A method for optimal path planning based on a fire rescue road network directed graph

Abstract

The application is suitable for the technical field of emergency rescue, and relates to an optimal path planning method based on a fire rescue road network directed graph.The application utilizes multi-source data such as an open street map road network, road conditions, investigation data, real-time road conditions and remote sensing image data, reconstructs the road network directed graph according to a road priority principle, and further constructs an optimal path planning algorithm based on the fire rescue road network directed graph based on a dynamic weight model.The application can effectively make up for the deficiency of the existing research using online map path planning, make the path planning more suitable for the path planning demand in the real fire rescue scene, accurately calculate the driving path of the fire rescue through the application, thereby more reasonably planning the path and improving the efficiency of the fire rescue.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of emergency rescue, and particularly relates to an optimal path planning method based on a fire rescue road network directed graph. BACKGROUND

[0002] In the field of emergency rescue, the rescue efficiency of fire vehicles depends on the effectiveness of the path planning algorithm. When the fire vehicles go to perform tasks, they are not restricted by driving speed, driving route, driving direction and command signal under the premise of ensuring safety. The construction and calculation of the path planning algorithm usually depend on the road network directed graph model. The fire rescue road network directed graph should be different from the road network directed graph of ordinary vehicles. However, the existing fire rescue dispatching system usually directly calls the ordinary vehicle route planning API in the online map to determine the rescue path. However, this path planning method does not conform to the actual application. In the traffic network of the online map, the road priority right of the rescue vehicle is not considered in the road traffic, and the calculated driving path does not necessarily represent the actual driving path of the fire vehicle, and thus cannot represent the shortest time path. This method may lead to underestimation of the coverage range of the fire rescue, has low accuracy, and also restricts the improvement of the fire rescue efficiency.

[0003] The patent application with the publication number CN114611797A provides a city rescue auxiliary system based on GIS path planning, which includes an unmanned aerial vehicle detection module, a vehicle management module, a road monitoring module, a city construction map, a route planning module, an audit reporting module, and a central coordination module. The unmanned aerial vehicle detection module is used to explore the road state within 2 kilometers around the rescue vehicle in the high air. The vehicle management module is used to investigate the vehicle information on all rescue routes through big data. The road monitoring module is used to investigate the vehicle information on all rescue routes through the cameras on the road. The city construction map is used to present the road traffic network graph of the city. This patent application realizes city rescue assistance through GIS path planning. However, the road priority right of the rescue vehicle is not considered, and the same drawbacks as the prior art exist.

[0004] Therefore, how to make the path planning more suitable for the path planning requirements in the real fire rescue scene, accurately calculate the driving path of the fire rescue, and improve the efficiency of the fire rescue is a problem to be solved by the personnel in the technical field. SUMMARY

[0005] In view of the deficiencies of the prior art, the purpose of the present application is to provide an optimal path planning method based on a fire rescue road network directed graph, so as to solve the problem that the online map path planning cannot accurately calculate the driving path of the fire rescue in the prior art, and the efficiency of the fire rescue is low.

[0006] In order to solve the above technical problems, the present application adopts the following technical solutions:

[0007] The application provides an optimal path planning method based on a fire rescue road network directed graph, comprising the following steps:

[0008] S10, determining a calculation region and extracting an open street map road network, completing data cleaning, obtaining remote sensing images and performing preprocessing;

[0009] S20, defining dynamic edges, local dynamic edges and ordinary edges, identifying road types, fusing road information of the remote sensing images and the road network data, preprocessing a topological structure of the road network data and unifying a spatial coordinate system;

[0010] S30, determining a comprehensive influence factor for fire rescue speed based on road conditions, field investigation data and real-time traffic influence factors to construct a dynamic weight model;

[0011] S40, defining dynamic nodes on the dynamic edges, processing ordinary edges as two parallel non-intersecting and opposite-direction one-way edges, and constructing a fire rescue road network directed graph with road priorities based on the dynamic weight model;

[0012] S50, storing fire rescue road network directed graph data by using an adjacency list, creating a shortest distance record array of each node, and initializing a distance array and a priority queue;

[0013] S60, iteratively processing the priority queue based on the principle of the Dijkstra algorithm, extracting a current shortest distance node each time to perform an adjacent node relaxation operation, and updating the queue until all reachable nodes are traversed;

[0014] S70, analyzing final distance array data, determining a shortest path trajectory of each intersection node by reverse tracing, and outputting a complete path sequence and its cumulative distance and time.

[0015] Further, the specific steps of S10 are as follows:

[0016] S101, first, the spatial range of the target region is determined, including a pre-set urban region or a self-defined arbitrary range;

[0017] S102, then, the region boundary is obtained, and the API is called to obtain traffic road network data in the open street map for the research region of the city, including road types, lengths, connection relationships, or the edge coordinates of a specific region are manually selected to realize the demarcation according to actual needs;

[0018] S103, the time range and the spatial coverage range of the remote sensing images are determined according to the research target, the remote sensing images are selected through a public remote sensing data platform, the preprocessing of the remote sensing images includes radiation correction, geometric correction and image enhancement, and normalization processing is performed.

[0019] Furthermore, the specific steps of S20 are as follows:

[0020] S201. Define a two-way road without fences or other obstacles in the middle as a dynamic edge; define a one-way road or a two-way road with fences or other obstacles in the middle as a normal edge; define a two-way road with flower beds or other obstacles in the middle as a locally dynamic road and a locally dynamic edge, that is, including a part of normal edges and a part of dynamic edges.

[0021] S202. Extract features from the extracted road region, including the geometric features of the road, the texture features of the road, the color features of the road, and other relevant features;

[0022] S203. Use deep learning algorithms to classify and identify the extracted road features. The classification is based on the identification of road conditions and traffic attributes.

[0023] S204. Convert the open street map road network and remote sensing image data into a unified format, determine a coordinate system as the reference coordinate system, and then use the coord_convert tool in the Python library to convert the coordinate systems of different data sources to the reference coordinate system. Verify the accuracy of the converted coordinates and evaluate the overlap accuracy between the open street map road network and the remote sensing image.

[0024] Furthermore, the specific steps of S30 are as follows:

[0025] S301. All influencing factors are divided into fixed factors F, real-time dynamic factors D, and other special factors S, and standardized. Fixed factors include road segment width f1, functional level f2, actual length f3, and capacity f4. Real-time dynamic factors include traffic flow d1, average driving speed d2, traffic control measures d3, traffic light control status d4, and current weather conditions d6. Other special factors include the driver's familiarity with the road network s1.

