CN111071305A - Intelligent estimation method and device for stop time of urban rail transit train - Google Patents
Intelligent estimation method and device for stop time of urban rail transit train Download PDFInfo
- Publication number
- CN111071305A CN111071305A CN201911238486.1A CN201911238486A CN111071305A CN 111071305 A CN111071305 A CN 111071305A CN 201911238486 A CN201911238486 A CN 201911238486A CN 111071305 A CN111071305 A CN 111071305A
- Authority
- CN
- China
- Prior art keywords
- getting
- time
- passenger
- bottleneck
- train
- 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.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L27/00—Central railway traffic control systems; Trackside control; Communication systems specially adapted therefor
- B61L27/60—Testing or simulation
Abstract
The embodiment of the invention provides an intelligent estimation method and device for stop time of an urban rail transit train, wherein the method comprises the following steps: based on video data of a target train, historical behavior data of passengers getting on or off the train is obtained by using an image recognition and processing method; calculating the time interval of adjacent passengers occupying each bottleneck of the target train according to historical behavior data of passengers getting on and off the train; carrying out statistical analysis on the time intervals of adjacent passengers to obtain pedestrian clusters passing through each bottleneck; simulating the passenger getting-on and getting-off process by utilizing a pre-established microscopic pedestrian simulation model based on the pedestrian clusters passing through each bottleneck to obtain the passenger getting-on and getting-off time corresponding to each bottleneck; and determining the stop time of the target train based on the passenger flow condition based on the passenger getting-on and getting-off time corresponding to each bottleneck. The embodiment of the invention provides an optimization scheme for dynamically adjusting the stop time of an urban rail transit train according to the passenger flow composition and the passenger behavior characteristics.
Description
Technical Field
The invention relates to the technical field of train control, in particular to an intelligent estimation method and device for stop time of an urban rail transit train.
Background
With the development and maturity of the rail unmanned technology, the driving of the vehicle can completely depend on a computer to realize operations such as train awakening, self-checking, automatic departure and the like. At present, although the conditions for automatically opening and closing the door are technically achieved, most subways still operate in an automatic door opening mode and a manual door closing mode. In the peak period of passenger flow, a large number of passengers are gathered in the urban rail transit station, and the situations of crowding, robbing doors and the like can occur. Different from the pedestrian evacuation process in a common building, the process of getting on or off passengers in the urban rail transit station is complex, and the process not only comprises queuing and lateral conflicts among the pedestrians in the same direction, but also relates to front conflicts among the pedestrians in opposite directions. Meanwhile, the evacuation efficiency of passengers is related to individual behaviors and passenger flow organization strategies. When the door is actually opened and closed automatically, the situation of incongruity between human and machine can occur, and a safety accident can be caused in serious cases.
In the existing research on the estimation of the getting-on and getting-off time, linear and nonlinear fitting is carried out on the scale of the number of people getting on and off and the time according to an empirical model of a capability manual, and the influence of the width of a vehicle door on the evacuation time is analyzed. Such studies, while able to roughly assess the trafficability of bottlenecks, lack refined predictions for individual passenger behavior. Modeling and analysis of urban rail transit passenger flow characteristics mainly depend on commercial pedestrian flow simulation software, but the software lacks interfaces for customizing pedestrian models, the models cannot be corrected according to pedestrian characteristics of all places, and parameters are difficult to verify. In addition, the passenger flow characteristics of the urban rail transit hub lack the accumulation of original data and the data of a comprehensive system at present, and the defects of small data sample quantity, low reliability, incomplete data and the like exist, so that the precision of rail transit passenger flow movement simulation modeling is low.
Therefore, how to flexibly and dynamically adjust the stop time of the urban rail transit train according to the passenger flow composition and the passenger behavior characteristics by considering the individual behavior difference of the passengers is a difficult problem to be solved urgently.
Disclosure of Invention
The embodiment of the invention provides an intelligent estimation method and device for the stop time of an urban rail transit train, which overcome the problems or at least partially solve the problems.
In a first aspect, an embodiment of the present invention provides an intelligent estimation method for stop time of an urban rail transit train, including:
based on video data of a target train, historical behavior data of passengers getting on or off the train is obtained by using an image recognition and processing method;
calculating the time interval of adjacent passengers occupying each bottleneck of the target train according to the historical behavior data of passengers getting on and off the train;
carrying out statistical analysis on the time intervals of the adjacent passengers to obtain pedestrian clusters passing through each bottleneck;
simulating the passenger getting-on and getting-off process by utilizing a pre-established microscopic pedestrian simulation model based on the pedestrian clusters passing through the bottlenecks to obtain the passenger getting-on and getting-off time corresponding to the bottlenecks;
and determining the stop time of the target train based on the passenger flow condition based on the passenger getting-on and getting-off time corresponding to each bottleneck.
