Mixed reality disaster escape route guiding method and related equipment thereof

Abstract

The invention belongs to the technical field of mine safety intelligent emergency, and particularly provides a mixed reality disaster escape route guiding method and related equipment thereof, and the method mainly comprises the steps: obtaining the original data of an underground mine, and carrying out the three-dimensional reconstruction and feature extraction processing of the original data, and obtaining basic environment features; performing topological skeleton extraction and disaster field fusion processing on the basic environment features to generate feature evolution early warning signals; performing node collaborative decision processing on the characteristic evolution early warning signal to generate collaborative decision characteristics; and executing path growth and disaster recursion detection processing on the collaborative decision feature, and outputting an escape path chain feature. According to the method, dynamic planning and intelligent adjustment of the escape route can be achieved, the real-time escape route is visually presented in combination with the mixed reality technology, the perception ability of personnel to the complex environment is improved, the escape decision time is shortened, the trapped risk caused by route blocking or information lagging is reduced, and the safety and efficiency of disaster escape are improved.

Description

Technical Field

[0001] This application belongs to the technical field of mine safety intelligent emergency, and particularly relates to a method for guiding escape routes in disasters using mixed reality and related equipment. Background Art

[0002] In the field of guiding disaster escape in complex environments such as underground mine tunnels, traditional methods mainly rely on pre-planned escape route maps and fixed signboards, and provide guidance for personnel by setting up escape signs on the tunnel walls and posting escape route maps.

[0003] However, the environment in underground mine tunnels is complex and changeable. When a disaster occurs, it can cause damage to the tunnel structure and sudden changes in the environmental conditions. Static guidance information is difficult to adapt to the dynamically changing environment, and it is difficult to timely reflect situations such as route blockages and new dangerous areas caused by disasters. It lacks the ability to intelligently plan and dynamically adjust the escape route. As a result, when a disaster occurs, the existing escape guidance methods are difficult to effectively help personnel evacuate quickly and safely, increasing the risk of being trapped and the difficulty of rescue. Summary of the Invention

[0004] This application effectively solves the problem that static guidance information in underground mine tunnels is difficult to adapt to the dynamically changing environment when a disaster occurs in the prior art, realizes the dynamic planning and intelligent adjustment of the escape route, intuitively presents the real-time escape route by combining mixed reality technology, improves the personnel's perception ability of the complex environment, shortens the escape decision-making time, reduces the risk of being trapped caused by route blockages or information lags, and improves the safety and efficiency of disaster escape.

[0005] To achieve the above object, this application adopts the following technical solutions: In the first aspect, this application provides a method for guiding escape routes in disasters using mixed reality, including: Obtain the original data of the underground mine tunnel, perform three-dimensional reconstruction and feature extraction processing on the original data to obtain the basic environmental features. Perform topological skeleton extraction and disaster field fusion processing on the basic environmental features to generate a feature evolution warning signal. Perform node collaborative decision-making processing on the feature evolution warning signal to generate collaborative decision-making features.

[0006] Perform path growth and disaster recursive detection processing on the collaborative decision-making features, and output the escape path chain features. Perform virtual-real mapping and dynamic rendering processing on the escape path chain features to generate mixed reality guidance features.

[0007] Further, the original data of the underground mine tunnel includes tunnel surface point cloud data, real-time data stream of harmful gases, and personnel movement trajectories.

[0008] Perform three-dimensional reconstruction and feature extraction processing on the original data to obtain basic environmental features, including: Perform three-dimensional point cloud reconstruction and boundary extraction processing on the roadway surface point cloud data to obtain roadway geometric contour features; perform spatio-temporal interpolation and concentration field modeling processing on the real-time data stream of harmful gases to obtain disaster particle concentration features; perform Kalman filter smoothing and feature point sampling processing on the personnel movement trajectory to obtain miner position pulsation features.

