Emergency rescue path planning method, system and equipment based on building earthquake damage simulation and medium

Abstract

The invention discloses an emergency rescue path planning method, system and device based on building earthquake damage simulation and a medium, and relates to the field of rescue path planning, and the method comprises the steps: building a building three-dimensional structure based on a two-dimensional plane graph of a building with an earthquake disaster; processing the three-dimensional structure of the building by adopting a physical engine to obtain a building damage and pavement accumulation result under an earthquake; performing indoor and outdoor integrated road network extraction on building damage and pavement accumulation results under an earthquake by adopting a navigation grid method to obtain a road network extraction result; and performing path planning based on the road network extraction result by adopting an optimized A * algorithm to obtain an emergency rescue path planning result. According to the method, the requirements of evacuation safety, trafficability and traffic capacity constraint and strain can be met, and indoor and outdoor integrated path planning service is provided for search and rescue personnel so as to respond to the optimal rescue path requirement of emergency.

Description

Technical Field

[0001] The present application relates to the field of rescue path planning, and in particular to a method, system, equipment and medium for emergency rescue path planning based on building earthquake damage simulation. Background Art

[0002] Under the influence of earthquakes, urban building structures often suffer damage and collapse. To enable rescue workers to conduct efficient, effective, and safe search and rescue operations, it is necessary to accurately obtain the damage and collapse of buildings after the earthquake disaster, as well as the scope and distribution of surrounding rubble accumulation, as soon as possible after the earthquake.

[0003] Currently, the progressive collapse analysis and evaluation of the progressive collapse resistance of reinforced concrete structures are primarily based on the finite element method (FEM). While the FEM can accurately simulate the behavior of structures under small, nonlinear deformations, this continuum mechanics-based approach struggles to simulate the collisions between separate elements during the collapse phase, making it unsuitable for solving problems involving large deformations and discontinuous structures.

[0004] Providing route planning services for rescuers requires considering restricted areas and promptly planning indoor escape routes based on the damage to indoor buildings. However, most current planning methods only focus on outdoor services, and integrated indoor and outdoor services are still in their infancy. Research in multiple areas, including map representation, data specifications, and indoor 3D model building standards, is urgently needed.

[0005] The factors affecting building collapse are complex. Due to the uncertainty of loads and effects and the complexity of structural dynamic responses, collapse behavior is highly random. The cost of research through experimental replication is high, and it is difficult to obtain reliable results of structural collapse analysis through theoretical analysis. Moreover, the traditional shortest path algorithms designed based on the above ideas are difficult to generate evacuation paths that meet the requirements of evacuation safety, accessibility, capacity constraints and adaptability. Summary of the Invention

[0006] The purpose of this application is to provide an emergency rescue path planning method, system, equipment and medium based on building earthquake damage simulation, which can meet the requirements of evacuation safety, accessibility, and traffic capacity constraints and adaptability, and provide search and rescue personnel with indoor and outdoor integrated path planning services to respond to the optimal rescue path needs of emergencies.

[0007] To achieve the above objectives, this application provides the following solutions:

[0008] In a first aspect, the present application provides an emergency rescue path planning method based on building earthquake damage simulation, comprising:

[0009] Constructing a three-dimensional structure of a building based on a two-dimensional plan view of the building that is subject to earthquake damage;

[0010] The physics engine is used to process the three-dimensional structure of the building to obtain the results of building damage and road accumulation under earthquake;

[0011] Using the navigation grid method, we extracted the indoor and outdoor integrated road network based on the building damage and road accumulation results caused by the earthquake, and obtained the road network extraction results.

[0012] The optimized A* algorithm is used to perform path planning based on the road network extraction results to obtain the emergency rescue path planning results; the optimized A* algorithm refers to the A* algorithm after the terrain complexity is introduced into the heuristic function.

[0013] Optionally, constructing a three-dimensional structure of a building based on a two-dimensional plan view of the building affected by the earthquake disaster includes:

[0014] Perform image segmentation and feature extraction on a two-dimensional plane image to obtain different object segmentation results and regions; the region features include at least one of edges, corners, and textures;

[0015] Obtain feature points based on different object segmentation results and regions;

[0016] A plurality of patches are formed based on the position and adjacent relationship of each feature point; the patch represents the surface of an object or a surface of an area in the building scene;

[0017] Using the camera calibration algorithm, the coordinates of the pixel points corresponding to the multiple facets and the two-dimensional plane image are converted into world coordinates to obtain three-dimensional points;

[0018] Determine the actual size and position relationship of different object segmentation results or regions based on the coordinates of the three-dimensional points;

[0019] Based on different object segmentation results or the actual size and position relationship of the region, multiple patches are aligned and fused to obtain the three-dimensional structure of the building.

[0020] Optionally, a physical engine is used to process the three-dimensional structure of the building to obtain the results of building damage and road accumulation under the earthquake, including:

[0021] Input seismic waves and use a physics engine to determine the contact force, acceleration, velocity, displacement, and rotation angle experienced by each component unit in the building's three-dimensional structure at each moment under the action of the seismic wave. The motion state of each component unit at each moment is also determined. The motion state includes the resultant force and torque generated by the center of gravity of each component unit.

[0022] Obtaining structural parameters of the three-dimensional structure of the building, and determining a generalized constrained fracture threshold and a plastic deformation threshold based on the structural parameters; the structural parameters of the three-dimensional structure of the building include the size of each component unit, the strength of steel bars and concrete, and the diameter and number of stress bars and stirrups;

[0023] Determine the deformation or force of each component unit of the building based on the motion state of each component unit at each moment, and determine the damage and fracture of the component unit under earthquake based on the generalized constrained fracture threshold and plastic deformation threshold, and determine the velocity change of the component unit after the collision, the displacement of the component unit, and the impulse generated by the component unit when the collision occurs;

[0024] Based on the velocity change of component units after collision, the displacement of component units and the impulse generated when component units collide, the results of building damage and road accumulation under earthquake are obtained.

[0025] Optionally, determining a generalized constrained fracture threshold based on the structural parameters includes:

[0026] Determine the unit stress value of each component unit based on the structural parameters; the unit stress value refers to the stress value per unit area of the cross section of each component unit;

[0027] The generalized constraints of each component unit are obtained, and the unit stress value of each component unit is transferred to the corresponding generalized constraint to obtain the generalized constraint fracture threshold.

[0028] Optionally, a navigation grid method is used to extract an indoor and outdoor integrated road network based on the building damage and road accumulation results under the earthquake, and the road network extraction results are obtained, including:

[0029] The navigation mesh method is used to extract the topological network structure by combining the road network and the three-dimensional structure of the building. The topological network structure includes the entire indoor and outdoor area environment in the three-dimensional structure of the building.

[0030] The topological network structure is optimized to obtain the road network extraction results.

[0031] Optionally, the topological network structure is optimized to obtain a road network extraction result, including:

[0032] The convex polygon mesh in the topological network structure is triangulated and split, and vertices are added inside or on the edge of the triangulated split result to obtain the road network extraction result.

[0033] Optionally, an optimized A* algorithm is used to perform path planning based on the road network extraction results to obtain emergency rescue path planning results, including:

[0034] The optimized A* algorithm is used to obtain the optimal path between the search and rescue starting point and the target point based on the road network extraction results;

[0035] Smoothing the optimal path between the search and rescue starting point and the target point to generate the shortest path;

[0036] Obtain the coordinate points of the shortest path, and visualize the coordinate points of the shortest path to obtain the emergency rescue path planning results.

[0037] In a second aspect, the present application provides an emergency rescue path planning system based on building earthquake damage simulation, comprising:

[0038] A three-dimensional building modeling module is used to construct a three-dimensional structure of a building based on a two-dimensional plan of the building that is affected by the earthquake disaster;

[0039] The physical engine calculation module is used to process the three-dimensional structure of the building using the physical engine to obtain the results of building damage and road accumulation under earthquake conditions;

[0040] The post-earthquake indoor and outdoor integrated extraction module is used to extract the indoor and outdoor integrated road network based on the building damage and road accumulation results caused by the earthquake using the navigation grid method to obtain the road network extraction results;

[0041] The rescue path analysis module is used to use the optimized A* algorithm to perform path planning based on the road network extraction results to obtain the emergency rescue path planning results; the optimized A* algorithm refers to the A* algorithm after introducing terrain complexity into the heuristic function.

