CN116894611A - Urban rail transit station passenger evacuation simulation method and system - Google Patents
Urban rail transit station passenger evacuation simulation method and system Download PDFInfo
- Publication number
- CN116894611A CN116894611A CN202310821421.XA CN202310821421A CN116894611A CN 116894611 A CN116894611 A CN 116894611A CN 202310821421 A CN202310821421 A CN 202310821421A CN 116894611 A CN116894611 A CN 116894611A
- Authority
- CN
- China
- Prior art keywords
- evacuation
- passenger
- passengers
- simulation
- station
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004088 simulation Methods 0.000 title claims abstract description 119
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000005516 engineering process Methods 0.000 claims abstract description 11
- 230000008569 process Effects 0.000 claims abstract description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 60
- 230000033001 locomotion Effects 0.000 claims description 40
- 230000006870 function Effects 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 19
- 230000004888 barrier function Effects 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 15
- 238000010586 diagram Methods 0.000 claims description 13
- 230000006399 behavior Effects 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 239000003086 colorant Substances 0.000 claims description 8
- 238000013135 deep learning Methods 0.000 claims description 7
- 238000004519 manufacturing process Methods 0.000 claims description 5
- 230000001133 acceleration Effects 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 4
- 230000035484 reaction time Effects 0.000 claims description 4
- 230000000903 blocking effect Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000008447 perception Effects 0.000 claims description 3
- 235000006679 Mentha X verticillata Nutrition 0.000 claims 1
- 235000002899 Mentha suaveolens Nutrition 0.000 claims 1
- 235000001636 Mentha x rotundifolia Nutrition 0.000 claims 1
- 238000011161 development Methods 0.000 abstract description 3
- 238000010276 construction Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q90/00—Systems or methods specially adapted for administrative, commercial, financial, managerial or supervisory purposes, not involving significant data processing
- G06Q90/20—Destination assistance within a business structure or complex
- G06Q90/205—Building evacuation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/62—Extraction of image or video features relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Computation (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Geometry (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Computer Security & Cryptography (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Primary Health Care (AREA)
- Architecture (AREA)
- Computer Graphics (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Compared with the traditional crowd evacuation simulation method, the method has the advantages of low cost, low risk, high simulation degree and the like, and therefore, the development of the crowd evacuation simulation technology is valued. The evacuation process of the subway station can be accurately simulated, and a new thought is provided for evacuating passengers in emergencies.
Description
Technical Field
The application relates to the technical field of big data processing, in particular to a passenger evacuation simulation method and system for an urban rail transit station.
Background
In recent years, along with the rapid development of social economy, the rail traffic industry is also continuously prospering. Urban rail transit is favored by people gradually due to the advantages of high speed, safety, convenience, less pollution and the like. Along with the continuous growth of the construction scale of urban rail transit, the road network structure is increasingly complex, and the diversity of transfer methods and train operation organizations enables the urban rail transit to gradually enter the networked operation era.
However, the urban rail transit is gradually increased in scale, and the attraction capacity to the passenger flow is continuously increased, so that the phenomenon of large passenger flow occurs. Because the rail transit station is relatively closed and narrow and has a complex structure, if an emergency occurs, the station passenger flow is difficult to be rapidly evacuated in a short time. Therefore, it is important to simulate the station passenger evacuation in this situation, and how to quickly find a safe path to evacuate passengers in a short time after an emergency occurs, so as to avoid further severe events, which is a difficult problem to be discussed and solved in the industry.
Disclosure of Invention
Aiming at the defects existing in the technology, the application provides the urban rail transit station passenger evacuation simulation method and system, compared with the traditional crowd evacuation simulation method, the computer simulation technology has the advantages of low cost, low risk, high simulation degree and the like, so that the development of the crowd evacuation simulation technology is valued. The evacuation process of the subway station can be accurately simulated, and a new thought is provided for evacuating passengers in emergencies.
In order to achieve the above purpose, the application provides a simulation method for evacuating passengers in an urban rail transit station, which comprises the following steps:
s1: target detection and tracking are carried out on target passengers in the subway station monitoring video through a deep learning technology, and real running track data of the passengers are obtained;
s2: building a passenger evacuation simulation model according to the evacuation scene information and the passenger parameter information, and extracting characteristics of the evacuation scene by using a model building unit of the system to obtain a three-dimensional model of the evacuation scene;
s3: the algorithm is improved based on the real passenger travelling track data, and the algorithm is used for calculating the optimal evacuation path of each passenger in the station;
s4: and carrying out a simulation experiment on the passenger evacuation behavior in the simulation system, and ending the simulation when all passengers are evacuated to a safety area to obtain a simulation result.
Preferably, target detection and tracking are performed on target passengers in a subway station monitoring video through a deep learning technology, and real running track data of the passengers are obtained, specifically:
acquiring evacuation motion videos of target passengers through an intelligent monitoring camera preset in an urban rail transit station, dividing the video data into video segments frame by frame according to the number of frames, and manufacturing a passenger motion data set;
performing target labeling according to the obtained data set, dividing the data set into a training set and a testing set, training the training set by utilizing a YOLO v5 target detection algorithm, performing effect test on the trained weight model by using the testing set, and finally outputting a target detection result;
tracking a motion trail of a target passenger by using a Deep Sort multi-target tracking algorithm according to a target detection result, setting up a rectangular coordinate system in a video image, determining a pixel position of the passenger in the video, outputting a position coordinate of the passenger and marking the motion trail;
and converting the pixel coordinates of the passengers into real world coordinates by adopting a linear matrix conversion method, and manufacturing a real track data set.
