CN115330360A - Pedestrian trajectory calculation method based on multi-agent simulation technology - Google Patents

Pedestrian trajectory calculation method based on multi-agent simulation technology Download PDF

Info

Publication number
CN115330360A
CN115330360A CN202211250488.4A CN202211250488A CN115330360A CN 115330360 A CN115330360 A CN 115330360A CN 202211250488 A CN202211250488 A CN 202211250488A CN 115330360 A CN115330360 A CN 115330360A
Authority
CN
China
Prior art keywords
trajectory
track
information
time
space
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
Application number
CN202211250488.4A
Other languages
Chinese (zh)
Other versions
CN115330360B (en
Inventor
李俊奇
王叶飞
姚奕鹏
陈扬航
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Yonghua Technology Co ltd
Original Assignee
Guangdong Yonghua Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangdong Yonghua Technology Co ltd filed Critical Guangdong Yonghua Technology Co ltd
Priority to CN202211250488.4A priority Critical patent/CN115330360B/en
Publication of CN115330360A publication Critical patent/CN115330360A/en
Application granted granted Critical
Publication of CN115330360B publication Critical patent/CN115330360B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • G06Q10/10—Office automation; Time management
    • G06Q10/109—Time management, e.g. calendars, reminders, meetings or time accounting
    • G06Q10/1091—Recording time for administrative or management purposes
    • 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"
    • 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services

Abstract

The invention relates to the technical field of track reduction, and discloses a pedestrian track calculation method based on a multi-agent simulation technology, which comprises the following steps: collecting detention information and building information of personnel; generating a sequence of spatiotemporal trajectory points of the person; generating a feasible motion track; and verifying the movement track of the personnel and outputting a complete personnel track. So as to realize the calculation of the pedestrian track in the junction facility. The invention provides a pedestrian trajectory calculation method based on a multi-agent simulation technology, which can accurately, efficiently and quickly restore the movement trajectory of a person.

