CN111292533B - Method for estimating flow of arbitrary section of highway at any time period based on multi-source data - Google Patents

Method for estimating flow of arbitrary section of highway at any time period based on multi-source data Download PDF

Info

Publication number
CN111292533B
CN111292533B CN202010086610.3A CN202010086610A CN111292533B CN 111292533 B CN111292533 B CN 111292533B CN 202010086610 A CN202010086610 A CN 202010086610A CN 111292533 B CN111292533 B CN 111292533B
Authority
CN
China
Prior art keywords
vehicle
time
section
information
road
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
CN202010086610.3A
Other languages
Chinese (zh)
Other versions
CN111292533A (en
Inventor
李新刚
尚影
杨珍珍
贾斌
赵建东
高自友
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.)
Beijing Jiaotong University
Original Assignee
Beijing Jiaotong 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 Beijing Jiaotong University filed Critical Beijing Jiaotong University
Priority to CN202010086610.3A priority Critical patent/CN111292533B/en
Publication of CN111292533A publication Critical patent/CN111292533A/en
Application granted granted Critical
Publication of CN111292533B publication Critical patent/CN111292533B/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
    • G08G1/0125—Traffic data processing
    • 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
    • G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
    • 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
    • G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count

Abstract

The embodiment of the invention provides a multisource data-based method for estimating the flow of any section of a highway at any time period, which comprises the following steps: s1, acquiring multi-source data of the target road; s2, matching the multi-source data; s3, classifying the vehicle path information and calculating the vehicle running time based on the data matching result; s4, processing abnormal data in the vehicle running time and calculating the average running speed of the vehicle; s5, calculating the average running speed and the average running time of the road section based on the average running speed of the vehicle, and acquiring a space-time matrix of the average running time of each road section of different vehicle types; s6, selecting a corresponding space-time matrix according to the type of the vehicle, dynamically distributing the vehicle running time, and calculating the corresponding running time of the vehicle on the road section; and S7, estimating the flow of any section in any period according to the dynamic distribution result of the vehicle running time. The method and the device effectively fuse and match the multi-source data to obtain complete traffic information and improve estimation precision.