As an optimization, a passenger evacuation simulation model is constructed according to evacuation scene information and passenger parameter information, and the system is utilized to build a model building unit to extract the characteristics of the evacuation scene to obtain a three-dimensional model of the evacuation scene, which is specifically as follows:
making a condition assumption on a model, wherein the model is used on the premise of being based on the assumption condition; secondly, setting a passenger evacuation target and constraint conditions, wherein the conditions for completing evacuation are that the last passenger is evacuated to a safety area, and setting the total time required by passenger evacuation as an optimized target, wherein the calculation formula of the total evacuation time T is as follows:
min T＝∑T k +λ (k＝1，2，3，4)
wherein T represents total passenger evacuation time, T 1 The reaction time of the passengers is represented, the value is 1 minute, T 2 Indicating the time for passengers at the hall to evacuate to the stairs or escalator, T 3 Time of passenger passing stairs and stairs, T 4 Representing the travel time of passengers at the hall level, λ represents the penalty factor of the objective function, and takes a value of 0 or 10 depending on the form of the station.
Time T representing evacuation of passengers from the hall floor to the stairway or escalator 2 The calculation formula of (2) is as follows:
wherein d 0 Representing the distance of platform floor passengers evacuating to the stairway or escalator entrance, v representing the average speed of passengers，
Time T representing passage of passengers through stairs and stairs 3 The calculation formula of (2) is as follows:
wherein v is 1 Representing the average travelling speed before the blocking of the passengers in the stair or at the escalator, v 2 Indicating average speed of travel of passengers, L, before passing through undisturbed sections of stairs 1 Representing the horizontal total length of stairs, L 2 Represents the horizontal total length of the stairway of the disturbed section, and phi represents the inclination angle of the stairway.
Representing the travel time T of a passenger at a hall floor 4 The calculation formula of (2) is as follows:
wherein d 1 Representing the distance from the entrance to the exit of the hall floor for evacuating passengers, and v represents the average speed of the passengers;
modeling the evacuation scene by a rasterization method, dividing the evacuation scene into an obstacle area and a passable area, enabling passengers to walk in the passable area by moving, and determining the positions of the passengers by the actual positions of the cells in the scene;
the passenger evacuation behavior modeling steps in the passenger evacuation simulation model are as follows:
initializing the number of passenger groups, and defining the number, weight, radius, expected speed, starting position, ending position, floor information and other attributes of each passenger;
step two, flexibly setting whether temporary barriers are included in the simulation scene or not and whether suction points exist or not;
third step, for each individual a i An initial evacuation path is defined by adopting path planning rule, the attraction force, the repulsive force and the driving force of the passengers are calculated by using a social force model, and the acceleration of the passengers is definedAnd direction, carry on the position adjustment to the initial movement of passenger;
fourth, each individual a is re-planned for each operating interval i According to the evacuation path of each individual a calculated according to the social force model i The position to be moved in the next step;
fifth step, individual a i Movement is initiated and either the moved position or not moved is selected. If the end position is reached, executing the next step; otherwise, returning to the previous step;
sixth step, individual a i When the simulation scene reaches the end position, the simulation scene is deleted for evacuating to a safe area, and the individual a i Ending the movement of (2).
Preferably, in step S3, the actual passenger travel track data improves a conventional a-routing algorithm, and uses the improved a-routing algorithm as a solving algorithm of a passenger evacuation simulation model to calculate an optimal evacuation path of each passenger in the station, which specifically includes:
by adding path selection weight coefficients and distance coefficients when approaching obstacles to traditional A * The algorithm is improved, and the social force model is fused into A * In the algorithm; utilizing a multi-layer neural network pair A according to the obtained real passenger travel track data * Parameters of an algorithm and a social force model are adjusted, and the improved A is adjusted by utilizing a multi-layer neural network according to real running track data of passengers * And the parameters of the path finding algorithm and the social force model are used for calculating the optimal path of passenger evacuation in the passenger evacuation simulation model.
Preferably, in step S4, the built simulation system is used to perform simulation analysis on the evacuation behavior of passengers in the station, and when all passengers in the station are evacuated to a safe area, the simulation is ended, and the simulation result is analyzed, where the system includes:
the initialization module is used for building an emergency evacuation simulation scene of the subway station and initializing personnel to be evacuated;
the passenger perception module can automatically perceive the surrounding environment, the own physiological and psychological states of people to be evacuated;
A * the path finding algorithm building module is used for building a path finding algorithm according to each to-be-evacuated modulePlanning an initial optimal evacuation path according to the starting position and the ending position of the personnel, and establishing an initial social force model of each personnel to be evacuated;
the evacuation simulation module simulates the motion path of the personnel to be evacuated according to the time step, calculates the stress condition by using the social force model in the motion process of each step, and adjusts the position to be moved in the next step in real time until reaching the end position, thereby obtaining the motion state and the final simulation result of the personnel to be evacuated at each simulation moment.
