Three-dimensional visualized comprehensive escape path planning method and system based on dijkstra algorithm

Abstract

The application discloses a kind of three-dimensional visual comprehensive escape path planning method and system based on Dijkstra algorithm, comprising: abstracting building three-dimensional model as the three-dimensional space topology graph containing node and edge;For each edge in topological graph, the dynamic comprehensive path weight model is constructed by combining channel geometric length, estimated travel time, environment risk level and channel passable state;When receiving environmental state change information, the path weight of the affected edge is dynamically updated;Using Dijkstra algorithm, the optimal escape path from at least one evacuation starting point to at least one exit node is calculated on the updated topological graph, and a backup path is generated;Finally, the path result is mapped to the three-dimensional model for visual display and output to the entity path indicating device.The application solves the problem of single path planning model in the prior art, lag response to environmental changes and insufficient use of three-dimensional information, and realizes dynamic, safe and intuitive intelligent evacuation guidance.

Description

Technical Field

[0001] This invention relates to the field of fire safety and intelligent emergency management technology, and in particular to a three-dimensional visualization integrated escape route planning method and system based on Dijkstra's algorithm. Background Technology

[0002] With the rapid pace of urbanization and the increasing number of large and complex buildings (such as commercial complexes, transportation hubs, and high-rise office buildings), emergency evacuation during fires, earthquakes, and other emergencies faces unprecedented challenges. Traditional evacuation guidance systems (such as static "safety exit" signs) rely on fixed, pre-set routes and cannot detect dynamic changes at the disaster site (such as the spread of flames, dense smoke, and blocked passageways). In complex and ever-changing environments, they may guide people into dangerous areas, posing serious safety hazards.

[0003] In existing technologies, there are two main types of technical solutions for personnel evacuation in emergencies such as building fires:

[0004] The first category is evacuation route planning schemes based on two-dimensional floor plans. These schemes typically abstract the building's floor plan into two-dimensional nodes and edges, using path length or travel distance as the primary, or even sole, optimization objective. They utilize traditional shortest path algorithms (such as Dijkstra's algorithm or A* algorithm) to calculate the route from a person's location to the nearest exit. However, this type of scheme has significant drawbacks: First, its route planning is largely based on static building information with fixed weights, making it difficult to reflect dynamic environmental changes during a fire, such as smoke, temperature, toxic gas concentration, and passageway blockages. This can lead to planned routes potentially traversing high-risk areas, resulting in insufficient safety. Second, its route display relies on two-dimensional floor plans or textual prompts, making it difficult to clearly express three-dimensional spatial relationships such as multiple floors, staircases, and vertical passages, easily leading to cognitive misjudgments among evacuees. Third, in complex scenarios with multiple people and multiple exits, its computational efficiency is low, and it lacks effective global coordination and visual decision support.

[0005] The second category is evacuation route planning schemes based on Building Information Modeling (BIM) or 3D building models. These schemes utilize 3D geometric models to model buildings and display evacuation routes in a 3D scene, improving intuitiveness. However, their technical shortcomings lie in the fact that the 3D model is usually only used for visualizing the final result and does not deeply participate in the route planning calculation process. Route planning itself still relies on preset static rules or simplified weight models, failing to fully utilize 3D spatial information for dynamic safety assessment. When the environment changes, the system struggles to automatically and in real-time update route weights and replan, exhibiting poor dynamic adaptability. Furthermore, this type of scheme lacks comprehensive consideration and unified modeling of multiple factors such as travel time, environmental risks, and crowd congestion, limiting the reliability of the planning results.

[0006] In summary, existing technologies all have shortcomings in terms of dynamic environmental adaptability, deep fusion of three-dimensional information, comprehensive evaluation of multiple factors, and real-time planning in complex scenarios. Therefore, developing intelligent, dynamic emergency evacuation route planning technologies that can respond to environmental changes in real time is of great significance for ensuring public safety and improving the level of urban public safety governance. Summary of the Invention

[0007] To address the shortcomings of existing technologies, this invention provides a three-dimensional visualization-based integrated escape path planning method based on Dijkstra's algorithm.

[0008] To achieve the above-mentioned objectives, the technical solution adopted by the present invention is as follows:

[0009] A three-dimensional visualization-based integrated escape path planning method based on Dijkstra's algorithm includes the following steps:

[0010] S1: 3D spatial modeling and topological abstraction of buildings: 3D modeling of buildings to be evacuated, abstracting structural elements of buildings into nodes, abstracting the passable relationships between nodes into edges, and constructing a 3D spatial topology graph;

[0011] S2: Construction of comprehensive path weight model: For each edge in the three-dimensional spatial topology graph, a comprehensive path weight is constructed based on multiple preset path weight factors;

[0012] S3: Dynamic update of path weights: When receiving information about changes in the environment, update the comprehensive path weights corresponding to the affected edges;

[0013] S4: Path planning based on Dijkstra's algorithm: The updated three-dimensional spatial topology map is searched using Dijkstra's algorithm to calculate the optimal escape path from at least one evacuation starting point node to at least one exit node.

[0014] S5: Multi-path generation and filtering: Based on the optimal escape path, generate several candidate escape paths and sort them to provide alternative evacuation paths;

[0015] S6: Path Result Output and Visualization Mapping: Map the calculated optimal escape path and / or candidate escape paths to the 3D building model and output them for visualization.

[0016] Furthermore, in step S2, the multiple preset path weighting factors include: channel geometric length, estimated travel time, channel environmental risk level, and channel passability status.

[0017] Furthermore, the comprehensive path weight is obtained by weighting the multiple preset path weight factors.

[0018] Furthermore, in step S3, the environmental state change information includes at least one of the following: fire smoke diffusion information, temperature change information, toxic gas concentration information, passage blockage information, and population density distribution change information.

[0019] Furthermore, in step S4, the Dijkstra algorithm, which supports dynamic weight updates, is used. After the path weight update is completed in step S3, only the affected path segments are recalculated.

[0020] Furthermore, in step S5, the candidate escape paths are ranked based on the magnitude of their comprehensive path weights.

[0021] Furthermore, in step S6, the output path result is further sent to the physical path indication device for dynamic physical path guidance.

[0022] This invention also discloses a three-dimensional visualization-based integrated escape path planning system based on Dijkstra's algorithm, comprising:

[0023] The Modeling and Topology Abstraction module is used to perform 3D modeling of buildings to be evacuated, abstracting building structural elements into nodes, abstracting the walkable relationships between nodes into edges, and constructing a 3D spatial topology graph.

[0024] The comprehensive weight model construction module is used to construct a comprehensive path weight for each edge in the three-dimensional spatial topology graph based on multiple preset path weight factors.

[0025] The dynamic weight update module is used to update the comprehensive path weights corresponding to the affected edges when environmental state change information is received.

[0026] The path planning module is used to perform path search on the updated three-dimensional spatial topology map using the Dijkstra algorithm, and to calculate the optimal escape path from at least one evacuation start node to at least one exit node.

[0027] The multi-path processing module is used to generate and sort several candidate escape paths based on the optimal escape path in order to provide alternative evacuation paths.

[0028] The output and visualization module is used to map the calculated optimal escape path and / or candidate escape path to the 3D building model and output it for visualization.

[0029] Furthermore, the output and visualization module is further connected in communication with the physical path indicator device to send the path results to the physical path indicator device for dynamic guidance.

[0030] The present invention also discloses a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the above method.

[0031] Compared with the prior art, the advantages of the present invention are as follows:

[0032] 1. Improved safety and accuracy of evacuation route assessment: By constructing a comprehensive route weight model that integrates multiple factors such as channel geometry length, estimated travel time, environmental risk level, and traffic status, the optimization objective of route search shifts from a single "shortest distance" to "minimizing overall travel cost." This ensures that the planned routes proactively avoid high-risk areas, significantly improving the inherent safety of evacuation routes from a theoretical perspective.

[0033] 2. Enhanced real-time response capability to dynamic disaster environments: By introducing a dynamic path weight update mechanism, the system can quickly update and replan the path weights only for the affected local areas when receiving information about changes in environmental conditions such as smoke, temperature, and congestion. This avoids redundant calculations of the global model, significantly shortens the path update lag time, and enables evacuation guidance to adapt to emergencies such as fire spread in real time.