[0026] S302. Optimize the accuracy of fire rescue routes through on-site surveys and supplement static road information. The net height and net width of fire trucks are respectively... and Ensure the road height of the road network and width and turning radius It can meet the passage requirements of fire trucks;

[0027] S303: Obtain real-time traffic data, including traffic flow speed and congestion, through Baidu Maps' real-time traffic API;

[0028] The traffic flow rating for S304 is as follows:

[0029]

[0030] wherein k is the current traffic density, kj is the jam density, i.e. the density at which traffic is completely stopped, γ k is a coefficient;

[0031] The score of traffic control is as follows:

[0032]

[0033] The score of signal light control is as follows:

[0034]

[0035] The score of weather condition is as follows:

[0036] The weather data API of the online map development platform is called to obtain the type and level of weather warning event in the current area;

[0037]

[0038] wherein Wet represents the type of weather warning event, di represents the percentage of reduced driving speed of the i-th weather warning event;

[0039]

[0040] wherein WL represents the level of weather warning event, and DoI represents the influence degree of the event;

[0041] The weighted accumulation mechanism is used to calculate the comprehensive influence score of weather, and the formula is as follows:

[0042]

[0043] wherein, represents the average influence degree of the i-th warning event type corresponding to the warning level;

[0044] β is set as the comprehensive influence factor of fire rescue speed:

[0045]

[0046] wherein ω i is the influence weight of the i-th factor, α i is the non-dimensional quantization result of the i-th fixed factor, and β i is the non-dimensional quantization result of the i-th real-time dynamic factor.

[0047] Further, the specific steps of S40 are as follows:

[0048] S401, define that the fire vehicle can freely turn in the dynamic edge, and the corresponding position is the dynamic node. The road section is visually represented in the form of a point, that is, a dynamic edge is composed of a series of dynamic nodes. All road sections that meet the dynamic edge conditions are obtained from the road network, and the collection line segment is discretized into a dynamic node sequence:

[0049]

[0050] wherein Vdi represents the node sequence discretized by the i-th dynamic edge di;

[0051] For any dynamic partial dynamic edge E pd ∈E, it can be represented as the union of a finite number of line segments and a set of dynamic nodes

[0052]

[0053]

[0054] wherein is a normal edge, (n≥1) is a set of dynamic nodes;

[0055] Traverse each partial dynamic edge to obtain its dynamic nodes and add them to the total sequence set of dynamic nodes:

[0056] ;

[0057] S402, for the road belonging to the normal edge type, the route of the fire vehicle in the driving process is the same as that of the normal vehicle. The edge of the original traffic network is defined as the original one-way edge e=(u,v). The two end nodes of the original one-way edge are translated to the right side based on the slope of the edge by a fixed distance F d to form an edge, which is called a translated one-way edge e′=(u′,v′):

[0058] ;

[0059] S403, define the fire rescue road network directed graph G={V,E,T}, including node set V, directed edge set E and edge type set T, wherein node v∈V represents the intersection or endpoint of the road section; road section e∈E represents a directed edge with starting point, endpoint, road section number and other attribute representation. A road that can be bidirectional is regarded as two one-way road sections; td, tds, ts∈T represent the types of road sections, respectively representing dynamic, partial dynamic and static types.

[0060] ​Further, a new directional relationship is established between the translation node (u', v') corresponding to each translated one-way edge and the original node (u, v), and their distance length is uniformly set to a fixed value of 1, the time is 1, each node corresponds to an integer, and is unique in the entire road network, using continuous integer labels (1, 2,..., N), where N = |V|, according to the latitude and longitude coordinates of all nodes , compare the horizontal and vertical coordinates one by one to determine the node order:

[0061]

[0062] In order to avoid repeated numbering caused by coordinate floating point error, a tolerance ε needs to be set:

[0063]

[0064] Where, N id (vi) represents the node flag of the i-th node, and the tolerance ε is 10 -6 degrees.

[0065] Find the smallest node coordinate and its corresponding node flag 1:

[0066] .

[0067] Further, for a directed road, initial distance weight and corresponding time weight are assigned according to the coordinates, the distance weight is calculated according to the following formula:

[0068]

[0069] Where x and y are the differences in longitude and latitude of the coordinate plane, respectively;

[0070] The initial time weight is set to the driving time T of an ordinary vehicle, and when calculating the driving time of a fire vehicle, the speed comprehensive influence factor of each road segment is called, and the time weight is changed to .

[0071] Further, the specific steps of the S50 are as follows:

[0072] S501, using an adjacency list to store directed graph data, a distance dictionary d[] is used to record the real-time weight from the starting point to all nodes in the graph, pb[u] represents pb[u]=1 if the vertex u is processed, otherwise it is equal to 0, for the initial node pb[src]=1, the predecessor array pre[] is used to record each predecessor node in the shortest path;

[0073] S502, initialize all elements except the source to a maximum value, i.e. d[else]=∞, indicating that the distance of these nodes is unknown at the beginning, while the distance from the source to the source is 0, so the distance of the source is set as d[src]=0, and a small root heap priority queue is created to dynamically manage the priority of the nodes to be processed, so that the node with the minimum current distance can be quickly inserted or extracted in logarithmic time complexity, after initialization, the source and its corresponding distance value are stored in the priority queue;

[0074] S503, according to the existing data, generate the directed graph of the fire rescue road network, determine each node and mark the name, draw the one-way edge and the bidirectional edge according to the actual road connection, mark the weight, determine the fire rescue related elements, mark the fire related dynamic edge with two end arrows dotted line, mark the local dynamic edge with special line, mark the fire rescue node with dark green, and further distinguish the dynamic node, so as to complete the drawing of the directed graph of the fire rescue road network.

[0075] Further, the specific steps of the step S60 are as follows:

[0076] S601, if the priority queue is not empty, the heap top element (d[u], u) is taken out from the priority queue, where d[u] is the weight of the current path, and u is the current vertex, it is checked whether the vertex is marked as 1, if not processed, it is marked as 1 to avoid subsequent repeated operation, and it is ensured that each node is relaxed only once; if the vertex has been processed, it is skipped;

[0077] S602, traverse all adjacent edges of the vertex u to perform relaxation operation, for each edge (u→v), it is judged whether the type of the edge is a dynamic edge, if it is a dynamic edge, d[v]=d[u]+dω(u,v) is updated, where dω(u,v) represents the dynamic weight of the dynamic edge (u→v); if it is a normal edge, i.e. one-way edge or bidirectional edge, d[v]=d[u]+ω(u,v) is updated, and (d[v], v) tuple is inserted into the tail, so as to ensure that the vertex v with the minimum current distance is processed preferentially, and the predecessor node of v is recorded as u, where ω(u,v) represents the weight of the normal edge (u→v);

[0078] S603, it is ensured that the mark of each vertex in the array pb is 1, so as to ensure that each vertex is processed.

