display unit is used to receive a click signal from the user, and after receiving the click signal, the secondary geographic information stored in the sixth layer unit of the cloud computing module is displayed, and the display effect is as follows: Figure 4 The secondary geographic information presents the details of the ground objects photographed by drone remote sensing, making up for the lack of accuracy of satellite remote sensing.

[0197] The present invention provides a geographic information mapping system based on remote sensing images. Through multi-source satellite remote sensing images and unmanned aerial vehicle remote sensing images, a geographic information mapping system with multi-layer display is established, the features of land objects are automatically identified and marked, importance maps and danger distribution maps are drawn for post-disaster mountainous areas, a safe area site selection module is designed to select the best safe area, and unmanned aerial vehicle remote sensing images are used to make up for the lack of accuracy of satellite remote sensing images, so as to map accurate geographic information for rescue and reconstruction in post-disaster mountainous areas, thereby facilitating rescue and reconstruction in post-disaster mountainous areas.

[0198] Example 2

[0199] A serious mudslide disaster occurred in a mountainous area. During the post-disaster rescue in the mountainous area, the geographic information mapping system based on remote sensing images can quickly and accurately provide the geographic information required for rescue, including land features, hazard distribution maps, importance maps, and optimal safety areas. The following process describes the specific application steps of the system:

[0200] Step S100: first remote sensing image acquisition.

[0201] Step S101: Use multi-source satellites to obtain remote sensing images of the post-disaster mountainous area, where the multi-source satellite remote sensing images include images of different resolutions and bands. Image processing includes radiometric calibration, radiometric correction, and geometric correction.

[0202] Step S102: fusing multi-source images through an image registration algorithm to obtain primary geographic information.

[0203] Step S103: Upload the processed primary geographic information to the cloud computing module.

[0204] Step S200: marking ground objects.

[0205] Step S201: Obtain and process primary geographic information to generate a first sub-image.

[0206] Step S202: Use a segmentation algorithm to segment the primary geographic information to obtain features to be classified, including primary features (landslide areas, debris flows, barrier lakes, fault zones), secondary features (buildings, roads, bridges) and tertiary features (rivers, vegetation).

[0207] Step S203: Calculate the geometric center of the object to be classified, obtain the node, and extract the feature of the object to construct a classification feature vector.

[0208] Step S204: using the support vector machine algorithm to classify the objects, and assign marking colors and labels to different objects.

[0209] Step S205: superimpose the marking result onto the first geographic information to generate the first geographic information including the feature information.

[0210] Step S300: Map drawing.

[0211] Step S301: Calculate the importance index and danger level index of the feature.

[0212] Step S302: Draw an importance map according to the importance index, and draw a danger distribution map according to the danger level index.

[0213] Step S303: Upload the importance map and the hazard distribution map to the cloud computing module.

[0214] Step S400: selecting a safe area.

[0215] Step S401: Divide candidate safety areas according to the hazard distribution map.

[0216] Step S402: Calculate the site selection target optimization function, solve the minimum value of the target optimization function through a genetic algorithm, and select the best safety area after satisfying the constraint conditions.

[0217] Step S403: Establish a rescue location and mark it on a geographic information surveying and mapping map.

[0218] Step S500: UAV path planning.

[0219] Step S501: Acquire ground features, calculate nodes, node weights and distances between nodes.

[0220] Step S502: Plan the optimal path according to the nodes, node weights and distances between nodes, and use the Dijkstra algorithm to solve the optimal path.

[0221] Step S600: Acquisition of a second remote sensing image.

[0222] Step S601: Collect UAV remote sensing images of the post-disaster mountainous area according to the optimal path.

[0223] Step S602: Process and obtain secondary geographic information, and upload the secondary geographic information to the cloud computing module in real time.

[0224] Step S700: Cloud computing and map display.

[0225] Step S701: The cloud computing module integrates multi-level geographic information, including primary geographic information, secondary geographic information, nodes, shortest paths, hazard distribution maps, importance maps, candidate safety areas and optimal safety areas, etc., to generate a geographic information surveying and mapping map.

[0226] Step S702: The geographic information display module receives a user click signal and displays geographic information at different levels, such as primary geographic information, hazard distribution map, importance map, candidate safety areas, optimal safety area location and optimal path.

[0227] The geographic information display module is updated in real time for the rescue team to view in real time, ensuring efficient rescue operations.

[0228] Through these steps, the system can provide detailed and accurate geographic information support to the rescue team, improve rescue efficiency and ensure the safety of the affected people.