The application also discloses a passenger evacuation simulation system of the urban rail transit station, which comprises a functional area and a simulation interface display area, wherein the functional area comprises a program provided with a passenger evacuation simulation method of the urban rail transit station, and the functional area and the simulation interface are connected with each other and electrically connected with the functional area: the function area is provided with a plurality of keys, including a function key, a chart generation key, an information display frame and a prompt frame; and the simulation interface display area displays the passenger evacuation situation in real time.
As a preferred mode, corresponding models are built for evacuation scenes, people to be evacuated and barriers in stations, so that computer identification is facilitated, particularly, a map generation rule is realized, when the system starts to operate, a two-dimensional plan of the stations is required to be read, rasterization is carried out on the plan, and each grid corresponds to corresponding position information; reading each pixel point in the plan, extracting RGB colors of the pixel points, and distinguishing the types of the cells into barriers and passable areas according to the brightness of different colors.
Preferably, the improved a-algorithm and social force model are adopted as a bottom layer calculation algorithm to carry out simulation on passenger evacuation, and the method specifically comprises the following steps:
the first step: selecting two processed plane diagrams, namely selecting a station hall plane diagram for the first time and selecting a station platform plane diagram for the second time;
and a second step of: generating an initial position of a station passenger in a passable area, and optionally setting facility equipment such as movable barriers, suction points and the like which influence the movement of the passenger;
and a third step of: and running a program, wherein the system calculates the position of each passenger at the next moment in each time interval, updates and stores the information such as the position, the expected direction and the like, and simulates the motion process of passenger evacuation step by step in each time stamp in a mode of drawing images. The end positions of all passengers are initially set as the gateway closest to the passengers, but the gateway can be flexibly selected for evacuation according to actual conditions;
fourth step: and after the simulation is finished, a corresponding data analysis chart is obtained, and a simulation result is analyzed.
The beneficial effects of the application are as follows: compared with the prior art, the method and the device have the advantages that target detection and tracking are carried out on target passengers in the subway station monitoring video through a deep learning technology, and real running track data of the passengers are obtained; building a passenger evacuation simulation model according to the evacuation scene information and the passenger parameter information, and extracting characteristics of the evacuation scene by using a model building unit of the system to obtain a three-dimensional model of the evacuation scene; the method comprises the steps of improving a traditional A-type routing algorithm based on real passenger travel track data, and using the improved A-type algorithm as a solving algorithm of a passenger evacuation simulation model to calculate an optimal evacuation path of each passenger in a station; and (3) carrying out simulation experiments on the passenger evacuation behaviors in the simulation system, and ending the simulation when all passengers are evacuated to a safety area. The application improves the efficiency of passenger evacuation, effectively solves the problem of passenger safety evacuation of subway stations under the condition of large passenger flow, and ensures the life and property safety of personnel in the stations.
Drawings
FIG. 1 is a flow chart of the steps of the present application;
FIG. 2 is a flow chart of the application for extracting the passenger travel track by using the deep learning technology;
FIG. 3 is a flow chart of a simulation model of passenger evacuation at a station of urban rail transit;
fig. 4 is a flowchart of a subway station passenger evacuation path planning method integrated with a social force model improvement a algorithm according to the present application;
fig. 5 is a flowchart of the passenger evacuation simulation system of the urban rail transit station of the present application.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, however, the present application may be practiced in other ways than those described herein, and therefore the scope of the present application is not limited to the specific embodiments disclosed below.
Referring to fig. 1 to 5, the application discloses a passenger evacuation simulation method for an urban rail transit station, which comprises the following steps: s1: target detection and tracking are carried out on target passengers in the subway station monitoring video through a deep learning technology, and real running track data of the passengers are obtained; s2: building a passenger evacuation simulation model according to the evacuation scene information and the passenger parameter information, and extracting characteristics of the evacuation scene by using a model building unit of the system to obtain a three-dimensional model of the evacuation scene; s3: the algorithm is improved based on the real passenger travelling track data, and the algorithm is used for calculating the optimal evacuation path of each passenger in the station; s4: and carrying out a simulation experiment on the passenger evacuation behavior in the simulation system, and ending the simulation when all passengers are evacuated to a safety area to obtain a simulation result.
In order to achieve the above purpose, the evacuation motion video of the target passengers is collected through an intelligent monitoring camera preset in the urban rail transit station, video data is divided into video segments frame by frame according to the number of frames, and a passenger motion data set is manufactured; performing target labeling according to the obtained data set, dividing the data set into a training set and a testing set, training the training set by utilizing a YOLO v5 target detection algorithm, performing effect test on the trained weight model by using the testing set, and finally outputting a target detection result; tracking a motion trail of a target passenger by using a Deep Sort multi-target tracking algorithm according to a target detection result, setting up a rectangular coordinate system in a video image, determining a pixel position of the passenger in the video, outputting a position coordinate of the passenger and marking the motion trail; and converting the pixel coordinates of the passengers into real world coordinates by adopting a linear matrix conversion method, and manufacturing a real track data set.