Description

Pedestrian trajectory calculation method based on multi-agent simulation technology
Technical Field
The invention relates to the technical field of track reduction, in particular to a pedestrian track calculation method based on a multi-agent simulation technology.
Background
Flow regulation is a very important task in the control of infectious diseases, but it is not easy for parties to remember their journey of the last 14 days. When the dispatching staff needs to collect the patient information, most of the dispatching staff rely on their own memories, but it is difficult for the dispatching staff to remember the whole journey from 14 days before diagnosis to before isolation, namely, the dispatching staff can hardly restore the movement track of the patient completely in a short time.
At present, the movement track of a patient is restored mainly by means of scanning place code records and monitoring camera records by the patient through a mobile phone, only the arrival time and the detention point position of the patient can be determined, the leaving time of the patient and the track of the patient running in a building cannot be known, and a flow adjustment person cannot directly obtain the movement track of the patient and make effective prevention and control measures.
Disclosure of Invention
The invention aims to overcome the defects of the existing personnel trajectory estimation prediction method and provide a pedestrian trajectory estimation method based on a multi-agent simulation technology, and the method can accurately restore the personnel trajectory.
A pedestrian trajectory reckoning method based on a multi-agent simulation technology comprises the following steps:
collecting detention information and building information of personnel;
generating a sequence of spatiotemporal trajectory points of the person;
generating a feasible motion track;
verifying the movement track of the personnel and outputting a complete personnel track;
the collecting of the retention information of the person specifically includes:
the flow adjustment personnel inquire by telephone, investigate the time-space trajectory of the personnel in the building and restore the time-space section information of the personnel in the building;
the generating of the feasible motion trajectory comprises:
acquiring terrain scene information and generating a feasible track sequence;
supplementing all persons with missing track sequences;
the obtaining of the terrain scene information and the generating of the feasible track sequence specifically include:
generating a set of recording point areas of a person based on the planar terrain information of the system scene
Figure 100002_DEST_PATH_IMAGE001
So that for any
Figure 100002_DEST_PATH_IMAGE002
And
Figure 100002_DEST_PATH_IMAGE003
is provided with
Figure 100002_DEST_PATH_IMAGE004
. For any purpose
Figure 100002_DEST_PATH_IMAGE005
And
Figure 100002_DEST_PATH_IMAGE006
（
Figure 100002_DEST_PATH_IMAGE007
) Generating a feasible track sequence set through A-star algorithm
Figure 100002_DEST_PATH_IMAGE008
At will
Figure 811089DEST_PATH_IMAGE005
And
Figure 17948DEST_PATH_IMAGE006
to (1) a
Figure 100002_DEST_PATH_IMAGE009
The sequence of feasible trajectories is represented as
Figure 100002_DEST_PATH_IMAGE010
。
The track sequences for supplementing all people with deletions specifically include:
for any person
Figure 575532DEST_PATH_IMAGE009
Adjacent space-time information of
Figure 100002_DEST_PATH_IMAGE011
And
Figure 100002_DEST_PATH_IMAGE012
selecting feasible track sequence from feasible track sequence set by heuristic rule
Figure 100002_DEST_PATH_IMAGE013
Forming a complete motion trajectory between adjacent spatial and temporal positions
Figure 100002_DEST_PATH_IMAGE014
Wherein
Figure 100002_DEST_PATH_IMAGE015
，
Figure 100002_DEST_PATH_IMAGE016
，
Figure 100002_DEST_PATH_IMAGE017
. For any person
Figure 708704DEST_PATH_IMAGE009
Forming a complementary complete sequence of traces
Figure 100002_DEST_PATH_IMAGE018
For all the persons, a complete supplementary trajectory set is formed
Figure 100002_DEST_PATH_IMAGE019
。
After the feasible motion trajectory is generated, the method may further include a second intervention of a flow adjustment person, and the generated several possible motion space-time trajectories are verified through monitoring device information, specifically:
verifying possible space-time trajectories among the stagnation points by flow regulators in combination with monitoring equipment information, and if the personnel can be found in peripheral monitoring equipment related to the space-time trajectories, taking the space-time trajectories as actual trajectories of the personnel among the stagnation points;
if no person is found in the monitoring equipment corresponding to the track point of the space-time track or the time is not matched, the motion track is eliminated;
and if the generated plurality of possible motion space-time trajectories are excluded, returning to regenerate new possible motion trajectories until a matched actual motion trajectory is found.
Verifying the trajectory of the person and outputting a complete trajectory of the person comprises:
calculating the degree of deviation of the generated spatio-temporal information of the track by combining the spatio-temporal information determined by the known personnel;
and (4) importing the complete motion trajectory into a pedestrian simulation system, and restoring the space-time information of the whole trajectory.
The calculating deviation degree of the generated spatio-temporal information of the trajectory by combining the spatio-temporal information determined by the known personnel is specifically as follows:
calculating the deviation degree of the track information with the same time in the actual space-time track and the simulated space-time track of the personnel, namely calculating the space deviation of the actual track and the simulated track at the same moment, and carrying out the calculation on the first step
Figure 100002_DEST_PATH_IMAGE020
Degree of deviation of individual person
Figure 100002_DEST_PATH_IMAGE021
The calculation is as follows:
Figure 100002_DEST_PATH_IMAGE022
degree of deviation for all persons
Figure 100002_DEST_PATH_IMAGE023
The calculation is as follows:
Figure 100002_DEST_PATH_IMAGE024
，in the formula (I), the compound is shown in the specification,
Figure 100002_DEST_PATH_IMAGE025
is as follows
Figure 981291DEST_PATH_IMAGE020