[0079] Further, the specific steps of the S70 are as follows:

[0080] S701, according to the predecessor node of each node, the reverse traversal from the terminal to the source is performed, the case that there is no predecessor node is processed, and the sequence of the reconstructed path needs to be reversed to generate a forward path sequence;

[0081] S702, the distance corresponding to each shortest path edge is taken out, and the driving time obtained by dividing the distance by the fire rescue vehicle speed is accumulated and summed to output the total fire rescue driving distance and time.

[0082] The optimal path planning method based on the fire rescue road network directed graph provided by the application has at least the following beneficial effects compared with the prior art:

[0083] The existing fire rescue dispatching system usually directly calls the normal vehicle route planning API in the online map to determine the rescue path, without considering the road priority passing right of the rescue vehicle. This way may lead to underestimation of the fire rescue coverage, low accuracy, and restricts the improvement of fire rescue efficiency. The application utilizes multi-source data such as open street map road network, road conditions, investigation data, real-time traffic, and fuses remote sensing image data, reconstructs the road network directed graph according to the road priority principle, and further constructs an optimal path planning algorithm based on the fire rescue road network directed graph based on a dynamic weight model. The application can effectively make up for the shortcomings of the existing research using online map path planning, make the path planning more suitable for the path planning requirements in the real fire rescue scene, accurately calculate the driving path of the fire rescue through the application, and more reasonably plan the path to improve the efficiency of the fire rescue. BRIEF DESCRIPTION OF DRAWINGS

[0084] In order to more clearly illustrate the scheme of the application, the drawings needed in the embodiment description will be simply introduced below. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0085] Fig. 1 The flowchart of the optimal path planning method based on the fire rescue road network directed graph provided by the embodiment of the application;

[0086] Fig. 2 The remote sensing image map in the optimal path planning method based on the fire rescue road network directed graph provided by the embodiment of the application;

[0087] Fig. 3 The schematic diagram of dynamically defining the road network directed graph edge and node according to the road priority passing right in the optimal path planning method based on the fire rescue road network directed graph provided by the embodiment of the application. DETAILED DESCRIPTION

[0088] For the purposes of promoting an understanding of the principles of the application, reference will now be made to the embodiments illustrated in the drawings. The embodiments shown are meant as non-limiting examples of the application. The application can be realized in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. The application is embodied in the combinations of the various features and aspects specifically described herein.

[0089] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0090] The application provides an optimal path planning method based on a fire rescue road network directed graph, which is applied to the rescue path planning process of fire vehicles in the field of emergency rescue. The optimal path planning method based on a fire rescue road network directed graph comprises the following steps:

[0091] S10, determine the calculation area and extract the open street map road network, complete data cleaning, obtain remote sensing images and perform pretreatment; S20, define dynamic edges, local dynamic edges and ordinary edges, identify road types, fuse the road information of remote sensing images with road network data, pretreat the topological structure of road network data, and unify the spatial coordinate system; S30, based on road conditions, field investigation data and real-time traffic influencing factors, determine a comprehensive influencing factor for fire rescue speed to construct a dynamic weight model; S40, define dynamic nodes on the dynamic edges, process ordinary edges as two parallel non-intersecting and opposite directional one-way edges, construct a fire rescue road network directed graph with road priority based on the dynamic weight model; S50, store the fire rescue road network directed graph data using an adjacency list, create a shortest distance record array of each node, initialize the distance array and the priority queue; S60, based on the principle of Dijkstra algorithm, iteratively process the priority queue, extract the current shortest distance node each time to perform an adjacent node relaxation operation, and update the queue until all reachable nodes are traversed; S70, analyze the final distance array data, determine the shortest path trajectory of each intersection node by reverse tracing, and output the complete path sequence and its cumulative distance and time.

[0092] The application utilizes open street map road network, road condition, investigation data, real-time road condition and other multi-source data, and fuses remote sensing image data, reconstructs a directed graph of a road network according to a road priority principle, and further constructs an optimal path planning algorithm based on a dynamic weight model and a directed graph of a fire rescue road network.

[0093] In order to enable personnel in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings.

[0094] The application provides an optimal path planning method based on a directed graph of a fire rescue road network, which is applied to a rescue path planning process of a fire vehicle in an emergency rescue field, and combines Figs. 1 to 3 In the embodiment, the optimal path planning method based on the directed graph of the fire rescue road network includes the following steps.

[0095] S10, determine a calculation region and extract an open street map road network, complete data cleaning, obtain remote sensing images and perform preprocessing

[0096] Specifically, in the embodiment, the specific steps of step S10 are as follows.

[0097] S101, determine the spatial range of a target region, which can be a pre-set urban region or a self-defined arbitrary range, and the specific range needs to be pre-defined according to the research purpose and data requirement.

[0098] S102, obtain the region boundary, call an API to obtain traffic road network data in an open street map for a research region of a city, including road type, length, connection relationship and the like, or manually select the edge coordinates of a specific region to realize the definition.

[0099] Further, in the embodiment, in order to improve the data quality, the original data needs to be cleaned and filtered to select roads meeting the actual requirement, and the road types suitable for the passing of ordinary vehicles are selected by analyzing the road properties in the road network data.

[0100] In this embodiment, the periphery of a certain city fire station is taken as the research area, the administrative division boundary of the area is obtained, and the corresponding traffic network data in the OpenStreetMap (OSM) is obtained for the research area. The Overpass API can extract road network information according to the city id. Roads suitable for vehicle traffic such as highways, main roads, secondary roads, etc. are selected. These road types usually include motorway, primary, secondary, tertiary, etc. In this process, bus lanes (such as busway), sidewalks (such as footway), pedestrian streets (such as pedestrian), and other roads unsuitable for ordinary vehicle traffic are excluded.

[0101] S103, to further supplement the traffic network data, the high-resolution remote sensing image corresponding to the research area needs to be obtained. The time range and spatial coverage range of the remote sensing image are determined according to the research target, and the spatio-temporal consistency of the remote sensing data and the traffic network data is ensured. The remote sensing image is selected through a public remote sensing data platform, such as Jilin No. 1, Sentinel-2, or high-resolution commercial satellite data, and Tuixing Earth, etc. Fig. 2 The remote sensing image picture corresponding to the research area is obtained through Tuixing Earth, and the key parameters such as resolution, band combination, and Acquisition time are focused on.