The simulation model construction process firstly needs to carry out condition assumption on a model, and the model is used on the premise of being based on the assumption condition; secondly, setting a passenger evacuation target and constraint conditions, wherein the conditions for completing evacuation are that the last passenger is evacuated to a safety area, and setting the total time required by passenger evacuation as an optimized target, wherein the calculation formula of the total evacuation time T is as follows:
min T＝∑T k +λ (k＝1，2，3，4)；
wherein T represents total passenger evacuation time, T 1 The reaction time of the passengers is represented, the value is 1 minute, T 2 Indicating the time for passengers at the hall to evacuate to the stairs or escalator, T 3 Time of passenger passing stairs and stairs, T 4 The running time of passengers in a hall layer is represented, lambda represents a penalty factor of an objective function, and the value of 0 or 10 is taken according to the form of a platform;
time T representing evacuation of passengers from the hall floor to the stairway or escalator 2 The calculation formula of (2) is as follows:
wherein d 0 The distance from the passengers on the platform layer to the stairs or the escalator entrance is represented, v represents the average speed of the passengers, and the average speed can be valued to be 1.25m/s for middle-aged and young men, 1.05m/s for middle-aged and young women, and 0.67m/s for children and old people according to different age ranges of the passengers;
time T representing passage of passengers through stairs and stairs 3 The calculation formula of (2) is as follows:
wherein v is 1 Indicating average travel speed before blocking the passengers in the stair or at the escalatorDegree, v 2 Indicating average speed of travel of passengers, L, before passing through undisturbed sections of stairs 1 Representing the horizontal total length of stairs, L 2 The horizontal total length of the stairway of the disturbed section is represented, and phi represents the inclination angle of the stairway;
representing the travel time T of a passenger at a hall floor 4 The calculation formula of (2) is as follows:
wherein d 1 Indicating the distance from the entrance to the exit at which the passengers at the hall are evacuated, and v indicating the average speed of the passengers.
The constraint conditions of the total time of passenger evacuation are as follows, and the time specified in the subway design Specification must be satisfied:
T k ≤6min (k＝1，2，3，4)
modeling the evacuation scene by a rasterization method, dividing the evacuation scene into an obstacle area and a passable area, enabling passengers to walk in the passable area by moving, and determining the positions of the passengers by the actual positions of the cells in the scene;
the passenger evacuation behavior modeling steps in the passenger evacuation simulation model are as follows:
initializing the number of passenger groups, and defining the number, weight, radius, expected speed, starting position, ending position, floor information and other attributes of each passenger;
step two, flexibly setting whether temporary barriers are included in the simulation scene or not and whether suction points exist or not;
third step, for each individual a i An initial evacuation path is drawn by adopting path planning rule, the attraction force and the repulsive force initially received by the passengers and the driving force of the passengers are calculated by using a social force model, the acceleration and the direction of the passengers are defined, and the initial movement of the passengers is subjected to position adjustment;
fourth, each individual a is re-planned for each operating interval i According to the evacuation path of each individual a calculated according to the social force model i The position to be moved in the next step;
fifth step, individual a i Movement is initiated and either the moved position or not moved is selected. If the end position is reached, executing the next step; otherwise, returning to the previous step;
sixth step, individual a i When the simulation scene reaches the end position, the simulation scene is deleted for evacuating to a safe area, and the individual a i Ending the movement of (2).
In step S3, the actual passenger travel track data improves the traditional a-routing algorithm, and uses the improved a-routing algorithm as a solving algorithm of a passenger evacuation simulation model to calculate an optimal evacuation path of each passenger in the station, specifically:
by adding path selection weight coefficients and distance coefficients when approaching obstacles to traditional A * The algorithm is improved, and the social force model is fused into A * In the algorithm; utilizing a multi-layer neural network pair A according to the obtained real passenger travel track data * Parameters of an algorithm and a social force model are adjusted, and the improved A is adjusted by utilizing a multi-layer neural network according to real running track data of passengers * And the parameters of the path finding algorithm and the social force model are used for calculating the optimal path of passenger evacuation in the passenger evacuation simulation model. It should be noted that, by adding the path selection weight coefficient and the distance coefficient when approaching the obstacle, the method is applied to the conventional A * The algorithm is improved, and the social force model is fused into A * In the algorithm; utilizing a multi-layer neural network pair A according to the obtained real passenger travel track data * Parameters of the algorithm and the social force model are adjusted; traditional A * The algorithm relies on the valuation function to calculate the position of the passenger for the next step, which is calculated as follows:
F(n)＝G(n)+H(n)
where F (n) represents the total cost consumed by the passenger moving from the originating node to node n, and G (n) represents the cost of movement of the passenger moving from the originating node to node n; h (n) represents the estimated cost of the passenger moving from node n to the target node;
A * algorithm in the actual searching processSome path nodes are not searched, and thus for A * Adding a path weight coefficient omega into a heuristic function in the algorithm, and optimizing a path searching algorithm on the basis of keeping planning out a better path so as to shorten the searching time; for the estimated cost H (n) value of node n, when the H (n) value is large, the ω value should also be large; when the value of H (n) is small, the value of ω should also be small. Assuming that the selected intermediate threshold value is k, and when the value of H (n) is larger than k, the value of omega is larger; whereas the omega value is smaller. The following formula is shown:
wherein ω represents a path weight coefficient, k is set to be 30, and when the distance between the node and the end point is greater than 30, the weight coefficient is selected to be 3.0; otherwise, selecting a weight coefficient of 0.8; the heuristic function after adding the path weight coefficient ω is therefore shown by:
F(n)＝G(n)+ωH(n)
the G (n) value in the heuristic function is used for balancing the movement cost, when the child nodes around the father node contain the barrier grid, the distance coefficient is added to increase the movement cost, the algorithm is prevented from selecting the node as the father node, so that the calculated path and the barrier keep a certain distance, and the situation of approaching the barrier is avoided. The value of the distance coefficient α can be obtained by the following formula:
the calculation method of the movement cost G (n) can be as follows:
wherein, alpha represents the path distance coefficient when approaching an obstacle, when the child node contains the obstacle, the alpha takes the value of infinity, when the child node does not contain the obstacle, the alpha takes the value of 1,
Therefore, it can be seen that, when the path selection weight coefficient ω and the distance coefficient α when approaching the obstacle are added, the estimation function calculation formula of the modified a-algorithm is as follows:
and fusing the social force model with the traditional A-based route searching algorithm, and establishing a passenger route planning algorithm containing the social force model. Acceleration of pedestrian i in social force model is driven by self-driving force of pedestrian iInteraction force between pedestrian i and pedestrian j - f ij And the interaction force f between the pedestrian i and the wall w iw The calculation formula is determined as follows:
wherein m is i The weight of the pedestrian i is indicated,the actual travel speed of the pedestrian i is indicated.
Self-driving force of pedestrian iThe calculation formula of (2) is as follows:
wherein, the liquid crystal display device comprises a liquid crystal display device,indicating the expected walking rate of pedestrian i in time t,/->Representing the actual speed of travel of pedestrian i at time t, lambda i Indicating the time for pedestrian i to avoid colliding with other pedestrians and obstacles, i.e. the reaction time of the speed adjustment,representing the expected direction of travel of pedestrian i;
interaction force between pedestrian i and pedestrian jBy repulsive force between them->And mutual attraction force
The calculation formula is as follows:
wherein A is i Is constant and represents the intensity of the psychological repulsive force of the pedestrian i, B i Is constant and represents the range size of the psychological repulsive force of the pedestrian i, r ij Representing the sum of the radii of pedestrian i and pedestrian j, the instant formula r ij ＝r i +r j Expressed, d ij Represents the centroid distance, n, between pedestrian i and pedestrian j ij Unit vector representing direction of acting force of pedestrian j on pedestrian i, i.e. instant equationExpressed by k, the body compression coefficient between persons, κ, the sliding friction coefficient between persons, t ij Represents tangential direction between pedestrians, < >>Wherein->Is the relative speed in the tangential direction between pedestrian i and pedestrian j;
g (x) is a step function, when r ij -d ij When there is mutual contact between pedestrian i and pedestrian j, > 0, there is g (x) =x, otherwise, g (x) =0, and the calculation formula is as follows:
wherein d iw Representing the distance of pedestrian i from the surface of obstacle w,normal unit direction vector, t, representing obstacle w pointing to pedestrian i iw A tangential unit direction vector representing a distance between the pedestrian i and the obstacle w; and according to the real running track data of the passengers, utilizing the multi-layer neural network to adjust the parameters of the improved A-based routing algorithm and the social force model, and calculating the optimal passenger evacuation path in the passenger evacuation simulation model.
It should be noted that, utilize the simulation system of setting up to carry out simulation analysis to the passenger evacuation action in the station, the simulation is ended when all passengers in the station evacuate to the safe area, analysis simulation result, this system includes:
the initialization module is used for building an emergency evacuation simulation scene of the subway station and initializing personnel to be evacuated;
the passenger perception module can automatically perceive the surrounding environment, the own physiological and psychological states of people to be evacuated;
A * road searchingThe algorithm building module is used for planning an initial optimal evacuation path according to the starting position and the ending position of each person to be evacuated and building an initial social force model of each person to be evacuated;
the evacuation simulation module simulates the motion path of the personnel to be evacuated according to the time step, calculates the stress condition by using the social force model in the motion process of each step, and adjusts the position to be moved in the next step in real time until reaching the end position, thereby obtaining the motion state and the final simulation result of the personnel to be evacuated at each simulation moment.