Wherein the passenger boarding and alighting historical behavior data comprises the following fields: passenger ID, time step, location coordinates, direction of motion, and whether a bottleneck is occupied.
Wherein, to adjacent passenger's time interval carry out statistical analysis, obtain the pedestrian cluster through each bottleneck, specifically do:
and carrying out statistics on adjacent passengers continuously occupying the same direction of the bottleneck within a certain time and with time intervals smaller than a preset time interval threshold value on each bottleneck of the target train to obtain the pedestrian clusters passing through the bottleneck.
Based on the pedestrian clusters passing through the bottlenecks, simulating the passenger getting-on and getting-off processes by using a pre-established microscopic pedestrian simulation model to obtain the passenger getting-on and getting-off time corresponding to the bottlenecks, which specifically comprises the following steps:
determining time intervals and bottleneck occupation probabilities between passengers and passengers in the same direction and opposite direction respectively and congestion probabilities in the same direction, the lateral direction and the opposite direction among the passengers on the basis of the pedestrian clusters passing through the bottlenecks;
based on a pre-established microscopic pedestrian simulation model, the time interval between the passenger and the passenger in the same direction and the passenger in the opposite direction, the bottleneck occupation probability and the crowding probability in the same direction, the lateral direction and the opposite direction between the passenger are taken as input parameters, the position and the speed of the passenger are updated through a probability transfer equation, the passenger getting-on and getting-off processes are simulated, and the passenger getting-on and getting-off time corresponding to each bottleneck is output.
The method comprises the following steps of determining the stop time of the target train based on passenger flow conditions based on the time of getting on or off the train of the passengers corresponding to each bottleneck, and specifically comprises the following steps:
acquiring the door opening time, the door closing time and the planned stop time of the target train;
determining the maximum time for passengers to get on or off the train corresponding to the target train based on the time for passengers to get on or off the train corresponding to each bottleneck;
and obtaining the stop time of the target train based on the passenger flow condition based on the maximum passenger getting-on and getting-off time, the door opening time length and the door closing time length of the target train and the planned stop time.
The method comprises the following steps of obtaining the stop time of a target train based on passenger flow conditions based on the maximum passenger getting-on and getting-off time, the door opening time and the door closing time of the target train and the planned stop time, and specifically comprises the following steps:
and adding the maximum time for passengers to get on or off the train, the door opening time and the door closing time of the target train and the planned stop time to obtain the stop time of the target train based on the passenger flow condition.
The microscopic pedestrian simulation model is specifically a microscopic pedestrian simulation model based on a cellular automaton.
In a second aspect, an embodiment of the present invention provides an intelligent estimation apparatus for stop time of an urban rail transit train, including:
the data acquisition module is used for acquiring historical passenger getting-on and getting-off behavior data by using an image recognition and processing method based on the video data of the target train;
the first calculation module is used for calculating the time interval of adjacent passengers occupying each bottleneck of the target train according to the historical passenger boarding and alighting behavior data;
the statistical analysis module is used for performing statistical analysis on the time intervals of the adjacent passengers to obtain pedestrian clusters passing through each bottleneck;
the simulation module is used for simulating the passenger getting-on and getting-off processes by utilizing a pre-established microscopic pedestrian simulation model based on the pedestrian clusters passing through the bottlenecks to obtain the passenger getting-on and getting-off time corresponding to the bottlenecks;
and the second calculation module is used for determining the stop time of the target train based on the passenger flow condition based on the passenger getting-on and getting-off time corresponding to each bottleneck.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, where the processor executes the program to implement the steps of the intelligent estimation method for stop time of an urban rail transit train according to the first aspect.
In a fourth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the intelligent estimation method for train stop time in urban rail transit as provided in the first aspect.