The first of an individual
Figure 100002_DEST_PATH_IMAGE026
The plane abscissa of the space-time section information,
Figure 100002_DEST_PATH_IMAGE027
is a first
Figure 347550DEST_PATH_IMAGE020
The first of an individual
Figure 314019DEST_PATH_IMAGE026
The plane ordinate of the space-time section information,
Figure 100002_DEST_PATH_IMAGE028
is as follows
Figure 629594DEST_PATH_IMAGE020
The first of an individual
Figure 682870DEST_PATH_IMAGE026
The occurrence time of the space-time section information,
Figure 100002_DEST_PATH_IMAGE029
the horizontal coordinate of the plane of the simulated trajectory position for the pedestrian,
Figure 100002_DEST_PATH_IMAGE030
a plane ordinate of the position of the simulated trajectory for the pedestrian,
Figure 100002_DEST_PATH_IMAGE031
to simulate the location occurrence time.
The step of guiding the complete motion trajectory into the pedestrian simulation system and the step of restoring the space-time information of the whole trajectory comprises the following steps:
generating a complete set of supplementary trajectories for all persons
Figure 100002_DEST_PATH_IMAGE032
And step s2, importing the plane structure information into a pedestrian simulation system, constraining the pedestrian to move according to a specified track in the pedestrian simulation system, calculating to obtain a complete space-time track, and exporting the pedestrian space-time track information
Figure 100002_DEST_PATH_IMAGE033
The simulation space-time trajectory form is
Figure 100002_DEST_PATH_IMAGE034
Wherein
Figure 100002_DEST_PATH_IMAGE035
The horizontal coordinate of the plane of the simulated trajectory position for the pedestrian,
Figure 100002_DEST_PATH_IMAGE036
a plane ordinate of the position of the simulated trajectory for the pedestrian,
Figure 100002_DEST_PATH_IMAGE037
the simulated position occurrence time.
The invention can conjecture the concrete place of the building that the personnel go through by collecting the detention information and the building information of the personnel, and can conjecture the stay time of the personnel in the building, in addition, the place where the personnel stay in the building can be connected in series by generating the time-space track point sequence of the personnel, thereby a plurality of action tracks which are possibly generated by the personnel can be forecasted, a theoretical basis is provided for judging the action tracks of the personnel, finally, the track of the personnel walking with the maximum probability can be forecasted by verifying the track information of the personnel, thereby the place where the personnel pass through and the stay time in the process can be judged, in the whole process, the personnel do not need to inquire whether the verification personnel pass through the concrete place of a certain building and the stay time one by one, the workload of the personnel is reduced, the personnel configuration can also be reduced, the action tracks of the judgment personnel can be accurately determined by an automatic judgment program and algorithm, errors which can be possibly generated by the personnel analysis are avoided, thereby the judgment precision of the whereabouts of the personnel is improved, and a scientific guidance method and a theoretical guidance method for the restoration of the forecast theory are provided for the action tracks of the personnel.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments or technical solutions in the prior art of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings without inventive labor.
FIG. 1 is a flow chart of a pedestrian trajectory estimation method based on multi-agent simulation technology according to the present invention;
FIG. 2 is a k-th personnel feasible track sequence of the pedestrian track calculation method based on multi-agent simulation technology provided by the invention
Figure DEST_PATH_IMAGE038
A schematic diagram;
FIG. 3 is a schematic diagram of a method for generating simulated spatiotemporal trajectories for a pedestrian trajectory estimation method based on multi-agent simulation technology according to the present invention
Figure DEST_PATH_IMAGE039
；
Fig. 4 is a flow chart of a person trajectory generated by verification of a pedestrian trajectory estimation method based on a multi-agent simulation technique according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. 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.
It should be noted that all directional indicators in the embodiment of the present invention, such as the upper, lower, left, right, front, and rear … … are only used to explain the relative position relationship between the components, the movement situation, etc. in a specific gesture, if the specific gesture changes, the directional indicator changes accordingly.
In addition, the descriptions related to "first", "second", etc. in the present invention are for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In addition, technical solutions between the embodiments may be combined with each other, but must be based on the realization of the technical solutions by a person skilled in the art, and when the technical solutions are contradictory to each other or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
A pedestrian trajectory estimation method based on a multi-agent simulation technology comprises the following steps:
step 100, collecting detention information and building information of personnel;
step 200, generating a spatiotemporal trajectory point sequence of personnel;
step 300, generating a feasible motion track;
step 400, verifying the movement track of the personnel and outputting a complete personnel track;
the invention can conjecture the concrete place of the building that the personnel go through by collecting the detention information and the building information of the personnel, and can conjecture the stay time of the personnel in the building, in addition, the place where the personnel stay in the building can be connected in series by generating the space-time track point sequence of the personnel, thereby a plurality of action tracks which are possibly generated by the personnel can be forecasted, a theoretical basis is provided for judging the action tracks of the personnel, finally, the track of the personnel walking with the maximum probability can be forecasted by verifying the track information of the personnel, thereby the place where the personnel pass through and the stay time in the process can be judged, in the whole process, the personnel do not need to inquire whether the verification personnel pass through the concrete place of a certain building and the stay time one by one, the workload of the personnel is reduced, the personnel configuration can also be reduced, the action tracks of the judgment personnel can be accurately determined by an automatic judgment program and algorithm, errors which can be generated by the personnel analysis can be avoided, thereby the judgment precision of the whereabouts of the personnel is improved, and a scientific guidance method and a theoretical guidance method for the forecast of the restoration of the action tracks of the personnel are provided.