[0229] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A geographic information mapping system based on remote sensing images, It is characterized in that include: The first remote sensing image acquisition module is used to acquire and process remote sensing images of post-disaster mountainous areas collected by multi-source satellites to obtain primary geographic information; A ground object marking module is used to obtain and process the primary geographic information to obtain a first sub-image; classify the first sub-image to obtain ground objects, and mark ground object features of the ground objects; A map drawing module, used to obtain the above-mentioned ground features, calculate the danger level index and draw a danger distribution map; Calculate importance index and draw importance map; The safe area site selection module is used to divide candidate safe areas in mountainous areas after disasters and select the best safe area to establish a rescue site; The UAV path planning module is used to obtain the ground object, calculate the nodes, node weights, distances between nodes and comprehensive weights of the ground object, and the calculation formula of the comprehensive weight is: Among them, C pq represents the comprehensive weight, d pq represents the distance between node p and node q, W p represents the weight of the pth node, W q represents the weight of the qth node, and θ represents the adjustment coefficient; the optimal path is planned according to the comprehensive weight; A second remote sensing image acquisition module is used to obtain the optimal path of the UAV path planning module, collect and process remote sensing images of the post-disaster mountainous area according to the optimal path, and obtain secondary geographic information; Cloud computing module, used to obtain and process information to obtain geographic information mapping maps; The geographic information display module is used to display the geographic information surveying and mapping map.

2. A geographic information surveying and mapping system based on remote sensing images according to claim 1, It is characterized in that The first remote sensing image acquisition module includes: Acquire remote sensing images of the post-disaster mountainous area collected by the multi-source satellites, wherein the remote sensing images of the post-disaster mountainous area collected by the multi-source satellites include different resolutions and bands; Performing radiometric calibration, radiometric correction and geometric correction on the post-disaster mountainous area remote sensing images collected by the multi-source satellites to obtain corrected multi-source images; The corrected multi-source images are fused through an image registration algorithm to obtain the primary geographic information, and the primary geographic information is uploaded to the cloud computing module.

3. A geographic information surveying and mapping system based on remote sensing images according to claim 1, It is characterized in that The object marking module comprises: The first-level geographic information is segmented to obtain the first sub-image; the first sub-image includes first-level features, second-level features and third-level features, the first-level features include: landslide area, debris flow, barrier lake and fault zone, the second-level features include buildings, roads and bridges, and the third-level features include rivers and vegetation; Extracting the features of the first sub-image to obtain a classification feature vector; the classification feature vector includes: soil features, flow texture features, spectral reflectance features, elevation mutation features, geometric shape features and pixel uniformity features; The calculation formula of the soil characteristics is: Wherein, A represents the soil characteristics, χ 1 represents the spectral weight coefficient, SW represents the reflectivity of the short-wave infrared band, NI represents the reflectivity of the near-infrared band, and χ 2 represents the area weight coefficient, S A represents the soil area, S represents the total area of ​​the land features, and χ 3 Represents the color weight coefficient, R represents the reflectivity of the red band, G represents the reflectivity of the green band, and B represents the reflectivity of the blue band; The calculation formula for the local directional gradient change of the flow texture feature is: Wherein, T represents the flow texture feature, I x (a, b) represents the horizontal gradient of the ground object sub-image at point (a, b), I y (a, b) represents the vertical gradient of the ground object sub-image at point (a, b), n represents the number of rows, and m represents the number of columns; The calculation formula of the elevation mutation feature is: Wherein, C represents the elevation mutation feature, H represents the elevation, represents the gradient of the elevation in the horizontal direction, Indicates the gradient of the elevation in the vertical direction; The calculation formula of the pixel uniformity feature is: Wherein, Q represents the uniform characteristic of the pixel, N represents the total number of pixels, μ represents the average gray value, and I(c) represents the gray value of the c-th pixel; Using a support vector machine algorithm to classify the first sub-image to obtain the ground object; marking the features of the features; The ground feature is uploaded to the cloud computing module.

4. A geographic information surveying and mapping system based on remote sensing images according to claim 1, It is characterized in that The map drawing module includes: The calculation formula of the importance index is: Among them, I i represents the importance index of the i-th feature, L e () represents an important function, α e Indicates e The weight coefficient, s e represents the e-th important feature of the i-th feature, and E represents the number of important features; Drawing the importance map according to the importance index of the feature; The calculation formula of the risk index is: Among them, D i represents the danger level index of the i-th feature, P g () represents the risk function, β g Indicates z g The weight coefficient, z g represents the g-th danger level feature of the i-th feature, and G represents the number of danger level features; Draw the danger distribution map according to the danger level index of the ground feature; The importance map and the hazard distribution map are uploaded to the cloud computing module.

