CN108806248B - Vehicle travel track division method for RFID electronic license plate data - Google Patents

Vehicle travel track division method for RFID electronic license plate data Download PDF

Info

Publication number
CN108806248B
CN108806248B CN201810548328.5A CN201810548328A CN108806248B CN 108806248 B CN108806248 B CN 108806248B CN 201810548328 A CN201810548328 A CN 201810548328A CN 108806248 B CN108806248 B CN 108806248B
Authority
CN
China
Prior art keywords
rfid
vehicle
acquisition points
data
adjacent
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.)
Active
Application number
CN201810548328.5A
Other languages
Chinese (zh)
Other versions
CN108806248A (en
Inventor
郑林江
夏冬
刘卫宁
孙棣华
赵敏
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.)
Chongqing University
Original Assignee
Chongqing University
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 Chongqing University filed Critical Chongqing University
Priority to CN201810548328.5A priority Critical patent/CN108806248B/en
Publication of CN108806248A publication Critical patent/CN108806248A/en
Application granted granted Critical
Publication of CN108806248B publication Critical patent/CN108806248B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
    • G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
    • G06K7/10009—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation sensing by radiation using wavelengths larger than 0.1 mm, e.g. radio-waves or microwaves
    • G06K7/10366—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation sensing by radiation using wavelengths larger than 0.1 mm, e.g. radio-waves or microwaves the interrogation device being adapted for miscellaneous applications
    • G06K7/10415—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation sensing by radiation using wavelengths larger than 0.1 mm, e.g. radio-waves or microwaves the interrogation device being adapted for miscellaneous applications the interrogation device being fixed in its position, such as an access control device for reading wireless access cards, or a wireless ATM
    • G06K7/10425—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation sensing by radiation using wavelengths larger than 0.1 mm, e.g. radio-waves or microwaves the interrogation device being adapted for miscellaneous applications the interrogation device being fixed in its position, such as an access control device for reading wireless access cards, or a wireless ATM the interrogation device being arranged for interrogation of record carriers passing by the interrogation device
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0133—Traffic data processing for classifying traffic situation
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Chemical & Material Sciences (AREA)
  • Toxicology (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Electromagnetism (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a vehicle travel track dividing method aiming at RFID electronic license plate data, which comprises the following steps: extracting the passing data of all vehicles passing through adjacent RFID acquisition points; traversing the traffic data of the adjacent RFID acquisition points, and selecting point pair data of different RFID acquisition points in the traffic data of all the adjacent RFID acquisition points; obtaining parameters of a vehicle travel time distribution probability model between adjacent RFID acquisition points according to vehicle passing time interval data between the adjacent RFID acquisition points; judging whether the vehicle stays between the two adjacent RFID acquisition points or not; according to the stopping condition of the vehicle between the adjacent RFID acquisition points, the starting point and the ending point of each trip of the vehicle are extracted, and the track of the vehicle is divided into a plurality of trip sections. The invention considers different traffic conditions between the RFID acquisition points through the travel time distribution probability model between the adjacent RFID acquisition points, and has strong adaptability to various different traffic conditions if the distances between the adjacent RFID acquisition points are different.