Description

Method for estimating flow of arbitrary section of highway at any time period based on multi-source data
Technical Field
The invention relates to the technical field of traffic flow prediction, in particular to a multisource data-based method for estimating the flow of any section of a highway at any time period.
Background
There are many methods for calculating the cross-section flow on the highway, including manual counting, cross-section detector counting, and determining the vehicle running track according to the floating vehicle data to obtain the cross-section flow, but the above methods have disadvantages. Manual counting is time-consuming and labor-consuming; the counting of the section detector has the problems of equipment maintenance and the like, and only the flow of the section where the detector is located can be obtained by the data of the detector, but the flow of any section cannot be obtained; the driving track of the vehicle can be clearly known according to the floating vehicle data, but generally, not all vehicles use the GPS device, which easily causes inaccuracy of estimation results. Therefore, at present, how to accurately estimate the flow of any section on the highway in the whole highway network still remains a problem to be solved. With the emergence of big data technology, an estimation method for carrying out section flow based on data driving is proposed successively, but the problems of single data form, low estimation precision and the like still exist. For multi-source data, each data contains abundant information and a certain relevance exists among various data. Therefore, it is necessary to perform effective fusion matching on these data to obtain more complete traffic information and improve estimation accuracy. At present, there are some methods for estimating highway traffic by using multi-source data, for example, patent No. 201710716406.3 discloses a real-time highway traffic estimation method for mining spatial-temporal correlation, which is to estimate and obtain preliminary highway traffic, also called signaling traffic, according to a mobile phone signaling sequence, then use the traffic data obtained by a traffic detector as input, obtain space constraints between the traffic of road sections according to the signaling traffic estimated in the first step, and simultaneously give time constraints between the traffic of road sections based on a Toeplitz matrix, and perform whole-road-section traffic sensing based on a spatial-temporal compression sensing technology to obtain real-time traffic of each road section of a highway. The invention patent with patent number 201610893481.2 is based on traffic characteristic values extracted from mobile phone signal data and microwave traffic detection system data, establishes a highway road network state-space model by combining a macroscopic traffic flow model, and designs a progressive extended Kalman filter estimator and a corresponding solving algorithm to estimate the traffic state of a highway. However, the above methods cannot effectively estimate the flow of any section at any time on the highway, which has a certain limitation for acquiring complete traffic state information on the highway.
Disclosure of Invention
The embodiment of the invention provides a multisource data-based method for estimating the flow of any section of a highway at any time period, which is used for overcoming the defects of the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme.
A method for estimating flow of any section of an expressway at any time period based on multi-source data comprises the following steps:
s1, acquiring multi-source data of the target road;
s2, matching the multi-source data;
s3, classifying the vehicle path information and calculating the vehicle running time based on the data matching result;
s4, processing abnormal data in the vehicle running time and calculating the average running speed of the vehicle;
s5, calculating the average running speed and the average running time of the road section based on the average running speed of the vehicle, and acquiring a space-time matrix of the average running time of each road section of different vehicle types;
s6, selecting a corresponding space-time matrix according to the type of the vehicle, dynamically distributing the vehicle running time, and calculating the corresponding running time of the vehicle on the road section;
and S7, estimating the flow of any section at any time period according to the dynamic distribution result of the vehicle running time.
Preferably, the multi-source data comprises: entrance toll station data, exit toll station data and card port data;
the entrance toll station data includes: vehicle origin information;
the exit toll station data includes: vehicle start and end point information;
the bayonet data includes: discrete state information of the vehicle during driving.
Preferably, the S2 includes:
s21, integrating the bayonet data, extracting all bayonet information that each vehicle passes through, arranging according to the time sequence, determining a threshold value T according to the distribution rule of the cameras on the road, so that the difference value of adjacent time in the bayonet information corresponding to each vehicle does not exceed the value T, otherwise, dividing the information, and considering that the vehicle passes through the road section again in another time period;
s22, determining a driving direction, extracting corresponding gate data, and respectively matching the gate data with entrance and exit charging data by taking the license plate number as a primary key value and the entrance time and the exit time as a secondary key value to obtain four types of data including entrance information and gate information, entrance and exit information, gate information and gate information, and the like, wherein each piece of information in each type of data corresponds to the complete or partial driving information of a vehicle on a target road.
Preferably, the S3 includes:
s31, after the matching is completed, classifying the route information included in all the vehicles, including:
for a vehicle entering from one junction and leaving from the target road from the other junction, the vehicle only comprises the bayonet information between the two junctions and corresponds to part of the path information on the target road;
for a vehicle entering from a toll station but leaving a target road from a junction, entrance information of the toll station and gate information between the toll station and the junction are contained, and the entrance information corresponds to partial path information on the target road;
for a vehicle entering a target road from a junction but leaving a toll station, exit information of the toll station and entrance information between the toll station and the junction are contained, and correspond to partial path information on the target road;
for vehicles entering from a toll station and leaving from a toll station on a target road, acquiring complete path information of the vehicles on the target road, including information of an entrance and an exit and information of a gate between two toll stations;
s32, based on the classification of the route information, two end points in the vehicle route information are obtained, and the travel time of each vehicle on the corresponding route on the target road is obtained, that is:
tOD＝tD-tO (1)
in the formula, tDThe destination time in the path information; t is tOIs the starting point moment in the path information;
the path information comprises a plurality of positions and corresponding time information, a sub-path of the vehicle on the target road is arranged between every two position points, based on the position information, the travel time and the average traveling speed of each vehicle passing through all the sub-paths are calculated, and if the path of each vehicle comprises R sub-paths, the method comprises the following steps:
Figure GDA0003122424620000041
in the formula, th,rIs the travel time of the vehicle h on the sub-path r; dh,rDistance of sub-path r for vehicle h;
Figure GDA0003122424620000042
the average speed of the vehicle h on the sub-path r.
Preferably, the S4 includes:
s41, removing the abnormal points
At a certain time, the maximum value of the travel time of all vehicles passing a given OD pair is tmaxMinimum value of tminAccording to the length of the link between OD pairsodGiven a threshold M, the following operations are performed:
s411, if the data volume Num in a certain time interval is more than 1, calculating tmax-tmin(ii) a Otherwise, judging whether T in one piece of data is reasonable or not, namely whether T is greater than T or notmaxOr t<TminIf so, put T into the data set to be corrected, where Tmax＝lod×1.5/vmin，Tmin＝lod/(vmax×1.5)；
S412, if tmax-tminIf the value is more than M, an extremely abnormal point exists; then calculating the skewness skew of the group of data, if skew>0, there is a great anomaly, and tmAxPutting a data set to be corrected; if skew<0, there is a very small anomaly point, and tminPutting a data set to be corrected;
s413, repeating the steps S411 and S412 until tmax-TminUntil the mass is less than or equal to M;
s42, 3 sigma criterion screening
S421, calculating the average value mu and the standard deviation sigma of all vehicle travel time after screening according to the screened data set of the antipodal abnormal value, determining the upper and lower boundaries of secondary screening, and setting the upper and lower boundaries as [ mu-2 sigma, mu +2 sigma ];
s422, for the travel time T of each vehicle, if T is more than or equal to mu-2 sigma and less than or equal to mu +2 sigma, keeping; otherwise, correcting the t value by using the travel time of other vehicles in the time period;
s423, repeating the steps S421 and S422 until all t values are within the [ mu-2 sigma, mu +2 sigma ];
s43 correction of a dataset to be corrected
All the data sets to be corrected are extremely abnormal values, the extremely abnormal values are corrected according to the result reserved in the step S42, normal data in the same time period with the extremely abnormal values are found, and the average value of the normal data replaces the t value in the abnormal data; if normal data in the same time interval cannot be found due to less data in certain time intervals, replacing the abnormal t value with the average value according to the principle that the interval with the current time interval is smaller and the normal data is preferentially selected until the normal data exists in a certain time interval;
and S44, after the abnormal travel time processing is finished, dividing the travel time by the corresponding travel distance again to obtain the processed average travel speed.
Preferably, the S5 includes:
for any road section on the target road, selecting a bayonet adjacent to the starting end of the road section and a bayonet adjacent to the terminal end of the road section, if the road section is a boundary road section, and the starting end or the terminal end of the boundary road section is a toll station, selecting the bayonet and the toll station, and finding all vehicles of the same type continuously passing through the two bayonets or the bayonet and the toll station, wherein in a certain period, the driving speed of the road section contained between the two bayonets or between the bayonet and the toll station is the average speed of all vehicles continuously passing through the two bayonets or the bayonet and the toll station in the certain period;
if the data of the two selected bayonets has obvious errors or missing information at the upstream bayonet, neglecting the bayonet with the wrong or missing information, and directly taking the average speed of all vehicles of the same type between the previous bayonet of the upstream bayonet and the selected downstream bayonet as the running speed on the road section for a certain period of time; if the information at the downstream bayonet is obviously wrong or missing, taking the average speed of all vehicles of the same type between the selected upstream bayonet and the subsequent bayonet of the downstream bayonet as the running speed on the road section;
the specific calculation formula is as follows:
Figure GDA0003122424620000061
Figure GDA0003122424620000062
in the formula (I), the compound is shown in the specification,
Figure GDA0003122424620000063
and
Figure GDA0003122424620000064
respectively the average running speed and the average running time of a certain road section a on the expressway in a time period k for vehicles with the vehicle type q; n (q) is the number of vehicles of which the vehicle type passing through the section A in the time period k is q; l isAIs the length of road segment a; r should be selected to give priority to the shortest sub-path;
for different vehicle types q, a space-time matrix of average travel time of each road section can be obtained, wherein K time periods and A road sections are finally represented as follows:
Figure GDA0003122424620000065
preferably, the S6 includes:
for vehicles with complete path information, after obtaining the space-time matrix, dynamically distributing the path driving time of each vehicle by using a formula (6), selecting corresponding t _ matrix (q) according to the vehicle type q,
Figure GDA0003122424620000066
in the formula, th(a) The driving time of the vehicle h on the road section a; s is the number of road segments passed by the whole travel of the vehicle h; over time, the vehicle travels different road sections in different time periods during the course of travel
Figure GDA0003122424620000067
In the method, the time interval and the road section corresponding to the time interval and the road section are selected from the space-time matrix
Figure GDA0003122424620000068
Value of then
Figure GDA0003122424620000069
Is shown in the time period
Figure GDA00031224246200000610
Travel time of the inner vehicle in a certain section a, wherein
Figure GDA00031224246200000611
A period k representing a change;
for a vehicle with only partial route information, performing dynamic time allocation on the travel time of the partial route according to a formula (6); and deducing which junction the vehicle leaves or enters the target road from the road sections with the missing information according to the position information of the gate, taking the average speed of the adjacent road sections as the driving speed of the vehicle on the road sections with the missing information, and calculating the corresponding driving time of the vehicle on the road sections.
Preferably, the S7 includes:
assuming that the vehicle runs at a constant speed on each divided road section, calculating the time of the vehicle reaching any cross section, assuming that a cross section is at a certain position x of the a-th road section, calculating the time of the vehicle h reaching the cross section x according to different vehicle conditions,
the time of arrival of the vehicle at a position upstream of the section x is known
Figure GDA0003122424620000071
In the formula, tenThe time when the vehicle reaches a certain position upstream of the section x; a1 shows that a position upstream of the section x is at the a1 th road segment; t is th(i) The driving time of the vehicle h on the road section i; Δ l1 is the distance from the starting point of the road section a to the section x; laIs the length of road segment a; t is th(a) The driving time of the vehicle h on the road section a; t is the time for the vehicle to reach the section x;
the time of arrival of the vehicle at a position downstream of section x is known
Figure GDA0003122424620000072
In the formula, texThe time when the vehicle reaches a certain position downstream of the section x; a2 shows that a position upstream of the section x is at the a2 th road segment; Δ l2 is the distance from section x to the end point of road section a;
the time of arrival of the vehicle at a position upstream and downstream of the section x is known
Figure GDA0003122424620000073
Figure GDA0003122424620000074
If the values of t1 and t2 are approximately equal, taking one of the values as t; otherwise, comparing the distance between the upstream and downstream positions of the fracture surface and the fracture surface, if the position upstream of the selected fracture surface is closer to the target fracture surface than the position downstream of the fracture surface, giving a weight of t1 greater than t2, otherwise, giving a weight of t2 greater than t 1:
Figure GDA0003122424620000075
in the formula, l1 and l2 are the distances between the positions at the upstream and downstream of the cross section and the cross section respectively;
for any section, judging the time of all vehicles passing through the section reaching the section, so as to obtain the section hour flow as follows for any selected time period:
q＝{N|t∈ΔT} (10)
in the formula, q is the hourly flow of an arbitrary section x; t is the time for the vehicle to reach the section x; delta T is a selected hour period; n is the number of vehicles reaching the cross-section x within Δ T.
According to the technical scheme provided by the embodiment of the invention, the embodiment of the invention provides the method for estimating the flow of the highway at any section in any time period based on the multi-source data, the driving track of each vehicle is obtained according to the gate data and the data of the entrance and exit toll station, the flow of any section of the highway is accurately estimated, the running characteristics on the road are obtained, the travel evolution law on the highway is explored, and the data support is provided for the accurate prediction of the flow of the highway, so that more complete road information is timely and effectively obtained.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for estimating flow of an arbitrary section of a highway at any time period based on multi-source data according to an embodiment of the invention;
fig. 2 is a schematic diagram illustrating distribution of an expressway toll station, a hub and a gate according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating an abnormal journey time processing procedure according to an embodiment of the present invention;
fig. 4 is a schematic diagram of road segment division provided by the embodiment of the present invention;
fig. 5 is a schematic diagram of a vehicle driving process provided by the embodiment of the invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or coupled. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
For the convenience of understanding the embodiments of the present invention, the following description will be further explained by taking several specific embodiments as examples in conjunction with the drawings, and the embodiments are not to be construed as limiting the embodiments of the present invention.
The embodiment of the invention provides a multisource data-based method for estimating the flow of any section of a highway at any time period, which comprises the following steps:
and S1, acquiring multi-source data of the target road.
The multi-source data comprises three parts which are respectively entrance toll station data, exit toll station data and card port data on a target road, wherein the entrance toll station data and the exit toll station data contain starting and ending point information of vehicles, the card port data comprise discrete state information of the vehicles in the driving process, and the specific data structures of the data are shown in the following tables 1-1, tables 1-2 and tables 1-3: (the original data contains too many fields, only the relevant fields after the filtering are listed here)
TABLE 1-1 import charges data Structure example
Figure GDA0003122424620000101
Table 1-2 Exit charging data Structure example
Figure GDA0003122424620000102
Table 1-3 bayonet data structure examples
Figure GDA0003122424620000103
Figure GDA0003122424620000111
And S2, matching the multi-source data.
Because the three parts of data are mutually independent, the driving track of the vehicle cannot be completely reflected by looking at any part of data alone. Wherein the data of the entrance toll station only comprises the entrance information of the vehicle, namely entrance position, entrance time and the like; the exit toll station data contains complete entrance and exit information of the vehicle, and as only the number information of the toll station on the target road is known, the specific entrance position of the vehicle entering from the toll station on other roads cannot be clarified only according to the number of the entrance toll station.
As shown in fig. 2, toll stations, hubs, gates, service areas, etc. on the highway are generally distributed as above, and in connection with the diagram, it can be known that: according to the entrance toll station information, the vehicles only running on the target road can be accurately judged. The gate data includes vehicle information captured by cameras distributed on roads, mainly capturing time, gate positions, driving directions and the like, and if one vehicle continuously passes through a plurality of gates, a plurality of gate data are available, and vehicles in a road network which pass through a junction and arrive at a target road from other roads or leave the target road to other roads can be directly judged according to the gate data.
Therefore, three parts of data need to be fused, each vehicle is taken as an object, and the driving track of each vehicle is finally extracted, and the implementation method is as follows:
and S21, integrating the card port data, extracting all card port information passed by each vehicle, and arranging according to the time sequence. And determining a threshold value T according to the distribution rule of the cameras on the road, so that the difference value of the adjacent time in the checkpoint information corresponding to each vehicle does not exceed the value T, otherwise, dividing the information, and considering that the vehicle passes through the road section again in another time period.
S22, determining a driving direction, extracting corresponding gate data, respectively matching the gate data with entrance and exit charging data by taking a license plate number as a primary key value and taking entrance time and exit time as a secondary key value, and finally obtaining four types of data including entrance information and gate information, entrance and exit information, gate information and gate information, and gate information, wherein each piece of information in each type of data corresponds to complete or partial driving information of a vehicle on a target road.
And S3, classifying the vehicle path information and calculating the vehicle running time based on the data matching result.
S31, after matching, the route information contained in all the vehicles can be classified into the following categories:
(1) for a vehicle entering from one junction and leaving from the target road from the other junction, only the bayonet information between the two junctions is contained, and the bayonet information corresponds to part of the path information on the target road;
(2) for a vehicle entering from a toll station but leaving a target road from a junction, entrance information of the toll station and gate information between the toll station and the junction are contained, and the entrance information corresponds to partial path information on the target road;
(3) for a vehicle entering the target road from the junction but leaving the toll station, the vehicle contains exit information of the toll station and entrance information between the toll station and the junction, and also corresponds to partial path information on the target road;
(4) for vehicles entering from the toll station and leaving from the toll station on the target road, complete path information of the vehicles on the target road can be obtained, wherein the path information comprises the information of an entrance and an exit and the information of a gate between the two toll stations.
S32, based on the classification of the route information, first simply take two end points in the vehicle route information to obtain the travel time of each vehicle on the corresponding route on the target road, that is:
tOD＝tD-tO (1)
in the formula, tDThe destination time in the path information; t is toIs the starting point moment in the path information;
meanwhile, because the path information comprises a plurality of positions and corresponding time information, and a sub-path of the vehicle on the target road is arranged between every two position points (including a bayonet and a bayonet or a bayonet and a toll station), on the basis of the path information, the travel time and the average traveling speed between all the sub-paths passed by each vehicle can be calculated, and if the path of each vehicle comprises R sub-paths, the following steps are provided:
Figure GDA0003122424620000121
in the formula, th,rIs the travel time of the vehicle h on the sub-path r; dh,rThe distance of the sub-path r of the vehicle h (which can be directly obtained from the mileage stake marks);
Figure GDA0003122424620000122
the average speed of the vehicle h on the sub-path r.