According to the intelligent estimation method and device for the stop time of the urban rail transit train, provided by the embodiment of the invention, the passenger microscopic motion characteristics and the group motion characteristics are analyzed, the passenger getting-on and getting-off processes are simulated by utilizing the microscopic human simulation model, the stop time according with the passenger flow condition is finally obtained, the stop time can be intelligently estimated according to the change condition of the passenger flow, and therefore, an optimization scheme for dynamically adjusting the stop time of the urban rail transit train according to the passenger flow composition and the passenger behavior characteristics is provided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of an intelligent estimation method for stop time of an urban rail transit train according to an embodiment of the present invention;
fig. 2a is a schematic diagram of the time interval distribution of boarding according to the embodiment of the present invention;
FIG. 2b is a schematic diagram of the time interval distribution of the departure according to the embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating the relationship between the time for a first passenger to get off and a pedestrian cluster according to an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating the stop time of an urban rail transit train according to an embodiment of the present invention;
FIG. 5 is a schematic structural diagram of an intelligent estimation apparatus for stop time of an urban rail transit train according to an embodiment of the present invention;
fig. 6 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, a schematic flow chart of an intelligent estimation method for stop time of an urban rail transit train according to an embodiment of the present invention includes:
specifically, basic data of intelligent estimation of the stop time of the urban rail transit train is obtained, namely historical passenger getting-on and getting-off behavior data are extracted from a monitoring or shooting video of a target train through an image recognition and processing method.
The passenger boarding and disembarking historical behavior data includes, but is not limited to, the following fields: passenger ID, time step, location coordinates, direction of motion, and whether a bottleneck is occupied.
As shown in table 1, an example of historical passenger boarding and disembarking behavior data is provided for an embodiment of the present invention. Wherein the time step is associated with a video frame; the position coordinates (i.e., x, y coordinates) are determined by the accuracy of the grid segmentation; the moving direction 1 represents getting-off, and the moving direction 2 represents getting-on; whether to occupy the bottleneck, 0 represents not to occupy and 1 represents to occupy.
Table 1 passenger boarding and disembarking historical behavior data example
specifically, after obtaining historical passenger boarding and disembarking behavior data, extracting historical passenger boarding and disembarking behavior data with a bottleneck field value of 1, identifying a crowd boarding and disembarking mode, and calculating a time interval of adjacent passengers occupying each bottleneck of the target train, specifically adopting the following formula to calculate:
wherein the content of the first and second substances,
for taking up the bottleneckThe time interval between the adjacent passengers is,
for the time of the (i + 1) th pedestrian occupying the bottleneck,
the time of the ith pedestrian occupying the bottleneck.
102, carrying out statistical analysis on the time intervals of the adjacent passengers to obtain pedestrian clusters passing through each bottleneck;
specifically, a time interval distribution curve can be obtained by counting time intervals of adjacent passengers occupying each bottleneck of the target train, and accurate distribution can be obtained by hypothesis testing and parameter fitting, as shown in fig. 2a and 2b, where fig. 2a is a schematic diagram of the time interval distribution of getting-on provided by the embodiment of the present invention, fig. 2b is a schematic diagram of the time interval distribution of getting-off provided by the embodiment of the present invention, and further, the group behavior characteristics can be extracted based on fig. 2a and 2 b.
Wherein, to adjacent passenger's time interval carry out statistical analysis, obtain the pedestrian cluster through each bottleneck, specifically do:
and carrying out statistics on adjacent passengers continuously occupying the same direction of the bottleneck within a certain time and with time intervals smaller than a preset time interval threshold value on each bottleneck of the target train to obtain the pedestrian clusters passing through the bottleneck.
Specifically, a time interval threshold value delta is set, for each bottleneck of the target train, statistics is carried out on adjacent passengers continuously occupying the same direction of the bottleneck within a certain time, and the time intervals are smaller than the preset time interval threshold value delta, pedestrian clusters (bursts) passing through the bottleneck are obtained, and finally each bottleneck corresponds to one pedestrian cluster.
103, simulating the passenger getting-on and getting-off process by utilizing a pre-established microscopic pedestrian simulation model based on the pedestrian clusters passing through the bottlenecks to obtain the passenger getting-on and getting-off time corresponding to the bottlenecks;
specifically, the embodiment of the invention establishes a microscopic pedestrian simulation model based on a cellular automaton to simulate the process of getting on or off the vehicle of the passenger based on a queuing theory model and a probability theory.
Generally speaking, the process of getting on or off passengers is influenced by the following factors: the traffic facilities are in geometric dimensions (such as horizontal clearance and vertical height difference between a platform and a carriage, and width of a vehicle door), personnel attributes (such as sex, weight, activity and the number of carried luggage), passenger flow scale (the number of people getting on or off the platform, the degree of crowding of the carriage, the number of people waiting at the platform and the distribution of the people), personnel behaviors (getting on or off the platform, queuing behaviors, crowding behaviors, waiting time and degree of excitation), and facilities in the station (such as prompt tones, shielded doors, guide posts, railings and passenger flow control strategies).