Description

Vehicle travel track division method for RFID electronic license plate data
Technical Field
The invention relates to the field of traffic, in particular to a vehicle travel track dividing method aiming at RFID electronic license plate data.
Background
Since the new century, the rapid development of the social economy and the urbanization level of China are continuously improved, and along with the dual growth of the urban holding quantity and the human holding quantity of motor vehicles, a series of difficulties in traffic are more prominent. Intelligent transportation is a main direction for people to solve traffic problems at present. The reasonable analysis of the travel demands of residents is the basis of intelligent traffic construction.
The analysis of resident travel demand is generally based on the track data of the vehicle, the stay part in the track is identified, on the basis, the travel track is divided, and the starting point O (origin) and the destination point D (destination) of each travel are extracted. Where difficulties are in the recognition of the dwell in the track. At present, research on recognition of stay in a track is mainly developed based on GPS data of vehicles, sampling time intervals of the GPS data are short and are generally about tens of seconds, GPS points are densely distributed in a smaller space in a stay part in the track, and therefore recognition of stay in the track can be achieved by adopting a distance threshold method or some clustering algorithms based on space density of sampling points, and good effect can be achieved. However, the number of vehicles equipped with the GPS or the beidou positioning system is small, and only a rental vehicle and a dangerous vehicle for two passengers can be analyzed, and all vehicles cannot be analyzed, so that the finally obtained travel data cannot represent the whole traffic condition of the whole city.
The RFID electronic license plate data does not have the problem, and the collection object of the RFID electronic license plate data covers all motor vehicles, so that the RFID electronic license plate data is very good resident trip analysis data. Currently, methods for dividing travel tracks of RFID electronic license plate data exist, and whether a vehicle stops between RFID acquisition points or not is judged by comparing the time interval of the vehicle passing through adjacent RFID acquisition points with a set time threshold. However, different RFID collection points have very different traffic conditions, some adjacent RFID collection points are only hundreds of meters apart from each other, some adjacent RFID collection points are more than 5 kilometers apart from each other, some road sections between adjacent RFID collection points pass through urban downtown areas, and some road sections between adjacent RFID collection points pass through urban expressways, so that it is difficult to set a proper time threshold value to be suitable for the traffic conditions between all adjacent RFID collection points.
Disclosure of Invention
In view of the above, in order to solve the above problems, the present invention provides a vehicle travel track dividing method for RFID electronic license plate data, which can accurately identify whether a vehicle stays between adjacent collection points, extract a start point and an end point of each travel of the vehicle, and divide the track of the vehicle into a plurality of travel segments, and meanwhile, the method can be applied to various traffic conditions between adjacent RFID collection points.
The purpose of the invention is realized by the following technical scheme: a vehicle travel track dividing method aiming at RFID electronic license plate data comprises the following steps:
step S1, extracting the traffic data record ═ eid, t of all vehicles passing through the adjacent RFID acquisition points0,rfid0,t1,rfid1T > where eid denotes the electronic license plate number of the vehicle, t0And rfid0Respectively representing the time when the vehicle passes through the first RFID acquisition point of two adjacent RFID acquisition points and the identification number, t, of the RFID acquisition point1And rfid1Respectively representing the time of the second RFID acquisition point of the two adjacent RFID acquisition points passed by the vehicle and the identification number of the RFID acquisition point, and t represents the time interval of the vehicle passing the two adjacent RFID acquisition points;
step S2, traversing the traffic data of the adjacent RFID acquisition points, and selecting the traffic data of all the adjacent RFID acquisition points, wherein the traffic data of all the adjacent RFID acquisition points is < eid, t0,rfid0,t1,rfid1T > Point-to-point data < RFID of different RFID acquisition points0,rfid1＞；
S3, establishing a travel time distribution probability model between adjacent RFID acquisition points, and solving parameters of the vehicle travel time distribution probability model between the adjacent RFID acquisition points according to vehicle passing time interval data between the adjacent RFID acquisition points;
step S4, judging whether the vehicle stops between two adjacent RFID acquisition points according to the time interval t when the vehicle passes through the two adjacent RFID acquisition points and the travel time distribution probability model between the two adjacent RFID acquisition points;
and S5, extracting the starting point and the end point of each trip of the vehicle according to the stop condition of the vehicle between the adjacent RFID acquisition points, and dividing the track of the vehicle into a plurality of trip sections.
Preferably, the step S1 specifically includes the following sub-steps:
s11, extracting all different eid numbers in the RFID electronic license plate data;
s12, selecting an eid number from the data obtained in the step S11, screening out all RFID electronic license plate data containing the eid number in the RFID electronic license plate data set, and sequencing according to the time ascending sequence of passing vehicles to obtain the track of the vehicles
Figure BDA0001680475040000021