The application also provides a passenger evacuation simulation system of the urban rail transit station, which comprises a functional area and a simulation interface display area, wherein the functional area comprises a program provided with a passenger evacuation simulation method of the urban rail transit station, and the functional area and the simulation interface are connected with each other and electrically connected with the functional area: the function area is provided with a plurality of keys, including a function key, a chart generation key, an information display frame and a prompt frame; the simulation interface display area displays the passenger evacuation situation in real time; establishing a corresponding model for an evacuation scene, people to be evacuated and obstacles in a station, facilitating computer identification, particularly a map generation rule, wherein when the system starts to operate, a two-dimensional plan of the station needs to be read first, the plan is subjected to rasterization, and each grid corresponds to corresponding position information; reading each pixel point in the plan, extracting RGB colors of the pixel points, and distinguishing the types of the cells into barriers and passable areas according to the brightness of different colors; in the implementation process, the simulation system is mainly developed by using C# language under the environment of Microsoft Visual Studio and 2019, and is built by adopting WinForm window functions based on a NET frame 4.7.2 Framework in a Windows 11 operating system, wherein used controls mainly include button, textBox, label, pictureBox, timer and the like. The agent.cs file is used for setting all attributes of the individual passengers, including passenger numbers, initial speeds, radiuses, weights, starting positions, ending positions, evacuation time, social forces and the like; the AStarAlgorithm.cs class file is the core code of the A-routing algorithm; the Point.cs class file is mainly used for defining the attribute of the passenger model; the socialforce.cs class file is a core code of the social force model; the using method.cs class file comprises various calculation methods which are used in the running process of the system; the function area mainly comprises function keys required by simulation, a chart generation key, an information display frame, a prompt frame and the like, the function keys comprise map generation, suction point setting, barrier setting, ticket checking area setting, simulation starting and the like, the result output keys comprise quantity-time diagram, crowd density diagram, individual information table, exit density diagram, running path diagram and the like, the information display frame is mainly used for checking the real-time residual number of stations and the running time of the systems during running, and the simulation interface display area is mainly used for displaying the passenger evacuation conditions of the hall layer and the platform layer. The output of the simulation result is not placed on the main interface, but is set into an independent output interface through keys, so that the simulation result is convenient for a user to check at any time.
It should be noted that the simulation system is characterized in that it can build corresponding models for evacuation scenes, people to be evacuated and obstacles in stations, and is convenient for computer recognition, specifically:
the map generation rule is that when the system starts to operate, a two-dimensional plan of a station is required to be read firstly, the plan is subjected to rasterization, and each grid corresponds to corresponding position information; reading each pixel point in the plan, extracting RGB colors of the pixel points, and distinguishing the types of the cells into barriers and passable areas according to the brightness of the three colors.
In the passenger representation method, the passenger evacuation simulation system represents the body characteristics of the individual passengers by a solid circle, and sets information such as the body radius, the mass size and the running speed of the passengers.
In the obstacle representation method, the passenger evacuation simulation system abstracts the obstacle, and the wall and other obstacles are represented by solid polygons.
Adopting the improved A algorithm and social force model as a bottom layer calculation algorithm to carry out simulation on passenger evacuation, wherein the simulation comprises the following steps:
the first step: selecting two processed plane diagrams, namely selecting a station hall plane diagram for the first time and selecting a station platform plane diagram for the second time;
and a second step of: generating an initial position of a station passenger in a passable area, and optionally setting facility equipment such as movable barriers, suction points and the like which influence the movement of the passenger;
and a third step of: running a program, wherein the system calculates the position of each passenger at the next moment in each time interval, updates and stores the information such as the position, the expected direction and the like of each passenger, and simulates the motion process of passenger evacuation step by step in each time stamp in a mode of drawing images; the end positions of all passengers are initially set as the gateway closest to the passengers, but the gateway can be flexibly selected for evacuation according to actual conditions;
fourth step: obtaining a corresponding data analysis chart after the simulation is finished, and analyzing a simulation result;
in the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (8)
1. The city rail traffic station passenger evacuation simulation method is characterized by comprising the following steps of:
s1: target detection and tracking are carried out on target passengers in the subway station monitoring video through a deep learning technology, and real running track data of the passengers are obtained;
s2: building a passenger evacuation simulation model according to the evacuation scene information and the passenger parameter information, and extracting characteristics of the evacuation scene by using a model building unit of the system to obtain a three-dimensional model of the evacuation scene;
s3: the algorithm is improved based on the real passenger travelling track data, and the algorithm is used for calculating the optimal evacuation path of each passenger in the station;
s4: and carrying out a simulation experiment on the passenger evacuation behavior in the simulation system, and ending the simulation when all passengers are evacuated to a safety area to obtain a simulation result.
2. The urban rail transit station passenger evacuation simulation method according to claim 1, wherein target passengers in the subway station monitoring video are subjected to target detection and tracking through a deep learning technology, and real running track data of the passengers are obtained, specifically:
acquiring evacuation motion videos of target passengers through an intelligent monitoring camera preset in an urban rail transit station, dividing the video data into video segments frame by frame according to the number of frames, and manufacturing a passenger motion data set;
performing target labeling according to the obtained data set, dividing the data set into a training set and a testing set, training the training set by utilizing a YOLO v5 target detection algorithm, performing effect test on the trained weight model by using the testing set, and finally outputting a target detection result;
tracking a motion trail of a target passenger by using a Deep Sort multi-target tracking algorithm according to a target detection result, setting up a rectangular coordinate system in a video image, determining a pixel position of the passenger in the video, outputting a position coordinate of the passenger and marking the motion trail;
and converting the pixel coordinates of the passengers into real world coordinates by adopting a linear matrix conversion method, and manufacturing a real track data set.