It can be understood that, based on the pedestrian clusters passing through the bottlenecks, by analyzing the relationship between the size of the pedestrian cluster and each factor influencing the getting-on and getting-off processes of the passengers, for example, analyzing the relationship between the size of the pedestrian cluster and the getting-off time of the first passenger, as shown in fig. 3, the influence of the behavior change characteristic of the passengers under time pressure on the time interval is analyzed for the relationship diagram between the getting-off time of the first passenger and the pedestrian cluster provided by the embodiment of the present invention, so that the microscopic behavior special effect and the group behavior characteristic of the passengers at each bottleneck of the target train can be determined.
And then inputting the microcosmic behavior special effect and the group behavior characteristics of the passengers at each bottleneck of the target train into a microcosmic pedestrian simulation model, simulating the passenger getting-on and getting-off processes, and finally outputting the passenger getting-on and getting-off time corresponding to each bottleneck.
In one embodiment, based on the pedestrian clusters passing through the bottlenecks, a pre-established microscopic pedestrian simulation model is used to simulate the boarding and alighting processes of passengers, so as to obtain the boarding and alighting time of the passengers corresponding to the bottlenecks, specifically:
determining time intervals and bottleneck occupation probabilities between passengers and passengers in the same direction and opposite direction respectively and congestion probabilities in the same direction, the lateral direction and the opposite direction among the passengers on the basis of the pedestrian clusters passing through the bottlenecks;
based on a pre-established microscopic pedestrian simulation model, the time interval between the passenger and the passenger in the same direction and the passenger in the opposite direction, the bottleneck occupation probability and the crowding probability in the same direction, the lateral direction and the opposite direction between the passenger are taken as input parameters, the position and the speed of the passenger are updated through a probability transfer equation, the passenger getting-on and getting-off processes are simulated, and the passenger getting-on and getting-off time corresponding to each bottleneck is output.
And step 104, determining the stop time of the target train based on the passenger flow condition based on the passenger getting-on and getting-off time corresponding to each bottleneck.
Specifically, as shown in fig. 4, a schematic diagram of the stop time of the urban rail transit train provided by the embodiment of the present invention is shown. Normally, the train's arrival and departure times are operated according to a predetermined schedule. The planned stop time plan is adjusted differently depending on the station level and the passenger flow size. In general, the stop time of the train is composed of the time TBA for passengers to get on or off the train and the time T for opening the train dooropenAnd the door closing time length TopenAnd (4) forming. Under certain special conditions (e.g., re-opening doors, waiting for passengers, technical malfunctions, etc.), the train needs to stay at the platform for a certain period of time. At this time, the station stop time needs to be added to the residence time TH on the basis of the above time.
And determining the stop time of the target train based on the passenger flow condition based on the time of getting on or off the train of the passengers corresponding to each bottleneck, specifically:
acquiring the door opening time T of the target trainopenTime length of closing door TopenAnd a planned stop time TH;
determining the maximum time for passengers to get on or off the train corresponding to the target train based on the time for passengers to get on or off the train corresponding to each bottleneck;
for a train with k bottlenecks, the time for passengers to get on or off the train corresponding to each bottleneck is TBA1,TBA2,…,TBAkDetermining the maximum time for passengers to get on or off the train, namely determining TBA1,TBA2,…,TBAkMaximum value of (2).
And obtaining the stop time of the target train based on the passenger flow condition based on the maximum passenger getting-on and getting-off time, the door opening time length and the door closing time length of the target train and the planned stop time.
Specifically, the stop time of the target train based on the passenger flow situation is calculated by adopting the following formula:
DT＝max{TBA1,TBA2,…,TBAk}+TH+Topen+Tclose
according to the intelligent estimation method for the stop time of the urban rail transit train, provided by the embodiment of the invention, the passenger getting-on and getting-off processes are simulated by analyzing the passenger micro motion characteristics and the group motion characteristics and utilizing the micro human simulation model, the stop time according with the passenger flow condition is finally obtained, the stop time can be intelligently estimated according to the change condition of the passenger flow, and therefore, an optimization scheme for dynamically adjusting the stop time of the urban rail transit train according to the passenger flow composition and the passenger behavior characteristics is provided.
As shown in fig. 5, a schematic structural diagram of an intelligent estimation apparatus for stop time of an urban rail transit train according to an embodiment of the present invention includes: a data acquisition module 510, a first computation module 520, a statistical analysis module 530, a simulation module 540, and a second computation module 550, wherein,
the data acquisition module 510 is configured to acquire historical passenger boarding and disembarking behavior data by using an image recognition and processing method based on video data of a target train;
specifically, the data obtaining module 510 obtains basic data of intelligent estimation of the stop time of the urban rail transit train, that is, historical behavior data of passengers getting on or off the train is extracted from a monitoring or shooting video of a target train through an image recognition and processing method.