Wherein TraAThe track of the vehicle A is shown, R represents a piece of RFID electronic license plate data, v represents the electronic license plate number of the vehicle, R represents the identification number of an RFID acquisition point, t represents the time when the vehicle is recognized,
Figure BDA0001680475040000022
representing the time when the vehicle A passes the ith RFID acquisition point;
combining the data of the adjacent RFID electronic license plates in the track to obtain the passing data of the vehicle passing through the adjacent RFID acquisition points, wherein the passing data of the vehicle passing through the adjacent RFID acquisition points is represented as:
Figure BDA0001680475040000023
wherein, recodri AData representing the traffic of the ith vehicle passing through the adjacent RFID acquisition points,
Figure BDA0001680475040000025
an electronic license plate number of the vehicle a is shown,
Figure BDA0001680475040000026
the identification number represents that the vehicle A passes through the ith RFID acquisition point;
s13, executing a step S12 on all the eid numbers, and storing the traffic data of all vehicles passing through the adjacent RFID acquisition points into a database.
Preferably, the step S3 includes the following sub-steps:
s31, establishing a travel time distribution probability model between adjacent RFID acquisition points, wherein the travel time distribution probability model between the two adjacent RFID acquisition points is as follows:
Figure BDA0001680475040000031
wherein: p (t) represents the probability that the time interval between the vehicle passing two adjacent RFID acquisition points is t,μmove、σmove、wmoverespectively representing the expectation, standard deviation and weight coefficient after logarithm of passing time interval data of all vehicles when the vehicles rapidly pass through two adjacent RFID acquisition pointsjam、σjam、wjamRespectively representing the expectation, standard deviation and weight coefficient mu of the passing time interval data of all vehicles when the vehicles encounter traffic jam in the process of passing through two adjacent RFID acquisition pointsstop、σstop、wstopRespectively representing the expectation, standard deviation and weight coefficient of the passing time interval data of all vehicles when the vehicles stay in the process of passing through two adjacent RFID acquisition points;
s32, according to the passing time interval data of the vehicles between the adjacent RFID acquisition points, calculating the parameters of the vehicle travel time distribution probability model between the adjacent RFID acquisition points.
Preferably, the step S32 includes the following sub-steps:
s321, reading data of point pairs < RFID _ a and RFID _ b > of adjacent RFID acquisition points of the travel time distribution probability model parameters;
s322, extracting vehicle passing time interval data Train ═ t through adjacent RFID acquisition points RFID _ a and RFID _ b1,t2,…,tNDenoted traffic interval data sample data set, tiIs the ith sample data of the passing time interval, N represents the total amount of samples of the passing time interval data, i belongs to [1, N ∈]；
S323, assigning initial values to parameters of a vehicle travel time distribution probability model between adjacent RFID acquisition points RFID _ a and RFID _ b;
s324, calculating the passing time interval t of each sample according to the initial parameters of the travel time distribution probability model or the parameters after the last iterationiSize of probability of
Figure BDA0001680475040000032
S325, passing time interval t in all samplesiCalculating the optimal value of each parameter in the travel time distribution probability model under the condition that the probability of the travel time distribution probability model is determined;
s326, performing iteration execution on the step S324 and the step S325 until the parameters of the travel time distribution probability model obtained after multiple iterations converge;
s327, executing the steps S322 to S326 on the point-to-point data of all the adjacent RFID acquisition points to obtain parameters of a vehicle travel time distribution probability model among all the adjacent RFID acquisition points.
Preferably, the step S4 specifically includes the following sub-steps:
s41, extracting traffic data of all adjacent RFID acquisition points of a vehicle, wherein the traffic data is less than eid and RFID0,rfid1,t＞，
S42, selecting traffic data of one vehicle passing through adjacent RFID acquisition points, and assuming that the passing adjacent RFID acquisition points are RFID _ a and RFID _ b; calculating the time interval of the vehicle passing between adjacent RFID acquisition points RFID _ a and RFID _ b as t,
when the vehicle rapidly passes through two adjacent RFID acquisition points, the probability is P (state ═ move | t);
when a vehicle encounters traffic jam in the process of passing through two adjacent RFID acquisition points, the probability is P (state) and j am t;
when the vehicle stops in the process of passing through two adjacent RFID acquisition points, the probability is P (stop | t);
if the state is greater than P (stop | t) > P (state is greater than move | t) and the state is greater than P (stop | t) > P (state is greater than jam | t), judging that the vehicle stays between the two adjacent RFID acquisition points, otherwise, judging that the vehicle does not stay between the two adjacent RFID acquisition points;
s43, executing step S42 on all traffic data of the vehicle passing through the adjacent RFID acquisition points;
s44, performing steps S42 and S43 for all vehicles.
Preferably, the step S5 specifically includes the following sub-steps:
s51, selecting the RFID electronic license plate number of one vehicle, screening all the passing data of the vehicle passing through the adjacent RFID acquisition points, and sequencing the data in an ascending order according to the time of passing through the first acquisition point in the adjacent acquisition points;