And S4, processing abnormal data in the vehicle running time and calculating the average running speed of the vehicle.
Due to equipment failure or untimely data transmission, problems of data missing, data redundancy, data abnormity and the like may exist in the acquired data, and the data with abnormal travel time is mainly correspondingly processed below to prevent the influence on the estimation precision. According to the fact that the travel time of vehicles passing through the same road section in the same time period is subject to Gaussian distribution theoretically, data with too long or too short travel time can be effectively eliminated by using a 3 sigma criterion. However, it is well understood that the effectiveness of this method is greatly reduced when an extremely abnormal value exists, and when an extremely abnormal value exists, the standard deviation of the data as a whole is likely to be too large, so that the range of [ mu-3 sigma, mu +3 sigma ] is expanded, and the abnormal value is likely to be included. Therefore, a method for screening out the extreme abnormal points and then screening according to the 3 sigma criterion is provided, and the specific method comprises the following steps:
s41, removing the abnormal points
At a certain time, the maximum value of the travel time of all vehicles passing a given OD pair is tmaxMinimum value of tminAccording to the length of the link between OD pairsodGiven a threshold M, the following operations are performed, wherein the OD pairs are the starting point and the ending point between the driving paths or sub-paths of the vehicles on the target roads, which may be any two gates or a gate and a toll station.
S411, if the data volume Num in a certain time interval is more than 1, calculating tmax-tmin(ii) a Otherwise, judging whether t in one data is reasonable or not, namely whether t in one data is reasonable or notPresence of T > TmaxOr t<TminIf so, put T into the data set to be corrected, where Tmax＝lod×1.5/vmin，Tmin＝lod/(vmax×1.5)；
S412, if tmax-tminIf the value is more than M, an extremely abnormal point exists; then calculating the skewness skew of the group of data, if skew>0, there is a great anomaly, and tmaxPutting a data set to be corrected; if skew<0, there is a very small anomaly point, and tminPutting a data set to be corrected;
s413, repeating the steps S411 and S412 until tmax-tminUntil the mass is less than or equal to M.
S42, 3 sigma criterion screening
S421, calculating the average value mu and the standard deviation sigma of all vehicle travel time after screening for the data set with the extremely abnormal values, determining the upper and lower boundaries of the secondary screening, and setting the upper and lower boundaries as [ mu-2 sigma, mu +2 sigma ] in order to identify the abnormality as much as possible;
s422, for the travel time T of each vehicle, if T is more than or equal to mu-2 sigma and less than or equal to mu +2 sigma, keeping; otherwise, correcting the t value by using the travel time of other vehicles in the time period;
and S423, repeating the steps S421 and S422 until all the t values are within the [ mu-2 sigma, mu +2 sigma ] interval.
S43 correction of a dataset to be corrected
It can be known from the steps S41 and S42 that all the data sets to be corrected are extremely abnormal values, and for the part of data, correction is performed according to the result retained in step S42, that is, for each abnormal data, normal data in the same time period as the abnormal data is found, and the average value is used to replace the t value in the abnormal data; if normal data in the same time interval cannot be found due to the fact that the data amount in some time intervals is small, the average value is used for replacing the abnormal t value according to the principle that the interval with the current time interval is smaller and the normal data exists in a certain time interval. The total exception travel time processing flow is shown in FIG. 3.
By using the method to process the abnormal processing of the travel time, the problems of overlong travel time and the like caused by congestion can not be deleted by mistake, and the characteristics embodied by data can be retained to the maximum extent.
And S44, after the abnormal travel time processing is finished, dividing the travel time by the corresponding travel distance again to obtain the processed average travel speed.
And S5, calculating the average running speed and the average running time of the road section based on the average running speed of the vehicle, and acquiring a space-time matrix of the average running time of each road section of different vehicle types.
In this step, the evolution of the traffic flow in time and space is taken into account simultaneously. Spatially, as shown in fig. 4, on one highway, there are N1 toll booths, N2 gates and N3 hubs, the toll booths, the gates and the hubs are respectively represented by letters E, C and P, and finally, the target road is divided into a road segments according to the positions of the toll booths, the hubs, the gates and the like on the target road; in terms of time, any time length is selected as a granularity according to needs, and finally, the time of day is divided into K time intervals.
The method comprises the following steps of calculating the average driving speed and the average driving time of different sections at different time intervals on a target road, distinguishing a cart from a trolley according to license plate color information in checkpoint data, wherein the driving states of the cart and the trolley on an expressway are obviously different, and therefore, the calculation of the section driving time needs to be considered by vehicle type, and the specific method comprises the following steps:
a plurality of gates are arranged on any road section on the target road, a gate adjacent to the starting end of the road section and a gate adjacent to the end of the road section are selected (if the road section is a boundary road section, the starting end or the end of the road section is a toll station, the gate and the toll station are selected), then all vehicles of the same type continuously passing through the two gates (passing through the gate and the toll station) are found, and the driving speed of the road section contained between the two gates (the gate and the toll station) in a certain period can be considered as the average speed of all vehicles continuously passing through the two gates (the gate and the toll station) in the certain period.
If the data of the two selected bayonets has obvious errors or missing information at the upstream bayonet, neglecting the bayonet with the wrong or missing information, and directly taking the average speed of all vehicles of the same type between the previous bayonet of the upstream bayonet and the selected downstream bayonet as the running speed on the road section for a certain period of time; and if the information at the downstream card entrance is obviously wrong or missing, taking the average speed of all vehicles of the same type between the selected upstream card entrance and the card entrance behind the downstream card entrance as the running speed on the road section.
As shown in FIG. 4, for the road section 2, the adjacent bayonets are C0And C1If there are more vehicles passing the two gates in succession, the speed of travel for segment 2 may be used for all vehicles passing the segment during the selected time period at C0、C1The average speed between the bayonets.
If the data of the adjacent gates has obvious errors or missing information at one gate due to equipment failure and other reasons, for example, some vehicles continuously pass through C0、C1And C2Bayonet, but there is little C in the path information1The card-entrance information or its time recording is obviously wrong, at this time, the card-entrance C is ignored for the section 21For a certain period of time, directly taking C0And C2The average speed of all vehicles of the same type between the gates is taken as the travel speed on the section 2.
And the rest cases are analogized, and the specific calculation formula is as follows:
Figure GDA0003122424620000151
Figure GDA0003122424620000152
in the formula (I), the compound is shown in the specification,
Figure GDA0003122424620000161
and
Figure GDA0003122424620000162
respectively the average running speed and the average running time of a certain road section a on the expressway in a time period k for vehicles with the vehicle type q; n (q) is the number of vehicles of type q that will pass through the section a during a time period k (e.g., 8: 00-8: 15); laIs the length of road segment a; the selection of r should prioritize the shortest sub-path.
Through the step, for different vehicle types q, a space-time matrix of the average travel time of each road section can be obtained, wherein K time intervals and A road sections are finally expressed as follows:
Figure GDA0003122424620000163
and S6, selecting a corresponding space-time matrix according to the type of the vehicle, dynamically distributing the vehicle running time, and calculating the corresponding running time of the vehicle on the road section.
Note that in the data matching step, it is mentioned that complete or partial information of each vehicle on the target road is finally obtained in the matched data, "complete" means that two end points in the vehicle path information are exactly the positions where the vehicle arrives at and departs from the target road; the term "part" means that the vehicle path information may only contain a section of the vehicle traveling path, mainly because when the vehicle enters or leaves from the junction, the collected information is the gate information adjacent to the junction, and the information of the section from the junction to the gate is missing.
For vehicles with complete path information, the path travel time of each vehicle can be dynamically allocated according to the space-time matrix obtained in step S5 by using the following formula (6), and a corresponding t _ matrix (q) is selected according to the vehicle type q.
Figure GDA0003122424620000164
In the formula, th(a) The driving time of the vehicle h on the road section a; s is the section of the vehicle h over its entire journeyCounting; over time, the vehicle may be in different time periods when traveling different road segments during the course of travel
Figure GDA0003122424620000165
In the example shown in FIG. 5, a vehicle 8:20 enters the road segment 1 and travels forward, and when traveling to the road segment 4, it may be at 8:38, and step S5, it is mentioned that 15 minutes is a time granularity, so that 8:20 and 8:40 belong to different time intervals, and it is necessary to select the time interval and the road segment corresponding to the time interval and the road segment from the space-time matrix
Figure GDA0003122424620000171
Value of then
Figure GDA0003122424620000172
Is shown in the time period
Figure GDA0003122424620000173
Travel time of the inner vehicle in a certain section a, wherein
Figure GDA0003122424620000174
Indicating a period of variation k.
For a vehicle with only partial route information, dynamically allocating the running time of the partial route according to the formula (6); and for those links with missing information, according to the position information of the gate, the junction from which the vehicle leaves or enters the target road can be deduced, and then the average speed of the adjacent links is taken as the driving speed of the vehicle on the links with missing information, so as to calculate the corresponding driving time of the vehicle on the links.
And S7, estimating the flow of any section at any time period according to the dynamic distribution result of the vehicle running time.
Assuming that the vehicle travels at a constant speed on each divided road segment, the time for the vehicle to reach any cross section can be obtained according to the result of step S6, and assuming that a cross section is at a certain position x of the a-th road segment, the time for the vehicle h to reach the cross section x can be calculated according to different vehicle conditions.
(1) The time of arrival of the vehicle at a position upstream of the section x is known
Figure GDA0003122424620000175
In the formula, tenThe time when the vehicle reaches a certain position upstream of the section x; a1 shows that a position upstream of the section x is at the a1 th road segment; t is th(i) The driving time of the vehicle h on the road section i; Δ l1 is the distance from the starting point of the road section a to the section x; laIs the length of road segment a; t is th(a) The driving time of the vehicle h on the road section a; t is the time for the vehicle to reach section x.
(2) The time of arrival of the vehicle at a position downstream of section x is known
Figure GDA0003122424620000176
In the formula, texThe time when the vehicle reaches a certain position downstream of the section x; a2 shows that a position upstream of the section x is at the a2 th road segment; Δ l2 is the distance from section x to the end point of section a.
(3) The time of arrival of the vehicle at a position upstream and downstream of the section x is known
Figure GDA0003122424620000181
Figure GDA0003122424620000182
In general, t1 and t2 should be approximately equal, and one of the values may be taken as t; otherwise, comparing the positions upstream and downstream of the cross section with the distance between the cross sections, if the position upstream of the selected cross section is closer to the target cross section, then giving t1 a larger weight, and vice versa, and finally:
Figure GDA0003122424620000183
in the formula, l1 and l2 are distances between the upstream and downstream positions of the cross section and the cross section, respectively.
As shown in fig. 4, taking a section on the road section 3 as an example, some vehicles may come from the junction P in all vehicles passing through the sectionoAt this time, the accurate time of the vehicle reaching any position in front of the section cannot be determined, but the vehicle can reach C after passing through the section1At the time of vehicle taking at the gate1The snapshot time at the bayonet is taken as texCalculation is performed using equation (8) if C1If the data of the bayonet is missing or has obvious errors, the next bayonet adjacent to the bayonet is selected to carry out the same treatment. In addition, a slave junction P is also present in all vehicles passing through the section0The vehicle having previously been on the target road, then this portion of the vehicle will also pass through the gate C upstream of the target section0Will also pass through downstream bayonet C1At this time, t1 and t2 may be obtained by using equations (7) and (8), respectively, and the values of both may be compared to determine the value of t.
In summary, for any section, the time of all vehicles passing through the section reaching the section can be accurately judged, so that for any selected time period, the section hour flow is obtained as follows:
q＝{N|t∈ΔT} (10)
in the formula, q is the hourly flow of an arbitrary section x; t is the time for the vehicle to reach the section x; delta T is a selected hour period; n is the number of vehicles reaching the cross-section x within Δ T.
In summary, the embodiment of the present invention provides a method for estimating flow of an arbitrary section of an expressway at any time based on multi-source data, which performs effective fusion matching on bayonet data and data of an import/export toll station to obtain a driving track of each vehicle, divides a target road into a plurality of short-distance road sections, assumes that a driving state of the vehicle on the road sections is unchanged, and infers complete driving information of the vehicle on the target road according to a traffic state of the road sections, thereby determining a time when each vehicle reaches the arbitrary section, thereby estimating the flow of the arbitrary section of the expressway at any time, obtaining operation characteristics on the road, exploring a travel evolution law on the expressway, providing data support for accurate prediction of the flow of the expressway, and thereby effectively obtaining more complete road information in time.
Those of ordinary skill in the art will understand that: the figures are merely schematic representations of one embodiment, and the blocks or flow diagrams in the figures are not necessarily required to practice the present invention.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for apparatus or system embodiments, since they are substantially similar to method embodiments, they are described in relative terms, as long as they are described in partial descriptions of method embodiments. The above-described embodiments of the apparatus and system are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (2)