The passenger boarding and disembarking historical behavior data includes, but is not limited to, the following fields: passenger ID, time step, location coordinates, direction of motion, and whether a bottleneck is occupied.
A first calculating module 520, configured to calculate a time interval between adjacent passengers occupying each bottleneck of the target train according to the historical passenger boarding and disembarking behavior data;
specifically, after obtaining historical passenger boarding and disembarking behavior data, the first calculation module 520 extracts historical passenger boarding and disembarking behavior data that whether the value of the occupied bottleneck field is 1, identifies a crowd boarding and disembarking mode, and calculates a time interval between adjacent passengers occupying each bottleneck of the target train, specifically using the following formula to calculate:
wherein the content of the first and second substances,
for the time interval of the adjacent passengers occupying the bottleneck,
for the time of the (i + 1) th pedestrian occupying the bottleneck,
the time of the ith pedestrian occupying the bottleneck.
A statistical analysis module 530, configured to perform statistical analysis on the time intervals of the adjacent passengers to obtain pedestrian clusters passing through each bottleneck;
specifically, the statistical analysis module 530 performs statistics on the time intervals of the adjacent passengers occupying each bottleneck of the target train, so as to obtain a time interval distribution curve, and through hypothesis testing and parameter fitting, accurate distribution can be obtained, and further, the group behavior characteristics can be extracted.
The statistical analysis module 530 is specifically configured to:
and carrying out statistics on adjacent passengers continuously occupying the same direction of the bottleneck within a certain time and with time intervals smaller than a preset time interval threshold value on each bottleneck of the target train to obtain the pedestrian clusters passing through the bottleneck.
Setting a time interval threshold delta, carrying out statistics on adjacent passengers continuously occupying the same direction of the bottleneck within a certain time and having time intervals smaller than the preset time interval threshold delta for each bottleneck of the target train to obtain pedestrian clusters (bursts) passing through the bottleneck, and finally enabling each bottleneck to correspond to one pedestrian cluster.
The simulation module 540 is used for simulating the passenger getting-on and getting-off processes by utilizing a pre-established microscopic pedestrian simulation model based on the pedestrian clusters passing through the bottlenecks to obtain the passenger getting-on and getting-off time corresponding to the bottlenecks;
specifically, the embodiment of the invention establishes a microscopic pedestrian simulation model based on a cellular automaton to simulate the process of getting on or off the vehicle of the passenger based on a queuing theory model and a probability theory.
The simulation module 540 may determine the microscopic behavior special effect and the group behavior characteristics of the passengers at each bottleneck of the target train by analyzing the relationship between the size of the pedestrian cluster and each factor affecting the getting-on and getting-off process of the passengers, for example, analyzing the relationship between the size of the pedestrian cluster and the getting-off time of the first passenger, and analyzing the influence of the behavior change characteristics of the passengers under the time pressure on the time interval based on the pedestrian cluster passing through each bottleneck.
And then inputting the microcosmic behavior special effect and the group behavior characteristics of the passengers at each bottleneck of the target train into a microcosmic pedestrian simulation model, simulating the passenger getting-on and getting-off processes, and finally outputting the passenger getting-on and getting-off time corresponding to each bottleneck.
And a second calculating module 550, configured to determine a stop time of the target train based on the passenger flow situation based on the time for the passenger to get on or off the train corresponding to each bottleneck.
Specifically, the second calculating module 550 first obtains the door opening duration, the door closing duration and the planned stop time of the target train; then determining the maximum time for passengers to get on or off the train corresponding to the target train based on the time for passengers to get on or off the train corresponding to each bottleneck; and finally, adding the maximum time for passengers to get on or off the train, the door opening time and the door closing time of the target train and the planned stop time to obtain the stop time of the target train based on the passenger flow condition.
According to the intelligent estimation device for the stop time of the urban rail transit train, provided by the embodiment of the invention, the passenger getting-on and getting-off processes are simulated by analyzing the passenger micro motion characteristics and the group motion characteristics and utilizing the micro human-shaped simulation model, so that the stop time according with the passenger flow condition is finally obtained, and the stop time can be intelligently estimated according to the passenger flow change condition.