[0009] Generate basic environmental features including roadway geometric contour features, disaster particle concentration features, and miner position pulsation features.

[0010] Furthermore, perform topological skeleton extraction and disaster field fusion processing on the basic environmental features to generate feature evolution warning signals, including: Perform point cloud skeleton extraction processing on the roadway geometric contour features to generate roadway blood vessel features that penetrate the roadway.

[0011] Sample and discretize at a preset interval on the roadway blood vessel features to generate symbiotic node features with topological node numbers.

[0012] Map the disaster particle concentration features to the symbiotic node feature space range, calculate the mean value to generate disaster pulse feature values; establish a connection relationship graph between symbiotic node features, and generate blood vessel kinship based on the direction of roadway blood vessel features.

[0013] When it is detected that the disaster pulse feature value continuously rises, generate a feature evolution warning signal through broadcast processing in the blood vessel kinship network.

[0014] Furthermore, perform node collaborative decision-making processing on the feature evolution warning signal to generate collaborative decision-making features, including: Perform nearest neighbor matching processing on the miner position pulsation features and the symbiotic node feature coordinates to generate ontology node features.

[0015] According to the topological connection relationship of blood vessel kinship, retrieve directly adjacent nodes to generate an adjacent decision feature set.

[0016] Calculate the safety factor and freedom factor for each node in the adjacent decision feature set to generate survival will features.

[0017] Instruct the ontology node features to send a voting instruction to the adjacent decision feature set, and the receiving node returns a voting tendency feature according to the survival will feature.

[0018] Statistically analyze the distribution ratio of the voting tendency features to generate collaborative decision-making features including forward collaborative decision-making features, risk avoidance collaborative decision-making features, and standby collaborative decision-making features.

[0019] Further, perform path growth and disaster recursive detection processing on the collaborative decision-making features, and output the escape path chain features, including: Analyze the execution actions of the collaborative decision-making features, record the position change nodes, and generate the position change record features.

[0020] Add the new nodes in the position change record features to the linked list, and update the escape path feature chain.

[0021] Perform disaster trend detection on the collaborative decision-making features. When the disaster pulse feature value continuously rises, execute the step of generating a feature evolution warning signal through the blood kinship network broadcast processing.

[0022] Further, analyze the execution actions of the collaborative decision-making features, record the position change nodes, and generate the position change record features, including: For the forward collaborative decision-making features, locate the direct downstream nodes in the blood kinship and set them as the forward target features; for the hazard avoidance collaborative decision-making features, retrieve the node with the maximum safety factor in the adjacent decision-making feature set and set it as the hazard avoidance target feature; for the standby collaborative decision-making features, maintain the position of the ontology node features.

[0023] Further, perform virtual-real mapping and dynamic rendering processing on the escape path chain features to generate mixed reality guidance features, including: Perform spatial coordinate registration processing on the roadway blood vessel features according to the preset positioning reference points in the roadway.

[0024] Generate a circular halo feature at the position of the symbiotic node features, and generate a decision guidance feature at the ground position of the miner's field of vision; perform light band fitting processing on the escape path feature chain to generate a glowing path band feature.

[0025] When receiving the feature evolution warning signal, enhance the intensity of the circular halo feature.

[0026] In a second aspect, the present application provides a mixed reality disaster escape route guidance system, including: Data acquisition and environment modeling module: Obtain the original data of the underground mine cave, perform three-dimensional reconstruction and feature extraction processing on the original data, and obtain the basic environment features. Topological analysis and disaster warning module: Perform topological skeleton extraction and disaster field fusion processing on the basic environment features to generate a feature evolution warning signal. Collaborative decision-making processing module: Perform node collaborative decision-making processing on the feature evolution warning signal to generate collaborative decision-making features.

[0027] Intelligent path planning module: Perform path growth and disaster recursive detection processing on the collaborative decision-making features, and output the escape path chain features. Mixed reality rendering module: Perform virtual-real mapping and dynamic rendering processing on the escape path chain features to generate mixed reality guidance features.