[0102] Further, in this embodiment, the obtained original image needs to go through a preprocessing procedure, including radiation correction, geometric correction, and image enhancement operations, to eliminate the interference of clouds, shadows, and noise, improve the visualization effect and analysis accuracy of the image, and perform normalization processing.

[0103] In this embodiment, for radiation correction, the dark pixel method is used to eliminate the influence of atmospheric scattering; geometric correction is realized by combining ground control points with a polynomial model to realize image registration; median filtering is used to remove salt and pepper noise, and wavelet transform is used to reduce high-frequency noise; histogram matching is used to eliminate the radiation anomaly of clouds and shadows, and CLAHE (Contrast Limited Adaptive Histogram Equalization) is used to enhance the texture details; Min-Max normalization is used for multi-spectral bands to unify the numerical values of each band to the interval [0, 1], ensuring data comparability.

[0104] S20, define dynamic edges, local dynamic edges, and ordinary edges, identify road types, fuse road information of the remote sensing image with the road network data, preprocess the topological structure of the road network data, and unify the spatial coordinate system.

[0105] Specifically, in this embodiment, the specific steps of step S20 are as follows:

[0106] S201, define the two-way road without barriers or other obstacles in the middle as a dynamic edge; define the one-way road or the two-way road with barriers or other obstacles in the middle as a common edge; define the two-way road with part of the flower bed or other obstacles in the middle as a local dynamic road as a local dynamic edge, that is, including a part of the common edge and a part of the dynamic edge; classify and label the type of road in the remote sensing image through the tool. Identify each road in the remote sensing image one by one, and for each road, make corresponding labeling (r1, r2, r3) according to its type. After each image is classified and labeled, quality inspection is carried out to ensure the accuracy and consistency of the labeling.

[0107] S202, feature extraction is performed on the extracted road area, mainly including the geometric features of the road (such as the center line, width, etc. of the road), the texture features of the road (such as the distribution of lane lines, etc.), the color features of the road (such as gray scale, color spectrum, etc.) and other related features.

[0108] In this embodiment, Canny edge detection is used to extract the road boundary:

[0109]

[0110] Wherein, G(x,y) is a Gaussian filter, and f(x,y) is an edge intensity map.

[0111] The road center line is extracted, the method based on distance transformation is adopted to calculate the road width, and the bilateral distance measurement of the road center line is adopted:

[0112]

[0113] Wherein, the fixed point is (x,y), and the point on the road center line is ( , ).

[0114] The extracted feature vector of each road is represented as:

[0115]

[0116] Wherein, f1 represents the geometric feature, f2 represents the texture feature, f3 represents the color feature, and f4 represents other features.

[0117] S203, using a deep learning algorithm in machine learning, classifying and identifying the extracted road features. The basis of classification includes the identification of road conditions (such as good, damaged, congestion, etc.), traffic attributes (such as one-way, two-way, speed limit signs, etc.). Using deep learning methods such as convolutional neural networks (CNN), transfer learning, etc., input the extracted features into the trained model to complete the automatic classification and identification of the road. Use convolutional neural network (CNN) as the classification model, and use ResNet pre-trained model. Input the extracted feature vector F, and output the probability distribution of three types of roads.

[0118]

[0119] where W and b are model parameters, is the road category.

[0120] Further, in this embodiment, the road information detected in the remote sensing image is fused with the road network data. By comparative analysis, the consistency and difference between the two are calculated to ensure the consistency of the road information detected by remote sensing image and the actual road network. At the same time, if there is a difference, data correction and optimization are carried out to ensure that the final road information has high accuracy and reliability.

[0121] In this embodiment, taking a certain road segment as an example, the road attribute oneway of the road segment in the open street map road network information is F, that is, the road segment is a two-way road. The information detected by the acquired remote sensing image is a dynamic road, so the road attribute dynamic of the road segment is set to TT; if it is a local dynamic road, it is TF; if it is a normal road, it is FF. Comprehensive judgment of road attribute oneway is F, and attribute dynamic is TT, then the road must be a dynamic road.

[0122] Further, in this embodiment, after matching, redundant information is removed and possible topological errors are repaired to ensure the accuracy and integrity of the data, establish the topological structure of the road network, set rules for topological checking, and generate a geometrically consistent road network model.

[0123] The rules include: there should be no error hanging points. Define a hanging point as an end point connected to only one line segment (a node with degree 1), for any node v∈V, its degree is , the set of hanging points with degree 1 is: , the set of hanging points with degree 1 is:

[0124]

[0125] There must be no overlap, meaning there must be two or more line segments in close proximity. A line segment is considered to significantly overlap if the length of the spatial overlap between two line segments L1 and L2 is greater than the product of the shortest line segment length and the overlap threshold α. In this case, the shorter line segment is deleted. The shortest line segment length refers to the smaller of the lengths of L1 and L2 (proportion threshold α = 0.8).

[0126] .

[0127] S204. Convert the open street map road network and remote sensing image data into a unified format, determine a coordinate system as the reference coordinate system, and then use the `coord_convert` tool in the Python library to convert the coordinates from different data sources to the reference coordinate system. Verify the accuracy of the converted coordinates and evaluate the overlap accuracy between the open street map road network and the remote sensing image. If discrepancies exist, error analysis and correction are required to ensure the accurate spatial relationship between the two, thereby achieving precise alignment between the open street map road network and the remote sensing image.

[0128] In this embodiment, the open street network and remote sensing image data of the study area are uniformly converted into shapefile format. Using the BD09 coordinate system as the reference coordinate system, assuming the WGS84 coordinates of a certain location are (lon_wgs=116.3913, lat_wgs=39.9073), the wgs84_to_gcj02 function in the coord_convert library is called to convert the latitude and longitude coordinates from WGS-84 to the GCJ-02 coordinate system. The GCJ02 coordinates are then encrypted as (lon_gci=116.397627, lat_gcj=39.908656). Then, the gcj02_to_bd09 function in the coord_convert library is called again to obtain the Baidu BD09 coordinates (lon_bd=116.404044, lat_bd=39.915022). Finally, accuracy verification and error correction are performed.

[0129] S30. Based on road conditions, field survey data, and real-time traffic influencing factors, a dynamic weight model is constructed by determining comprehensive influencing factors for fire rescue speed.