s52, reading a piece of passing data of the vehicle passing through the adjacent RFID acquisition points, starting to divide the trip of the vehicle if the data is the first passing data of the vehicle, and taking the first acquisition point of the two adjacent acquisition points as the starting point of the trip;
s53, if the traffic data is the last traffic data of the vehicle, saving the second acquisition point of the two adjacent acquisition points as the end point of the current trip;
s54, executing steps S52 to S53 on all traffic data of the vehicle passing through adjacent RFID acquisition points to obtain starting point data and end point data of each trip of the vehicle;
s55, executing steps S51 to S54 on all vehicles, and obtaining the starting point data and the end point data of each trip of all vehicles.
Preferably, after the step S52, the method further includes:
if the vehicle does not stay between the two adjacent RFID acquisition points, the traffic data is considered to belong to the current trip; if the vehicle stays between the two adjacent RFID acquisition points, the first acquisition point of the two adjacent acquisition points is saved as the terminal point of the current trip, the division of the current trip is completed, the division of the next trip is started simultaneously, and the second acquisition point of the two adjacent acquisition points is saved as the starting point of the next trip.
Due to the adoption of the technical scheme, the invention has the following advantages:
1. the invention can determine the starting point and the end point of each trip of the vehicle.
2. The invention considers different traffic conditions between the RFID acquisition points through the travel time distribution probability model between the adjacent RFID acquisition points, and has strong adaptability to various different traffic conditions if the distances between the adjacent RFID acquisition points are different.
3. The invention is suitable for all vehicles with RFID electronic license plates and has wide application range.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objectives and other advantages of the invention may be realized and attained by the means of the instrumentalities and combinations particularly pointed out hereinafter.
Drawings
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the accompanying drawings:
FIG. 1 is a general flow diagram;
FIG. 2 is a flow chart of the parameter calculation of a vehicle travel time distribution probability model between adjacent RFID acquisition points;
FIG. 3 is a flow chart illustrating a determination of a vehicle stopping between two adjacent RFID acquisition points;
FIG. 4 is a flow chart of extracting a vehicle trip start point and end point;
fig. 5 is an exemplary diagram of vehicle travel trajectory division.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention.
Please refer to fig. 1 to 5. It should be noted that the drawings provided in the present embodiment are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
As shown in fig. 1, the new method for dividing the vehicle travel track applied to the RFID electronic license plate data provided in this embodiment includes the following steps:
step S1: original RFID electronic license plateData is obtained for all vehicles passing through adjacent RFID acquisition points, and the data can be expressed in a quintuple format of record ═ eid, t0,rfid0,t1,rfid1T > where eid denotes the electronic license plate number of the vehicle, t0And rfid0Respectively representing the time of the first RFID acquisition point of two adjacent RFID acquisition points passed by the vehicle and the identification number, t, of the RFID acquisition point1And rfid1Respectively represents the time of the second RFID acquisition point of two adjacent RFID acquisition points passed by the vehicle and the identification number of the RFID acquisition point, and t represents the time interval of the two adjacent RFID acquisition points passed by the vehicle.
S11, extracting all different eid numbers in the RFID electronic license plate data;
s12, selecting an EID number from the data obtained in the step S11, screening out all RFID electronic license plate data of the EID number in the RFID electronic license plate data set, and sequencing according to the time ascending sequence of passing vehicles to obtain the track of the vehicles
Figure BDA0001680475040000061
Wherein TraAThe track of the vehicle A is shown, R represents a piece of RFID electronic license plate data, v represents the electronic license plate number of the vehicle, R represents the identification number of an RFID acquisition point, t represents the time when the vehicle is recognized,
Figure BDA0001680475040000062
indicating the time that vehicle a passes the ith RFID collection point. And then combining the data of the adjacent RFID electronic license plates in the track to obtain the passing data of the vehicles passing through the adjacent RFID acquisition points, and storing the passing data into a database. The traffic data for a vehicle passing an adjacent RFID collection point can be expressed as:
Figure BDA0001680475040000063
wherein, recodri AData representing the traffic of the ith vehicle passing through the adjacent RFID acquisition points,
Figure BDA0001680475040000065
an electronic license plate number of the vehicle a is shown,
Figure BDA0001680475040000066
and the identification number represents that the vehicle A passes through the ith RFID acquisition point.
S13, executing a step S12 on all the eid numbers, and storing the traffic data of all vehicles passing through the adjacent RFID acquisition points into a database.
Step S2: and extracting point pair data of all adjacent RFID acquisition points. Traversing the traffic data of the adjacent RFID acquisition points, and selecting point pair data < RFID of different RFID acquisition points in all data0,rfid1>. The database is stored with it.