[0028] In a third aspect, the present application provides a mixed reality disaster escape route guidance device, which includes a memory and a processor; the memory is used to store a computer program; the processor is used to implement the steps of the mixed reality disaster escape route guidance method described in the first aspect when executing the computer program.

[0029] In a fourth aspect, the present application provides a readable storage medium, in which computer program instructions are stored. When the computer program instructions are read and run by a processor, the steps of the mixed reality disaster escape route guidance method described in the first aspect are executed.

[0030] Advantages of the present application: Through technologies such as three-dimensional reconstruction, topological skeleton extraction, node collaborative decision-making, and path growth, the present application realizes the dynamic fusion of environmental features and disaster information and the intelligent generation of escape paths, effectively solving the problem in the prior art that static guidance information is difficult to adapt to the dynamically changing environment during underground mine disasters, realizing the dynamic planning and intelligent adjustment of escape paths, intuitively presenting the real-time escape route in combination with mixed reality technology, enhancing the personnel's perception ability of complex environments, shortening the escape decision-making time, reducing the risk of being trapped caused by route blockage or information lag, and improving the safety and efficiency of disaster escape.

[0031] Other features and advantages of the present application will be described in the subsequent specification, and part of them will become obvious from the specification or be understood by implementing the present application. The objectives and other advantages of the present application can be achieved and obtained through the structures pointed out in the specification and the drawings. Description of the Drawings

[0032] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0033] Figure 1 Shows a schematic flowchart of a mixed reality disaster escape route guidance method of the present application; Figure 2 Shows a schematic module diagram of a mixed reality disaster escape route guidance system of the present application. Detailed Embodiments

[0034] To solve the problems raised in the background art, the present application realizes the dynamic fusion of environmental features and disaster information and the intelligent generation of escape routes through technologies such as three-dimensional reconstruction, topological skeleton extraction, node collaborative decision-making, and path growth, realizes the dynamic planning and intelligent adjustment of escape routes, and improves the safety and efficiency of disaster escape.

[0035] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the scope of protection of the present application.

[0036] In some embodiments, as Figure 1 shown, the present application provides a method for guiding a disaster escape route in mixed reality, including: S1. Obtain the original data of the underground mine tunnel, perform three-dimensional reconstruction and feature extraction processing on the original data, and obtain the basic environmental features. S2. Perform topological skeleton extraction and disaster field fusion processing on the basic environmental features to generate a feature evolution warning signal. S3. Perform node collaborative decision-making processing on the feature evolution warning signal to generate a collaborative decision-making feature.

[0037] S4. Perform path growth and disaster recursive detection processing on the collaborative decision-making feature, and output the escape route chain feature. S5. Perform virtual-real mapping and dynamic rendering processing on the escape route chain feature to generate a mixed reality guidance feature.

[0038] In some embodiments, the original data of the underground mine tunnel in S1 includes roadway surface point cloud data, real-time data stream of harmful gases, and personnel movement trajectories.

[0039] Performing three-dimensional reconstruction and feature extraction processing on the original data in S1 to obtain the basic environmental features includes: S11. Perform three-dimensional point cloud reconstruction and boundary extraction processing on the roadway surface point cloud data to obtain roadway geometric contour features; perform spatio-temporal interpolation and concentration field modeling processing on the real-time data stream of harmful gases to obtain disaster particle concentration features; perform Kalman filter smoothing and feature point sampling processing on the personnel movement trajectories to obtain miner position pulsation features.

[0040] Collect the point cloud data of the roadway surface through a mine three-dimensional laser scanning device, perform three-dimensional point cloud reconstruction and boundary extraction processing on the original point cloud, use the Iterative Closest Point (ICP) algorithm to register the point cloud data of multiple scanning stations into a unified coordinate system to eliminate the deviation caused by different perspectives, and use the alpha shape algorithm to extract the roadway boundary line to obtain the geometric contour features of the roadway.