The step 100 of collecting the retention information of the person specifically includes:
the flow adjustment personnel inquire by telephone, investigate the time-space trajectory of the personnel in the building and restore the time-space section information of the personnel in the building;
the caller of the shunting obtains the telephone number of the patient through the telephone directory of the resident collected by the cell committee, and then dials the number to inquire the shunting information of the patient, wherein the shunting information comprises the name, the age, the place to be passed in seven days, the detention time, the vehicle to be taken and the like.
The flow regulating personnel checks the activities of the confirmed patients in the building through telephone inquiry and combining with the activity records available for the confirmed patients to generate the activity retention information of the confirmed patients in the building, and the activity retention information comprises the following items:
TABLE 1 Activity retention information items
Figure 848009DEST_PATH_IMAGE040
Step 101, describing the space-time section information of each person in the system scene as
Figure DEST_PATH_IMAGE041
Wherein
Figure DEST_PATH_IMAGE042
Is a first
Figure 287343DEST_PATH_IMAGE020
Individual personThe information of the space-time section of the image,
Figure DEST_PATH_IMAGE043
the number of the total people in the system,
Figure DEST_PATH_IMAGE044
is as follows
Figure 644375DEST_PATH_IMAGE020
The sequence of the horizontal coordinates of the plane of the individual,
Figure DEST_PATH_IMAGE045
is as follows
Figure 587928DEST_PATH_IMAGE020
The sequence of the vertical coordinates of the plane of the individual person,
Figure DEST_PATH_IMAGE046
is the sequence of time instants at which the coordinates occur.
Step 102, the first
Figure 459938DEST_PATH_IMAGE020
Each space-time profile information of an individual is described as
Figure DEST_PATH_IMAGE047
Wherein
Figure DEST_PATH_IMAGE048
Is as follows
Figure 702962DEST_PATH_IMAGE020
The first of an individual
Figure 258709DEST_PATH_IMAGE026
The information of the space-time section is obtained,
Figure DEST_PATH_IMAGE049
is a first
Figure 122628DEST_PATH_IMAGE020
Number of space-time section information possessed by individual personTo achieve the purpose of improving the immunity of human beings,
Figure 763825DEST_PATH_IMAGE025
is as follows
Figure 869928DEST_PATH_IMAGE020
The first of an individual
Figure 545760DEST_PATH_IMAGE026
The plane abscissa of the space-time section information,
Figure 128051DEST_PATH_IMAGE027
is as follows
Figure 505812DEST_PATH_IMAGE020
The first of an individual
Figure 933382DEST_PATH_IMAGE026
The plane ordinate of the space-time section information,
Figure 948874DEST_PATH_IMAGE028
is as follows
Figure 436487DEST_PATH_IMAGE020
The first of an individual
Figure 317855DEST_PATH_IMAGE026
The occurrence time of the space-time profile information.
The method has the advantages that more detailed information can be obtained by directly inquiring personnel than by filling in tables by personnel, different problems can be formulated for each personnel, the problems can be flexibly changed without being fixed, a plurality of invalid problems can be eliminated, the effectiveness of collected data is improved, the redundancy of the data is reduced, the time for recovering feedback data is reduced, the cost for collecting the data is reduced, the detention place, the detention starting time, the detention ending time, the next detention place, the drawing of the internal facility of the building, the layout of the internal plane and other information of the person can be more flexibly, directly and effectively collected, one-person one-file 'fine' modeling is realized, the model is established in a one-person one-file mode, the traceability of a subsequent result is improved, specific and accurate personnel track points can be obtained by combining the detention information of the personnel, powerful data support is provided for the subsequent track reduction, and the efficiency and the accuracy of the track reduction are improved.
The step 200 of generating a feasible motion trajectory comprises:
step 201, obtaining terrain scene information and generating a feasible track sequence;
step 202, supplementing missing track sequences for all people;
and obtaining a building internal facility drawing and building internal plane layout information from a building manager to generate building plane information for multi-agent pedestrian simulation. And importing the building plane information and the detention information of the patient in the building into a multi-agent pedestrian simulation system to generate a plurality of possible motion space-time trajectories among the detention points of the diagnosed patient.
The method comprises the steps of obtaining a building internal facility drawing and building internal plane layout information to generate building plane information which can be used for multi-agent pedestrian simulation, avoiding generating motion tracks which do not conform to reality, reducing workload of follow-up track screening, guiding the building plane information and retention information of personnel in a building into a multi-agent pedestrian simulation system, generating a plurality of possible motion space-time track sequences among stagnation points of the personnel, enabling tracks generated by the multi-agent pedestrian simulation system to be matched with the actual motion tracks of the personnel, outputting the tracks in a sequence mode to facilitate follow-up screening processing of the tracks one by one, enabling tracks generated by the simulation system to be faster than tracks of manual analysis personnel, selecting more output feasible tracks, enabling the error rate of a machine to compare the feasible tracks to be low, intelligently supplementing the track sequences missing by the personnel, enabling presumed tracks to be more complete and more comprehensive, enabling tracks generated by the system to be higher in precision than manual analysis due to comprehensive information, reducing a large amount of workload, and saving time.
The step 201 of acquiring terrain scene information and generating a feasible track sequence specifically includes:
2011, according to the terrain information of the system scene, generating a set of recording point areas of the person
Figure 798384DEST_PATH_IMAGE001
So as to be arbitrary
Figure 183229DEST_PATH_IMAGE002
And
Figure 841743DEST_PATH_IMAGE003
is provided with
Figure 698491DEST_PATH_IMAGE004
. For any purpose
Figure 467864DEST_PATH_IMAGE005
And
Figure 238373DEST_PATH_IMAGE006
（
Figure 51478DEST_PATH_IMAGE007
) Generating feasible track sequence set by A-star algorithm
Figure 641859DEST_PATH_IMAGE008
At will
Figure 214923DEST_PATH_IMAGE005
And
Figure 793934DEST_PATH_IMAGE006
to (1) a
Figure 794251DEST_PATH_IMAGE009
The sequence of feasible trajectories is represented as
Figure 590037DEST_PATH_IMAGE010
As in fig. 2.
The personnel record points generated according to the plane terrain of the system scene avoid the situation that the personnel can not reach the record points when the system directly generates the personnel record points, the operation method enables the generated record point area to exclude wrong data, reduces the possibility of errors, reduces the processing amount of subsequent data, and can be more practical.
The algorithm A is the most effective direct search method for solving the shortest path in the static road network, and is also an effective algorithm for solving a plurality of search problems. The method has quick response to the environment, direct search path, and the closer the estimated distance value in the algorithm is to the actual value, the faster the final search speed is, and the A-x algorithm can quickly output comprehensive data information, thereby providing a large amount of data reference and support for subsequent track reduction work.
The step 202 of supplementing missing track sequences for all people specifically includes:
for any person
Figure 701213DEST_PATH_IMAGE009
Adjacent space-time information of
Figure 662959DEST_PATH_IMAGE011
And
Figure 834178DEST_PATH_IMAGE012
selecting feasible track sequence from feasible track sequence set by heuristic rule
Figure 867993DEST_PATH_IMAGE013
Forming a complete motion trajectory between adjacent spatial and temporal positions
Figure 32127DEST_PATH_IMAGE014
Wherein
Figure 834998DEST_PATH_IMAGE015
，
Figure 193429DEST_PATH_IMAGE016
，
Figure 714540DEST_PATH_IMAGE017
. For any person
Figure 167518DEST_PATH_IMAGE009
Forming a complementary complete sequence of traces
Figure 605322DEST_PATH_IMAGE018
For all persons, forming a complete set of complementary trajectories
Figure 852763DEST_PATH_IMAGE019
。
The heuristic rule can select any constraint condition and the condition which needs to be met to carry out path planning, the shortest input distance, the least time consumption and the least stair walking are adopted, the greatest heuristic rule has the advantages of low complexity, can be well applied to dynamic real-time scheduling, has global sensitivity, can generate different path schemes between adjacent position space points according to different constraint conditions, can generate comprehensive and feasible personnel motion tracks, supplements missing motion tracks, enables the tracks to be comprehensive and complete and is more beneficial to analysis. Compared with the traditional manual analysis for generating the movement track, the heuristic rule for generating the movement track of the person has the advantages of shorter time consumption, higher precision and more comprehensive coverage, supplements the missing movement track, avoids the condition of error and leakage of the generated movement track caused by incomplete analysis, and improves the efficiency and the accuracy of generating the track.
After the feasible motion trajectory is generated in step 300, a shunting staff may intervene again, and the generated possible motion spatiotemporal trajectories are verified through monitoring equipment information, specifically:
step 301, verifying possible space-time trajectories among the stagnation points by flow regulators in combination with monitoring equipment information, and if the personnel can be found in peripheral monitoring equipment related to the space-time trajectories, taking the space-time trajectories as actual trajectories of the personnel among the stagnation points;
step 302, if no person is found in the monitoring equipment corresponding to the track point of the space-time track or the time is not matched, the motion track is eliminated;
and step 303, if the generated plurality of possible motion space-time trajectories are excluded, returning to regenerate new possible motion trajectories until a matched actual motion trajectory is found.
Screening tracks by means of checking monitoring equipment and the like by flow dispatching personnel, verifying each stagnation point of the generated tracks one by one, manually analyzing possible space-time tracks among the stagnation points, judging the accuracy of the generated tracks more accurately than that of machine verification through an algorithm, if the generated tracks are not matched with the monitoring equipment, removing the tracks and returning to be regenerated, the error rate of the predicted tracks can be reduced through a manual verification method, the reasonability of the generated motion tracks is proved, and the accuracy of software prediction is improved.
The step 400 of verifying the trajectory of the person and outputting the complete trajectory of the person comprises:
step 401, calculating a deviation degree of the generated track spatiotemporal information by combining the spatiotemporal information determined by known personnel;
and step 402, importing the complete motion trajectory into a pedestrian simulation system, and restoring the space-time information of the whole trajectory.
The deviation of the actual personnel movement track and the generated movement track is calculated, the quality of the model can be evaluated, the model is further optimized after the deviation is calculated, the deviation degree is reduced, the deviation degree is more fit with the actual personnel movement track, the output movement track is more accurate, the accuracy of the restoration track is improved, and the dispatching personnel are helped to improve the tracing ability.
The information of personnel investigation and the space-time information of the generated track are compared, the authenticity of the space-time information can be proved, the specific evaluation standard is measured by adopting the degree of deviation in the scheme, the accuracy of information judgment can be improved, the judgment can be conveniently and rapidly carried out, and the judgment speed is improved.
Through leading-in simulation system with complete movement track, restore the spatiotemporal information of whole orbit, can make the spatiotemporal information vivid image of orbit present in the staff, can look over the pedestrian at any time in the simulation system at any time and appear the information in a certain place, made things convenient for staff's investigation work simultaneously for subsequent orbit analysis, behavioral analysis, provided data support to pedestrian's contact information.
The step 401 of calculating the degree of deviation of the generated spatiotemporal information of the trajectory by combining the spatiotemporal information determined by the known person specifically includes:
calculating the deviation degree of the track information with the same time in the actual space-time track and the simulated space-time track of the personnel, namely calculating the space deviation of the actual track and the simulated track at the same moment, and comparing the deviation degree with the deviation degree
Figure 868693DEST_PATH_IMAGE020
Degree of deviation of individual person
Figure 859783DEST_PATH_IMAGE021
The calculation is as follows:
Figure 152093DEST_PATH_IMAGE022
degree of deviation for all persons
Figure 101594DEST_PATH_IMAGE023
The calculation is as follows:
Figure 597298DEST_PATH_IMAGE024
，in the formula (I), the compound is shown in the specification,
Figure 142811DEST_PATH_IMAGE025
is as follows
Figure 40360DEST_PATH_IMAGE020
The first of an individual
Figure 878872DEST_PATH_IMAGE026
The plane abscissa of the space-time section information,
Figure 127450DEST_PATH_IMAGE027
is as follows
Figure 725922DEST_PATH_IMAGE020
The first of an individual
Figure 960201DEST_PATH_IMAGE026
The plane ordinate of the space-time section information,
Figure 251505DEST_PATH_IMAGE028
is as follows
Figure 705489DEST_PATH_IMAGE020
The first of an individual
Figure 107651DEST_PATH_IMAGE026
The occurrence time of the space-time section information,
Figure 199366DEST_PATH_IMAGE029
the horizontal coordinate of the plane of the simulated trajectory position for the pedestrian,
Figure 661572DEST_PATH_IMAGE030
a plane ordinate of the position of the simulated trajectory for the pedestrian,
Figure 353584DEST_PATH_IMAGE031
to simulate the location occurrence time.
The degree of deviation of the generated motion trajectory is calculated by combining the known motion trajectory determined by personnel, the accuracy of the method can be verified more powerfully, the authenticity of the time-space information can be proved, and the specific evaluation standard is measured by adopting the degree of deviation in the scheme, so that the accuracy of information judgment can be improved, the judgment can be conveniently and rapidly carried out, and the judgment rate is improved.
Step 402 is to introduce the complete motion trajectory into the pedestrian simulation system, and the reduction of the spatiotemporal information of the whole trajectory includes:
generating a complete set of supplementary trajectories for all persons
Figure 543126DEST_PATH_IMAGE032
And step s2, importing the plane structure information into a pedestrian simulation system, constraining the pedestrian to move according to a specified track in the pedestrian simulation system, calculating to obtain a complete space-time track, and exporting the pedestrian space-time track information
Figure 269773DEST_PATH_IMAGE033
The simulation space-time trajectory form is
Figure 390963DEST_PATH_IMAGE034
Wherein
Figure 570272DEST_PATH_IMAGE035
The horizontal coordinate of the plane of the simulated trajectory position for the pedestrian,
Figure 314237DEST_PATH_IMAGE036
a plane ordinate of the position of the simulated trajectory for the pedestrian,
Figure 144658DEST_PATH_IMAGE037
the simulated position occurrence time.
The complete motion trajectory is led into the simulation system, the spatiotemporal information of the whole trajectory is restored, the spatiotemporal information of the trajectory can be vividly presented to workers, and the simulation system is convenient for the workers to understand and use, so that the simulation system is easier to master, is suitable for beginners, reduces unnecessary software training, can check the information of pedestrians appearing in a certain place at a certain time in the simulation system at any time, facilitates the dispatching work of the workers, and provides data support for subsequent trajectory analysis and behavior analysis and the contact information of the pedestrians.
Repeating the steps 401 and 402 to construct a track reduction model:
the optimization target is that the deviation degree of all the personnel trajectories is minimum, and the target function is as follows:
Figure DEST_PATH_IMAGE050
constraint conditions are as follows:
decision variables being arbitrary
Figure DEST_PATH_IMAGE051
To (1) a
Figure DEST_PATH_IMAGE052
A feasible track sequence
Figure DEST_PATH_IMAGE053
The constraint is:
Figure DEST_PATH_IMAGE054
Figure DEST_PATH_IMAGE055
Figure DEST_PATH_IMAGE056
the compensation sequence is generated by pedestrian simulation
Figure DEST_PATH_IMAGE057
Figure DEST_PATH_IMAGE058
Figure DEST_PATH_IMAGE059
Figure DEST_PATH_IMAGE060
Figure DEST_PATH_IMAGE061
Simulation model for pedestrian
And solving the constructed track reduction model by using a genetic algorithm to obtain a complete pedestrian space-time track.
Obtaining any person through a track reduction model
Figure DEST_PATH_IMAGE062
Has a track of
Figure DEST_PATH_IMAGE063
As in fig. 3.
The foregoing are merely exemplary embodiments of the present invention, which enable those skilled in the art to understand or practice the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (9)