The method includes the steps that the passing data of adjacent RFID acquisition points are stored in a data table with a table name of table _ passing, and the attribute of the data in the table is that record is less than eid, t0,rfid0,t1,rfid1T > where eid denotes the electronic license plate number of the vehicle, t0And rfid0Respectively representing the time of the first RFID acquisition point of two adjacent RFID acquisition points passed by the vehicle and the identification number, t, of the RFID acquisition point1And rfid1Respectively represents the time of the second RFID acquisition point of two adjacent RFID acquisition points passed by the vehicle and the identification number of the RFID acquisition point, and t represents the time interval of the two adjacent RFID acquisition points passed by the vehicle. The same settings will be used here, with the traffic data of adjacent RFID acquisition points being used several times in the following.
The point pair data of different RFID acquisition points in all the traffic data can be directly extracted through the sql statement.
Sql:select rfid0,rfid1from table_passing group by rfid0,rfid1
Step S3: and establishing a travel time distribution probability model between adjacent RFID acquisition points, and solving parameters of the vehicle travel time distribution probability model between the adjacent RFID acquisition points according to the passing time interval data of the vehicles between the adjacent RFID acquisition points.
S31, establishing a travel time distribution probability model between adjacent RFID acquisition points.
A vehicle passing two adjacent RFID collection points encounters one of three conditions: 1. the vehicle rapidly passes through two adjacent RFID acquisition points; 2. the vehicle encounters traffic jam in the process of passing through two adjacent RFID acquisition points; 3. the vehicle stops in the process of passing through two adjacent RFID acquisition points. Therefore, the probability model of the travel time distribution between two adjacent RFID acquisition points is the combination of the probability models of the travel time distribution between the two adjacent RFID acquisition points in the three cases. Research shows that the travel time distribution probability model between the adjacent RFID acquisition points in the case 1 is a lognormal distribution model, and the travel time distribution probability model between the adjacent RFID acquisition points in the cases 2 and 3 is a normal distribution model. The probability model of the distribution of the travel time t between two adjacent RFID acquisition points is therefore expressed as:
Figure BDA0001680475040000071
wherein: p (t) represents the probability that the time interval between the two adjacent RFID acquisition points is t, mumoveAnd σmoveRepresentative is the log expectation and standard deviation, μ, of the transit time interval data for all vehicles in case 1jamAnd σjamRepresentative is the expected and standard deviation, μ, of the transit time interval data for all vehicles in case 2stopAnd σstopRepresentative is the expected and standard deviation, w, of the transit time interval data for all vehicles in case 3move,wjam,wstopThe weighting coefficients of case 1, case 2, and case 2 are shown.
S32, according to the passing time interval data of the vehicles between the adjacent RFID acquisition points, the parameters of the vehicle travel time distribution probability model between the adjacent RFID acquisition points are obtained by applying an EM algorithm, and the parameters are shown in figure 2.
S321, firstly, selecting point pair data of adjacent RFID acquisition points for obtaining the travel time distribution probability model parameters, and assuming that the point pair of the adjacent acquisition points is < RFID _ a and RFID _ b >;
s322, vehicle passing time interval data passing through adjacent RFID acquisition points RFID _ a and RFID _ b are extracted, and Train is { t }1,t2,…,tNTrain is a sample data set of traffic interval data, tiIs the transit time interval.
Can be screened out from the data table _ passing storing the traffic data of the adjacent RFID acquisition points by sql statements.
Sql:select t from table_passing where rfid0＝rfid_a and rfid1＝rfid_b
And S323, assigning initial values to parameters of the vehicle travel time distribution probability model between the adjacent RFID acquisition points RFID _ a and RFID _ b. Firstly, a sample data set Train is randomly divided into 3 parts { Trainmove,Trainjam,TrainstopThen, the 3 groups of data are used to calculate the specific calculation formula of the initialization parameter as follows
Figure BDA0001680475040000072
Figure BDA0001680475040000081
Figure BDA0001680475040000082
Figure BDA0001680475040000083
Figure BDA0001680475040000084
Figure BDA0001680475040000085
Figure BDA0001680475040000086
Wherein | Trainmove|，|Trainjam|，|TrainstopI is respectively Trainmove,Trainjam,TrainstopThe number of samples in (a) is,
Figure BDA0001680475040000087
is a parameter of (1)<wmove,wjam,wstop,μmove,μjam,μstop,σmove,σjam,σstop>Initial value of (d), In (t)i) Represents a pair tiAnd (6) carrying out logarithm calculation.
S324, calculating the passing time interval t of each sample according to the initial parameters of the travel time distribution probability model or the parameters after the last iterationiProbability of three traffic conditions
Figure BDA0001680475040000088
The specific calculation is shown in formulas (9) to (12):
Figure BDA0001680475040000089
Figure BDA00016804750400000810
Figure BDA00016804750400000811
Figure BDA00016804750400000812
wherein
Figure BDA00016804750400000813
Is the value of the corresponding parameter in equation (1) after k iterations, tiIndicating the ith sample transit time interval,
Figure BDA00016804750400000814
representing the pass time interval t for the parameters after k iterationsiAnd belongs to the probability of occurrence of situation 1,
Figure BDA0001680475040000091
representing the pass time interval t for the parameters after k iterationsiAnd belongs to the probability of occurrence of situation 2,
Figure BDA0001680475040000092
representing the pass time interval t for the parameters after k iterationsiAnd belongs to the probability of occurrence of case 3. z is a radical ofiIndicating the situation to which the ith sample transit time interval belongs, zi＝move、zi＝jam、ziStop means belonging to case 1, case 2 and case 3,
Figure BDA00016804750400000912
it is shown that for the parameters after k iterations the ith sample transit time interval belongs to the case ziThe probability value of (2).
S325, obtaining all sample passing time intervals t through the step S324iThe probability of belonging to three traffic cases is evaluated and the traffic interval t of all samples assumed is determinediThe optimal values of the parameters in the travel time distribution probability model for the case where the probabilities pertaining to the three traffic cases have been determined are shown in equations (13) to (21).
Figure BDA0001680475040000093
Figure BDA0001680475040000094
Figure BDA0001680475040000095
Figure BDA0001680475040000096
Figure BDA0001680475040000097
Figure BDA0001680475040000098
Figure BDA0001680475040000099
Figure BDA00016804750400000910
Figure BDA00016804750400000911
Where many of the parameters in equations (13) - (21) are consistent with and mean the same as in the previous equations, and N represents the total number of samples of the transit time interval data.
And S326, iterating the step S324 and the step S325 until the parameters of the travel time distribution probability model obtained after multiple iterations are converged (basically do not change any more), and storing the obtained parameters into a database.
S327, executing the steps S322 to S326 on the point-to-point data of all the adjacent RFID acquisition points to obtain parameters of a vehicle travel time distribution probability model among all the adjacent RFID acquisition points.
Step S4: according to the traffic time interval t of the vehicle between two adjacent RFID acquisition points and the travel time distribution probability model between the two adjacent RFID acquisition points, the Bayesian theory is used for judging whether the vehicle stops between the two adjacent RFID acquisition points, as shown in FIG. 3.
S41, selecting a vehicle, wherein the RFID electronic license plate number of the vehicle is denoted as e0Extracting the passing data of all the adjacent RFID acquisition points of the vehicle, including the RFID electronic license plate number, the identification numbers of two adjacent RFID acquisition points, the passing time interval passing through the two adjacent RFID acquisition points, is less than eid, RFID0,rfid1T >. The various attributes in the tuple are the same as the correlation settings in step 2.
Can be screened out from the data table _ passing storing the traffic data of the adjacent RFID acquisition points by sql statements. The table _ passing is set in accordance with the foregoing.
Sql:select eid,rfid0,rfid1,t from table from table_passing where eid＝e0
S42, selecting a vehicle e0Let the passing adjacent RFID acquisition points be RFID _ a and RFID _ b, and the transit time interval between the two RFID acquisition points is t. And inquiring to obtain a travel time distribution probability model between the RFID acquisition points RFID _ a and RFID _ b. Calculating the time interval of the vehicle passing between the adjacent RFID acquisition points RFID _ a and RFID _ b as t, the probability of case 1 is P (state) and the probability of case 2 is P (state) and the probability of case 3 is P (state) and calculating methods (22) - (24) show that the meanings of the relevant parameters in the formula are consistent with those in step 3. If P (state ═ stop | t)>P (state) and P (stop | t)>And P (state) judging that the vehicle stays between the two adjacent RFID acquisition points, otherwise, judging that the vehicle does not stay between the two adjacent RFID acquisition points. And the judgment result is stored.
Figure BDA0001680475040000101
Figure BDA0001680475040000111
Figure BDA0001680475040000112
S43, for vehicle e0All traffic data passing through the adjacent RFID collection point is processed to step S42;
s44, the steps S42 and S43 are performed for all the vehicles.
Step S5: according to the obtained condition whether the vehicle stays between the adjacent RFID acquisition points or not, the starting point and the ending point of each trip of all vehicles are extracted, as shown in FIG. 4. The method comprises the following specific steps:
s51, selecting the RFID electronic license plate number of one vehicle, screening all the passing data of the vehicle passing through the adjacent RFID acquisition points, and sequencing the data in an ascending order according to the time of passing through the first acquisition point in the adjacent acquisition points.
S52, reading a piece of traffic data of the vehicle passing through the adjacent RFID acquisition points, starting to divide the trip of the vehicle if the piece of data is the first piece of traffic data of the vehicle, and taking the first acquisition point of the two adjacent acquisition points as the starting point of the trip.
S53, according to the result of the step S4, if the vehicle does not stay between the two adjacent RFID acquisition points, the traffic data is considered to belong to the current trip; if the vehicle stays between the two adjacent RFID acquisition points, the first acquisition point of the two adjacent acquisition points is saved as the terminal point of the current trip, the division of the current trip is completed, the division of the next trip is started simultaneously, and the second acquisition point of the two adjacent acquisition points is saved as the starting point of the next trip.
And S54, if the traffic data is the last traffic data of the vehicle, saving the second acquisition point of the two adjacent acquisition points as the end point of the current trip.
S55, executing steps S52 to S54 on all traffic data of the vehicle passing through the adjacent RFID acquisition points to obtain the starting point data and the end point data of each trip of the vehicle.
S56, executing steps S51 to S55 on all vehicles, and obtaining the starting point data and the end point data of each trip of all vehicles.
Fig. 5 shows an example of extracting a travel OD for a single vehicle.
Finally, the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions, and all of them should be covered in the protection scope of the present invention.

Claims (5)

1. A vehicle travel track division method for RFID electronic license plate data is characterized by comprising the following steps:
step S1, extracting the traffic data record ═ eid, t of all vehicles passing through the adjacent RFID acquisition points0,rfid0,t1,rfid1T > where eid denotes the electronic license plate number of the vehicle, t0And rfid0Respectively representing the time when the vehicle passes through the first RFID acquisition point of two adjacent RFID acquisition points and the identification number, t, of the RFID acquisition point1And rfid1Respectively representing the time of the second RFID acquisition point of the two adjacent RFID acquisition points passed by the vehicle and the identification number of the RFID acquisition point, and t represents the time interval of the vehicle passing the two adjacent RFID acquisition points;
step S2, traversing the traffic data of the adjacent RFID acquisition points, and selecting the traffic data of all the adjacent RFID acquisition points, wherein the traffic data of all the adjacent RFID acquisition points is < eid, t0,rfid0,t1,rfid1T > Point-to-point data < RFID of different RFID acquisition points0,rfid1＞；
S3, establishing a travel time distribution probability model between adjacent RFID acquisition points, and solving parameters of the vehicle travel time distribution probability model between the adjacent RFID acquisition points according to vehicle passing time interval data between the adjacent RFID acquisition points;
step S4, judging whether the vehicle stops between two adjacent RFID acquisition points according to the time interval t when the vehicle passes through the two adjacent RFID acquisition points and the travel time distribution probability model between the two adjacent RFID acquisition points;
step S5, extracting the starting point and the end point of each trip of the vehicle according to the stop condition of the vehicle between each adjacent RFID acquisition point, and dividing the track of the vehicle into a plurality of trip sections;
the step S1 specifically includes the following sub-steps:
s11, extracting all different eid numbers in the RFID electronic license plate data;
s12, selecting an eid number from the data obtained in the step S11, screening out all RFID electronic license plate data containing the eid number in the RFID electronic license plate data set, and sequencing according to the time ascending sequence of passing vehicles to obtain the track of the vehicles
Figure FDA0002980641400000011
R＝＜v,r,t＞，
Figure FDA0002980641400000012
Wherein TraAThe track of the vehicle A is shown, R represents a piece of RFID electronic license plate data, v represents the electronic license plate number of the vehicle, R represents the identification number of an RFID acquisition point, t represents the time when the vehicle is recognized,
Figure FDA0002980641400000013
representing the time when the vehicle A passes the ith RFID acquisition point;
combining the data of the adjacent RFID electronic license plates in the track to obtain the passing data of the vehicle passing through the adjacent RFID acquisition points, wherein the passing data of the vehicle passing through the adjacent RFID acquisition points is represented as:
Figure FDA0002980641400000014
wherein, recodri AData representing the passage of the ith vehicle between adjacent RFID acquisition points, Ri AV denotes the electronic license plate number of the vehicle a,
Figure FDA0002980641400000015
the identification number represents that the vehicle A passes through the ith RFID acquisition point;
s13, executing a step S12 on all the eid numbers, and storing the passing data of all vehicles passing through adjacent RFID acquisition points into a database;
the step S3 includes the following sub-steps:
s31, establishing a travel time distribution probability model between adjacent RFID acquisition points, wherein the travel time distribution probability model between the two adjacent RFID acquisition points is as follows:
Figure FDA0002980641400000021
wherein: p (t) represents the probability that the time interval between the vehicle passing two adjacent RFID acquisition points is t, mumove、σmove、wmoveRespectively representing the expectation, standard deviation and weight coefficient after logarithm of passing time interval data of all vehicles when the vehicles rapidly pass through two adjacent RFID acquisition pointsjam、σjam、wjamRespectively representing the expectation, standard deviation and weight coefficient mu of the passing time interval data of all vehicles when the vehicles encounter traffic jam in the process of passing through two adjacent RFID acquisition pointsstop、σstop、wstopRespectively representing the expectation, standard deviation and weight coefficient of the passing time interval data of all vehicles when the vehicles stay in the process of passing through two adjacent RFID acquisition points;
s32, according to the passing time interval data of the vehicles between the adjacent RFID acquisition points, calculating the parameters of the vehicle travel time distribution probability model between the adjacent RFID acquisition points.
2. The vehicle travel track division method for the RFID electronic license plate data of claim 1, wherein the step S32 comprises the following sub-steps:
s321, reading data of point pairs < RFID _ a and RFID _ b > of adjacent RFID acquisition points of the travel time distribution probability model parameters;
s322, extracting vehicle passing time interval data Train ═ t passing through adjacent RFID acquisition points rfi _ da and RFID _ b1,t2,…,tNDenoted traffic interval data sample data set, tiIs the ith sample data of the passing time interval, N represents the total amount of samples of the passing time interval data, i belongs to [1, N ∈]；
S323, assigning initial values to parameters of a vehicle travel time distribution probability model between adjacent RFID acquisition points RFID _ a and RFID _ b;
s324, calculating the passing time interval t of each sample according to the initial parameters of the travel time distribution probability model or the parameters after the last iterationiSize of probability of
Figure FDA0002980641400000022
S325, passing time interval t in all samplesiCalculating the optimal value of each parameter in the travel time distribution probability model under the condition that the probability of the travel time distribution probability model is determined;
s326, performing iteration execution on the step S324 and the step S325 until the parameters of the travel time distribution probability model obtained after multiple iterations converge;
s327, executing the steps S322 to S326 on the point-to-point data of all the adjacent RFID acquisition points to obtain parameters of a vehicle travel time distribution probability model among all the adjacent RFID acquisition points.
3. The method for dividing the vehicle travel track according to the RFID electronic license plate data of claim 2, wherein the step S4 specifically includes the following sub-steps:
s41, extracting traffic data of all adjacent RFID acquisition points of a vehicle, wherein the traffic data is less than eid and RFID0,rfid1,t＞，
S42, selecting traffic data of one vehicle passing through adjacent RFID acquisition points, and assuming that the passing adjacent RFID acquisition points are RFID _ a and RFID _ b; calculating the time interval of the vehicle passing between adjacent RFID acquisition points RFID _ a and RFID _ b as t,
when the vehicle rapidly passes through two adjacent RFID acquisition points, the probability is P (state ═ move | t);
when a vehicle encounters traffic jam in the process of passing through two adjacent RFID acquisition points, the probability is P (state) and j am t;
when the vehicle stops in the process of passing through two adjacent RFID acquisition points, the probability is P (stop | t);
if the state is greater than P (stop | t) > P (state is greater than move | t) and the state is greater than P (stop | t) > P (state is greater than jam | t), judging that the vehicle stays between the two adjacent RFID acquisition points, otherwise, judging that the vehicle does not stay between the two adjacent RFID acquisition points;
s43, executing step S42 on all traffic data of the vehicle passing through the adjacent RFID acquisition points;
s44, performing steps S42 and S43 for all vehicles.
4. The method for dividing the vehicle travel track according to the RFID electronic license plate data of claim 3, wherein the step S5 specifically includes the following sub-steps:
s51, selecting the RFID electronic license plate number of one vehicle, screening all the passing data of the vehicle passing through the adjacent RFID acquisition points, and sequencing the data in an ascending order according to the time of passing through the first acquisition point in the adjacent acquisition points;
s52, reading a piece of passing data of the vehicle passing through the adjacent RFID acquisition points, starting to divide the trip of the vehicle if the data is the first passing data of the vehicle, and taking the first acquisition point of the two adjacent acquisition points as the starting point of the trip;
s53, if the traffic data is the last traffic data of the vehicle, saving the second acquisition point of the two adjacent acquisition points as the end point of the current trip;
s54, executing steps S52 to S53 on all traffic data of the vehicle passing through adjacent RFID acquisition points to obtain starting point data and end point data of each trip of the vehicle;
s55, executing steps S51 to S54 on all vehicles, and obtaining the starting point data and the end point data of each trip of all vehicles.
5. The vehicle travel track division method for the RFID electronic license plate data according to claim 4, wherein the step S52 is followed by further comprising:
if the vehicle does not stay between the two adjacent RFID acquisition points, the traffic data is considered to belong to the current trip; if the vehicle stays between the two adjacent RFID acquisition points, the first acquisition point of the two adjacent acquisition points is saved as the terminal point of the current trip, the division of the current trip is completed, the division of the next trip is started simultaneously, and the second acquisition point of the two adjacent acquisition points is saved as the starting point of the next trip.
CN201810548328.5A 2018-05-31 2018-05-31 Vehicle travel track division method for RFID electronic license plate data Active CN108806248B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810548328.5A CN108806248B (en) 2018-05-31 2018-05-31 Vehicle travel track division method for RFID electronic license plate data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810548328.5A CN108806248B (en) 2018-05-31 2018-05-31 Vehicle travel track division method for RFID electronic license plate data