[0130] Specifically, in this embodiment, step S30 consists of the following steps:

[0131] S301, all influencing factors are divided into fixed factors F, real-time dynamic factors D and other special factors S, and standardized processing is performed, the fixed factors include the width f1, the functional grade f2, the actual length f3 and the capacity f4 of the road section, the real-time dynamic factors include the traffic flow d1, the average driving speed d2, the traffic control measures d3, the signal lamp control condition d4 and the current weather condition d6, and the other special factors include the familiarity s1 of the driver to the road network; the number of influencing factors is l, the influence factor weight set of a road is established as W, W={w i |i=1, 2, …, l} and satisfies the formula:

[0132]

[0133] Then, the real-time factors and the other special factors are subjected to Min-Max standardization to eliminate the dimensional difference:

[0134]

[0135]

[0136] wherein, w i is the historical data set of the i-th factor in the influence factor weight set.

[0137] S302, the accuracy of the fire rescue path is optimized through field research to supplement the road static information, the net height and the net width of the fire vehicle are and respectively, and it is ensured that the road height and the width and the turning radius of the road network can meet the traffic demand of the fire vehicle; for some special road sections such as narrow streets or height-limited bridges, they are marked as impassable.

[0138]

[0139] wherein, E is a road network edge set, represents the i-th road section, , represents the effective net width and net height, is the turning radius, and v k is the fire vehicle model.

[0140] For the road section in the temporary construction state, the closed road section and the predicted recovery time are recorded, and the traffic of the line is temporarily frozen.

[0141]

[0142] wherein, t c is the current time, [t st e ] is the construction time interval.

[0143] S303, obtain real-time traffic data including traffic flow speed, congestion situation and other dynamic information through Baidu map real-time traffic API. Store the obtained vehicle passing speed speed as v, wherein speed is the average passing speed of the current road section (unit: km / h), the fire rescue vehicle is not limited by the driving speed, so that the passing speed is faster than the speed of ordinary vehicles. The congestion level , {0, 1, 2, 3, 4} ∈ respectively represent unknown road condition, smooth, slow, congestion, and serious congestion of five levels.

[0144] In this embodiment, taking a certain road section in a certain city from west to east as an example, the data v derived after execution is 1.97 km / h, which is automatically converted into a standard unit of 0.547 m / s, and the congestion level is 4.

[0145] S304, distribute and dynamically adjust the weight, and establish a dynamic weight calculation model of multiple factors such as comprehensive road passing difficulty and real-time traffic speed.

[0146] The score of traffic flow is as follows:

[0147]

[0148] Wherein, k is the current traffic density (veh / km), kj is the jam density (veh / km), that is, the density when the traffic is completely blocked, γ k is the coefficient;

[0149] The score of traffic control is as follows:

[0150]

[0151] The score of signal light control is as follows:

[0152]

[0153] The score of weather condition is as follows:

[0154] Call the weather data API of the online map development platform to obtain the weather warning event type and warning level (such as ice and snow, typhoon, heavy rain, strong wind, etc.) and warning level (blue, yellow, orange, red) of the current area. The influence degree of the warning event is represented by the warning level.

[0155]

[0156] Wherein, Wet represents the type of weather warning event, di represents the percentage of reduced driving speed of the i-th weather warning event;

[0157]

[0158] Where WL represents the level of the weather warning event, and DoI represents the degree of impact of the event;

[0159] When multiple weather warnings are issued simultaneously (such as heavy rain and strong winds), the cumulative effect of the weather needs to be considered. A weighted summation mechanism is used to calculate the comprehensive weather impact score, as shown in the following formula:

[0160]

[0161] in, This represents the average impact level corresponding to the warning level of the i-th warning event type;

[0162] Let β be the comprehensive influencing factor of fire rescue speed:

[0163]

[0164] Where, ω i Let α be the influence weight of the i-th factor. i For the dimensionless quantization result of the i-th fixed factor, β i This represents the dimensionless quantization result of the i-th real-time dynamic factor.

[0165] Let T be the travel time of a regular vehicle on a certain path, then the travel time...

[0166]

[0167] The travel time of fire trucks along this route for:

[0168]

[0169] Where L is the length of the road segment. It is the average speed of that road section.

[0170] S40. Define dynamic nodes on dynamic edges, and process ordinary edges as two parallel, non-intersecting, and opposite unidirectional edges. Construct a directed graph of the fire and rescue road network with road priority based on the dynamic weight model.

[0171] Specifically, in this embodiment, step S40 consists of the following steps:

[0172] S401. Define fire trucks as vehicles that can freely turn within dynamic edges, with the corresponding positions being dynamic nodes. Road segments are visualized as points, meaning a dynamic edge consists of a series of dynamic nodes. Obtain all road segments from the road network that meet the dynamic edge conditions, and discretize their set of line segments into a sequence of dynamic nodes.

[0173]

[0174] wherein Vdi represents the sequence of nodes discretized by the i-th dynamic edge di;

[0175] Local dynamic edges can only turn at the locations in the road segment that belong to the dynamic road, and this part of the dynamic road can be directly represented by dynamic nodes. For any dynamic local dynamic edge E pd ∈E, can be represented as the union of a finite number of line segments and dynamic nodes

[0176]

[0177]

[0178] wherein, is a normal edge, (n≥1) is a set of dynamic nodes;

[0179] Traverse each local dynamic edge, get its dynamic nodes, and add them to the total sequence set of dynamic nodes:

[0180] ;

[0181] S402, for the road belonging to the normal edge type, the route of the fire vehicle and the normal vehicle in the driving process is the same, define the original traffic road network edge as the original one-way edge e=(u,v), based on the slope of the edge, the two end nodes of the original one-way edge are translated to the right side by a fixed distance F d The edge formed after translation is called translated one-way edge e'=(u',v'):

[0182] ;

[0183] Determine the direction of the parallel one-way edge according to the national road traffic characteristics (such as right-hand drive), and the direction of the original one-way edge is just opposite.

[0184] In this embodiment, according to the traffic characteristics of Chinese roads, the road is driven on the right side, so for the two nodes u' and v' of the translated one-way edge, the node with smaller latitude value is the starting point, and the node with larger latitude value is the terminal point, such as the latitude and longitude of the nodes u'= (116.39277, 39.883716) and v'= (116.764166, 40.08495). It can be determined that u' is the starting point and v' is the terminal point.

[0185] ​S403, define the fire rescue road network directed graph G={V, E, T}, including node set V, directed edge set E and edge type set T, wherein node v∈V, representing the intersection or end point of the road section; road section e∈E, representing the directed edge, having starting point, end point, road section number and other attribute representation, a bidirectional road is regarded as two single-direction road sections; td, tds, ts∈T, representing the type of road section, respectively representing dynamic, local dynamic and static type.

[0186] Further, in the embodiment, new directional relationship is established between the translation node (u', v') corresponding to each translated single-direction edge and the original node (u, v), and their distance length is uniformly set as a fixed value 1, the time is 1, each node corresponds to an integer, and is unique in the whole road network, using continuous integer label (1, 2,..., N), wherein N=|V|, according to the longitude and latitude coordinates of all nodes , the node order is determined by comparing the horizontal and vertical coordinates one by one:

[0187]

[0188] In order to avoid repeated numbering caused by coordinate floating point error, the tolerance ε needs to be set:

[0189]

[0190] Wherein, N id (vi) represents the node mark of the i th node, and the tolerance ε is 10 -6 degrees.

[0191] Find the smallest node coordinate and its corresponding node mark 1:

[0192] .

[0193] Further, in the embodiment, for the directed road, the initial distance weight and the corresponding time weight are given according to the coordinates, the distance weight is calculated according to the following formula:

[0194]

[0195] Wherein, x and y are the difference values of the coordinate plane longitude and latitude respectively;

[0196] The initial time weight is set as the driving time T of the ordinary vehicle, when calculating the driving time of the fire vehicle, the speed comprehensive influence factor of each road is called, and the time weight is changed to .

[0197] S50, using the adjacency list to store the fire rescue road network directed graph data, creating the shortest distance record array of each node, initializing the distance array and the priority queue.

[0198] Specifically, in this embodiment, the specific steps of step S50 are as follows:

[0199] S501, using the adjacency list to store the directed graph data, the distance dictionary d[] represents the real-time weight of recording from the starting point to all nodes in the graph, pb[u] represents pb[u]=1 if the vertex u is iterated, otherwise it is equal to 0, for the initial node pb[src]=1, the predecessor array pre[] is used to record each predecessor node in the shortest path, which is convenient for subsequent path reconstruction;

[0200] S502, initialize all elements except the starting point to a maximum value, that is, d[else]=∞, indicating that the distance of these nodes is unknown at the beginning, and the distance from the starting point to the starting point is 0, so the distance of the starting point is set to d[src]=0, which is the reference point for subsequent path calculation. Generally, the node represented by the fire station is taken as the starting point. A small root heap priority queue heap is created to dynamically manage the priority of the nodes to be processed, so as to quickly insert or extract the node with the minimum distance in logarithmic time complexity. After initialization, the starting point and its corresponding distance value are stored in the priority queue together;

[0201] In this embodiment, the data of the directed graph is initialized as an array:

[0202] The node list is V=["v1", "v2",..., "v28", "vd1", "vd2"]

[0203] d={v1:0,v2:float("inf"),···,"v28":float("inf"),"vd1":float("inf"),"vd2":float("inf")}

[0204] pb={"v1":1,"v2":0,···,"v28":0,"vd1":0,"vd2":0}

[0205] pre={"v1":None,"v2":None,···,"v28":None,"vd1":None,"vd2":None,}

[0206] S503, according to the existing data, generate the directed graph of the fire rescue road network, determine each node and mark the name, draw one-way edges (solid arrows) and bidirectional edges (two ends with solid arrows) according to the actual road connection, mark the weight, determine the fire rescue related elements, mark the dynamic edge related to fire with two ends with dashed arrows, mark the local dynamic edge with special lines, mark the fire rescue node with dark green, and further distinguish the dynamic node. In this way, the directed graph of the fire rescue road network is drawn.

[0207] In the embodiment, the data of a road section is stored, and part of the data is as follows: adj={

[0208] "v1":[("v3","E001","td",250,61),("v5","E002","td",232,58)],

[0209] "v7":[("v3","E003","ts",600,79),("v9","E004","td",1,1),("v5","E005","tds",250,60)],

[0210] "vd1":[("v5","E006","ts",162,32),("vd2","E007","td",1,1)]

[0211] The storage structure of the road network data adj is "node": ("adjacent node", "road section number", "road section type", fire rescue driving distance, fire rescue driving time). The unit of the distance between the dynamic node on the local dynamic edge and the two nodes at the same traffic intersection is 1 by default. The fire rescue road network directed graph of the main road in the research area is shown in FIG. 2, wherein the weight is the time weight. Fig. 3

[0212] S60, based on the principle of Dijkstra algorithm, iteratively processes the priority queue, extracts the current shortest distance node each time to perform the adjacent node relaxation operation, and updates the queue until all reachable nodes are traversed.

[0213] Specifically, in the embodiment, the specific steps of step S60 are as follows:

[0214] The specific steps of step S60 are as follows:

[0215] S601, if the priority queue is not empty, the heap top element (d[u], u) is taken out from the priority queue, wherein d[u] is the weight of the current path, and u is the current vertex. It is checked whether the vertex is marked as 1. If not processed, it is marked as 1 to avoid subsequent repeated operations and ensure that each node is relaxed only once. If the vertex has been processed, it is skipped.

[0216] In the embodiment:

[0217] ​For pb = {"v1": 1, "v2": 1, "v3": 1, "v4": 0, "v5": 0,..., "v28": 0, "vd1": 0, "vd2": 0}, when traversing the node corresponding to v4, the corresponding mark is 1, that is, after marking, pb = {"v1": 1, "v2": 1, "v3": 1, "v4": 1, "v5": 0,..., "v11": 0, "vd1": 0, "vd2": 0}

[0218] S602, traverse all adjacent out edges of the vertex u to perform a relaxation operation, for each edge (u→v), determine whether the type of the edge is a dynamic edge, if it is a dynamic edge, update d[v] = d[u] + dω(u, v), wherein dω(u, v) represents the dynamic weight of the dynamic edge (u→v); if it is a normal edge, that is, a one-way edge or a bidirectional edge, update d[v] = d[u] + ω(u, v), and insert a (d[v], v) tuple into the tail of the queue to ensure that the vertex v with the minimum current distance is processed preferentially, and record the predecessor node of v as u, wherein ω(u, v) represents the weight of the normal edge (u→v);

[0219] S603, ensure that the mark of each vertex is 1, that is, the element corresponding to all vertices in the array pb is 1, so as to ensure that each vertex is processed.

[0220] S70, parse the final distance array data, reversely trace to determine the shortest path trajectory of each intersection node, and output the complete path sequence and the cumulative distance and time.

[0221] Specifically, in the embodiment, the specific steps of step S70 are as follows:

[0222] S701, according to the predecessor node of each node, traverse from the terminal point to the starting point in reverse, process the case of no predecessor node (path unreachable), and sequentially reverse the reconstructed path to generate a forward path sequence;

[0223] In the embodiment:

[0224] pre = {"v1": v5, "v2": v4, "v3": v1, "v4": v2, "v5": v6, "v6": v5, "v7": v9, "v8": v11, "v9": v7, "v10": v9,...}

[0225] If the reverse tracking path is: v10←v9←v6←v5←v1

[0226] Then the forward path is: v1→v5→v6→v9→v10

[0227] S702, the distance corresponding to the edge in each shortest path is taken out, and the driving time obtained by dividing the distance by the fire rescue vehicle speed is accumulated and summed to output the total fire rescue driving distance and time.

[0228] In the embodiment, in the optimal path v1-v5-v6-v9-v10, the distance weight of the edge from v1 to v5 is 250, the distance unit is set as m, the fire rescue vehicle speed is called as 4.3 m / s, the fire rescue driving time is calculated as 58 s, and the driving time standardization unit is set as second (s).

[0229] Compared with the prior art, the optimal path planning method based on the fire rescue road network directed graph in the above embodiment directly calls the ordinary vehicle route planning API in the online map to determine the rescue path, does not consider the road priority passing right of the rescue vehicle, and the method may cause underestimation of the fire rescue coverable range, is low in accuracy, and restricts the improvement of the fire rescue efficiency. The application reconstructs the road network directed graph according to the road priority principle by using multi-source data such as the open street map road network, road conditions, investigation data, real-time road conditions and fusion remote sensing image data, and further constructs the optimal path planning algorithm based on the fire rescue road network directed graph based on the dynamic weight model. The application can effectively make up for the deficiency of the prior art using the online map path planning, make the path planning more suitable for the path planning demand in the real fire rescue scene, accurately calculate the driving path of the fire rescue, and more reasonably plan the path, thereby improving the efficiency of the fire rescue.

[0230] Obviously, the above-described embodiments are only the preferred embodiments of the present application, but not all the embodiments. The preferred embodiments of the present application are shown in the drawings, but do not limit the patent scope of the present application. The present application can be realized in many different forms, and the embodiments are provided to make the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art can modify the technical solutions recorded in the foregoing embodiments, or equivalently replace some technical features. Any equivalent structure made by using the content of the present application specification and drawings, directly or indirectly used in other related technical fields, is also within the patent protection scope of the present application.

Claims

1. An optimal path planning method based on a directed graph of a fire and rescue road network, characterized in that, Includes the following steps: S10. Determine the calculation area and extract the road network of the open street map, complete data cleaning, acquire remote sensing images and perform preprocessing; S20. Define two-way roads without fences or other obstacles in the middle as dynamic edges, define one-way roads or two-way roads with fences or other obstacles in the middle as ordinary edges, and define two-way roads with some flower beds or other obstacles in the middle as locally dynamic roads and locally dynamic edges, that is, including some ordinary edges and some dynamic edges, identify road types, fuse road information from remote sensing images with road network data, preprocess the topology of road network data, and unify the spatial coordinate system; S30. Based on road conditions, field survey data, and real-time traffic influencing factors, a dynamic weight model is constructed by determining comprehensive influencing factors for fire rescue speed. S40. Define fire trucks as being able to turn freely on dynamic edges, with the corresponding positions being dynamic nodes. Treat ordinary edges as two parallel, non-intersecting, and opposite unidirectional edges. Construct a directed graph of the fire rescue road network with road priority based on the dynamic weight model. S50. Use an adjacency list to store the directed graph data of the fire and rescue road network, create an array of shortest distance records for each node, and initialize the distance array and priority queue; S60. Based on the principle of Dijkstra's algorithm, iteratively process the priority queue, extract the current shortest distance node each time, perform adjacent node relaxation operation, and update the queue until all reachable nodes have been traversed. S70. Parse the final distance array data, trace back to determine the shortest path trajectory of each intersection node, and output the complete path sequence and its cumulative distance and time.

2. The optimal path planning method based on a directed graph of a fire rescue road network according to claim 1, characterized in that, The specific steps of S10 are as follows: S101. First, define the spatial range of the target area, including pre-defined urban areas or any custom range; S102. Next, obtain the area boundary. For the research area of ​​the city, call the API to obtain the traffic network data in the open street map, including road type, length, and connection relationship, or manually select the edge coordinates of a specific area to achieve the delineation according to actual needs. S103. Determine the temporal and spatial coverage of the remote sensing images based on the research objectives, select remote sensing images through a publicly available remote sensing data platform, and perform preprocessing of the remote sensing images, including radiometric correction, geometric correction, and image enhancement, and then perform normalization processing.

3. The optimal path planning method based on a directed graph of a fire rescue road network according to claim 1, characterized in that, The specific steps of S20 are as follows: S201. Extract features from the extracted road region, including the geometric features of the road, the texture features of the road, the color features of the road, and other relevant features; S202. Use deep learning algorithms to classify and identify the extracted road features. The classification is based on the identification of road conditions and traffic attributes. S203. Convert the open street map road network and remote sensing image data into a unified format, determine a coordinate system as the reference coordinate system, and then use the coord_convert tool in the Python library to convert the coordinate systems of different data sources to the reference coordinate system. Verify the accuracy of the converted coordinates and evaluate the overlap accuracy between the open street map road network and the remote sensing image.

4. The optimal path planning method based on a directed graph of a fire rescue road network according to claim 1, characterized in that, The specific steps of S30 are as follows: S301. All influencing factors are divided into fixed factors F, real-time dynamic factors D, and other special factors S, and standardized. Fixed factors include road segment width f1, functional level f2, actual length f3, and capacity f4. Real-time dynamic factors include traffic flow d1, average driving speed d2, traffic control measures d3, traffic light control status d4, and current weather conditions d6. Other special factors include the driver's familiarity with the road network s1. S302. Optimize the accuracy of fire rescue routes through on-site surveys and supplement static road information. The net height and net width of fire trucks are respectively... and Ensure the road height of the road network and width and turning radius It can meet the passage requirements of fire trucks; S303: Obtain real-time traffic data, including traffic flow speed and congestion, through Baidu Maps' real-time traffic API; The traffic flow rating for S304 is as follows: ； Where k is the current traffic density, kj is the congestion density (i.e., the density when traffic is completely blocked), and γ k For coefficients; The traffic control measures are rated as follows: ； The traffic light control performance is rated as follows: ； Among them, t r t represents the remaining time of the red light. g t represents the remaining time of the green light. y The remaining time of the yellow light; The weather conditions are rated as follows: Call the weather data API of the online map development platform to obtain the weather warning event type and warning level for the current area; ； Where Wet represents the type of weather warning event, and di represents the percentage reduction in driving speed for the i-th weather warning event; ； Where WL represents the level of the weather warning event, and DoI represents the degree of impact of the event; The weighted cumulative mechanism is used to calculate the comprehensive weather impact score, as shown in the following formula: ； in, This represents the average impact level corresponding to the warning level of the i-th warning event type; Let β be the comprehensive influencing factor of fire rescue speed: ； Where ω is the influence weight of the factor, α is the non-dimensional quantification result of the fixed factor, and β is the non-dimensional quantification result of the dynamic factor.

5. The optimal path planning method based on a directed graph of a fire rescue road network according to claim 4, characterized in that, The specific steps of S40 are as follows: S401. Visualize road segments in the form of points, that is, a dynamic edge is composed of a series of dynamic nodes. Obtain all road segments that meet the dynamic edge conditions from the road network, and discretize their set of line segments into a sequence of dynamic nodes: ； Where Vdi represents the node sequence discretized by the i-th dynamic edge di; For any dynamic local edge E pd ∈E can be represented as the union of a finite number of line segments and the dynamic nodes. gather: ； in, For ordinary edges, (n≥1) is the set of dynamic nodes; Traverse each local dynamic edge, obtain its dynamic node, and add it to the overall dynamic node sequence set: ； S402. For roads of the ordinary edge type, fire trucks and ordinary vehicles take the same route during their journey. Define the original traffic network edge as the original one-way edge e=(u,v). Translate the two endpoints of the original one-way edge to the right by a fixed distance F based on the slope of the edge. d The resulting edge is called the translated one-way edge e′=(u′,v′): ； S403. Define a directed graph G={V,E,T} for the fire and rescue road network, including a set of nodes V, a set of directed edges E, and a set of edge types T, where nodes v∈V represent the intersections or endpoints of road segments; road segments e∈E represent directed edges, with a start point, end point, road segment number, and other attributes; a road that allows bidirectional traffic is considered as two one-way road segments; td, tds, ts∈T represent the types of road segments, which are dynamic, locally dynamic, and static types, respectively.

6. The optimal path planning method based on a directed graph of a fire rescue road network according to claim 5, characterized in that, Establish a new directional relationship between the translated node (u′, v′) and the original node (u, v) corresponding to each translated unidirectional edge, and set their distance to a fixed value of 1. The time interval is 1. Each node corresponds to an integer, which is unique throughout the entire road network, using consecutive integer labels (1, 2, ..., N), where N = |V|. This is based on the latitude and longitude coordinates of all nodes. The node order is determined by comparing the magnitudes of the horizontal and vertical coordinates one by one. ； To avoid duplicate numbering caused by coordinate floating-point errors, a tolerance ε needs to be set: ； Where, N id (vi) represents the node flag of the i-th node, with a tolerance ε of 10. -6 Spend; Find the smallest node coordinate and its corresponding node label 1: 。 7. The optimal path planning method based on a directed graph of a fire rescue road network according to claim 5, characterized in that, For directed roads, initial distance weights and corresponding time weights are assigned based on coordinates. The distance weights are calculated using the following formula: ； Where x and y are the differences between the longitude and latitude of the coordinate plane, respectively; The initial time weight is set to the travel time T of ordinary vehicles. When calculating the travel time of fire trucks, the speed comprehensive influence factor of each road segment is used, and the time weight is changed to... .

8. The optimal path planning method based on a directed graph of a fire rescue road network according to claim 7, characterized in that, The specific steps of S50 are as follows: S501. Use an adjacency list to store directed graph data. The distance dictionary d[] records the real-time weights from the starting point to all nodes in the graph. pb[u] indicates that if vertex u has been iterated, pb[u] = 1, otherwise it is equal to 0. For the initial node, pb[src] = 1. The predecessor array pre[] is used to record each predecessor node in the shortest path. S502. Initialize all elements except the starting point to a maximum value, i.e., d[else]=∞, indicating that the distance of these nodes is unknown at the beginning. The distance from the starting point to the starting point is 0, so the distance of the starting point is set to d[src]=0. Create a min-heap priority queue heap to dynamically manage the priority of nodes to be processed, so as to quickly insert or extract the node with the smallest current distance in logarithmic time complexity. After initialization, store the starting point and its corresponding distance value together in the priority queue. S503. Based on the existing data, when generating the directed graph of the fire and rescue road network, determine each node and label its name. Draw one-way and two-way edges according to the actual road connections, label the weights, determine the fire and rescue related elements, and use dashed lines with arrows at both ends to represent dynamic edges related to fire protection, and use special lines to represent local dynamic edges. Mark fire and rescue nodes with dark green, and further distinguish dynamic nodes to complete the drawing of the directed graph of the fire and rescue road network.

9. The optimal path planning method based on a directed graph of a fire rescue road network according to claim 8, characterized in that, The specific steps of step S60 are as follows: S601. If the priority queue is not empty, take the top element (d[u], u) from the priority queue, where d[u] is the weight of the current path and u is the current vertex. Check if the vertex is marked as 1. If it has not been processed, mark it as 1 to avoid repeated operations in the future and ensure that each node is relaxed only once. If the vertex has been processed, skip it. S602. Traverse all adjacent outgoing edges of vertex u and perform relaxation operations. For each edge (u→v), determine whether the edge type is a dynamic edge. If it is a dynamic edge, update d[v]=d[u]+dω(u,v), where dω(u,v) represents the dynamic weight of the dynamic edge (u→v). If it is a normal edge, i.e., a one-way edge or a two-way edge, update d[v]=d[u]+ω(u,v) and insert it into the tail of the queue in the form of (d[v],v) tuple to ensure that the vertex v with the smallest current distance is processed first, and record the predecessor node of v as u, where ω(u,v) represents the weight of the normal edge (u→v). S603. Ensure that the label of each vertex is 1, that is, the element after all vertices in the array pb is 1, thus ensuring that each vertex has been processed.

10. The optimal path planning method based on a directed graph of a fire rescue road network according to claim 9, characterized in that, The specific steps of S70 are as follows: S701. Based on the predecessor node of each node, traverse backwards from the end point to the starting point. Handle the case where there is no predecessor node. After the path is reconstructed, the order needs to be reversed to generate a forward path sequence. S702. Extract the distance corresponding to each edge in the shortest path, and the travel time obtained by dividing the distance by the speed of the fire and rescue vehicle. Sum them up and output the total fire and rescue travel distance and time.

Images