[0041] When performing spatio-temporal interpolation and concentration field modeling processing on the real-time data stream of harmful gases, based on a distributed gas sensor network, the inverse distance weighted algorithm can be used to calculate the concentration values in the uncovered areas. : , where , represents the concentration value at the grid point to be calculated, represents the concentration measurement value of the i-th sensor, represents the spatial influence weight of the i-th gas sensor, represents the distance from the grid point to be calculated to the position of the i-th sensor, p represents the distance attenuation coefficient, p can take the standard value of 2, n represents the number of sensors participating in the calculation, and the concentration characteristics of disaster particles are obtained.

[0042] The original data of the personnel movement trajectory can be collected through a mine intrinsically safe positioning system, perform Kalman filter smoothing and feature point sampling processing on the original trajectory, and extract the key points of the personnel trajectory every first specified time (such as 0.5 seconds) to obtain the position pulsation characteristics of the miners.

[0043] S12. Generate basic environment features including roadway geometric contour features, disaster particle concentration features, and miner position pulsation features.

[0044] The roadway geometric contour features are stored in a triangular mesh data structure, including a vertex coordinate list and a face index list, which completely describe the three-dimensional geometric shape of the roadway roof, floor, and two sides. Each triangular face represents the smallest geometric unit of the roadway surface.

[0045] The disaster particle concentration features are stored as a mapping data structure of spatial grid-concentration values, and each record item contains three-dimensional coordinates (x, y, z) and the corresponding concentration value.

[0046] The miner position pulsation features are stored in a time series format, and each record contains a timestamp, position coordinates (x, y), and a velocity vector ( , ).

[0047] In some embodiments, in S2, perform topological skeleton extraction and disaster field fusion processing on the basic environment features to generate feature evolution warning signals, including: S21. Perform point cloud skeleton extraction processing on the roadway geometric contour features to generate roadway blood vessel features that penetrate the roadway.

[0048] Adopt the shrinking bounding box algorithm to establish the three-dimensional minimum bounding box of the roadway point cloud, calculate the long axis direction of the bounding box as the initial main axis, set interval points along this axis, and shrink the point cloud along the normal direction to the convergence center line to form a continuous space curve running through the roadway.

[0049] During the processing, the curve curvature is kept continuous. In the curved roadway section with a turning radius of the first specified length (such as 2.5 meters), the curved center line is automatically adapted. When dealing with branch roadways, independent branch axes are created and smoothly connected, and finally the roadway blood vessel characteristics are output.

[0050] The roadway blood vessel characteristics are represented as a continuous three-dimensional curve of the roadway center line and stored as an ordered point set. Each point contains three-dimensional coordinates (x, y, z) and the topological connection relationship between nodes.

[0051] S22. Sample and discretize on the roadway blood vessel characteristics at a preset interval to generate the coexisting node characteristics with topological node numbers.

[0052] Based on the roadway blood vessel characteristics, sample discrete points on the roadway blood vessel characteristics at a fixed interval of the second specified length (such as 20 meters). Each sampling point is automatically numbered and given three-dimensional space attributes to obtain the coexisting node characteristics.

[0053] The coexisting node characteristics are stored as an ordered node list, including numbers, three-dimensional coordinates and connection relationships. The head and tail nodes of the list are automatically marked as the entrance / exit nodes of the roadway.

[0054] S23. Map the disaster particle concentration characteristics to the spatial range of the coexisting node characteristics, calculate the mean value to generate the disaster pulse characteristic value; establish a connection relationship graph between the coexisting node characteristics, and process according to the direction of the roadway blood vessel characteristics to generate the blood vessel kinship.

[0055] For each coexisting node characteristic, calculate the disaster particle concentration characteristics within its spatial influence range.

[0056] The spatial range is defined as a spherical area centered on the node with a radius of the third specified length (such as 15 meters). Take the time-weighted average of all sensor monitoring values within this range and mark it as the disaster pulse characteristic value Cvodp. The weight of the current cycle value can be taken as 0.7, and the weight of the disaster pulse characteristic value of the previous cycle can be taken as 0.3. The calculation formula is: ; where represents the monitoring peak value within the spatial range in this cycle, represents the disaster pulse characteristic value of the previous cycle.

[0057] Construct the node connection relationship based on the direction topology of the roadway blood relationship. Automatically identify the following three types of key nodes: terminal nodes (with only 1 connection), relay nodes (with 2 connections), and branch nodes (≥3 connections, i.e., three-way / four-way nodes). The connection relationship is stored as an adjacency vector to obtain the blood relationship.

[0058] S24. When it is detected that the disaster pulse characteristic value continuously rises, broadcast and process through the blood relationship network to generate a characteristic evolution warning signal.

[0059] Perform time series analysis on the disaster pulse characteristic value to trigger a warning. For example, when a certain node shows an absolute increase greater than 0.2% in three consecutive monitoring cycles (each cycle is 5 seconds), it is determined as a disaster evolution risk, and a warning is implemented through the blood relationship. The first level sends a first-level warning to the directly adjacent nodes, the second level forwards a second-level warning to the adjacent nodes of the adjacent nodes, and the third level terminates the propagation to obtain the characteristic evolution warning signal.

[0060] Each characteristic evolution warning signal contains a quadruple of the source node ID, disaster type, danger level, and timestamp.

[0061] In some embodiments, in S3, perform node collaborative decision-making processing on the characteristic evolution warning signal to generate collaborative decision-making characteristics, including: S31. Perform nearest neighbor matching processing on the miner position pulsation characteristic and the characteristic coordinates of the symbiotic nodes to generate the ontology node characteristic.

[0062] The ontology node characteristic is generated by a spatial nearest neighbor matching algorithm. Input the real-time coordinates of the miner position pulsation characteristic and the three-dimensional position set of the symbiotic node characteristics, calculate the Euclidean distance from the real-time coordinates to all symbiotic node characteristic nodes, and select the node with the minimum distance as the ontology node characteristic.

[0063] S32. According to the topological connection relationship of the blood relationship, retrieve the directly adjacent nodes and process them to generate an adjacent decision-making characteristic set.

[0064] Scan the connection vector corresponding to the ontology node characteristic in the blood relationship adjacency matrix and output the adjacent decision-making characteristic set.

[0065] The adjacent decision-making characteristic set contains candidate nodes that are physically adjacent and topologically directly connected, covering all possible choices of the escape direction.

[0066] S33. Calculate the safety factor and freedom factor for each node in the adjacent decision-making characteristic set to generate the survival will characteristic.

[0067] Mark the difference between 1 and the disaster pulse characteristic value of the node in the adjacent decision-making characteristic set as the safety factor.

[0068] Count the number of unblocked path nodes downstream of the nodes in the adjacent decision feature set, and mark it as the free coefficient.

[0069] Generate a survival will feature that includes a safety coefficient and a free coefficient.

[0070] S34. The instruction body node feature issues a voting instruction to the adjacent decision feature set, and the receiving node returns a voting tendency feature according to the survival will feature.

[0071] The voting tendency features include "Advance", "Warning", and "Standby".

[0072] Exemplarily, when the safety coefficient is greater than or equal to a first value (such as 0.9) and the free coefficient is greater than or equal to a second value (such as 2), return "Advance"; when the safety coefficient is less than or equal to a third value (such as 0.5), return "Warning"; otherwise return "Standby".

[0073] S35. Count the distribution ratio of the voting tendency features to generate a collaborative decision feature that includes an advance collaborative decision feature, a risk avoidance collaborative decision feature, and a standby collaborative decision feature.