1. A pedestrian trajectory calculation method based on a multi-agent simulation technology is characterized by comprising the following steps:
collecting detention information and building information of personnel;
generating a space-time trajectory point sequence of the personnel;
generating a feasible motion track;
and verifying the movement track of the personnel and outputting a complete personnel track.
2. The pedestrian trajectory estimation method based on multi-agent simulation technology as claimed in claim 1, wherein the collecting of retention information of the person specifically comprises:
the flow adjustment personnel inquire by telephone, investigate the time-space trajectory of the personnel in the building and restore the time-space section information of the personnel in the building.
3. The multi-agent simulation technology-based pedestrian trajectory estimation method according to claim 1, wherein the generating of the feasible motion trajectory comprises:
acquiring terrain scene information and generating a feasible track sequence;
all persons were supplemented with missing track sequences.
4. The pedestrian trajectory estimation method based on the multi-agent simulation technology as claimed in claim 3, wherein the obtaining of the terrain scene information and the generation of the feasible trajectory sequence specifically include:
generating a recording point area set of personnel according to the plane terrain information of a system scene
Figure DEST_PATH_IMAGE001
So that for any
Figure DEST_PATH_IMAGE002
And
Figure DEST_PATH_IMAGE003
is provided with
Figure DEST_PATH_IMAGE004
To any one of
Figure DEST_PATH_IMAGE005
And
Figure DEST_PATH_IMAGE006
（
Figure DEST_PATH_IMAGE007
) Generating feasible track sequence set by A-star algorithm
Figure DEST_PATH_IMAGE008
At will
Figure 57354DEST_PATH_IMAGE005
And
Figure 427024DEST_PATH_IMAGE006
to (1) a
Figure DEST_PATH_IMAGE009
The sequence of feasible trajectories is represented as
Figure DEST_PATH_IMAGE010
。
5. The pedestrian trajectory estimation method based on the multi-agent simulation technology as claimed in claim 3, wherein the supplementing missing trajectory sequences for all the persons specifically comprises:
for any person
Figure 98440DEST_PATH_IMAGE009
Adjacent space-time information of
Figure DEST_PATH_IMAGE011
And
Figure DEST_PATH_IMAGE012
selecting feasible track sequence from feasible track sequence set by heuristic rule
Figure DEST_PATH_IMAGE013
Forming a complete motion trajectory between adjacent spatial and temporal positions
Figure DEST_PATH_IMAGE014
Wherein
Figure DEST_PATH_IMAGE015
，
Figure DEST_PATH_IMAGE016
，
Figure DEST_PATH_IMAGE017
For any person
Figure 444714DEST_PATH_IMAGE009
Forming a complementary complete sequence of traces
Figure DEST_PATH_IMAGE018
For all persons, forming a complete set of complementary trajectories
Figure DEST_PATH_IMAGE019
。
6. The method for estimating the pedestrian trajectory based on the multi-agent simulation technology as claimed in claim 1, wherein after the feasible motion trajectory is generated, a dispatcher intervenes again, and verifies the generated several possible motion spatiotemporal trajectories by monitoring device information, specifically:
verifying possible space-time trajectories among the stagnation points by flow regulators in combination with monitoring equipment information, and if the personnel can be found in peripheral monitoring equipment related to the space-time trajectories, taking the space-time trajectories as actual trajectories of the personnel among the stagnation points;
if no person is found in the monitoring equipment corresponding to the track point of the space-time track or the time is not matched, the motion track is eliminated;
and if the generated plurality of possible motion space-time trajectories are excluded, returning to regenerate new possible motion trajectories until a matched actual motion trajectory is found.
7. The multi-agent simulation technology-based pedestrian trajectory estimation method according to claim 1, wherein the verifying the trajectory of the person and outputting the complete trajectory of the person comprises:
calculating the degree of deviation of the generated spatiotemporal information of the track by combining the spatiotemporal information determined by the known personnel;
and (4) importing the complete motion trajectory into a pedestrian simulation system, and restoring the space-time information of the whole trajectory.
8. The pedestrian trajectory estimation method based on the multi-agent simulation technology as claimed in claim 7, wherein the calculating the degree of deviation of the spatiotemporal information of the generated trajectory in combination with the spatiotemporal information determined by the known person is specifically as follows:
calculating the deviation degree of the track information with the same time in the actual space-time track and the simulated space-time track of the personnel, namely calculating the space deviation of the actual track and the simulated track at the same moment, and carrying out the calculation on the first step
Figure DEST_PATH_IMAGE020
Degree of deviation of individual person
Figure DEST_PATH_IMAGE021
The calculation is as follows:
Figure DEST_PATH_IMAGE022
degree of deviation for all persons
Figure DEST_PATH_IMAGE023
The calculation is as follows:
Figure DEST_PATH_IMAGE024
，in the formula (I), the compound is shown in the specification,
Figure DEST_PATH_IMAGE025
is as follows
Figure 134452DEST_PATH_IMAGE020
The first of an individual
Figure DEST_PATH_IMAGE026
The plane abscissa of the space-time section information,
Figure DEST_PATH_IMAGE027
is as follows
Figure 851522DEST_PATH_IMAGE020
The first of an individual
Figure 321818DEST_PATH_IMAGE026
The plane ordinate of the space-time section information,
Figure DEST_PATH_IMAGE028
is as follows
Figure 707669DEST_PATH_IMAGE020
The first of an individual
Figure 845389DEST_PATH_IMAGE026
The occurrence time of the space-time section information,
Figure DEST_PATH_IMAGE029
the horizontal coordinate of the plane of the simulated trajectory position for the pedestrian,
Figure DEST_PATH_IMAGE030
a plane ordinate of the position of the simulated trajectory for the pedestrian,
Figure DEST_PATH_IMAGE031
to simulate the location occurrence time.
9. The method for estimating the pedestrian trajectory based on the multi-agent simulation technology as claimed in claim 7, wherein the step of introducing the complete motion trajectory into the pedestrian simulation system to recover the spatiotemporal information of the complete trajectory comprises:
generating a complete set of supplementary trajectories for all persons
Figure DEST_PATH_IMAGE032
And step s2, importing the plane structure information into a pedestrian simulation system, constraining the pedestrians to move according to a specified track in the pedestrian simulation system, calculating to obtain a complete space-time track, and exporting the pedestrian space-time track information, the first step
Figure DEST_PATH_IMAGE033
The simulation space-time trajectory form is
Figure DEST_PATH_IMAGE034
In which
Figure DEST_PATH_IMAGE035
The horizontal coordinate of the plane of the simulated trajectory position for the pedestrian,
Figure DEST_PATH_IMAGE036
a plane ordinate of the position of the simulated trajectory for the pedestrian,
Figure DEST_PATH_IMAGE037
to simulate the location occurrence time.
CN202211250488.4A 2022-10-13 2022-10-13 Pedestrian trajectory calculation method based on multi-agent simulation technology Active CN115330360B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211250488.4A CN115330360B (en) 2022-10-13 2022-10-13 Pedestrian trajectory calculation method based on multi-agent simulation technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211250488.4A CN115330360B (en) 2022-10-13 2022-10-13 Pedestrian trajectory calculation method based on multi-agent simulation technology