[0034] 3. Improved consistency between path planning and actual building structure: By converting the building's 3D model (such as BIM) into a 3D spatial topology map that can be directly used in calculations, the path planning algorithm can operate within the 3D spatial relationships. This overcomes the problem of unclear floor connections in 2D planning, ensuring that the generated paths (such as cross-floor paths) fully conform to the building's physical structure, reducing the risk of infeasible or counterintuitive planned paths.

[0035] 4. Optimized computational efficiency and applicability in complex scenarios: By supporting a path planning mechanism from multiple source points (locations of multiple trapped individuals) to multiple target points (multiple safety exits) and utilizing an improved Dijkstra algorithm for one-time global computation, the system can efficiently handle evacuation scenarios with dispersed personnel distribution within large-scale buildings. This improves the system's computational efficiency and its practicality and scalability in large-scale complex scenarios.

[0036] 5. Improved the intuitiveness and feasibility of evacuation guidance: By mapping the calculated optimal and alternative routes back to a 3D model for visualization, it provides decision support for command personnel. Simultaneously, the planning results can be directly output to physical guidance devices (such as dynamic directional signs), achieving seamless linkage from "digital routes" to "physical guidance," reducing the cognitive load on personnel understanding and executing routes, and improving the overall efficiency and reliability of emergency evacuation. Attached Figure Description

[0037] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is a schematic diagram of an application environment for the three-dimensional visualization integrated escape path planning method in this embodiment of the invention. Detailed Implementation

[0039] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0040] like Figure 1 As shown in the figure, this invention provides a three-dimensional visualization-based integrated escape path planning method based on Dijkstra's algorithm. The implementation subject of this embodiment can be a server deployed in an emergency command center. The method includes the following steps:

[0041] S1: Architectural 3D Space Topology Modeling

[0042] Obtain the Building Information Model (BIM) or oblique photogrammetry 3D model of the target building. Through semantic segmentation and spatial structure analysis of the model, the building entities are abstracted into elements of a topological network: key locations such as rooms, corridor intersections, stair landings, and safety exits are abstracted as nodes; and accessible pathways connecting two nodes (such as corridor segments, staircase segments, and doorways) are abstracted as edges. Finally, a weighted graph for pathfinding is constructed. ,in It is a set of nodes. It is a set of edges.

[0043] S2: Constructing a comprehensive path weight model

[0044] For weighted graph Each edge in (Connecting nodes) and Calculate a dynamic integrated path weight. This weight is obtained by weighted summation of multiple factors affecting traffic efficiency and safety, and its professional expression is as follows:

[0045]

[0046] In the formula: This represents the normalized channel geometry length factor, whose value is positively correlated with the actual three-dimensional spatial length of the edge.

[0047] The normalized estimated travel time factor is determined by the basic travel speed corresponding to the passage length, passage type (flat road, upstairs staircase, downstairs staircase), and the real-time crowd density correction coefficient estimated by visual sensors or Wi-Fi probes.

[0048] The normalized channel environmental risk factor is calculated using real-time monitoring data from temperature sensors, smoke sensors, carbon monoxide (CO) sensors, and other sensors deployed near the channel, through a pre-defined risk assessment function. It is derived from fusion calculations. For example, (Temperature, smoke concentration, CO concentration), when any of these parameters exceeds the standard... The value increases.

[0049] This represents the passability state factor of the channel. When the edge... When the corresponding passage is determined to be completely blocked (e.g., when debris is identified through video analysis), Set to a very large positive number (Theoretically, it approaches +∞, causing the edge to be avoided in path search; under normal conditions...) .

[0050] , , , The pre-defined non-negative weight coefficients satisfy the following conditions: These coefficients can be configured during system deployment based on building attributes (such as hospitals and shopping malls) and the focus of the evacuation strategy (fastest evacuation or safest evacuation).

[0051] S3: Dynamic update of path weights

[0052] The system connects in real-time to the building's fire alarm system and environmental sensor network. When a fire alarm signal or environmental sensor data from a specific area exceeds a threshold, a dynamic update of the weights is triggered.

[0053] 1. Determining the scope of impact: Based on the location of the event, determine the set of edges in the topology graph that are affected. .

[0054] 2. Weight recalculation: For the set Each edge in Based on the latest sensor data, its environmental risk factor was recalculated. and traffic status factor .

[0055] 3. Graph Update: Using Formula 1 and the recalculated factors, update the combined weights of the corresponding edges in the graph. This process is an incremental update, which avoids rebuilding the entire graph model and ensures real-time performance.

[0056] S4: Path planning based on an improved Dijkstra's algorithm

[0057] Path search is performed on the initial weight graph or the dynamically updated weight graph. To handle scenarios with multiple starting points (multiple locations of trapped personnel) leading to multiple exits, the Dijkstra algorithm (Multi-source Dijkstra) is adopted, which initializes with multiple source points simultaneously.

[0058] 1. Initialization: Add the nodes corresponding to the known locations of all trapped personnel to the minimum priority queue and set their arrival cost. Initialize to 0, and set the other nodes to 0. Initialize to infinity.

[0059] 2. Iterative search: Take the node u with the minimum current cost from the queue and traverse all its adjacent nodes. Calculation via node arrive The cost: .if Then update and record The predecessor node is ,Will Add or update its position in the queue.

[0060] 3. Path Determination: When the algorithm finishes running, each node... of Records from the nearest source to The minimum cumulative weight cost for any safe exit node. By tracing back to the predecessor node, the specific path from the location of the most recently trapped person to the exit can be obtained. This can be achieved by comparing all exit nodes. of The path corresponding to the exit with the smallest value is the globally optimal escape path.

[0061] S5: Alternative Path Generation

[0062] To provide decision redundancy, generate strip( Alternative paths. The method of "re-planning after deleting critical edges from the optimal path" is adopted: after obtaining the optimal path... Then, each edge is temporarily "deleted" (its weight is set to infinity), and S4 is executed again to obtain a new optimal path. The resulting set of new paths is sorted according to their cumulative weight cost to form a candidate path set.

[0063] S6: 3D Visualization Mapping and Entity Guidance

[0064] 1. Visual Mapping: The calculated node sequences of the optimal and alternative paths are matched and overlaid with the original 3D model in S1 using spatial coordinates. In the 3D scene, the optimal path is indicated by a highlighted green dynamic arrow, and alternative paths are indicated by dashed lines of different colors (such as blue and yellow).

[0065] 2. Drive physical indicator devices: The system uses the Internet of Things protocol to convert the path planning results into control commands and send them to the intelligent evacuation indicator signs (such as dynamic direction indicator lights and laser projection indicators) deployed at key nodes of the physical channel, controlling the direction of their arrows to achieve physical and dynamic evacuation guidance.

[0066] In another embodiment, a three-dimensional visualization-based integrated escape route planning system based on an improved Dijkstra algorithm is provided. This system corresponds one-to-one with the three-dimensional visualization-based integrated escape route planning method described in the above embodiments. This system is typically deployed on a server or cloud platform and connects to various terminal devices within the building via a network. Functionally, the system mainly includes the following modules:

[0067] Data Acquisition Module: Used to acquire building environment information in real time or periodically, including dynamic data from automatic fire alarm systems, temperature sensors, smoke sensors, video surveillance systems, personnel positioning systems, etc. This module provides a data source for the dynamic update of path weights (S3).

[0068] 3D Topology Modeling Module: Used to perform step S1, importing and parsing the building's BIM or 3D model data, abstracting it into a weighted graph composed of nodes and edges. To construct the basic spatial topology for path computation.

[0069] The comprehensive weight calculation module is the core calculation used to perform steps S2 and S3. This module has a built-in comprehensive path weight model and is responsible for calculating the initial weight of each edge in the graph based on real-time data. When environmental changes are detected, it triggers and completes the dynamic recalculation and update of the weights of the affected edges.

[0070] Path planning engine: This is the core algorithm module used to execute steps S4 and S5. The engine incorporates an improved Multi-source Dijkstra algorithm, receives the weighted graph updated by the comprehensive weight calculation module, performs shortest path search across multiple source and target points, and generates the optimal path and a sorted set of alternative paths.

[0071] Visualization and Rendering Module: This module is used to perform the visualization portion of step S6. It merges and renders the path node sequence output by the path planning engine with the original 3D model, generating a 3D visualization scene with highlighted path indicators for display on the command center's large screen, computer terminal, or tablet computer.

[0072] Command Issuance Module: This module executes the physical linkage part of step S6. It converts the path planning results into specific control commands and issues them to the intelligent evacuation signs (such as dynamic directional indicators and laser projectors) in the building via IoT protocols (such as MQTT and LoRaWAN) or a dedicated network, controlling their direction of indication and realizing physical guidance.

[0073] In another embodiment of the present invention, a storage medium is provided, specifically a computer-readable storage medium (Memory). This computer-readable storage medium is a memory device in a terminal device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and extended storage media supported by the terminal device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device.

[0074] One or more instructions stored in a computer-readable storage medium can be loaded and executed by a processor to implement the corresponding steps of the three-dimensional visualization integrated escape path planning method in the above embodiments; one or more instructions in the computer-readable storage medium are loaded and executed by a processor.

[0075] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0076] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0077] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A three-dimensional visualization-based integrated escape path planning method based on Dijkstra's algorithm, characterized in that, Includes the following steps: S1: 3D spatial modeling and topological abstraction of buildings: 3D modeling of buildings to be evacuated, abstracting structural elements of buildings into nodes, abstracting the passable relationships between nodes into edges, and constructing a 3D spatial topology graph; S2: Construction of comprehensive path weight model: For each edge in the three-dimensional spatial topology graph, a comprehensive path weight is constructed based on multiple preset path weight factors; S3: Path weight dynamic update steps: When environmental state change information is received, the comprehensive path weight corresponding to the affected edge is updated; S4: Path planning based on Dijkstra's algorithm: The updated three-dimensional spatial topology map is searched using Dijkstra's algorithm to calculate the optimal escape path from at least one evacuation starting point node to at least one exit node. S5: Multi-path generation and filtering: Based on the optimal escape path, generate several candidate escape paths and sort them to provide alternative evacuation paths; S6: Path Result Output and Visualization Mapping: Map the calculated optimal escape path and / or candidate escape paths to the 3D building model and output them for visualization.

2. The method according to claim 1, characterized in that, In step S2, the multiple preset path weighting factors include: channel geometric length, estimated travel time, channel environmental risk level, and channel passability status.

3. The method according to claim 2, characterized in that, The comprehensive path weight is obtained by weighting the multiple preset path weight factors.

4. The method according to claim 1, characterized in that, In step S3, the environmental state change information includes at least one of the following: fire smoke diffusion information, temperature change information, toxic gas concentration information, passage blockage information, and population density distribution change information.

5. The method according to claim 1, characterized in that, In step S4, the Dijkstra algorithm, which supports dynamic weight updates, is used. After the path weight update is completed in step S3, only the affected path segments are recalculated.

6. The method according to claim 1, characterized in that, In step S5, the candidate escape paths are ranked based on their comprehensive path weights.

7. The method according to claim 1, characterized in that, In step S6, the output path result is further sent to the physical path indication device for dynamic physical path guidance.

8. A three-dimensional visualization-based integrated escape path planning system based on Dijkstra's algorithm, characterized in that, For implementing the method as described in any one of claims 1 to 7, comprising: The Modeling and Topology Abstraction module is used to perform 3D modeling of buildings to be evacuated, abstracting building structural elements into nodes, abstracting the walkable relationships between nodes into edges, and constructing a 3D spatial topology graph. The comprehensive weight model construction module is used to construct a comprehensive path weight for each edge in the three-dimensional spatial topology graph based on multiple preset path weight factors. The dynamic weight update module is used to update the comprehensive path weights corresponding to the affected edges when environmental state change information is received. The path planning module is used to perform path search on the updated three-dimensional spatial topology map using the Dijkstra algorithm, and to calculate the optimal escape path from at least one evacuation start node to at least one exit node. The multi-path processing module is used to generate and sort several candidate escape paths based on the optimal escape path in order to provide alternative evacuation paths. The output and visualization module is used to map the calculated optimal escape path and / or candidate escape path to the 3D building model and output it for visualization.

9. The system according to claim 8, characterized in that, The output and visualization module is further connected to the physical path indicator device for sending path results to the physical path indicator device for dynamic guidance.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images