[0042] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-mentioned emergency rescue path planning method based on building earthquake damage simulation.

[0043] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned emergency rescue path planning method based on building earthquake damage simulation.

[0044] According to the specific embodiments provided in this application, this application has the following technical effects:

[0045] The present application provides an emergency rescue path planning method, system, equipment and medium based on building earthquake damage simulation, which uses a physical engine to process the three-dimensional structure of the building, and can simulate the new position information of component units, other larger building components and these components in the damaged building and the accumulation of rubble in the event of an earthquake, so as to provide earthquake damage prediction and emergency measures for personnel escape; according to the damage of restricted outdoor areas and indoor areas of buildings, the navigation grid method and the optimized A* algorithm are used to integrate the macro outdoor space and the micro indoor environment for path analysis to meet the requirements of evacuation safety, accessibility, traffic capacity constraints and adaptability, and provide search and rescue personnel with integrated indoor and outdoor path planning services, so as to respond to the optimal rescue path needs of emergencies. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0047] Figure 1 A flowchart of an emergency rescue path planning method based on building earthquake damage simulation provided in one embodiment of the present application;

[0048] Figure 2 A schematic diagram of collision detection provided in an embodiment of the present application;

[0049] Figure 3 A schematic diagram showing comparison results of meshes before and after optimization provided in an embodiment of the present application;

[0050] Figure 4 A schematic diagram of generating the shortest path provided in an embodiment of the present application;

[0051] Figure 5 A schematic diagram of the overall technical framework of an emergency rescue path planning system based on building earthquake damage simulation provided in one embodiment of the present application;

[0052] Figure 6 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0054] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0055] In an exemplary embodiment, the present application provides an emergency rescue path planning method based on building earthquake damage simulation. The method is executed by a computer device, specifically a computer device such as a terminal or a server, or a terminal and a server. In the embodiment of the present application, the method is applied to a server as an example for explanation. Figure 1 As shown, the method includes:

[0056] Step 100: construct a three-dimensional structure of a building based on a two-dimensional plan view of the building affected by the earthquake disaster.

[0057] Step 101: Use a physical engine to process the three-dimensional structure of the building to obtain the results of building damage and road accumulation under the earthquake.

[0058] Step 102: Using the navigation grid method, perform indoor and outdoor integrated road network extraction on the building damage and road accumulation results caused by the earthquake to obtain a road network extraction result.

[0059] Step 103: Using the optimized A* algorithm, path planning is performed based on the road network extraction result to obtain an emergency rescue path planning result. The optimized A* algorithm refers to the A* algorithm after the terrain complexity is introduced into the heuristic function.

[0060] By implementing the above steps 100 to 103, the present application can provide earthquake damage prediction and emergency measures for personnel escape. At the same time, it can meet the requirements of evacuation safety, accessibility, traffic capacity constraints and adaptability, and provide search and rescue personnel with indoor and outdoor integrated path planning services, thereby responding to the optimal rescue path needs of emergencies.

[0061] In another exemplary embodiment of the present application, in order to achieve accurate construction of a three-dimensional structure of a building, in this embodiment, the implementation of the above-mentioned step 100 can be replaced by the following steps 200 to 205.

[0062] Step 200: Perform image segmentation and feature extraction on the two-dimensional plane image to identify different object segmentation results and regions. The features of the region include edges, corners, and textures.

[0063] Step 201: Obtain feature points based on different object segmentation results and regions.

[0064] Step 202: Based on the location and proximity of each feature point, multiple facets are formed. For example, based on the location and proximity of the feature points, triangulation, multi-view geometry, or other methods are used to connect the feature points to form facets. Facets represent the surface of an object or area in the building scene.

[0065] Step 203: Using a camera calibration algorithm, the coordinates of the pixel points corresponding to the multiple facets and the two-dimensional plane image are converted into world coordinates to obtain three-dimensional points.

[0066] Step 204: Determine the actual size and position relationship of different object segmentation results or regions based on the coordinates of the three-dimensional points.

[0067] Step 205: align and fuse multiple facets based on different object segmentation results or the actual sizes and positional relationships of the regions, so as to obtain a complete three-dimensional structure of the building.

[0068] In another exemplary embodiment of the present application, a physical engine can be used to simulate component units, other larger building components, and the new position information of these components in the damaged building and the accumulation of rubble in the event of an earthquake. Based on this, the implementation process of the above-mentioned step 101 can be replaced by the following steps 300-303.

[0069] Step 300: Input seismic waves and use a physics engine to determine the contact force, acceleration, velocity, displacement, and rotation angle experienced by each component unit in the three-dimensional structure of the building at each moment under the action of the seismic wave, and determine the motion state of each component unit at each moment. The motion state includes the resultant force and torque generated by the center of gravity of each component unit, where:

[0070]

[0071] Where F is the resultant force generated by the center of gravity of the component unit, M is the resultant moment, m i is the mass of component unit i, r ij v is the distance from the point where component j acts on component i to the center of gravity of component i, i and ω i are the velocity vector and angular velocity vector of component unit i, I iis the moment of inertia of component unit i. In this embodiment, the net external force on the component unit only considers its own gravity and the contact force it receives. The contact force is further divided into the normal contact force and tangential contact force g is the acceleration due to gravity, and t is the time.

[0072] Step 301: Obtain the structural parameters of the three-dimensional building structure and determine the generalized constrained fracture threshold and plastic deformation threshold based on the structural parameters. The structural parameters of the three-dimensional building structure include the size of each component unit, the strength of steel bars and concrete, the diameter and number of stress bars and stirrups, etc.

[0073] The process of determining the generalized constraint fracture threshold includes:

[0074] (1) Determine the unit stress value of each component unit based on the structural parameters. The unit stress value refers to the stress value per unit area of the cross section of each component unit. For example, when each component unit is a reinforced concrete component, its unit stress value is expressed as:

[0075] N - =f c A(1-ξ)+f s ξA.

[0076] N + =f s ξA.

[0077] V + / - =αf s e'vh 2 .

[0078]

[0079] Where N - 、N + 、V + / - and M + / - Respectively represent the bearing capacity of reinforced concrete components in terms of pressure, tension, shear and bending moment. A is the cross-sectional area of the component. c is the design value of concrete compressive strength. s is the yield strength of the steel bar. h and b are the height and width of the concrete member section. ξ, e', α, and v are the reinforcement ratio, the ratio of the concrete core height to the section height, the shear capacity coefficient, and the shear rate, respectively.

[0080] (2) Obtain the generalized constraints of each component unit, and transfer the unit stress value of each component unit to the corresponding generalized constraint to obtain the generalized constraint fracture threshold.

[0081] Furthermore, the plastic deformation stage of the building structure is simulated by a spring, and the specific process of determining the plastic deformation threshold is described, including:

[0082] When the component unit reaches the fracture threshold of the generalized constraint (i.e., the generalized constraint fracture threshold) and is damaged, the generalized constraint will be released, and the building structure will then undergo plastic deformation. Once the deformation or force of the spring constraint exceeds its maximum allowable deformation value and ultimate bearing capacity, it will fracture and the building will begin to damage. At this time, the expression formula for the plastic deformation threshold is:

[0083]

[0084] Where μ is the spring constraint fracture threshold per unit area. su is the ultimate tensile stress of the steel bar. n is the simulation time step. The constant 2 is a necessary correction factor.

[0085] Step 302: Determine the deformation or force exerted on each component unit of the building based on the motion state of each component unit of the building at each moment, determine the damage and fracture of the component unit under the earthquake based on the generalized constrained fracture threshold and the plastic deformation threshold, and determine the velocity change of the component unit after the collision, the displacement of the component unit, and the impulse generated when the component unit collides.

[0086] Among them, after determining that a collision occurs between damaged component units, the velocity change of the component units after the collision is calculated, and then the displacement of the component units at the next time step (i.e. the next moment) and the impulse generated when the component units collide are calculated, and finally the damage situation of the building under earthquake conditions is obtained. Figure 2 As shown, the red line represents the overlapping part between the component units. At this time, a collision occurs between the two component units a and b.

[0087] Step 303: Based on the velocity change of the component units after the collision, the displacement of the component units, and the impulse generated when the component units collide, the building damage and road surface accumulation results under the earthquake are obtained.

[0088] In another exemplary embodiment of the present application, in order to integrate the macro outdoor space and the micro indoor environment for path analysis based on the restricted outdoor area and the damage inside the building, in this embodiment, the implementation process of the above-mentioned step 102 can be replaced by the following steps 400-401.

[0089] Step 400: Using the navigation mesh method, the road network and the three-dimensional structure of the building are combined to directly extract the topological network structure of the entire indoor and outdoor area environment. The indoor and outdoor areas are divided relative to the structure given by the three-dimensional structure of the building.

[0090] Step 401, optimize the topological network structure to obtain the road network extraction result. For example, the convex polygon mesh is triangulated and split using the ear clipping method, and vertices are added inside or on the edge of the polygon to add high details to ensure that the mesh fits the surface of the original model (i.e., the three-dimensional structure of the building) better, generating a fine navigation mesh that is closer to the surface shape (i.e., the road network extraction result). The ear clipping method process is as follows: the algorithm first connects the vertices of the polygon in a clockwise or counterclockwise order to form a simple polygon. Then, starting from any vertex of the polygon, check whether the angle of the side corresponding to the vertex is a convex angle (less than 180 degrees). If so, the vertex is called an "ear", and the triangle corresponding to the ear is cut off (i.e., the vertex corresponding to the ear is deleted from the polygon) to obtain a new polygon with fewer vertices. Repeat steps 2 and 3 until three vertices are left. In this way, the triangulation of the original polygon is obtained. By continuously searching for ears and cutting them off, the ear clipping algorithm quickly triangulates the mesh composed of the input convex polygons into non-intersecting triangles. Based on the existing navigation grid, the quality of the navigation grid is improved and data redundancy is eliminated. The comparison results of the grid before and after optimization are as follows: Figure 3 shown. Figure 3 In the figure, part (a) is the mesh result before optimization, and part (b) is the mesh result after optimization.

[0091] In another exemplary embodiment of the present application, in order to further improve the accuracy of emergency rescue path planning, in this embodiment, the implementation process of the above-mentioned step 103 can be replaced by the following steps 500-502.

[0092] Step 500: Use the optimized A* algorithm to obtain the optimal path between the search and rescue starting point and the target point based on the road network extraction result.

[0093] Step 501: Smooth the optimal path between the search and rescue starting point and the target point to generate the shortest path. Figure 4 shown.

[0094] Step 502: Obtain the coordinate points of the shortest path and visualize the coordinate points of the shortest path to obtain the emergency rescue path planning result. For example, the path points (i.e., the coordinate points of the shortest path) are visualized in a three-dimensional scene using ThreeJS.

[0095] In another exemplary embodiment of the present application, the terrain complexity T is introduced, and the heuristic function h(n) of the A* algorithm is modified on the navigation grid generated based on the three-dimensional scene to obtain an optimized A* algorithm. Among them, the terrain slope M and the terrain roughness N are used as the main evaluation factors for constructing the terrain complexity T. Different slopes have different effects on pedestrian activities. For example, when the slope is 100% (1:1) to 50% (1:2), it is difficult for people to stand and balance. When the slope is 50% (1:2) to 25% (1:4), people can stand, but there is a risk of rolling. When the slope is less than 20% (1:5), people can stand and walk, with a little effort, but basically no discomfort. When the slope is less than 10% (1:10), people walking on it feel like walking on flat ground. Based on the "Code for Planning and Design of Urban Residential Areas (GB 50180-93)" and taking into account people's walking habits, the terrain slope is selected as gentle slope between 3% (1:33.4) and 8% (1:12.5), and the terrain slope is selected as medium slope between 8% (1:12.5) and 25% (1:4). The formula for determining terrain complexity T is proposed as follows:

[0096]

[0097] For the heuristic function h(n), the Euclidean distance from the search node n to the target node t' is selected, and the heuristic function is dynamically adjusted according to the terrain complexity T during the search process to provide a more accurate estimate and make it closer to the actual situation. The modified heuristic function h'(n) is calculated by the following formula:

[0098]

[0099] In the formula, (x n ,y n ,z n ) is the coordinate of the search node n, (x t' ,y t' ,z t' ) are the coordinates of the target node.

[0100] At this time, the evaluation function of the optimized A* algorithm is adjusted to:

[0101] f(n)=g(n)+h'(n).

[0102] Based on the above description, this application studies emergency rescue path planning methods under earthquake damage simulation for urban building earthquake scenarios. This method provides the necessary conditions and a solid foundation for timely and efficient emergency rescue applications after an earthquake. It integrates and fully utilizes information about structural units, other larger building components, their new positions within damaged buildings, and the accumulation of rubble during earthquakes, providing support and services for rescuers' decision-making and rescue efforts.

[0103] Based on the rescue needs of earthquake scenarios, building simulation and indoor and outdoor integrated rescue path planning are carried out to achieve visual simulation of indoor and outdoor integrated emergency search and rescue, providing a basis for emergency rescue after an earthquake. The method provided in this application can be successfully applied to meet the needs of indoor and outdoor integrated search and rescue after an earthquake. In addition, the emergency rescue path planning method based on building earthquake damage simulation provided in this application has the characteristics of efficient real-time calculation, and can simulate the component units, other larger building components and the new position information of these components in the damaged building and the accumulation of rubble under earthquake conditions, providing earthquake damage prediction and emergency measures for personnel escape. According to the damage to the restricted outdoor area and the indoor environment of the building, the navigation grid method is used to integrate the macro outdoor space with the micro indoor environment for path analysis to meet the requirements of its evacuation safety, accessibility, and traffic capacity constraints and adaptability, and provide search and rescue personnel with indoor and outdoor integrated path planning services, thereby responding to the optimal rescue path needs of emergencies.

[0104] Based on the same inventive concept, the embodiments of the present application also provide an emergency rescue path planning system for implementing the aforementioned method for emergency rescue path planning based on building earthquake damage simulation. The implementation solution provided by this system is similar to the implementation solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the emergency rescue path planning system based on building earthquake damage simulation provided below can be found in the above-mentioned limitations of the method for emergency rescue path planning based on building earthquake damage simulation, and will not be repeated here.

[0105] In an exemplary embodiment, Figure 5 As shown, an emergency rescue path planning system based on building earthquake damage simulation is provided, which includes: a building three-dimensional modeling module, a physical engine calculation module, a post-earthquake indoor and outdoor integrated extraction module and a rescue path analysis module.

[0106] The building three-dimensional modeling module is used to construct the building three-dimensional structure based on the two-dimensional plan of the building that is affected by the earthquake disaster.

[0107] The physical engine calculation module is used to process the three-dimensional structure of the building using the physical engine to obtain the results of building damage and road accumulation under earthquake.

[0108] The post-earthquake indoor and outdoor integrated extraction module is used to extract the indoor and outdoor integrated road network based on the building damage and road accumulation results under the earthquake using the navigation grid method to obtain the road network extraction results.

[0109] The rescue path analysis module uses an optimized A* algorithm to perform path planning based on the road network extraction results, resulting in an emergency rescue path planning result. The optimized A* algorithm refers to the A* algorithm that incorporates terrain complexity into the heuristic function.

[0110] As an optional implementation, the building three-dimensional modeling module includes: a feature extraction unit, a triangulation unit and a three-dimensional reconstruction unit.

[0111] The feature extraction unit performs image segmentation and feature extraction on the two-dimensional plane image to identify different objects and areas.

[0112] The triangulation unit connects the feature points to form patches based on their positions and proximity, using triangulation, multi-view geometry, and other methods. Patches represent the surface of an object or area in the scene.

[0113] The 3D reconstruction unit uses a camera calibration algorithm to convert the pixel coordinates corresponding to the facets and planar images into world coordinates. Based on the positions of the 3D points, the true size and position of the object or area are calculated. By aligning and fusing multiple planar images, the complete 3D structure of the building is obtained.

[0114] As an optional implementation, the physical engine calculation module includes: a contact model unit, a generalized constraint solving unit, a spring constraint solving unit and a collision detection unit.

[0115] When seismic waves are input, the contact model unit solves the contact force and acceleration, velocity, displacement and rotation angle of each component unit of the building, thereby determining its motion state at each moment.

[0116] The generalized constraint solving unit solves the generalized constraint fracture threshold, where the stress value per unit area of the cross section is calculated and passed to the corresponding generalized constraint.

[0117] The spring constraint solver solves the spring constraint fracture threshold. Once a component element reaches the fracture threshold and breaks, the generalized constraint is released, and the spring simulates the plastic deformation phase of the building structure. Once the spring constraint's deformation or force exceeds its maximum allowable deformation and ultimate bearing capacity, the constraint breaks, and the building begins to deteriorate.

[0118] After the collision detection unit determines that a collision has occurred between damaged component units (i.e., rigid bodies), it calculates the velocity change of the rigid bodies after the collision, and then calculates the displacement of the rigid bodies in the next time step and the impulse generated when the rigid bodies collide, and finally obtains the damage condition of the building in the event of an earthquake.

[0119] As an optional implementation, the post-earthquake indoor and outdoor integrated extraction module includes: an indoor and outdoor structure extraction unit and a navigation grid optimization unit.

[0120] The indoor and outdoor structure extraction unit is based on the road network and the existing three-dimensional model, combining the two, and then directly extracting the topological network structure of the entire indoor and outdoor area environment through the navigation mesh method.

[0121] The navigation mesh optimization unit optimizes the extracted topological network structure. It triangulates the convex polygon mesh using ear clipping, adds vertices inside or on the edges of the polygons, and adds high-level details to ensure the mesh fits the original model surface better. This generates a refined navigation mesh that more closely matches the surface shape, resulting in an optimized 3D navigation mesh.

[0122] As an optional implementation, the rescue path analysis module includes: a path search unit, a path smoothing unit and a path visualization unit.

[0123] The path search unit finds the optimal path between the search and rescue starting point and the target point by using the optimized A* algorithm based on the optimized three-dimensional navigation grid.

[0124] The path smoothing unit further smoothes the optimal path generated by the optimized A* algorithm to generate an actual shortest path.

[0125] The path visualization unit outputs the coordinate points of the actual shortest path and visualizes the path points in a three-dimensional scene through ThreeJS.

[0126] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store emergency rescue path planning data based on building earthquake damage simulation. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for emergency rescue path planning based on building earthquake damage simulation is implemented.

[0127] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0128] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0129] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0130] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0131] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0132] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (RRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0133] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may include, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, and the like.

[0134] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0135] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for emergency rescue path planning based on building earthquake damage simulation, characterized in that: include: Constructing a three-dimensional structure of a building based on a two-dimensional plan view of the building that is subject to earthquake damage; The physics engine is used to process the three-dimensional structure of the building to obtain the results of building damage and road accumulation under earthquake; Using the navigation grid method, we extracted the indoor and outdoor integrated road network based on the building damage and road accumulation results caused by the earthquake, and obtained the road network extraction results. The optimized A* algorithm is used to perform path planning based on the road network extraction results to obtain the emergency rescue path planning results; the optimized A* algorithm refers to the A* algorithm after the terrain complexity is introduced into the heuristic function.

2. The method for emergency rescue path planning based on building earthquake damage simulation according to claim 1 is characterized in that: Construct a 3D structure of a building based on a 2D floor plan of the building exposed to earthquake hazards, including: Perform image segmentation and feature extraction on a two-dimensional plane image to obtain different object segmentation results and regions; the region features include at least one of edges, corners, and textures; Obtain feature points based on different object segmentation results and regions; A plurality of patches are formed based on the position and adjacent relationship of each feature point; the patch represents the surface of an object or a surface of an area in the building scene; Using the camera calibration algorithm, the coordinates of the pixel points corresponding to the multiple facets and the two-dimensional plane image are converted into world coordinates to obtain three-dimensional points; Determine the actual size and position relationship of different object segmentation results or regions based on the coordinates of the three-dimensional points; Based on different object segmentation results or the actual size and position relationship of the region, multiple patches are aligned and fused to obtain the three-dimensional structure of the building.