3. The urban rail transit station passenger evacuation simulation method according to claim 1, wherein the passenger evacuation simulation model is constructed according to the evacuation scene information and the passenger parameter information, and the model building unit is utilized to extract the characteristics of the evacuation scene, so as to obtain the three-dimensional model of the evacuation scene, which is specifically:
making a condition assumption on a model, wherein the model is used on the premise of being based on the assumption condition; secondly, setting a passenger evacuation target and constraint conditions, wherein the conditions for completing evacuation are that the last passenger is evacuated to a safety area, and setting the total time required by passenger evacuation as an optimized target, wherein the calculation formula of the total evacuation time T is as follows:
minT＝∑T k +λ(k＝1，2，3，4)
wherein T represents total passenger evacuation time, T 1 The reaction time of the passengers is represented, the value is 1 minute, T 2 Indicating the time for passengers at the hall to evacuate to the stairs or escalator, T 3 Time of passenger passing stairs and stairs, T 4 The running time of passengers in a hall layer is represented, lambda represents a penalty factor of an objective function, and the value of 0 or 10 is taken according to the form of a platform;
time T representing evacuation of passengers from the hall floor to the stairway or escalator 2 The calculation formula of (2) is as follows:
wherein d 0 Representing the distance of platform floor passengers evacuating to the stairway or escalator entrance, v representing the average speed of passengers；
Time T representing passage of passengers through stairs and stairs 3 The calculation formula of (2) is as follows:
wherein v is 1 Representing the average travelling speed before the blocking of the passengers in the stair or at the escalator, v 2 Indicating average speed of travel of passengers, L, before passing through undisturbed sections of stairs 1 Representing the horizontal total length of stairs, L 2 The horizontal total length of the stairway of the disturbed section is represented, and phi represents the inclination angle of the stairway;
representing the travel time T of a passenger at a hall floor 4 The calculation formula of (2) is as follows:
wherein d 1 Representing the distance from the entrance to the exit of the hall floor for evacuating passengers, and v represents the average speed of the passengers;
modeling the evacuation scene by a rasterization method, dividing the evacuation scene into an obstacle area and a passable area, enabling passengers to walk in the passable area by moving, and determining the positions of the passengers by the actual positions of the cells in the scene;
the passenger evacuation behavior modeling steps in the passenger evacuation simulation model are as follows:
initializing the number of passenger groups, and defining the number, weight, radius, expected speed, starting position, ending position, floor information and other attributes of each passenger;
step two, flexibly setting whether temporary barriers are included in the simulation scene or not and whether suction points exist or not;
third step, for each individual a i An initial evacuation path is drawn by adopting path planning rule, the attraction force, the repulsive force and the driving force of the passengers are calculated by using a social force model, and the passengers are definedThe magnitude and direction of acceleration are used for adjusting the initial movement of the passengers;
fourth, each individual a is re-planned for each operating interval i According to the evacuation path of each individual a calculated according to the social force model i The position to be moved in the next step;
fifth step, individual a i Movement is initiated and either the moved position or not moved is selected. If the end position is reached, executing the next step; otherwise, returning to the previous step;
sixth step, individual a i When the simulation scene reaches the end position, the simulation scene is deleted for evacuating to a safe area, and the individual a i Ending the movement of (2).
4. The method for simulating the evacuation of passengers at the urban rail transit station according to claim 1, wherein in step S3, the actual passenger travel track data is modified by a conventional a-routing algorithm, and the modified a-routing algorithm is used as a solving algorithm of the passenger evacuation simulation model to calculate an optimal evacuation path of each passenger at the station, which is specifically as follows:
by adding path selection weight coefficients and distance coefficients when approaching obstacles to traditional A * The algorithm is improved, and the social force model is fused into A * In the algorithm; the parameters of an A-algorithm and a social force model are adjusted by using a multi-layer neural network according to the obtained real running track data of the passengers, and the improved A is adjusted by using the multi-layer neural network according to the real running track data of the passengers * And the parameters of the path finding algorithm and the social force model are used for calculating the optimal path of passenger evacuation in the passenger evacuation simulation model.
5. The method for simulating the evacuation of passengers at a station of urban rail transit according to claim 1, wherein in step S4, the constructed simulation system is used to perform simulation analysis on the evacuation behavior of passengers at the station, and when all passengers at the station are evacuated to a safe area, the simulation is ended, and the simulation result is analyzed, the system comprises:
the initialization module is used for building an emergency evacuation simulation scene of the subway station and initializing personnel to be evacuated;
the passenger perception module can automatically perceive the surrounding environment, the own physiological and psychological states of people to be evacuated;
A * the path finding algorithm building module is used for planning an initial optimal evacuation path according to the starting position and the ending position of each person to be evacuated and building an initial social force model of each person to be evacuated;
the evacuation simulation module simulates the motion path of the personnel to be evacuated according to the time step, calculates the stress condition by using the social force model in the motion process of each step, and adjusts the position to be moved in the next step in real time until reaching the end position, thereby obtaining the motion state and the final simulation result of the personnel to be evacuated at each simulation moment.
6. The utility model provides a city track traffic station passenger evacuation simulation system which characterized in that: the system comprises a functional area and a simulation interface display area, wherein the functional area comprises a program provided with a passenger evacuation simulation method of an urban rail transit station, and the functional area and the simulation interface are connected with each other and electrically connected with the functional area: the function area is provided with a plurality of keys, including a function key, a chart generation key, an information display frame and a prompt frame; and the simulation interface display area displays the passenger evacuation situation in real time.