1. A method for estimating the flow of any section of an expressway at any time period based on multi-source data is characterized by comprising the following steps:
s1, obtaining multi-source data of the target road, wherein the multi-source data comprises: entrance toll station data, exit toll station data and card port data; the entrance toll station data includes: vehicle origin information; the exit toll station data includes: vehicle start and end point information; the bayonet data includes: discrete state information of the vehicle in the driving process;
s2, matching the multi-source data, including: s21, integrating the bayonet data, extracting all bayonet information that each vehicle passes through, arranging according to the time sequence, determining a threshold value T according to the distribution rule of the cameras on the road, so that the difference value of adjacent time in the bayonet information corresponding to each vehicle does not exceed the value T, otherwise, dividing the information, and considering that the vehicle passes through the road section again in another time period; s22, determining a driving direction, extracting corresponding gate data, and respectively matching the gate data with entrance and exit charging data by taking a license plate number as a primary key value and entrance time and exit time as a secondary key value to obtain four types of data including entrance information and gate information, entrance and exit information, gate information and gate information, gate information and entrance and exit information, wherein each piece of information in each type of data corresponds to complete or partial driving information of a vehicle on a target road;
s3, classifying the vehicle path information and calculating the vehicle running time based on the data matching result;
s4, processing the abnormal data in the vehicle running time and calculating the average running speed of the vehicle, wherein the method comprises the following steps: s41, removing the abnormal points
At a certain time, the maximum value of the travel time of all vehicles passing a given OD pair is tmaxMinimum value of tminAccording to the length of the link between OD pairsodGiven a threshold M, the following operations are performed:
s411, if the data volume Num in a certain time interval is more than 1, calculating tmax-tmin(ii) a Otherwise, judging whether T in one piece of data is reasonable or not, namely whether T is greater than T or notmaxOr T < TminIf so, put T into the data set to be corrected, where Tmax＝lod×1.5/vmin，Tmin＝lod/(vmax×1.5)；
S412, if tmax-tminIf the value is more than M, an extremely abnormal point exists; then calculating the skewness skew of the group of data, if skew is more than 0, if a great abnormal point exists, calculating tmaxPutting a data set to be corrected; if skew < 0, there is a very small outlier, let tminPutting a data set to be corrected;
s413, repeating the steps S411 and S412 until tmax-tminUntil the mass is less than or equal to M;
s42, 3 sigma criterion screening
S421, calculating the average value mu and the standard deviation sigma of all vehicle travel time after screening according to the screened data set of the antipodal abnormal value, determining the upper and lower boundaries of secondary screening, and setting the upper and lower boundaries as [ mu-2 sigma, mu +2 sigma ];
s422, for the travel time t of each vehicle, if t is more than or equal to mu-2 sigma and less than or equal to mu +2 sigma, reserving; otherwise, correcting the t value by using the travel time of other vehicles in the time period;
s423, repeating the steps S421 and S422 until all t values are within the [ mu-2 sigma, mu +2 sigma ];
s43 correction of a dataset to be corrected
All the data sets to be corrected are extremely abnormal values, the extremely abnormal values are corrected according to the result reserved in the step S42, normal data in the same time period with the extremely abnormal values are found, and the average value of the normal data replaces the t value in the abnormal data; if normal data in the same time interval cannot be found due to less data in certain time intervals, replacing the abnormal t value with the average value according to the principle that the interval with the current time interval is smaller and the normal data is preferentially selected until the normal data exists in a certain time interval;
s44, after the abnormal travel time processing is finished, dividing the travel time by the corresponding travel distance again to obtain the processed average travel speed;
s5, calculating the average running speed and the average running time of the road section based on the average running speed of the vehicle, and acquiring a space-time matrix of the average running time of each road section of different vehicle types, wherein the space-time matrix comprises the following steps: for any road section on the target road, selecting a bayonet adjacent to the starting end of the road section and a bayonet adjacent to the terminal end of the road section, if the road section is a boundary road section, and the starting end or the terminal end of the boundary road section is a toll station, selecting the bayonet and the toll station, and finding all vehicles of the same type continuously passing through the two bayonets or the bayonet and the toll station, wherein in a certain period, the driving speed of the road section contained between the two bayonets or between the bayonet and the toll station is the average speed of all vehicles continuously passing through the two bayonets or the bayonet and the toll station in the certain period;
if the data of the two selected bayonets has obvious errors or missing information at the upstream bayonet, neglecting the bayonet with the wrong or missing information, and directly taking the average speed of all vehicles of the same type between the previous bayonet of the upstream bayonet and the selected downstream bayonet as the running speed on the road section for a certain period of time; if the information at the downstream bayonet is obviously wrong or missing, taking the average speed of all vehicles of the same type between the selected upstream bayonet and the subsequent bayonet of the downstream bayonet as the running speed on the road section;
the specific calculation formula is as follows:
Figure FDA0003122424610000031
Figure FDA0003122424610000032
in the formula (I), the compound is shown in the specification,
Figure FDA0003122424610000033
and
Figure FDA0003122424610000034
respectively the average running speed and the average running time of a certain road section a on the expressway in a time period k for vehicles with the vehicle type q; n (q) is the model of the vehicle which will pass through the section a in the time period kq number of vehicles; laIs the length of road segment a; r should be selected to give priority to the shortest sub-path;
for different vehicle types q, a space-time matrix of average travel time of each road section can be obtained, wherein K time periods and A road sections are finally represented as follows:
Figure FDA0003122424610000035
s6, selecting a corresponding space-time matrix according to the vehicle type, dynamically distributing the vehicle running time, and calculating the corresponding running time of the vehicle on the road section, wherein the method comprises the following steps: for vehicles with complete path information, after obtaining the space-time matrix, dynamically distributing the path driving time of each vehicle by using a formula (6), selecting corresponding t _ matrix (q) according to the vehicle type q,
Figure FDA0003122424610000041
in the formula, th(a) The driving time of the vehicle h on the road section a; s is the number of road segments passed by the whole travel of the vehicle h; t is tODThe travel time of the corresponding path of the vehicle on the target road is taken; over time, the vehicle travels different road sections in different time periods during the course of travel
Figure FDA0003122424610000043
In the method, the time interval and the road section corresponding to the time interval and the road section are selected from the space-time matrix
Figure FDA0003122424610000048
Value of then
Figure FDA0003122424610000049
Is shown in the time period
Figure FDA0003122424610000046
The vehicle is in a certain positionTravel time of a section a, wherein
Figure FDA0003122424610000047
A period k representing a change;
for a vehicle with only partial route information, performing dynamic time allocation on the travel time of the partial route according to a formula (6); deducing which junction the vehicle leaves or enters the target road from according to the position information of the gate for the road sections with missing information, taking the average speed of the adjacent road sections as the driving speed of the vehicle on the road sections with the missing information, and calculating the corresponding driving time of the vehicle on the road sections;
s7, estimating the flow of any section at any time period according to the dynamic distribution result of the vehicle running time, comprising the following steps: assuming that the vehicle runs at a constant speed on each divided road section, calculating the time of the vehicle reaching any cross section, assuming that a cross section is at a certain position x of the a-th road section, calculating the time of the vehicle h reaching the cross section x according to different vehicle conditions,
the time of arrival of the vehicle at a position upstream of the section x is known
Figure FDA0003122424610000042
In the formula, tenThe time when the vehicle reaches a certain position upstream of the section x; a1 shows that a position upstream of the section x is at the a1 th road segment; t is th(i) The driving time of the vehicle h on the road section i; Δ l1 is the distance from the starting point of the road section a to the section x; laIs the length of road segment a; t is th(a) The driving time of the vehicle h on the road section a; t is the time for the vehicle to reach the section x;
the time of arrival of the vehicle at a position downstream of section x is known
Figure FDA0003122424610000051
In the formula, texFor vehicle arrivalTime at a position downstream of section x; a2 shows that a position upstream of the section x is at the a2 th road segment; Δ l2 is the distance from section x to the end point of road section a;
the time of arrival of the vehicle at a position upstream and downstream of the section x is known
Figure FDA0003122424610000052
Figure FDA0003122424610000053
If the values of t1 and t2 are approximately equal, taking one of the values as t; otherwise, comparing the distance between the upstream and downstream positions of the fracture surface and the fracture surface, if the position upstream of the selected fracture surface is closer to the target fracture surface than the position downstream of the fracture surface, giving a weight of t1 greater than t2, otherwise, giving a weight of t2 greater than t 1:
Figure FDA0003122424610000054
in the formula, l1 and l2 are the distances between the positions at the upstream and downstream of the cross section and the cross section respectively;
for any section, judging the time of all vehicles passing through the section reaching the section, so as to obtain the section hour flow as follows for any selected time period:
q＝{N|t∈ΔT} (10)
in the formula, q is the hourly flow of an arbitrary section x; t is the time for the vehicle to reach the section x; delta T is a selected hour period; n is the number of vehicles reaching the cross-section x within Δ T.
2. The method according to claim 1, wherein the S3 includes:
s31, after the matching is completed, classifying the route information included in all the vehicles, including:
for a vehicle entering from one junction and leaving from the target road from the other junction, the vehicle only comprises the bayonet information between the two junctions and corresponds to part of the path information on the target road;
for a vehicle entering from a toll station but leaving a target road from a junction, entrance information of the toll station and gate information between the toll station and the junction are contained, and the entrance information corresponds to partial path information on the target road;
for a vehicle entering a target road from a junction but leaving a toll station, exit information of the toll station and entrance information between the toll station and the junction are contained, and correspond to partial path information on the target road;
for vehicles entering from a toll station and leaving from a toll station on a target road, acquiring complete path information of the vehicles on the target road, including information of an entrance and an exit and information of a gate between two toll stations;
s32, based on the classification of the route information, two end points in the vehicle route information are obtained, and the travel time of each vehicle on the corresponding route on the target road is obtained, that is:
tOD＝tD-tO (1)
in the formula, tDThe destination time in the path information; t is tOIs the starting point moment in the path information;
the path information comprises a plurality of positions and corresponding time information, a sub-path of the vehicle on the target road is arranged between every two position points, based on the position information, the travel time and the average traveling speed of each vehicle passing through all the sub-paths are calculated, and if the path of each vehicle comprises R sub-paths, the method comprises the following steps:
Figure FDA0003122424610000061
in the formula, th，rIs the travel time of the vehicle h on the sub-path r; dh，rDistance of sub-path r for vehicle h;
Figure FDA0003122424610000062
the average speed of the vehicle h on the sub-path r.
CN202010086610.3A 2020-02-11 2020-02-11 Method for estimating flow of arbitrary section of highway at any time period based on multi-source data Active CN111292533B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010086610.3A CN111292533B (en) 2020-02-11 2020-02-11 Method for estimating flow of arbitrary section of highway at any time period based on multi-source data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010086610.3A CN111292533B (en) 2020-02-11 2020-02-11 Method for estimating flow of arbitrary section of highway at any time period based on multi-source data