[0074] The collaborative decision feature includes an advance collaborative decision, a risk avoidance collaborative decision, and a standby decision trigger.

[0075] Exemplarily, when the voting tendency feature of nodes in the adjacent decision feature set that account for a first ratio value (such as 60%) is "Advance", an advance collaborative decision is triggered; when the voting tendency feature of nodes in the adjacent decision feature set that account for a second ratio value (such as 40%) is "Warning", a risk avoidance collaborative decision is triggered; otherwise, a standby decision is triggered, that is, maintaining the status quo.

[0076] In some embodiments, in S4, path growth and disaster recursive detection processing are performed on the collaborative decision feature, and an escape path chain feature is output, including: S41. Analyze the execution actions of the collaborative decision feature, record the position change nodes, and generate a position change record feature.

[0077] S42. Add the new nodes in the position change record feature to the linked list, and update the escape path feature chain.

[0078] Generate an escape path feature chain according to the position change record feature. The linked list nodes store three-dimensional coordinates and topological relationships in chronological order, and at the same time record the snapshot of the disaster pulse feature value. When a standby decision occurs, create a redundant node at the same position to maintain path continuity.

[0079] S43. Perform disaster trend detection on the collaborative decision feature. When the disaster pulse feature value continuously rises, execute the step of generating a feature evolution warning signal through broadcast processing in the blood kinship network.

[0080] Scan the change trend of the disaster pulse feature value of the end node of the escape path feature chain every second specified time (such as 2 seconds). If the absolute growth exceeds 3% for 3 consecutive records within the detection period, it is determined that the disaster is continuously evolving, and an immediate feature evolution warning signal is sent to all adjacent nodes through the topological relationship of blood kinship.

[0081] In some embodiments, in S41, the collaborative decision-making feature execution actions are parsed, the position change nodes are recorded, and a position change record feature is generated, including: For the forward collaborative decision-making feature, locate the direct downstream node in the blood kinship and set it as the forward target feature; for the hazard avoidance collaborative decision-making feature, retrieve the node with the highest safety factor in the adjacent decision-making feature set and set it as the hazard avoidance target feature; for the standby collaborative decision-making feature, maintain the position of the ontology node feature.

[0082] In some embodiments, in S5, virtual-real mapping and dynamic rendering processing are performed on the escape path chain feature to generate a mixed reality guidance feature, including: S51. Perform spatial coordinate registration processing on the roadway blood vessel feature according to the preset positioning reference points in the roadway.

[0083] Based on the preset physical positioning reference points in the roadway (such as laser reflective markers or UWB anchors), perform spatial alignment operations on the roadway blood vessel feature.

[0084] First, collect the physical coordinates of at least 4 reference points (such as coordinate points A(0,0,0), B(50,0,0), C(0,40,0), D(0,0,3)) and the corresponding point coordinates of the roadway blood vessel feature model, and calculate the spatial transformation matrix using the least squares registration algorithm.

[0085] S52. Generate a circular halo feature at the position of the symbiotic node feature, and generate a decision guidance feature at the ground position of the miner's field of vision; perform light band fitting processing on the escape path feature chain to generate a glowing path band feature.

[0086] Project a halo at the position corresponding to the symbiotic node feature.

[0087] Exemplarily, nodes with a safety factor greater than the fourth value (such as 0.7) display a green halo with a specified diameter; nodes with a safety factor less than the fifth value (such as 0.3) display a pulsed red halo with a specified pulse frequency.

[0088] Render according to the current collaborative decision-making feature type to generate a decision guidance feature. For example, for a forward decision, a blue arrow can be projected; for a hazard avoidance decision, a flashing yellow diamond mark is projected at the position of the node with the highest safety factor; for a standby decision, a rotating red warning ring can be projected.

[0089] Perform Catmull-Rom spline fitting on the escape path feature chain to generate the luminous path band feature.

[0090] S53. When receiving the feature evolution warning signal, enhance the intensity of the annular halo feature.

[0091] When receiving the feature evolution warning signal, perform enhancement of the annular halo feature. For example, for the target node, the warning source node, and its associated nodes within two hops, increase the brightness and the blinking frequency until the warning is lifted or overwritten by a new instruction.

[0092] In some embodiments, as Figure 2 shown, the present application provides a mixed reality disaster escape route guidance system, including: Data acquisition and environment modeling module: Obtain the original data of the underground mine tunnel, perform three-dimensional reconstruction and feature extraction processing on the original data to obtain the basic environment features. Topological analysis and disaster warning module: Perform topological skeleton extraction and disaster field fusion processing on the basic environment features to generate the feature evolution warning signal. Collaborative decision-making processing module: Perform node collaborative decision-making processing on the feature evolution warning signal to generate collaborative decision-making features.

[0093] Intelligent path planning module: Perform path growth and disaster recursive detection processing on the collaborative decision-making features, and output the escape path chain features. Mixed reality rendering module: Perform virtual-real mapping and dynamic rendering processing on the escape path chain features to generate the mixed reality guidance features.

[0094] In some embodiments, the present application provides a mixed reality disaster escape route guidance device, which includes a memory and a processor; the memory is used to store a computer program; the processor is used to implement the steps of the mixed reality disaster escape route guidance method when executing the computer program.

[0095] In some embodiments, the present application provides a readable storage medium, in which computer program instructions are stored. When the computer program instructions are read and run by a processor, the steps of the mixed reality disaster escape route guidance method are executed.

[0096] Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided by the present application may include non-volatile and / or volatile memories. The non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. The volatile memory may include random access memory (RAM) or an external cache memory.

[0097] It should be noted that in this text, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0098] Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they may still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements 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 application.

Claims

1. A method for guiding the escape route in a mixed reality disaster, characterized in that, Including: Obtain the original data of the underground mine cave, perform three-dimensional reconstruction and feature extraction processing on the original data to obtain the basic environmental features; Perform topological skeleton extraction and disaster field fusion processing on the basic environmental features to generate feature evolution warning signals; Perform node collaborative decision-making processing on the feature evolution warning signals to generate collaborative decision-making features; Perform path growth and disaster recursive detection processing on the collaborative decision-making features to output the escape path chain features; Perform virtual-real mapping and dynamic rendering processing on the escape path chain features to generate mixed reality guidance features.

2. The method for guiding a mixed reality disaster escape route according to claim 1, wherein, The original data of the underground mine cave includes roadway surface point cloud data, real-time data stream of harmful gases, and personnel movement trajectories; Perform three-dimensional reconstruction and feature extraction processing on the original data to obtain the basic environmental features, including: Perform three-dimensional point cloud reconstruction and boundary extraction processing on the roadway surface point cloud data to obtain the roadway geometric contour features; perform spatio-temporal interpolation and concentration field modeling processing on the real-time data stream of harmful gases to obtain the disaster particle concentration features; perform Kalman filter smoothing and feature point sampling processing on the personnel movement trajectories to obtain the miner position pulsation features; Generate the basic environmental features including roadway geometric contour features, disaster particle concentration features, and miner position pulsation features.

3. The method for guiding a mixed reality disaster escape route according to claim 2, wherein, Perform topological skeleton extraction and disaster field fusion processing on the basic environmental features to generate feature evolution warning signals, including: Perform point cloud skeleton extraction processing on the roadway geometric contour features to generate roadway blood vessel features that penetrate the roadway; Sample and discretize at a preset interval on the roadway blood vessel features to generate symbiotic node features with topological node numbers; Map the disaster particle concentration features to the symbiotic node feature space range, calculate the mean value to generate the disaster pulse feature value; establish a connectivity relationship graph between symbiotic node features, and generate blood vessel kinship according to the direction of the roadway blood vessel features; When it is detected that the disaster pulse feature value continuously rises, generate a feature evolution warning signal through broadcast processing in the blood vessel kinship network.

4. The method for guiding a mixed reality disaster escape route according to claim 3, wherein, Perform node collaborative decision-making processing on the feature evolution warning signals to generate collaborative decision-making features, including: Perform nearest neighbor matching processing on the miner position pulsation features and the symbiotic node feature coordinates to generate ontology node features; According to the topological connection relationship of the blood vessel kinship, retrieve directly adjacent nodes to process and generate an adjacent decision-making feature set; Calculate the safety factor and freedom factor for each node in the adjacent decision-making feature set to generate the survival will feature; Instruct the ontology node features to send a voting instruction to the adjacent decision-making feature set, and the receiving node returns the voting tendency feature according to the survival will feature; Statistically analyze the distribution ratio of the voting tendency features to generate collaborative decision-making features including forward collaborative decision-making features, risk avoidance collaborative decision-making features, and standby collaborative decision-making features.

5. The method for guiding a mixed reality disaster escape route according to claim 4, characterized in that, Perform path growth and disaster recursive detection processing on the collaborative decision-making features to output the escape path chain features, including: Analyze the execution actions of the collaborative decision-making features, record the position change nodes, and generate position change record features; Add the new nodes in the position change record features to the linked list to update the escape path feature chain; Perform disaster trend detection on collaborative decision-making features. When the disaster pulse feature value continuously rises, execute the step of broadcasting and processing through the blood relationship network to generate a feature evolution warning signal.

6. The method for guiding a mixed reality disaster escape route according to claim 5, characterized in that, Analyze the execution actions of collaborative decision-making features, record the position change nodes, and generate position change record features, including: For the forward collaborative decision-making feature, locate the direct downstream node in the blood relationship and set it as the forward target feature; for the hazard avoidance collaborative decision-making feature, retrieve the node with the largest safety factor in the adjacent decision-making feature set and set it as the hazard avoidance target feature; for the standby collaborative decision-making feature, maintain the feature position of the ontology node.

7. The method for guiding a mixed reality disaster escape route according to claim 5, wherein, Perform virtual-real mapping and dynamic rendering processing on the escape path chain features to generate mixed reality guidance features, including: Perform spatial coordinate registration processing on the roadway blood features according to the preset positioning reference points in the roadway. Generate a circular halo feature at the position of the symbiotic node feature, and generate a decision guidance feature at the ground position of the miner's field of vision; perform light band fitting processing on the escape path feature chain to generate a glowing path band feature. When receiving the feature evolution warning signal, enhance the intensity of the circular halo feature.

8. A mixed reality disaster escape route guidance system, characterized in that, Including: Data acquisition and environment modeling module: Obtain the original data of the underground mine cave, perform three-dimensional reconstruction and feature extraction processing on the original data to obtain the basic environment features. Topological analysis and disaster warning module: Perform topological skeleton extraction and disaster field fusion processing on the basic environment features to generate a feature evolution warning signal. Collaborative decision-making processing module: Perform node collaborative decision-making processing on the feature evolution warning signal to generate collaborative decision-making features. Intelligent path planning module: Perform path growth and disaster recursive detection processing on the collaborative decision-making features, and output the escape path chain features. Mixed reality rendering module: Perform virtual-real mapping and dynamic rendering processing on the escape path chain features to generate mixed reality guidance features.

9. A mixed reality disaster escape route guidance device, characterized in that, It includes a memory and a processor; the memory is used to store a computer program; the processor is used to implement the steps of the mixed reality disaster escape route guidance method according to any one of claims 1-7 when executing the computer program.

10. A readable storage medium, characterized in that, Computer program instructions are stored in a readable storage medium. When the computer program instructions are read and run by a processor, the steps of the mixed reality disaster escape route guidance method according to any one of claims 1-7 are executed.

Images