7. The urban rail transit station passenger evacuation simulation system according to claim 6, wherein a corresponding model is built for evacuation scenes, people to be evacuated and obstacles in the station, so that computer identification is facilitated, and particularly, a map generation rule is realized, when the system starts to operate, a two-dimensional plan of the station is required to be read first, the plan is subjected to rasterization, and each grid corresponds to corresponding position information; reading each pixel point in the plan, extracting RGB colors of the pixel points, and distinguishing the types of the cells into barriers and passable areas according to the brightness of different colors.
8. The urban rail transit station passenger evacuation simulation system according to claim 6, wherein the improved algorithm and social force model are adopted as a bottom layer calculation algorithm to perform simulation on passenger evacuation, specifically:
the first step: selecting two processed plane diagrams, namely selecting a station hall plane diagram for the first time and selecting a station platform plane diagram for the second time;
and a second step of: generating an initial position of a station passenger in a passable area, and optionally setting facility equipment such as movable barriers, suction points and the like which influence the movement of the passenger;
and a third step of: and running a program, wherein the system calculates the position of each passenger at the next moment in each time interval, updates and stores the information such as the position, the expected direction and the like, and simulates the motion process of passenger evacuation step by step in each time stamp in a mode of drawing images. The end positions of all passengers are initially set as the gateway closest to the passengers, but the gateway can be flexibly selected for evacuation according to actual conditions;
fourth step: and after the simulation is finished, a corresponding data analysis chart is obtained, and a simulation result is analyzed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310821421.XA CN116894611A (en) | 2023-07-05 | 2023-07-05 | Urban rail transit station passenger evacuation simulation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310821421.XA CN116894611A (en) | 2023-07-05 | 2023-07-05 | Urban rail transit station passenger evacuation simulation method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116894611A true CN116894611A (en) | 2023-10-17 |
Family
ID=88309617
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310821421.XA Pending CN116894611A (en) | 2023-07-05 | 2023-07-05 | Urban rail transit station passenger evacuation simulation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116894611A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117436620A (en) * | 2023-12-21 | 2024-01-23 | 天津交控科技有限公司 | Artificial intelligence's emergent evacuation analysis system of track traffic |
| CN117610437A (en) * | 2024-01-24 | 2024-02-27 | 青岛理工大学 | Prediction method and device for evacuation high-risk area of underground station in flood scene |
-
2023
- 2023-07-05 CN CN202310821421.XA patent/CN116894611A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117436620A (en) * | 2023-12-21 | 2024-01-23 | 天津交控科技有限公司 | Artificial intelligence's emergent evacuation analysis system of track traffic |
| CN117436620B (en) * | 2023-12-21 | 2024-04-12 | 天津交控科技有限公司 | Artificial intelligence's emergent evacuation analysis system of track traffic |
| CN117610437A (en) * | 2024-01-24 | 2024-02-27 | 青岛理工大学 | Prediction method and device for evacuation high-risk area of underground station in flood scene |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | Application of the best evacuation model of deep learning in the design of public structures | |
| CN116894611A (en) | Urban rail transit station passenger evacuation simulation method and system | |
| Teknomo | Microscopic pedestrian flow characteristics: Development of an image processing data collection and simulation model | |
| Fu et al. | Walking behavior of pedestrian social groups on stairs: A field study | |
| Hoogendoorn et al. | Extracting microscopic pedestrian characteristics from video data | |
| CN106384093B (en) | A kind of human motion recognition method based on noise reduction autocoder and particle filter | |
| CN103150559B (en) | Head recognition and tracking method based on Kinect three-dimensional depth image | |
| CN106875424A (en) | A kind of urban environment driving vehicle Activity recognition method based on machine vision | |
| CN107730903A (en) | Parking offense and the car vision detection system that casts anchor based on depth convolutional neural networks | |
| CN111832489A (en) | Subway crowd density estimation method and system based on target detection | |
| US10603591B1 (en) | System, method, and computer program product for extracting location information using gaming technologies from real world data collected by various sensors | |
| CN114970321A (en) | Scene flow digital twinning method and system based on dynamic trajectory flow | |
| CN104864873B (en) | A kind of method that utilization human body motion feature aids in Orientation on map | |
| KR102117007B1 (en) | Method and apparatus for recognizing object on image | |
| Liu et al. | Modeling the effect of visibility on upstairs crowd evacuation by a stochastic FFCA model with finer discretization | |
| CN110543917B (en) | Indoor map matching method by utilizing pedestrian inertial navigation track and video information | |
| CN111402632B (en) | Risk prediction method for pedestrian movement track at intersection | |
| CN106951829A (en) | A kind of notable method for checking object of video based on minimum spanning tree | |
| CN108376198A (en) | A kind of crowd simulation method and system based on virtual reality | |
| CN110490978A (en) | Outdoor scene based on mixed reality technology is ridden training method | |
| CN103198182B (en) | The pedestrian guide sign design method of view-based access control model perception simulation technology | |
| CN103605960B (en) | A kind of method for identifying traffic status merged based on different focal video image | |
| Kaminka et al. | Simulating urban pedestrian crowds of different cultures | |
| CN112034983B (en) | Eye tracking and virtual reality combined indoor navigation road network construction method | |
| Chen et al. | Generating synthetic photogrammetric data for training deep learning based 3D point cloud segmentation models |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |