CN113380036A - Queuing length calculation method based on electronic police data - Google Patents

Queuing length calculation method based on electronic police data Download PDF

Info

Publication number
CN113380036A
CN113380036A CN202110668088.4A CN202110668088A CN113380036A CN 113380036 A CN113380036 A CN 113380036A CN 202110668088 A CN202110668088 A CN 202110668088A CN 113380036 A CN113380036 A CN 113380036A
Authority
CN
China
Prior art keywords
vehicle
data
time
intersection
queuing length
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202110668088.4A
Other languages
Chinese (zh)
Other versions
CN113380036B (en
Inventor
王浩
鞠建敏
武志薪
田恒
缪奇峰
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.)
Shanghai Institute of Technology
Original Assignee
Shanghai Institute of Technology
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 Shanghai Institute of Technology filed Critical Shanghai Institute of Technology
Priority to CN202110668088.4A priority Critical patent/CN113380036B/en
Publication of CN113380036A publication Critical patent/CN113380036A/en
Application granted granted Critical
Publication of CN113380036B publication Critical patent/CN113380036B/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
    • 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
    • G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
    • G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a queuing length calculation method based on electronic police data, which comprises the following steps of S1: collecting data: acquiring the license plate number, the vehicle type and the time data of driving away from a stop line of a vehicle from a START traffic diagnosis and optimization system by combining the kinematic law of traffic waves; step S2: data preprocessing: performing data cleaning on abnormal data, missing data and repeated data in the electronic police; step S3: determining the number of times of parking of the vehicle on the road section according to the distribution condition of the travel time; step S4: and constructing an intersection queuing length calculation method according to the number of times of vehicle parking, the time of the vehicle driving away from the stop line of the upstream intersection and the time of the vehicle driving away from the stop line of the intersection. Compared with the traditional queuing length estimation model, the model requires less original data, has higher prediction precision and stronger generalization capability, and can more accurately predict the queuing length of the urban signalized intersection.

Description

Queuing length calculation method based on electronic police data
Technical Field
The invention relates to the field of intelligent traffic control, in particular to a queuing length calculation method based on electronic police data.
Background
In an intelligent traffic system, the method is vital to estimation of the queuing length, timely and accurate acquisition of the queuing length at an intersection can reflect the change process of road smoothness and congestion in real time, provides data support for management and optimization of traffic signal control, can better evaluate the traffic efficiency of urban road network traffic, and is a key factor for measuring the urban traffic service level. The appearance of electronic police provides huge space for the development of urban traffic, the conventional detection equipment (such as geomagnetic induction coil data, RFID data, GPS data and the like) has the defects of detection error, signal loss, interference, limited equipment coverage and the like, the traffic flow condition of continuous intersections needs to be considered sometimes, the required data amount is huge, and the defects exist in practical application. With the change of the detection mode, the electronic police develops rapidly, can better solve the situations of signal loss, unstable data and the like in the past, can provide the track information of the vehicle, and can be used as important data support in the research of the queuing length.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a queuing length calculation method based on electronic police data, which innovatively utilizes travel time to calculate the queuing length and aims to improve the convenience and the applicability of the queuing length calculation.
In order to achieve the above purpose, the technical solution for solving the technical problem is as follows:
a queuing length calculation method based on electronic police data comprises the following steps:
step S1: collecting data: acquiring the license plate number, the vehicle type and the time data of driving away from a stop line of a vehicle from a START traffic diagnosis and optimization system by combining the kinematic law of traffic waves;
step S2: data preprocessing: performing data cleaning on abnormal data, missing data and repeated data in the electronic police;
step S3: determining the number of times of parking of the vehicle on the road section according to the distribution condition of the travel time;
step S4: and constructing an intersection queuing length calculation method according to the number of times of vehicle parking, the time of the vehicle driving away from the stop line of the upstream intersection and the time of the vehicle driving away from the stop line of the intersection.
Further, in the step S1, the traffic wave kinematics rule analyzes the vehicle blockage situation, and it is known that data related to the queuing length, including vehicle delay, vehicle departure time data, road segment length, road segment number, and vehicle driving direction, needs to be acquired.
Further, the travel time in step S1 is a time difference from a time when the vehicle leaves the stop line at the upstream intersection to the stop line at the intersection, and the travel time is calculated by taking the road segment from the intersection a to the intersection B as an example, a vehicle leaves the stop line at the intersection a and leaves the stop line at the intersection B, and the travel time of the road segment is Tab＝tb-ta。
Further, in the step S2, in the preprocessing of the electronic police data, part of missing values are compensated by taking the mean value of adjacent points, the whole missing of the intersection data is compensated by using a machine learning algorithm, and the abnormal data is corrected by using the mean value.
Further, when a time difference of a red light duration r exists between the travel time T or the departure time T of two adjacent vehicles, the time difference is called jump, jump characteristics are extracted according to the distribution of travel time points, and jump is divided into two types of situations according to the position of the time difference r:
when the driving-off time of two adjacent vehicles has a time difference r, recording as cross-cycle jump;
when the travel time T of two adjacent vehicles has a time difference r and the time difference of the driving-away time is less than r, recording as the jump in the period;
other non-illustrated cases are considered to be no hopping.
Further, in step S3, the same travel time interval corresponds to different parking times, where the parking times are recorded as n, and there are the following situations:
suppose the travel time T e (T) of the vehicle0+(n-1)C，T0+ nC) with a number of stops of n;
suppose the travel time T e (T) of the vehicle0+nC+g，T0+ (n +1) C) with the number of parking times n + 1;
suppose the travel time T e (T) of the vehicle0+nC，T0+ nC + g) with a number of stops of n or n +1, which is further determined by the travel time forward traversal.
Further, in step S4, the calculation method for preliminarily determining the queuing length of the vehicle by using the vehicle travel time and the number of times of parking is as follows:
Figure BDA0003117737040000031
wherein S is the basic saturation flow rate of the intersection entrance lane, n is the number of stops, txThe timestamp of the x-th vehicle driving away from the stop line of the intersection, and g is the green time.
Further, in step S4, when the vehicle drives from the stop line at the upstream intersection to the tail of the queue of the queued vehicle, the queued vehicle may be in a dissipation process, so that the dissipation process is added to the queuing length calculation method, and the queuing length calculation method is further optimized, where the formula is as follows:
Figure BDA0003117737040000032
wherein L is the road length, L1Length of queue at green light on, T0Is the free travel time.
Due to the adoption of the technical scheme, compared with the prior art, the invention has the following advantages and positive effects:
1. according to the method for calculating the queuing length based on the electronic police data, complex data such as signal timing, traffic flow, traffic starting waves and parking waves do not need to be acquired, and the queuing length is estimated only by analyzing the vehicle travel time data of the key nodes and the data of the time when the vehicle leaves the intersection, so that the method has better applicability and stronger operability;
2. the invention relates to a queuing length calculation method based on electronic police data, which adopts full-sample and track-based bayonet type electronic police data and is more beneficial to reflecting real urban road traffic conditions;
3. the invention relates to a queuing length calculation method based on electronic police data, which is characterized in that the electronic police and a vehicle identification system such as a gate are used for acquiring travel time data, and the relationship between the travel time and the vehicle driving-away time is compared, so that the queuing length of vehicles at a signalized intersection can be accurately estimated. Compared with the traditional queuing length estimation model, the model requires less original data, has higher prediction precision and stronger generalization capability, can more accurately predict the queuing length of the urban signalized intersection, reflects the service level of the road to a certain extent, and provides foreseeable data support for related management departments.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. It is obvious that the drawings in the following description are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort. In the drawings:
FIG. 1 is a flow chart of a queuing length calculation method according to the present invention;
FIG. 2 is a diagram of a vehicle obstruction relating to the present invention;
FIG. 3 is a schematic view of an electronic police installation to which the present invention relates;
FIG. 4 is a graph of a time-of-flight characterization according to the present invention;
fig. 5 is a distribution diagram of the parking number interval according to the present invention;
FIG. 6 is a graph of queue dispersion variation to which the present invention relates;
FIG. 7 is a comparison of A-period queuing lengths according to the present invention;
FIG. 8 is a comparison of B-period queuing lengths as contemplated by the present invention;
fig. 9 is a comparison of C-period queuing lengths in accordance with the present invention.
Detailed Description
While the embodiments of the present invention will be described and illustrated in detail with reference to the accompanying drawings, it is to be understood that the invention is not limited to the specific embodiments disclosed, but is intended to cover various modifications, equivalents, and alternatives falling within the scope of the invention as defined by the appended claims.
As shown in fig. 1 to 9, the present embodiment discloses a queuing length calculation method based on electronic police data, which includes the following steps:
step S1: collecting data: and (2) acquiring the license plate number, the vehicle type and the data of the time when the vehicle leaves the stop line from the START traffic diagnosis and optimization system by combining the kinematics rule of the traffic wave, acquiring the vehicle travel time between signalized intersections by comparing the license plate data of the matched vehicles between adjacent intersections, wherein the vehicles captured by an electronic police at an upstream intersection and the intersection are called matched vehicles.
In step S1, the traffic wave kinematics rule analyzes the vehicle blockage situation, and it is known that data related to the queuing length, including vehicle delay, vehicle departure time data, road length, road serial number, and vehicle driving direction, needs to be acquired.
Further, the travel time in step S1 is a time difference from a time when the vehicle leaves the stop line at the upstream intersection to the stop line at the intersection, and the travel time is calculated by taking the road segment from the intersection a to the intersection B as an example, a vehicle leaves the stop line at the intersection a and leaves the stop line at the intersection B, and the travel time of the road segment is Tab＝tb-ta。
Step S2: data preprocessing: the method is characterized in that special vehicles in electronic police data, including police cars, ambulances and military vehicles, are filtered, the queuing length cannot completely and effectively reflect the queuing length condition of the vehicles only by adopting the time difference of the vehicles from the driving-off of a stop line at an upstream intersection to the driving-off of the stop line at the intersection as the travel time, the electronic police data need to be subjected to data cleaning, and abnormal data and missing data are compensated and corrected by utilizing a mode of combining statistics and machine learning.
Further, in the step S2, in the preprocessing of the electronic police data, part of missing values are compensated by taking the mean value of adjacent points, the whole missing of the intersection data is compensated by using a machine learning algorithm, and the abnormal data is corrected by using the mean value. In addition, the oversize data and the undersize data in the abnormal data are subjected to data compensation by using the mean value, the missing data is compensated, and the repeated data is subjected to deduplication processing.
Step S3: and determining the parking times of the vehicle on the road section according to the distribution condition of the travel time, wherein the travel time of the vehicle does not correspond to the parking times one by one, and different parking times can be determined in the same travel time, so that different parking times in the same travel time are required to be determined.
Further, when a time difference of a red light duration r exists between the travel time T or the departure time T of two adjacent vehicles, the time difference is called jump, jump characteristics are extracted according to the distribution of travel time points, and jump is divided into two types of situations according to the position of the time difference r:
when the driving-off time of two adjacent vehicles has a time difference r, recording as cross-cycle jump;
when the travel time T of two adjacent vehicles has a time difference r and the time difference of the driving-away time is less than r, recording as the jump in the period;
other non-illustrated cases are considered to be no hopping.
Further, in step S3, the same travel time interval corresponds to different parking times, where the parking times are recorded as n, and referring to fig. 5, there are the following situations:
suppose the travel time T e (T) of the vehicle0+(n-1)C，T0+ nC) with a number of stops of n;
suppose the travel time T e (T) of the vehicle0+nC+g，T0+ (n +1) C) with the number of parking times n + 1;
suppose the travel time T e (T) of the vehicle0+nC，T0+ nC + g) with a number of stops of n or n +1, which is further determined by the travel time forward traversal.
Step S4: and judging the maximum queuing length of the vehicle in the process of the travel according to the number of times of vehicle parking, the time of the vehicle driving away from the stop line of the upstream intersection and the time of the vehicle driving away from the stop line of the intersection, and constructing an intersection queuing length calculation method.
In step S4, the calculation method for preliminarily determining the queuing length of the vehicle by using the vehicle travel time and the number of times of parking is as follows:
Figure BDA0003117737040000061
wherein S is the basic saturation flow rate of the intersection entrance lane, n is the number of stops, txThe timestamp of the x-th vehicle driving away from the stop line of the intersection, and g is the green time.
Further, in step S4, when the vehicle drives from the stop line at the upstream intersection to the tail of the queue of the queued vehicle, the queued vehicle may be in a dissipation process, as shown in fig. 6, so that the dissipation process is added to the queuing length calculation method, and the queuing length calculation method is further optimized, where the formula is as follows:
Figure BDA0003117737040000062
wherein L is the road length, L1Length of queue at green light on, T0Is the free travel time.
Example (b):
one, data source
The data source adopted by the embodiment is based on the license plate identification information detected by an electronic police. The electronic police are arranged at the crossroads, the pedestrian crossings, the main and auxiliary road entrances and exits, and the like. When a vehicle passes through a stop line, the high-definition digital camera shoots a picture of the tail part of the vehicle, and the electronic police system can process the picture according to the picture and extract vehicle information, so that refined electronic warning and wiping data are obtained. The all-weather real-time recorded data of the electric alarm data comprises the following fields: collection location, lane number, direction, time (year, month, day, hour, minute, second), license plate type, license plate number, etc.
For a section of road L from the intersection a to BabFor example, a vehicle exits the stop line at intersection A and exits the stop line at intersection B, with a segment travel time Tab＝tb-ta. In the research process, the average value of the first 5% with the minimum travel time in the electric alarm data of one day is taken as the free stream travel time in the model. The time at which the vehicle is driven off from the intersection stop line is referred to as a vehicle drive-off time, and the time elapsed from the drive-off of the upstream intersection stop line to the drive-off of the intersection stop line is referred to as a vehicle travel time. The travel time analysis of the vehicles can be conveniently carried out between matched vehicles, and the method only utilizes the travel time data in the electronic police data to research the queuing length.
Second, vehicle queue analysis
As shown in fig. 2 for the case of a blocked vehicle, q represents the arrival rate of the traffic flow, N represents the traffic capacity, and S is the saturation flow rate. One signal period C represents the time from the start of a red light to the end of a green light, and when the number qC of arriving vehicles in one signal period (the effective red light time length r and the effective green light time length g) is greater than the number Sg of discharged vehicles during the green light period, an oversaturation state occurs at the intersection, and a stuck vehicle is generated. The number of vehicles Q remaining in front of the stop line after the end of the first signal period is the initial queuing length of the second signal period.
Third, data preprocessing
The length of queue vehicle analyzed by this embodiment is the length of queue between ordinary vehicles, so it is necessary to filter out some special vehicles. The special vehicles include police cars, ambulances, military vehicles and the like. The queuing length cannot be completely and effectively reflected by calculating the queuing length only by taking the time difference from the driving-off of the vehicle from the stop line at the upstream intersection to the driving-off of the stop line at the intersection as the travel time, the data of the electronic police is required to be cleaned, and abnormal data and missing data are mainly processed. Abnormal or missing data may be generated in several cases:
(1) during the midway traveling of the vehicle, the stopping of the vehicle (vehicle breaking, midway passenger carrying and the like) for some special reasons causes time delay higher than that of the normally traveling vehicle;
(2) the method comprises the following steps that a branch which is not provided with detection equipment leaves a detection area during the running of a vehicle, so that an electronic police system cannot be matched with license plate identification data;
(3) the vehicles travel for two or more times in the road section, so that the same license plate data appears in the electronic police system for multiple times.
(4) An electronic police is not installed at the upstream intersection, so that the detection of the downstream intersection is inaccurate.
And (4) making up and correcting abnormal data and missing data by combining statistics and machine learning.
Fourthly, actual verification
The study object of this embodiment is a direct two-lane at the west entrance of the intersection between the official road and the north road of east ring in Ningbo city, the distance between the two intersections is 369m, the signal periods are both 95s, wherein the yellow light time is 3s, the full red time is 1s, and the signal timing scheme is shown in Table 1.
TABLE 1 Signal timing scheme
Figure BDA0003117737040000081
And selecting three different time periods for empirical analysis according to the actual traffic flow conditions at the intersection from 1 month to 20 months from 4 months to 4 months in 2020. A. B is the peak flattening period and C is the early peak period, as in table 2. In order to more accurately acquire the traffic flow at the intersection, the arrival and departure time of the vehicle and the maximum queuing length of the vehicle, the data sampling interval is set to be 95s and is consistent with the signal period. And 40 periods are selected for model verification in the peak-balancing period, and 60 periods are selected for model verification in the peak period.
TABLE 2 time period selection and flow distribution
Figure BDA0003117737040000082
In order to better evaluate the prediction performance of the road section overtaking rate prediction model, the embodiment adopts two objective functions of Mean-square Error (MSE) and Mean Absolute Error (MAD).
Figure BDA0003117737040000083
Figure BDA0003117737040000084
In the formula: p (i) is a real value of the overtaking rate of the road section;
Figure BDA0003117737040000085
the predicted value of the overtaking rate of the road section is obtained; and n is the number of the prediction verification data sets.
Fifth, experimental results and analysis
The results of the experiment were analyzed as follows:
(1) mean Square Error (MSE) and Mean Absolute Error (MAD) were used for model evaluation for A, B, C time periods. The Mean Absolute Error (MAE) of the calculated model is: 7.725m, 7.750m, 7.833m, the mean relative error (MAPE) is: 11.42%, 12.84%, 7.89%;
(2) the error of the calculation result for the peak period is smaller than that for the flat period. When the traffic flow is large, the control is better for the number of the vehicles with the queuing length;
(3) the calculated value of the embodiment is smaller than the measured value in most cases, and overall, the average accuracy of the model reaches over 86.40%, so that the queue length of the signalized intersection can be better estimated, and the method has good adaptability.
With the continuous acceleration of the urbanization process, the public demand for travel is higher and higher. Traffic congestion not only breaks the dynamic balance of urban road networks, but also restricts the rapid development of social economy. Because the traffic system is a high-dimensional and complex dynamic system, how to design a proper queuing length calculation method is the important point in analyzing the importance of traffic jam. The embodiment provides a queuing length calculation method based on electronic police data, and the applicability and the reliability of the model in the peak flattening period and the peak peaking period are analyzed respectively. The result shows that the method has better accuracy, can be used for calculating the queuing length of the urban intersections, and has important significance for solving traffic jam, analyzing the urban traffic network and providing data support for traffic polices. Through verification, the average accuracy of the method reaches about 86.40%, and the calculation accuracy is better in the peak period. In conclusion, the method has a remarkable effect on the calculation of the queuing length.
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 (8)

1. A queuing length calculation method based on electronic police data is characterized by comprising the following steps:
step S1: collecting data: acquiring the license plate number, the vehicle type and the time data of driving away from a stop line of a vehicle from a START traffic diagnosis and optimization system by combining the kinematic law of traffic waves;
step S2: data preprocessing: performing data cleaning on abnormal data, missing data and repeated data in the electronic police;
step S3: determining the number of times of parking of the vehicle on the road section according to the distribution condition of the travel time;
step S4: and constructing an intersection queuing length calculation method according to the number of times of vehicle parking, the time of the vehicle driving away from the stop line of the upstream intersection and the time of the vehicle driving away from the stop line of the intersection.
2. The method for calculating the queuing length based on the electronic police data as claimed in claim 1, wherein the traffic wave kinematics law in step S1 analyzes the vehicle blockage situation, and knows that the data related to the queuing length, including the vehicle delay, the vehicle driving-away time data, the road section length, the road section number and the vehicle driving direction, needs to be acquired.
3. A method according to claim 2, wherein the travel time in step S1 is the time difference from the time when the vehicle leaves the stop line at the upstream intersection to the stop line at the intersection, and the travel time is calculated based on the distance from the intersection a to the intersection B, and the distance from the intersection a to the intersection B to the stop line at the intersection B is Tab＝tb-ta。
4. The method for calculating the queuing length based on the electronic police data as claimed in claim 1, wherein in the step S2, the electronic police data is preprocessed, part of missing values are compensated by taking the mean value of adjacent points, the whole missing data of the intersection is compensated by using a machine learning algorithm, and abnormal data is corrected by using the mean value.
5. The method as claimed in claim 1, wherein in step S3, when there is a time difference of red light duration r between the travel time T or the departure time T of two adjacent vehicles, it is called jump, the jump feature is extracted according to the travel time point distribution, and the jump is divided into two types according to the position of the time difference r:
when the driving-off time of two adjacent vehicles has a time difference r, recording as cross-cycle jump;
when the travel time T of two adjacent vehicles has a time difference r and the time difference of the driving-away time is less than r, recording as the jump in the period;
other non-illustrated cases are considered to be no hopping.
6. A queuing length calculation method based on electronic police data as claimed in claim 5 wherein in step S3, the same journey time interval corresponds to different parking times, the parking times is recorded as n, there are following cases:
suppose the travel time T e (T) of the vehicle0+(n-1)C，T0+ nC) with a number of stops of n;
suppose the travel time T e (T) of the vehicle0+nC+g，T0+ (n +1) C) with the number of parking times n + 1;
suppose the travel time T e (T) of the vehicle0+nC，T0+ nC + g) with a number of stops of n or n +1, which is further determined by the travel time forward traversal.
7. The method of claim 1, wherein in step S4, the calculation method for preliminarily determining the queuing length of the vehicle by using the vehicle travel time and the number of parking is represented by the following formula:
Figure FDA0003117737030000021
wherein S is the basic saturation flow rate of the intersection entrance lane, n is the number of stops, txThe timestamp of the x-th vehicle driving away from the stop line of the intersection, and g is the green time.
8. The method for calculating the queuing length based on the electronic police data as claimed in claim 7, wherein in step S4, when the vehicle drives from the stop line of the upstream intersection to the tail of the queuing vehicle, the queuing vehicle may be in a dissipation process, so that the dissipation process is added to the queuing length calculation method, and the queuing length calculation method is further optimized by the following formula:
Figure FDA0003117737030000022
wherein L is the road length, L1Length of queue at green light on, T0Is the free travel time.
CN202110668088.4A 2021-06-16 2021-06-16 Queuing length calculation method based on electronic police data Active CN113380036B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110668088.4A CN113380036B (en) 2021-06-16 2021-06-16 Queuing length calculation method based on electronic police data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110668088.4A CN113380036B (en) 2021-06-16 2021-06-16 Queuing length calculation method based on electronic police data

Publications (2)

Publication Number Publication Date
CN113380036A true CN113380036A (en) 2021-09-10
CN113380036B CN113380036B (en) 2023-02-07

Family

ID=77572826

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110668088.4A Active CN113380036B (en) 2021-06-16 2021-06-16 Queuing length calculation method based on electronic police data

Country Status (1)

Country Link
CN (1) CN113380036B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113706873A (en) * 2021-09-28 2021-11-26 长沙智能驾驶研究院有限公司 Vehicle arrival time prediction method, device, equipment and computer storage medium
CN113947925A (en) * 2021-10-20 2022-01-18 上海应用技术大学 Green wave evaluation method, device and equipment based on electronic police data
CN115273488A (en) * 2022-07-29 2022-11-01 中国市政工程西南设计研究总院有限公司 Road vehicle parking judgment method based on travel time

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105225502A (en) * 2015-11-02 2016-01-06 招商局重庆交通科研设计院有限公司 A kind of intersection signal control method based on multiple agent
CN106097730A (en) * 2016-08-10 2016-11-09 青岛海信网络科技股份有限公司 The method of estimation of a kind of section vehicle queue length, Apparatus and system
CN106571029A (en) * 2016-10-18 2017-04-19 青岛海信网络科技股份有限公司 Method and device for detecting vehicle queue length
JP2018107690A (en) * 2016-12-27 2018-07-05 パナソニックＩｐマネジメント株式会社 Required time estimation system and required time estimation method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105225502A (en) * 2015-11-02 2016-01-06 招商局重庆交通科研设计院有限公司 A kind of intersection signal control method based on multiple agent
CN106097730A (en) * 2016-08-10 2016-11-09 青岛海信网络科技股份有限公司 The method of estimation of a kind of section vehicle queue length, Apparatus and system
CN106571029A (en) * 2016-10-18 2017-04-19 青岛海信网络科技股份有限公司 Method and device for detecting vehicle queue length
JP2018107690A (en) * 2016-12-27 2018-07-05 パナソニックＩｐマネジメント株式会社 Required time estimation system and required time estimation method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
王浩等: ""Estimation of Queue Length at Signalized Intersections based on Electronic Police Data"", 《ESAET 2020》 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113706873A (en) * 2021-09-28 2021-11-26 长沙智能驾驶研究院有限公司 Vehicle arrival time prediction method, device, equipment and computer storage medium
CN113706873B (en) * 2021-09-28 2022-11-29 长沙智能驾驶研究院有限公司 Vehicle arrival time prediction method, device, equipment and computer storage medium
CN113947925A (en) * 2021-10-20 2022-01-18 上海应用技术大学 Green wave evaluation method, device and equipment based on electronic police data
CN115273488A (en) * 2022-07-29 2022-11-01 中国市政工程西南设计研究总院有限公司 Road vehicle parking judgment method based on travel time
CN115273488B (en) * 2022-07-29 2023-09-22 中国市政工程西南设计研究总院有限公司 Road section vehicle parking judging method based on travel time

Also Published As

Publication number Publication date
CN113380036B (en) 2023-02-07

Similar Documents

Publication Publication Date Title
CN113380036B (en) Queuing length calculation method based on electronic police data
CN109272756B (en) Method for estimating queuing length of signal control intersection
WO2018064931A1 (en) Method for estimating travel time distribution of taxi on urban roads when operating states of taxis are considered
CN101710448B (en) Road traffic state detecting device based on omnibearing computer vision
CN107204115B (en) Method for estimating parking rate of main line traffic flow
CN109191830B (en) Road congestion detection method based on video image processing
Brockfeld et al. Benefits and limits of recent floating car data technology–an evaluation study
CN110363985B (en) Traffic data analysis method, device, storage medium and equipment
CN110164132B (en) Method and system for detecting road traffic abnormity
CN110176139A (en) A kind of congestion in road identification method for visualizing based on DBSCAN+
CN107590999B (en) Traffic state discrimination method based on checkpoint data
CN109979197B (en) Method and system for constructing highway traffic time map based on fusion data
CN110796862B (en) Highway traffic condition detection system and method based on artificial intelligence
Glick et al. Measuring the determinants of bus dwell time: New insights and potential biases
CN111445700B (en) Regional running and stopping vehicle monitoring method based on license plate identification data
CN109472985B (en) Actual traffic demand flow estimation method based on road section travel time
CN115410375A (en) Fusion traffic index set generation method based on fusion traffic data of thunder card
Kazagli et al. Arterial travel time estimation from automatic number plate recognition data
Zhang et al. Statistical analysis of the stability of bus vehicles based on GPS trajectory data
CN113420618A (en) Signal intersection standard vehicle accurate conversion method, device and system
Langer et al. An improved moving observer method for traffic flow estimation at signalized intersections
CN113593222B (en) Multi-source data supported traffic control diagnosis method
CN110853350B (en) Arterial road phase difference optimization method based on floating car track data
CN114842661A (en) Method and system for managing real-time state of indoor map passing road section
Morris et al. Real-time video based highway traffic measurement and performance monitoring

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