Publications (2)

Publication Number Publication Date
CN108806248A CN108806248A (en) 2018-11-13
CN108806248B true CN108806248B (en) 2021-07-20

Family

ID=64089692

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810548328.5A Active CN108806248B (en) 2018-05-31 2018-05-31 Vehicle travel track division method for RFID electronic license plate data

Country Status (1)

Country Link
CN (1) CN108806248B (en)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110379159A (en) * 2019-06-24 2019-10-25 重庆大学 Trip chain extracting method based on motor vehicle electronic mark data
CN110491157B (en) * 2019-07-23 2022-01-25 中山大学 Vehicle association method based on parking lot data and checkpoint data
CN110851490B (en) * 2019-10-16 2022-04-26 青岛海信网络科技股份有限公司 Vehicle travel common stay point mining method and device based on vehicle passing data
CN111951551B (en) * 2020-08-10 2022-08-23 北京计算机技术及应用研究所 Method for detecting traffic jam degree by radio frequency identification
CN114548335B (en) * 2022-02-24 2022-12-06 四川省机场集团有限公司 Unpowered equipment mileage frequency calculation method and system based on driving domain feature points
CN115862337B (en) * 2023-03-01 2023-05-23 杭州三一谦成科技有限公司 Cloud-based vehicle travel detection method
CN116663592B (en) * 2023-06-12 2024-02-02 广东车卫士信息科技有限公司 Vehicle driving route intelligent recognition system based on electronic license plate

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080284571A1 (en) * 2005-10-26 2008-11-20 Wilbrink Tijs I System for utilizing rfid tags to manage automotive parts
CN102610088A (en) * 2012-03-08 2012-07-25 东南大学 Method for forecasting travel time between bus stops
CN106327866A (en) * 2016-08-30 2017-01-11 重庆市交通规划研究院 Vehicle travel OD dividing method and system based on RFID
CN106971545A (en) * 2017-05-16 2017-07-21 青岛大学 A kind of bus arrival time Forecasting Methodology

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080284571A1 (en) * 2005-10-26 2008-11-20 Wilbrink Tijs I System for utilizing rfid tags to manage automotive parts
CN102610088A (en) * 2012-03-08 2012-07-25 东南大学 Method for forecasting travel time between bus stops
CN106327866A (en) * 2016-08-30 2017-01-11 重庆市交通规划研究院 Vehicle travel OD dividing method and system based on RFID
CN106971545A (en) * 2017-05-16 2017-07-21 青岛大学 A kind of bus arrival time Forecasting Methodology

Also Published As

Publication number Publication date
CN108806248A (en) 2018-11-13

Similar Documents

Publication Publication Date Title
CN108806248B (en) Vehicle travel track division method for RFID electronic license plate data
CN110097755B (en) Highway traffic flow state identification method based on deep neural network
CN108550261B (en) Urban traffic OD (origin-destination) calculation method based on RFID (radio frequency identification) electronic license plate
CN108761509B (en) Automobile driving track and mileage prediction method based on historical data
CN111243277A (en) Commuting vehicle space-time trajectory reconstruction method and system based on license plate recognition data
CN108122069B (en) Mass traffic data-based resident travel starting point and end point matrix extraction method
CN107563566B (en) Inter-bus-station operation time interval prediction method based on support vector machine
CN109359690B (en) Vehicle travel track identification method based on checkpoint data
CN110836675B (en) Decision tree-based automatic driving search decision method
CN109598566B (en) Ordering prediction method, ordering prediction device, computer equipment and computer readable storage medium
CN110120218A (en) Expressway oversize vehicle recognition methods based on GMM-HMM
CN109254861B (en) OD demand extraction and reliability analysis method based on track data
CN105809193B (en) A kind of recognition methods of the illegal vehicle in use based on kmeans algorithm
CN110738247A (en) fine-grained image classification method based on selective sparse sampling
CN107845260B (en) Method for identifying public transport trip mode of user
CN109767615B (en) Method for analyzing key flow direction and key path of road network traffic flow
CN106682703A (en) Method for recognizing travel mode of driver based on OBD data
CN116628455A (en) Urban traffic carbon emission monitoring and decision support method and system
CN109489679A (en) A kind of arrival time calculation method in guidance path
CN106297296A (en) A kind of fine granularity distribution method hourage based on sparse tracing point data
CN111724593A (en) Bus travel time prediction method considering traffic flow transfer rate based on RFID
CN115205086A (en) Abnormal track detection method and system driven by big data of moving track and electronic equipment
CN111523562A (en) Commuting mode vehicle identification method based on license plate identification data
CN109849926B (en) Method and system for distinguishing whether taxi is handed to others for driving
CN108053646B (en) Traffic characteristic obtaining method, traffic characteristic prediction method and traffic characteristic prediction system based on time sensitive characteristics

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