Publications (2)

Publication Number Publication Date
CN115330360A true CN115330360A (en) 2022-11-11
CN115330360B CN115330360B (en) 2022-12-27

Family

ID=83913546

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211250488.4A Active CN115330360B (en) 2022-10-13 2022-10-13 Pedestrian trajectory calculation method based on multi-agent simulation technology

Country Status (1)

Country Link
CN (1) CN115330360B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115587503A (en) * 2022-11-23 2023-01-10 深圳市城市交通规划设计研究中心股份有限公司 Individual trip chain restoration method based on multi-mode simulation
CN115966313A (en) * 2023-03-09 2023-04-14 创意信息技术股份有限公司 Integrated management platform based on face recognition

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102163259A (en) * 2011-03-29 2011-08-24 交通运输部公路科学研究所 System assessment method of simulation model of pedestrian microscopic traffic flow
CN111783295A (en) * 2020-06-28 2020-10-16 中国人民公安大学 Dynamic identification and prediction evaluation method and system for urban community specific human behavior chain
CN113450923A (en) * 2020-03-27 2021-09-28 中国科学院深圳先进技术研究院 Method and system for simulating influenza spatiotemporal propagation process by large-scale trajectory data
CN115071762A (en) * 2022-08-22 2022-09-20 北京理工大学前沿技术研究院 Pedestrian trajectory prediction method, model and storage medium oriented to urban scene

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102163259A (en) * 2011-03-29 2011-08-24 交通运输部公路科学研究所 System assessment method of simulation model of pedestrian microscopic traffic flow
CN113450923A (en) * 2020-03-27 2021-09-28 中国科学院深圳先进技术研究院 Method and system for simulating influenza spatiotemporal propagation process by large-scale trajectory data
CN111783295A (en) * 2020-06-28 2020-10-16 中国人民公安大学 Dynamic identification and prediction evaluation method and system for urban community specific human behavior chain
CN115071762A (en) * 2022-08-22 2022-09-20 北京理工大学前沿技术研究院 Pedestrian trajectory prediction method, model and storage medium oriented to urban scene

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115587503A (en) * 2022-11-23 2023-01-10 深圳市城市交通规划设计研究中心股份有限公司 Individual trip chain restoration method based on multi-mode simulation
CN115966313A (en) * 2023-03-09 2023-04-14 创意信息技术股份有限公司 Integrated management platform based on face recognition
CN115966313B (en) * 2023-03-09 2023-06-09 创意信息技术股份有限公司 Integrated management platform based on face recognition

Also Published As

Publication number Publication date
CN115330360B (en) 2022-12-27

Similar Documents

Publication Publication Date Title
CN115330360B (en) Pedestrian trajectory calculation method based on multi-agent simulation technology
CN111667101B (en) Personalized electric power field operation path planning method and system integrating high-resolution remote sensing image and terrain
CN105911988A (en) Automatic drawing device and method
CN108108831B (en) Destination prediction method and device
CN103295414A (en) Bus arrival time forecasting method based on mass historical GPS (global position system) trajectory data
CN107228677A (en) Driftage recognition methods and device
CN108256431A (en) A kind of hand position identification method and device
CN109767141A (en) A kind of monitoring method of patrolling railway, device, medium and equipment
CN112489426A (en) Urban traffic flow space-time prediction scheme based on graph convolution neural network
CN110309952B (en) City employment spatial layout optimization auxiliary system based on commuting model
CN104424812A (en) Bus arrival time prediction system and method
JP2019012494A (en) Human flow estimating device, human flow estimating system and human flow estimating method
JP2019220048A (en) Traffic flow prediction device and traffic flow prediction system
CN115600022A (en) Training and processing method, device and medium of spatio-temporal data processing model
CN109579848A (en) A kind of middle plan method of robot under holding global path
CN115909121A (en) Mine underground drill rod counting method, system and equipment based on improved YOLOV5 and Deepsort
CN105632114A (en) Monitoring measurement point safety state monitoring method based on GIS technology
CN114937293A (en) Agricultural service management method and system based on GIS
CN117036112B (en) Geographic information system and method for land planning
CN113837148A (en) Pedestrian trajectory prediction method based on self-adjusting sparse graph transform
CN115688952A (en) Big data-based campus congestion area prediction method
JP6884819B2 (en) Safety management equipment, safety management methods and safety management programs
CN116952277A (en) Potential position estimation method and system based on artificial intelligence and behavior characteristics
Song et al. Statistical traffic generation methods for urban traffic simulation
JP2019101860A (en) Congestion analyzer and congestion analysis method

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