5. A geographic information surveying and mapping system based on remote sensing images according to claim 1, It is characterized in that The safe area site selection module includes: Dividing the candidate safety area according to the hazard distribution map; The calculation formula of the site selection objective optimization function is: Wherein, F represents the site selection objective optimization function, γ 1 Indicates I i The weight coefficient, I i represents the importance index of the i-th feature, γ 2 Indicates D i The weight coefficient, D i represents the danger level index of the i-th feature, γ 3 Indicates h i The weight coefficient, h i represents the elevation of the i-th feature, S represents the location of the candidate safe area, K i represents the node of the i-th feature, dist() represents the distance between the candidate safety area and the i-th feature, γ 4 Indicates M S The weight coefficient, M S represents the area of ​​the candidate safe area, γ 5 Indicates H S The weight coefficient, H S Indicates the maximum height difference of the candidate safety area; The formula for the first constraint is: dist(S,K i )≥d min ; Among them, d min Indicates the minimum distance between the position of the candidate safety area and the primary feature; The formula for the second constraint is: dist(S,K i )≤d max ; Among them, d max Indicates the maximum distance between the candidate safety area and the secondary feature; The formula for the third constraint is: M S ≥m min ; Among them, M S Represents the area of ​​the candidate safe area, m min Indicates the minimum area of ​​the safe area; The formula for the fourth constraint is: H S ≤h max ; Among them, H S represents the maximum height difference of the candidate safety area, h max Indicates the maximum height difference of the safety area; The genetic algorithm is used to solve the minimum value of the above objective optimization function and meet all constraints to select the best safety area S * , establish a rescue site.

6. A geographic information surveying and mapping system based on remote sensing images according to claim 1, It is characterized in that The UAV path planning module includes: Acquire the object, calculate the geometric center of the object, and obtain the node; The calculation formula of the node weight is: W i =exp(ω 1 ·f(S i )+ω 2 ·f(I i )+ω 3 ·f(h i )+ω 4 ·f(D i )); Among them, W i represents the weight of the i-th node, ω 1 Indicates S i The weight coefficient, S i represents the area of ​​the i-th feature, ω 2 Indicates I i The weight coefficient, I i represents the importance index of the i-th feature, ω 3 Indicates h i The weight coefficient, h i represents the elevation of the i-th feature, ω 4 Indicates D i The weight coefficient, D i represents the danger level index of the i-th feature, and f represents a normalization function; ω 1 、 ω 2 、 ω 3 and ω 4 satisfy ω 1 + ω 2 + ω 3 + ω 4 = 1; The calculation formula of comprehensive weight is: Among them, C pq represents the comprehensive weight, d pq represents the distance between node p and node q, W p represents the weight of the pth node, W q represents the weight of the qth node, and θ represents the adjustment coefficient; The optimal path is solved by using the Dijkstra algorithm in combination with the comprehensive weight.

7. A geographic information surveying and mapping system based on remote sensing images according to claim 1, It is characterized in that The second remote sensing image acquisition module includes: The optimal path of the path planning module is obtained, and the drone traverses the nodes and collects and processes remote sensing images according to the optimal path to obtain the secondary geographic information; and the secondary geographic information is uploaded to the cloud computing module.

8. A geographic information surveying and mapping system based on remote sensing images according to claim 1, It is characterized in that The cloud computing module includes: A first layer unit, used to store the primary geographic information, the land feature and the secondary geographic information node; A second layer unit, used for storing the danger level index and the danger distribution map; A third layer unit, used for storing the importance index and the importance map; A fourth layer unit, used for storing the positions of the candidate safety area and the optimal safety area; A fifth layer unit, used for storing the optimal path; The sixth layer unit is used to store the secondary geographic information.

9. A geographic information surveying and mapping system based on remote sensing images according to claim 1, It is characterized in that The geographic information display module comprises: A first layer display unit is used to receive a click signal from a user, and after receiving the click signal, display the primary geographic information, the land feature and the secondary geographic information node stored in the first layer unit of the cloud computing module; A second layer display unit is used to receive the click signal of the user, and display the danger level index and the danger distribution map stored in the second layer unit of the cloud computing module after receiving the click signal; a third layer display unit, configured to receive the click signal of the user, and display the importance index and the importance map stored in the third layer unit of the cloud computing module after receiving the click signal; a fourth layer display unit, configured to receive the click signal of the user, and display the positions of the candidate safety area and the optimal safety area stored in the fourth layer unit of the cloud computing module after receiving the click signal; The fifth layer display unit is used to receive the user's click signal, and display the optimal path stored in the fifth layer unit of the cloud computing module after receiving the click signal.

10. A geographic information surveying and mapping system based on remote sensing images according to claim 9, It is characterized in that The secondary geographic information node includes: The secondary geographic information node is used to receive a click signal from a user, and after receiving the click signal, displays the secondary geographic information stored in the sixth layer unit of the cloud computing module.

Images