Fig. 6 is a schematic entity structure diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 6, the electronic device may include: a processor (processor)610, a communication Interface (Communications Interface)620, a memory (memory)630 and a communication bus 640, wherein the processor 610, the communication Interface 620 and the memory 630 communicate with each other via the communication bus 640. The processor 610 may call a computer program stored on the memory 630 and operable on the processor 610 to execute the intelligent estimation method for the stop time of the urban rail transit train provided by the above method embodiments, for example, including: based on video data of a target train, historical behavior data of passengers getting on or off the train is obtained by using an image recognition and processing method; calculating the time interval of adjacent passengers occupying each bottleneck of the target train according to the historical behavior data of passengers getting on and off the train; carrying out statistical analysis on the time intervals of the adjacent passengers to obtain pedestrian clusters passing through each bottleneck; simulating the passenger getting-on and getting-off process by utilizing a pre-established microscopic pedestrian simulation model based on the pedestrian clusters passing through the bottlenecks to obtain the passenger getting-on and getting-off time corresponding to the bottlenecks; and determining the stop time of the target train based on the passenger flow condition based on the passenger getting-on and getting-off time corresponding to each bottleneck.
In addition, the logic instructions in the memory 630 may be implemented in software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for intelligently estimating the stop time of an urban rail transit train, which is provided by the above-mentioned method embodiments, and includes: based on video data of a target train, historical behavior data of passengers getting on or off the train is obtained by using an image recognition and processing method; calculating the time interval of adjacent passengers occupying each bottleneck of the target train according to the historical behavior data of passengers getting on and off the train; carrying out statistical analysis on the time intervals of the adjacent passengers to obtain pedestrian clusters passing through each bottleneck; simulating the passenger getting-on and getting-off process by utilizing a pre-established microscopic pedestrian simulation model based on the pedestrian clusters passing through the bottlenecks to obtain the passenger getting-on and getting-off time corresponding to the bottlenecks; and determining the stop time of the target train based on the passenger flow condition based on the passenger getting-on and getting-off time corresponding to each bottleneck.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. An intelligent estimation method for stop time of an urban rail transit train is characterized by comprising the following steps:
based on video data of a target train, historical behavior data of passengers getting on or off the train is obtained by using an image recognition and processing method;
calculating the time interval of adjacent passengers occupying each bottleneck of the target train according to the historical behavior data of passengers getting on and off the train;
carrying out statistical analysis on the time intervals of the adjacent passengers to obtain pedestrian clusters passing through each bottleneck;
simulating the passenger getting-on and getting-off process by utilizing a pre-established microscopic pedestrian simulation model based on the pedestrian clusters passing through the bottlenecks to obtain the passenger getting-on and getting-off time corresponding to the bottlenecks;
and determining the stop time of the target train based on the passenger flow condition based on the passenger getting-on and getting-off time corresponding to each bottleneck.
2. The intelligent estimation method for stop time of urban rail transit train according to claim 1, wherein the historical behavior data of passengers getting on and off the train comprises the following fields: passenger ID, time step, location coordinates, direction of motion, and whether a bottleneck is occupied.
3. The intelligent estimation method for the stop time of the urban rail transit train according to claim 1, wherein the statistical analysis is performed on the time intervals of the adjacent passengers to obtain pedestrian clusters passing through each bottleneck, and specifically comprises the following steps:
and carrying out statistics on adjacent passengers continuously occupying the same direction of the bottleneck within a certain time and with time intervals smaller than a preset time interval threshold value on each bottleneck of the target train to obtain the pedestrian clusters passing through the bottleneck.
4. The intelligent estimation method for the stop time of the urban rail transit train according to claim 1, wherein based on the pedestrian clusters passing through each bottleneck, the passenger getting-on and getting-off process is simulated by using a pre-established microscopic pedestrian simulation model to obtain the time for getting-on and getting-off of the passenger corresponding to each bottleneck, specifically:
determining time intervals and bottleneck occupation probabilities between passengers and passengers in the same direction and opposite direction respectively and congestion probabilities in the same direction, the lateral direction and the opposite direction among the passengers on the basis of the pedestrian clusters passing through the bottlenecks;
based on a pre-established microscopic pedestrian simulation model, the time interval between the passenger and the passenger in the same direction and the passenger in the opposite direction, the bottleneck occupation probability and the crowding probability in the same direction, the lateral direction and the opposite direction between the passenger are taken as input parameters, the position and the speed of the passenger are updated through a probability transfer equation, the passenger getting-on and getting-off processes are simulated, and the passenger getting-on and getting-off time corresponding to each bottleneck is output.
5. The intelligent estimation method for the stop time of the urban rail transit train according to claim 1, wherein the stop time of the target train based on the passenger flow situation is determined based on the time of the passengers getting on or off the train corresponding to each bottleneck, and specifically comprises:
acquiring the door opening time, the door closing time and the planned stop time of the target train;
determining the maximum time for passengers to get on or off the train corresponding to the target train based on the time for passengers to get on or off the train corresponding to each bottleneck;
and obtaining the stop time of the target train based on the passenger flow condition based on the maximum passenger getting-on and getting-off time, the door opening time length and the door closing time length of the target train and the planned stop time.
6. The intelligent estimation method for the stop time of the urban rail transit train according to claim 5, wherein the stop time of the target train based on the passenger flow situation is obtained based on the maximum passenger getting-on/off time, the door opening time, the door closing time and the planned stop time, and specifically comprises:
and adding the maximum time for passengers to get on or off the train, the door opening time and the door closing time of the target train and the planned stop time to obtain the stop time of the target train based on the passenger flow condition.
7. The intelligent estimation method for the stop time of the urban rail transit train according to claim 4, wherein the micro pedestrian simulation model is a micro pedestrian simulation model based on a cellular automaton.
8. The utility model provides an urban rail transit train stop time intelligent estimation device which characterized in that includes:
the data acquisition module is used for acquiring historical passenger getting-on and getting-off behavior data by using an image recognition and processing method based on the video data of the target train;
the first calculation module is used for calculating the time interval of adjacent passengers occupying each bottleneck of the target train according to the historical passenger boarding and alighting behavior data;
the statistical analysis module is used for performing statistical analysis on the time intervals of the adjacent passengers to obtain pedestrian clusters passing through each bottleneck;
the simulation module is used for simulating the passenger getting-on and getting-off processes by utilizing a pre-established microscopic pedestrian simulation model based on the pedestrian clusters passing through the bottlenecks to obtain the passenger getting-on and getting-off time corresponding to the bottlenecks;
and the second calculation module is used for determining the stop time of the target train based on the passenger flow condition based on the passenger getting-on and getting-off time corresponding to each bottleneck.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and operable on the processor, wherein the processor when executing the program implements the steps of the intelligent estimation method of stop time of urban rail transit train according to any one of claims 1 to 7.
10. A non-transitory computer readable storage medium, having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the intelligent estimation method for stop time of urban rail transit train according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911238486.1A CN111071305B (en) | 2019-12-06 | 2019-12-06 | Intelligent estimation method and device for stop time of urban rail transit train |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911238486.1A CN111071305B (en) | 2019-12-06 | 2019-12-06 | Intelligent estimation method and device for stop time of urban rail transit train |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111071305A true CN111071305A (en) | 2020-04-28 |
| CN111071305B CN111071305B (en) | 2021-12-31 |
Family
ID=70313260
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911238486.1A Active CN111071305B (en) | 2019-12-06 | 2019-12-06 | Intelligent estimation method and device for stop time of urban rail transit train |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111071305B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112131756A (en) * | 2020-10-10 | 2020-12-25 | 清华大学 | Pedestrian crossing scene simulation method considering individual shock rate |
| CN112508755A (en) * | 2020-11-24 | 2021-03-16 | 河北工业大学 | Personnel evacuation method based on queuing decision model |
| CN112685895A (en) * | 2020-12-29 | 2021-04-20 | 北京交通大学 | Urban rail train operation simulation method aiming at emergency scene |
| CN113570148A (en) * | 2021-08-02 | 2021-10-29 | 上海市城市建设设计研究总院（集团）有限公司 | Passenger simulation-based urban rail station stop time optimal setting method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101826200A (en) * | 2010-04-02 | 2010-09-08 | 北京交通大学 | Method for evaluating operating effect of urban track traffic hub |
| CN104992300A (en) * | 2015-07-23 | 2015-10-21 | 南京轨道交通系统工程有限公司 | Passenger characteristic analysis method for track transportation junction |