3. The method for emergency rescue path planning based on building earthquake damage simulation according to claim 1, characterized in that: The physics engine is used to process the three-dimensional structure of the building, and the results of building damage and road accumulation under earthquakes are obtained, including: Input seismic waves and use a physics engine to determine the contact force, acceleration, velocity, displacement, and rotation angle experienced by each component unit in the building's three-dimensional structure at each moment under the action of the seismic wave. The motion state of each component unit at each moment is also determined. The motion state includes the resultant force and torque generated by the center of gravity of each component unit. Obtaining structural parameters of the three-dimensional structure of the building, and determining a generalized constrained fracture threshold and a plastic deformation threshold based on the structural parameters; the structural parameters of the three-dimensional structure of the building include the size of each component unit, the strength of steel bars and concrete, and the diameter and number of stress bars and stirrups; Determine the deformation or force of each component unit of the building based on the motion state of each component unit at each moment, and determine the damage and fracture of the component unit under earthquake based on the generalized constrained fracture threshold and plastic deformation threshold, and determine the velocity change of the component unit after the collision, the displacement of the component unit, and the impulse generated by the component unit when the collision occurs; Based on the velocity change of component units after collision, the displacement of component units and the impulse generated when component units collide, the results of building damage and road accumulation under earthquake are obtained.

4. The method for emergency rescue path planning based on building earthquake damage simulation according to claim 3 is characterized in that: Determining a generalized constrained fracture threshold based on the structural parameters includes: Determine the unit stress value of each component unit based on the structural parameters; the unit stress value refers to the stress value per unit area of the cross section of each component unit; The generalized constraints of each component unit are obtained, and the unit stress value of each component unit is transferred to the corresponding generalized constraint to obtain the generalized constraint fracture threshold.

5. The method for emergency rescue path planning based on building earthquake damage simulation according to claim 1, characterized in that: Using the navigation grid method, we extracted an indoor and outdoor integrated road network based on the building damage and road accumulation results caused by the earthquake. The road network extraction results include: The navigation mesh method is used to extract the topological network structure by combining the road network and the three-dimensional structure of the building. The topological network structure includes the entire indoor and outdoor area environment in the three-dimensional structure of the building. The topological network structure is optimized to obtain the road network extraction results.

6. The method for emergency rescue path planning based on building earthquake damage simulation according to claim 5, characterized in that: Optimize the topological network structure and obtain the road network extraction results, including: The convex polygon mesh in the topological network structure is triangulated and split, and vertices are added inside or on the edge of the triangulated split result to obtain the road network extraction result.

7. The method for emergency rescue path planning based on building earthquake damage simulation according to claim 1, characterized in that: Using the optimized A* algorithm, we perform path planning based on the road network extraction results to obtain the emergency rescue path planning results, including: The optimized A* algorithm is used to obtain the optimal path between the search and rescue starting point and the target point based on the road network extraction results; Smoothing the optimal path between the search and rescue starting point and the target point to generate the shortest path; Obtain the coordinate points of the shortest path, and visualize the coordinate points of the shortest path to obtain the emergency rescue path planning results.

8. An emergency rescue path planning system based on building earthquake damage simulation, characterized in that: include: A three-dimensional building modeling module is used to construct a three-dimensional structure of a building based on a two-dimensional plan of the building that is affected by the earthquake disaster; The physical engine calculation module is used to process the three-dimensional structure of the building using the physical engine to obtain the results of building damage and road accumulation under earthquake conditions; The post-earthquake indoor and outdoor integrated extraction module is used to extract the indoor and outdoor integrated road network based on the building damage and road accumulation results caused by the earthquake using the navigation grid method to obtain the road network extraction results; The rescue path analysis module is used to use the optimized A* algorithm to perform path planning based on the road network extraction results to obtain the emergency rescue path planning results; the optimized A* algorithm refers to the A* algorithm after introducing terrain complexity into the heuristic function.

9. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the emergency rescue path planning method based on building earthquake damage simulation according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for emergency rescue path planning based on building earthquake damage simulation according to any one of claims 1 to 7 is implemented.

Images