Publications (2)

Publication Number Publication Date
CN111292533A CN111292533A (en) 2020-06-16
CN111292533B true CN111292533B (en) 2021-07-30

Family

ID=71020153

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010086610.3A Active CN111292533B (en) 2020-02-11 2020-02-11 Method for estimating flow of arbitrary section of highway at any time period based on multi-source data

Country Status (1)

Country Link
CN (1) CN111292533B (en)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111724595B (en) * 2020-06-23 2022-04-01 重庆大学 Highway section flow estimation method based on charging data
CN112184931B (en) * 2020-09-28 2022-09-13 广西信路威科技发展有限公司 Vehicle charging path optimization system and analysis method based on highway network
CN113345252B (en) * 2021-06-08 2022-07-22 重庆大学 Short-time prediction method and device for lower-path flow of toll station
CN113362602A (en) * 2021-06-29 2021-09-07 山东旗帜信息有限公司 Congestion analysis method and equipment based on portal traffic data
CN113674538B (en) * 2021-08-09 2023-04-18 南京领航交通科技有限公司 Section flow monitoring system
CN114758493B (en) * 2022-03-21 2024-03-12 山东省交通规划设计院集团有限公司 Expressway traffic flow monitoring method and system based on data fusion
CN114783194A (en) * 2022-04-02 2022-07-22 贵州汇联通电子商务服务有限公司 Method and system for acquiring section flow based on high-speed portal frame
CN114862011B (en) * 2022-04-29 2023-04-07 上海理工大学 Road section time-interval traffic demand estimation method considering congestion state
CN114999162B (en) * 2022-08-02 2022-10-21 北京交研智慧科技有限公司 Road traffic flow obtaining method and device

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101783075A (en) * 2010-02-05 2010-07-21 北京科技大学 System for forecasting traffic flow of urban ring-shaped roads
CN103839409A (en) * 2014-02-27 2014-06-04 南京大学 Traffic flow state judgment method based on multiple-cross-section vision sensing clustering analysis
CN104123837A (en) * 2013-04-28 2014-10-29 上海济祥智能交通科技有限公司 Interrupted flow travel time estimation method based on microwave and video data fusion
CN110148295A (en) * 2019-04-03 2019-08-20 东南大学 A method of estimation section free stream velocity and intersection upstream reach flow rate

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6587781B2 (en) * 2000-08-28 2003-07-01 Estimotion, Inc. Method and system for modeling and processing vehicular traffic data and information and applying thereof
CN101436347A (en) * 2008-12-09 2009-05-20 北京交通大学 Prediction method for rapid road travel time
CN101882374A (en) * 2009-05-04 2010-11-10 上海宝康电子控制工程有限公司 System and method for analysis of comprehensive information on vehicle trip distribution
CN104504897B (en) * 2014-09-28 2017-10-31 北京工业大学 A kind of analysis of intersection traffic properties of flow and vehicle movement Forecasting Methodology based on track data
CN205564023U (en) * 2015-12-29 2016-09-07 中国城市规划设计研究院 Monitoring system is reliably spent to express way journey time
CN106504528A (en) * 2016-11-02 2017-03-15 浙江大学 A kind of utilization mobile phone signaling big data and the OD scaling methods of Used in Dynamic Traffic Assignment
US10733877B2 (en) * 2017-11-30 2020-08-04 Volkswagen Ag System and method for predicting and maximizing traffic flow
CN108648444B (en) * 2018-04-18 2020-05-05 北京交通大学 Signalized intersection operation evaluation method based on grid model
CN110299011A (en) * 2019-07-26 2019-10-01 长安大学 A kind of traffic flow forecasting method of the highway arbitrary cross-section based on charge data

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101783075A (en) * 2010-02-05 2010-07-21 北京科技大学 System for forecasting traffic flow of urban ring-shaped roads
CN104123837A (en) * 2013-04-28 2014-10-29 上海济祥智能交通科技有限公司 Interrupted flow travel time estimation method based on microwave and video data fusion
CN103839409A (en) * 2014-02-27 2014-06-04 南京大学 Traffic flow state judgment method based on multiple-cross-section vision sensing clustering analysis
CN110148295A (en) * 2019-04-03 2019-08-20 东南大学 A method of estimation section free stream velocity and intersection upstream reach flow rate

Also Published As

Publication number Publication date
CN111292533A (en) 2020-06-16

Similar Documents

Publication Publication Date Title
CN111292533B (en) Method for estimating flow of arbitrary section of highway at any time period based on multi-source data
US7680588B2 (en) Traffic information management system
CN105513339B (en) A kind of track of vehicle analysis method and equipment
CN107025788B (en) Travel time prediction method and device
CN111328412B (en) Adaptive traffic control based on vehicle trajectory data
CN104392606B (en) Bus location mileage-based road condition detection method and system
CN109712401B (en) Composite road network bottleneck point identification method based on floating car track data
DE102016104274B4 (en) JAM INFORMATION GENERATING DEVICE AND JAM INFORMATION GENERATING METHOD
CN111581538B (en) Expressway charging data-based expressway traffic flow state deducing method
Rahmani et al. Floating car and camera data fusion for non-parametric route travel time estimation
CN105447592A (en) Passenger route choice analysis method and passenger route choice analysis device
KR101913134B1 (en) Apparatus for generating lane by lane traffic velocity information in intelligent trasportation system
CN111712862A (en) Method and system for generating traffic volume or traffic density data
CN105096590A (en) Traffic information generation method and device
CN109099931B (en) Navigation method and navigation terminal for detecting sudden traffic incident in navigable road segment
CN112184931A (en) Vehicle charging path optimization system and analysis method based on highway network
US20210118296A1 (en) Traffic status estimation device, traffic status estimation method, program recording medium, and output device
CN109615865B (en) OD data increment based iterative road section traffic flow estimation method
CN114898571A (en) ETC big data-based highway all-section vehicle speed measuring method
CN110675631A (en) Traffic flow traceability analysis method and system
WO2010101199A1 (en) Road traffic information creation device and road traffic information creation method
EP2811467B1 (en) Method and devices for error detection in a toll system
CN111260935B (en) Vehicle passing method and device
CN115641721A (en) Multi-source traffic flow index fusion and road condition calculation method based on fusion index
CN114722127A (en) Electronic map correction method, navigation information setting method, navigation method and navigation device

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