| CN106529815A (en) * | 2016-11-15 | 2017-03-22 | 同济大学 | Estimation method of passenger trip spatial-temporal trajectory of urban rail transit network and application thereof |
| CN107066723A (en) * | 2017-04-10 | 2017-08-18 | 东南大学 | A kind of bus passenger based on social force model is got on or off the bus behavior simulation method |
-
2019
- 2019-12-06 CN CN201911238486.1A patent/CN111071305B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101826200A (en) * | 2010-04-02 | 2010-09-08 | 北京交通大学 | Method for evaluating operating effect of urban track traffic hub |
| CN104992300A (en) * | 2015-07-23 | 2015-10-21 | 南京轨道交通系统工程有限公司 | Passenger characteristic analysis method for track transportation junction |
| CN106529815A (en) * | 2016-11-15 | 2017-03-22 | 同济大学 | Estimation method of passenger trip spatial-temporal trajectory of urban rail transit network and application thereof |
| CN107066723A (en) * | 2017-04-10 | 2017-08-18 | 东南大学 | A kind of bus passenger based on social force model is got on or off the bus behavior simulation method |
Non-Patent Citations (2)
| Title |
|---|
| 苗沁，潘琢: "城市轨道交通列车停站时间研究", 《城市轨道交通研究》 * |
| 郑宣传: "基于图像处理的地铁车站乘客微观行为特征提取技术与乘客上下车行为仿真研究", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112131756A (en) * | 2020-10-10 | 2020-12-25 | 清华大学 | Pedestrian crossing scene simulation method considering individual shock rate |
| CN112508755A (en) * | 2020-11-24 | 2021-03-16 | 河北工业大学 | Personnel evacuation method based on queuing decision model |
| CN112508755B (en) * | 2020-11-24 | 2022-03-01 | 河北工业大学 | Personnel evacuation method based on queuing decision model |
| CN112685895A (en) * | 2020-12-29 | 2021-04-20 | 北京交通大学 | Urban rail train operation simulation method aiming at emergency scene |
| CN113570148A (en) * | 2021-08-02 | 2021-10-29 | 上海市城市建设设计研究总院（集团）有限公司 | Passenger simulation-based urban rail station stop time optimal setting method |
| CN113570148B (en) * | 2021-08-02 | 2024-04-09 | 上海市城市建设设计研究总院（集团）有限公司 | Urban rail station stop time optimization setting method based on passenger simulation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111071305B (en) | 2021-12-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111071305B (en) | Intelligent estimation method and device for stop time of urban rail transit train | |
| US10296860B2 (en) | Management of aircraft in-cabin activities occuring during turnaround using video analytics | |
| CN109711299A (en) | Vehicle passenger flow statistical method, device, equipment and storage medium | |
| Seriani et al. | Exploring the effect of boarding and alighting ratio on passengers’ behaviour at metro stations by laboratory experiments | |
| CN108364464B (en) | Probability model-based public transport vehicle travel time modeling method | |
| CN110348601A (en) | A kind of short-term passenger flow forecast method of subway based on two-way shot and long term memory network | |
| CN115018148A (en) | Urban rail transit network passenger flow distribution prediction method and system based on digital twin model | |
| CN112861706A (en) | Road state monitoring method, device, equipment and storage medium | |
| CN107767011A (en) | A kind of track station characteristic of pedestrian acquisition system and service horizontal dynamic evaluation method | |
| CN109918687A (en) | A kind of train dynamics emulation mode and emulation platform based on machine learning | |
| Trivedi et al. | Agent Based Modelling and Simulation to estimate movement time of pilgrims from one place to another at Allahabad Jn. Railway Station during Kumbh Mela-2019 | |
| EP2592586A1 (en) | Person flow simulation with waiting zones | |
| CN112200372A (en) | Method for calculating and guiding passenger sharing rate of land-side comprehensive traffic optimization of large-scale airport hub | |
| CN110376585B (en) | Carriage congestion degree detection method, device and system based on 3D radar scanning | |
| CN112347654A (en) | Simulation method and device based on subway passenger flow system | |
| Lochrane et al. | Modeling driver behavior in work and nonwork zones: Multidimensional psychophysical car-following framework | |
| CN110135633A (en) | A kind of railway service Call failure prediction technique and device | |
| CN112224239B (en) | Train point reporting time detection method and device | |
| EP2461270A1 (en) | Method, apparatus and computer program product for predicting the behaviour of entities | |
| Yang et al. | Level of service analysis based on maximum number of passengers in waiting room of railway passenger station using arena simulation | |
| Erdagi et al. | Cycle-by-cycle Delay Estimation at Signalized Intersections by using Machine Learning and Simulated Video Detection Data | |
| CN116386387B (en) | Method and device for predicting following behavior of driving vehicle of hybrid queue person | |
| CN113792906A (en) | Method, device and equipment for predicting long-time window running track of train and storage medium | |
| CN116011246B (en) | Method and device for regulating and controlling dynamic state of station bidirectional brake | |
| Wu et al. | Design of the passenger flow collection device of the intelligent scheduling system of public traffic vehicles |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |