CN111932877A - Road section traffic abnormal state identification method based on license plate data - Google Patents

Road section traffic abnormal state identification method based on license plate data Download PDF

Info

Publication number
CN111932877A
CN111932877A CN202010786823.7A CN202010786823A CN111932877A CN 111932877 A CN111932877 A CN 111932877A CN 202010786823 A CN202010786823 A CN 202010786823A CN 111932877 A CN111932877 A CN 111932877A
Authority
CN
China
Prior art keywords
time
road section
monitored
abnormal
travel time
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
CN202010786823.7A
Other languages
Chinese (zh)
Other versions
CN111932877B (en
Inventor
张雷元
张韧
华璟怡
蔡玉宝
刘成生
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.)
Traffic Management Research Institute of Ministry of Public Security
Original Assignee
Traffic Management Research Institute of Ministry of Public Security
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 Traffic Management Research Institute of Ministry of Public Security filed Critical Traffic Management Research Institute of Ministry of Public Security
Priority to CN202010786823.7A priority Critical patent/CN111932877B/en
Publication of CN111932877A publication Critical patent/CN111932877A/en
Application granted granted Critical
Publication of CN111932877B publication Critical patent/CN111932877B/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
    • 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
    • G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
    • 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

Landscapes

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

Abstract

The invention provides a road section abnormal traffic state identification method based on license plate data, which can monitor traffic states in real time, find abnormal traffic road sections in time, ensure that traffic management departments can actively and quickly deal with abnormal states, improve the instantaneity of traffic abnormal state processing and reduce the processing cost. According to the technical scheme, the travel time threshold is set, the travel time threshold of the road section to be monitored is obtained based on the contemporaneous historical data of the road section to be monitored, and whether the traffic state of the road section to be monitored in the time section to be monitored is abnormal or not is judged by comparing the current travel time in the time section to be monitored with the travel time threshold.

Description

Road section traffic abnormal state identification method based on license plate data
Technical Field
The invention relates to the technical field of intelligent traffic control, in particular to a road section traffic abnormal state identification method based on license plate data.
Background
In modern traffic control, traffic jam is often caused by various reasons such as accidents, and for road sections with traffic jam and the like, the specific case occurring road sections can be identified usually through alarming or manual patrol of a traffic police, and then police issuing processing is carried out; that is, in many conventional methods for handling traffic congestion, passive handling is performed after a certain period of time has elapsed, and there is hysteresis in handling traffic anomalies, which increases the handling cost.
Disclosure of Invention
In order to solve the problem that processing cost is increased due to hysteresis in traffic jam processing in the prior art, the invention provides the road section abnormal traffic state identification method based on the license plate data, which can monitor the traffic state in real time, find the abnormal road section in time, ensure that a traffic management department can actively and quickly handle the abnormal state, improve the real-time performance of traffic abnormal state processing and reduce the processing cost.
The technical scheme of the invention is as follows: a road section traffic abnormal state identification method based on license plate data is characterized by comprising the following steps:
s1: determining a road section to be monitored, setting the starting time TB of monitoring time, and setting the time period to be monitored as d;
determining two bayonets corresponding to adjacent intersections on the road section to be monitored, and according to the driving direction of the vehicle, respectively recording as follows: an upstream bayonet and a downstream bayonet;
s2: extracting vehicle identification data of the upstream gate and the downstream gate based on a pattern recognition technology;
s3: performing data identification and matching based on the vehicle identification data, acquiring all vehicles which sequentially pass through the upstream gate and the downstream gate in the time period to be monitored, and recording as vehicles to be analyzed;
subtracting the time T1 of the vehicle to be analyzed passing through the upstream gate from the time T2 of the vehicle to be analyzed passing through the downstream gate to obtain a time difference, and recording the time difference as a road section travel time T;
s4: acquiring the corresponding days of the week of the monitoring day in the week, and recording the days of the week as week X;
setting a historical data extraction time period: h, H days; setting the current monitoring day as a starting point, wherein n weeks X exist in the past H days;
extracting corresponding historical data from the starting time TB to the end of the time period d to be monitored from the vehicle identification historical data of each week X of the same upstream gate, and recording the historical data as T1iWherein: i is a positive integer, and i is more than or equal to 1 and less than or equal to n;
likewise, extract from the downstream bayonet T1iCorresponding vehicle identification history data, denoted as T2i；
Through Ti＝T2i-T1iAnd calculating and obtaining the historical travel time T of the road section of n weeks X in the historical data of the road section to be monitoredi；
S5: calculating the historical travel time T of the road sectioniThe corresponding average time of flight TTA and standard deviation SD are respectively marked as TTA _ h and SD _ h;
the method for calculating the mean time of flight TTA and the standard deviation SD is as follows:
Figure BDA0002622296640000011
Figure BDA0002622296640000021
s6: setting m vehicles to be analyzed on the road section to be monitored in the time period to be monitored, and calculating to obtain the road section travel time T corresponding to the vehicles to be analyzedjWherein j is a positive integer, and j is more than or equal to 1 and less than or equal to m;
based on TjCalculating the current travel time ATT of the road section to be monitored;
s7: calculating a travel time threshold UD of an abnormal delay state corresponding to the road section to be monitored according to the state of the road traffic of the road section to be monitored in different periods;
the method for calculating the travel time threshold UD of the abnormal delay state comprises the following steps:
UD＝TTA+K×SD
wherein TTA is historical contemporaneous average travel time; SD is the standard deviation of the historical travel time; k is a parameter for setting a threshold value, and the travel time threshold UD is different in value according to different values of K, so that different road traffic states are identified;
s8: comparing the actual measurement travel time in the time period to be monitored with all the travel time thresholds UD corresponding to the time period, and judging the traffic state of the time period;
i.e. comparing said current journey time ATT with said journey time threshold UD;
if the current travel time ATT does not exceed the abnormal state range identified by the travel time threshold UD, the traffic state of the road section to be monitored is a normal condition, and no alarm is given;
otherwise, sending out an early warning, wherein the traffic of the road section to be monitored enters the abnormal delay state;
s9: resetting the starting time TB of the monitoring time, circularly executing the steps S1-S9, and monitoring the traffic state of the road section to be monitored in real time.
It is further characterized in that:
the link travel time T in step S6jThe calculation method of (2) is as follows:
al, from the starting time TB to the end of the time period d to be monitored, extracting the vehicle identification data from the upstream bayonet;
a2, identifying all the vehicles to be analyzed, and sharing m vehicles to be analyzed; acquiring the time T1 for m vehicles to be analyzed to pass through the upstream gatej；
a3, taking the license plate number of the vehicle to be analyzed as a basis, extracting the vehicle identification data from the downstream gate, and obtaining the time T2 when the vehicle to be analyzed passes through the downstream gatej；
a4 by T2jMinus T1jAnd calculating and obtaining the corresponding road section travel of all the vehicles to be analyzedInter Tj；
In step S6, the method for calculating the current trip time ATT is as follows:
b 1: m of the road section travel time TjSorting according to the sequence from small to large;
b 2: taking all T within 15-85%jCalculating the average value, namely the current travel time ATT;
Figure BDA0002622296640000022
wherein p is T at the 15% position after sorting in step b1jQ is T at 85% positionjThe serial number of (2);
p and q are positive integers, and p is more than or equal to 1 and less than or equal to q and less than or equal to m;
in step S7, the abnormal delay state is subdivided according to the state of the road congestion at different times, and the travel time threshold of the abnormal delay state includes: an abnormal delay threshold UD1 and an abnormal long delay threshold UD 2; the abnormal delay threshold UD1 and the abnormal long-time delay threshold UD2 correspond to different parameters K respectively;
wherein the abnormal delay state UD1 is: the corresponding K value is 1.04 when the travel time is not more than 85% of the historical travel time;
the abnormal long-time delay state UD2 is: the corresponding K value is 1.65 when the travel time is not more than 95% of the historical travel time;
in step S8, the detailed steps include:
c 1: based on the historical travel time T of the road sectioniCalculating and obtaining the abnormal delay threshold UD1_ h and the abnormal long delay threshold UD2_ h corresponding to the road section to be monitored according to the corresponding average travel time TTA _ h and standard deviation SD _ h;
c 2: comparing the down-trip time ATT with the abnormal delay threshold UD1_ h and the abnormal long delay threshold UD2_ h;
if the ATT is less than or equal to UD1_ h, the state is normal, and no alarm is given;
if ATT > UD1_ h and ATT < UD2_ h, an early warning is given: the traffic of the road section to be monitored enters the abnormal delay state;
if ATT ≧ UD2_ h, a warning is issued: the traffic of the road section to be monitored enters the abnormal long-time delay state;
in step S4, H takes a value of 30 days;
and the value of the time period d to be monitored is 5 minutes.
The invention provides a road section traffic abnormal state identification method based on license plate data, which comprises the steps of setting a travel time threshold UD, obtaining the travel time threshold UD of a road section to be monitored based on contemporaneous historical data of the road section to be monitored, and judging whether the traffic state of the road section to be monitored in a time section to be monitored is abnormal or not by comparing current travel time ATT in the time section to be monitored with the travel time threshold, so that the technical scheme of the invention is ensured to realize real-time monitoring of the road section to be monitored by referring to the historical data and alarm the abnormal traffic state in real time; in the technical scheme of the invention, the judgment of the traffic state is based on objective data instead of artificial subjective judgment, so that the accuracy of the judgment result is ensured; based on the technical scheme of the invention, the road section to be monitored can be monitored in real time in a full-automatic and uninterrupted manner, the result is objective and accurate, the manpower is saved, and the cost of monitoring the traffic state is reduced; meanwhile, the travel time threshold UD is subdivided into different time thresholds according to different traffic states, and different warning information is provided for the traffic management department aiming at the different time thresholds, so that the traffic management department can clearly control the traffic state of the road section to be monitored.
Drawings
Fig. 1 is a schematic diagram of the probability distribution of travel time in the technical solution of the present invention.
Detailed Description
The invention relates to a road section traffic abnormal state identification method based on license plate data, which comprises the following steps.
S1: determining a road section to be monitored, setting the starting time TB of monitoring time, and setting the time period to be monitored as d, wherein the value of the time period to be monitored d is 5 minutes in the embodiment; the time period d to be monitored does not need to be over-small, the over-small value can cause large calculation amount, and a traffic state is not instant time and is bound to have a generation process; however, the interval cannot be too long, and the alarm instantaneity is insufficient due to the too long interval, so that the interval is set to be 5 minutes in the embodiment, the instantaneity can be ensured, and the calculation amount can be properly reduced;
determining two bayonets corresponding to adjacent intersections on a road section to be monitored, and recording the two bayonets as follows according to the driving direction of the vehicle: an upstream bayonet and a downstream bayonet.
Taking a certain road section in a certain city as an example, the starting time TB is 8:10 am, and the monitoring day is 2019, 12 and 2 months (tuesday), that is, the monitoring time period is 8:10-8: 15.
S2: based on a pattern recognition technology, vehicle recognition data of an upstream gate and a downstream gate are extracted; the existing high-definition bayonet system for road traffic monitoring adopts advanced photoelectric technology, image processing technology and pattern recognition technology to take images of each passing automobile, automatically recognizes license plates of the automobiles, and stores the acquired information data of the automobiles as automobile recognition data in a server database; the data is sufficient to support the data requirements of the technical scheme of the invention.
S3: based on a pattern recognition technology, carrying out data recognition and matching based on vehicle recognition data, acquiring all vehicles which sequentially pass through an upstream gate and a downstream gate in a time period to be monitored, and recording as vehicles to be analyzed;
subtracting the time T1 of the vehicle to be analyzed passing through the upstream gate from the time T2 of the vehicle to be analyzed passing through the downstream gate to obtain a time difference, and recording the time difference as the travel time T of the road section; in this embodiment, the detailed content of the road section travel time T of the vehicle to be analyzed is finally obtained, as shown in table 1 below:
table 1: vehicle and road section travel time to be analyzed
Serial number Vehicle number Passing upstream bayonet time Passing downstream bayonet time Road travel time (seconds)
1 83S22 8:14:10 8:14:54 44
2 5500M 8:12:44 8:13:31 47
3 3320C 8:12:39 8:13:32 53
4 5995N 8:11:38 8:12:41 63
5 MN039 8:13:50 8:14:53 63
6 XN662 8:10:40 8:11:45 65
7 FS001 8:13:45 8:14:50 65
8 GM693 8:10:36 8:11:43 67
9 G3151 8:13:12 8:14:19 67
10 56G98 8:13:06 8:14:14 68
11 50120 8:13:39 8:14:49 70
12 7168Q 8:13:04 8:14:15 71
13 GY630 8:11:15 8:12:29 74
14 93M88 8:11:30 8:12:48 78
15 GW937 8:10:24 8:11:43 79
S4: acquiring the corresponding days of the week of the monitoring day in the week, and recording the days of the week as week X;
setting a historical data extraction time period: h, in the example, the value of H is 30 days; setting the current day as a starting point, wherein n weeks X exist in the past H days;
in the vehicle identification history data of each week X of the same upstream gate, the corresponding history data (past upstream gate time) from the start time TB to the end of the time period d to be monitored is extracted and is marked as T1iWherein: i is a positive integer and is not less than 1≤n；
Similarly, extract from downstream bayonet T1iThe corresponding vehicle identification history data (past downstream gate time), denoted as T2i；
Through Ti＝T2i-T1iCalculating and obtaining the historical travel time T of the road section of n weeks X in the historical data of the road section to be monitoredi；
For the collection of historical data, different working days, rest days and different time periods need to be distinguished, because the traffic conditions of the different working days, rest days and time periods of each day in the same week have the unique representativeness; the technical scheme of the invention obtains and judges historical travel time T of the historical data road sectioniAnd in time, the data acquisition time is strictly distinguished, so that the final judgment result is ensured to be in accordance with the real road condition of the road section to be detected, and the judgment result is ensured to be real and usable.
In the present embodiment, the link historical travel time T in the same time period (8:10-8:15) every Tuesday in the past 30 is calculated for a certain linkiAs shown in table 2 for historical travel time for the link:
table 2: historical travel time of road segment
Serial number Date Time period Historical travel time (seconds) of road section
1 2019.10.29 8:10—8:15 51.00
2 2019.11.5 8:10—8:15 52.00
3 2019.11.12 8:10—8:15 64.00
4 2019.11.19 8:10—8:15 58.00
5 2019.11.26 8:10—8:15 63.00
S5: calculating the historical travel time T of the road sectioniThe corresponding average time of flight TTA and standard deviation SD are respectively marked as TTA _ h and SD _ h;
the method for calculating the mean time of flight TTA and the standard deviation SD comprises the following steps:
Figure BDA0002622296640000051
Figure BDA0002622296640000052
in this embodiment, the calculation is performed based on the data in table 2:
Figure BDA0002622296640000053
Figure BDA0002622296640000054
s6: setting m vehicles to be analyzed on the road section to be monitored in the time period to be monitored, and calculating to obtain the road section travel time T corresponding to the vehicles to be analyzedjWherein j is a positive integer, and j is more than or equal to 1 and less than or equal to m;
road section travel time TjThe calculation method of (2) is as follows:
al, extracting vehicle identification data from an upstream bayonet from the start time TB to the end of the time period d to be monitored;
a2, identifying all vehicles to be analyzed, wherein m vehicles to be analyzed are the same; obtaining the time T1 for m vehicles to be analyzed to pass through an upstream gatej；
a3, based on the license plate number of the vehicle to be analyzed, extracting the vehicle identification data from the downstream gate to obtain the time T2 when the vehicle to be analyzed passes through the downstream gatej；
a4 by T2jMinus T1jCalculating and obtaining the corresponding road section travel time T of all the vehicles to be analyzedj；
Based on TjCalculating the current travel time ATT of the road section to be monitored; the method for calculating the next trip time ATT is as follows:
b 1: the travel time T of the m road sectionsjSorting according to the sequence from small to large;
b 2: taking all T within 15-85%jThe average value is calculated as the current travel time ATT.
Figure BDA0002622296640000061
Wherein p is T at the 15% position after sorting in step b1jQ is T at 85% positionjThe serial number of (2);
p and q are positive integers, and p is more than or equal to 1 and less than or equal to q and less than or equal to m;
in this case, based on table 1, it can be seen that all the link travel times T within 15% to 85% of the bitjComprises the following steps: p is 3, q is 13;
then:
Figure BDA0002622296640000062
s7: as shown in the travel time probability distribution diagram of fig. 1, the abscissa is the travel time TT, and the ordinate is the probability P; the probability P represents a probability that the travel time TT is in different intervals, which is obtained after statistics according to historical data; according to the graph, the travel time of the road section to be monitored accords with the normal distribution rule;
calculating a travel time threshold UD of an abnormal delay state corresponding to the road section to be monitored according to the state of the road traffic of the road section to be monitored in different periods;
the method for calculating the travel time threshold UD of the abnormal delay state comprises the following steps:
UD＝TTA+K×SD
wherein TTA is historical contemporaneous average travel time; SD is the standard deviation of the historical travel time; k is a parameter for setting a threshold value, and the values of the travel time threshold UD are different according to the difference of the values of K, so that different road traffic states are identified;
subdividing the abnormal delay state according to the states of the road blockage in different periods, wherein in the embodiment, the travel time threshold of the abnormal delay state comprises: an abnormal delay threshold UD1 and an abnormal long delay threshold UD 2; the abnormal delay threshold UD1 and the abnormal long-time delay threshold UD2 correspond to different parameters K respectively;
the abnormal delay state UD1 is: the corresponding K value is 1.04 when the travel time is not more than 85% of the historical travel time;
the abnormal long delay state UD2 is: the corresponding K value is 1.65 when the travel time is not more than 95% of the historical travel time.
S8: comparing the actual measurement travel time in the time period to be monitored with all travel time thresholds UD corresponding to the time period, and judging the traffic state of the time period;
that is, the current travel time ATT is compared to the travel time threshold UD;
if the current travel time ATT does not exceed the abnormal state range identified by the travel time threshold UD, the traffic state of the road section to be monitored is a normal state, and no alarm is given;
otherwise, sending out early warning, and enabling the traffic of the road section to be monitored to enter an abnormal delay state;
the detailed steps of judgment and early warning comprise:
c 1: based on historical travel time T of road sectioniCalculating corresponding average travel time TTA _ h and standard deviation SD _ h to obtain an abnormal delay threshold UD1_ h and an abnormal long delay threshold UD2_ h corresponding to the road section to be monitored;
in this embodiment, the abnormal delay threshold UD1_ h and the abnormal long delay threshold UD2_ h are calculated as follows:
UD1_h＝TTA_h+1.04×SD_h＝57.60+1.04×6.02＝63.70(s)
UD2_h＝TTA_h+1.65×SD_h＝57.60+1.65×6.02＝67.53(s)
c 2: comparing the down travel time ATT with an abnormal delay threshold UD1_ h and an abnormal long delay threshold UD2_ h;
if the ATT is less than or equal to UD1_ h, the state is normal, and no alarm is given;
if ATT > UD1_ h and ATT < UD2_ h, an early warning is given: the traffic of the road section to be monitored enters an abnormal delay state;
if ATT ≧ UD2_ h, a warning is issued: the traffic of the road section to be monitored enters an abnormal long-time delay state;
in this embodiment, ATT is 66(s), UD1_ h is 63.70(s), and UD2_ h is 67.53(s), and the comparison results are:
ATT > UD1_ h, and ATT < UD2_ h, i.e., issue an early warning: the traffic of the road section to be monitored enters an abnormal delay state;
the travel time threshold UD is set according to historical data and is obtained through statistical calculation, and is not a fixed value; along with the change of the monitoring time, the related historical data acquisition time also changes, the travel time threshold UD is ensured to be a numerical value which accords with the latest state of the road section to be monitored, and the judgment of the traffic state of the road section to be detected is ensured to be in accordance with the latest real-time state of the road section to be detected.
S9: resetting the starting time TB of the monitoring time, circularly executing the steps S1-S9, and monitoring the traffic state of the road section to be monitored in real time;
according to the technical scheme, after the initial starting time TB and the time period d to be monitored are set at the current time in real time, TB + d can be set as the starting time of the next detection, meanwhile, the date (week X) is corrected and adjusted in real time based on the system clock, the historical data is obtained by combining the real-time date, the steps S1-S9 are circularly implemented, the road section to be monitored can be monitored uninterruptedly in real time, and the abnormal traffic state is alarmed in real time.

Claims (7)

1. A road section traffic abnormal state identification method based on license plate data is characterized by comprising the following steps:
s1: determining a road section to be monitored, setting the starting time TB of monitoring time, and setting the time period to be monitored as d;
determining two bayonets corresponding to adjacent intersections on the road section to be monitored, and according to the driving direction of the vehicle, respectively recording as follows: an upstream bayonet and a downstream bayonet;
s2: extracting vehicle identification data of the upstream gate and the downstream gate based on a pattern recognition technology;
s3: performing data identification and matching based on the vehicle identification data, acquiring all vehicles which sequentially pass through the upstream gate and the downstream gate in the time period to be monitored, and recording as vehicles to be analyzed;
subtracting the time T1 of the vehicle to be analyzed passing through the upstream gate from the time T2 of the vehicle to be analyzed passing through the downstream gate to obtain a time difference, and recording the time difference as a road section travel time T;
s4: acquiring the corresponding days of the week of the monitoring day in the week, and recording the days of the week as week X;
setting a historical data extraction time period: h, H days; setting the current monitoring day as a starting point, wherein n weeks X exist in the past H days;
extracting corresponding historical data from the starting time TB to the end of the time period d to be monitored from the vehicle identification historical data of each week X of the same upstream gate, and recording the historical data as T1iWherein: i is a positive integer, and i is more than or equal to 1 and less than or equal to n;
likewise, extract from the downstream bayonet T1iCorresponding vehicle identification history data, denoted as T2i；
Through Ti＝T2i-T1iAnd calculating and obtaining the historical travel time T of the road section of n weeks X in the historical data of the road section to be monitoredi；
S5: calculating the historical travel time T of the road sectioniThe corresponding average time of flight TTA and standard deviation SD are respectively marked as TTA _ h and SD _ h;
the method for calculating the mean time of flight TTA and the standard deviation SD is as follows:
Figure FDA0002622296630000011
Figure FDA0002622296630000012
s6: setting m vehicles to be analyzed on the road section to be monitored in the time period to be monitored, and calculating to obtain the road section travel time T corresponding to the vehicles to be analyzedjWherein j is a positive integer, and j is more than or equal to 1 and less than or equal to m;
based on TjCalculating the current travel time ATT of the road section to be monitored;
s7: calculating a travel time threshold UD of an abnormal delay state corresponding to the road section to be monitored according to the state of the road traffic of the road section to be monitored in different periods;
the method for calculating the travel time threshold UD of the abnormal delay state comprises the following steps:
UD＝TTA+K×SD
wherein TTA is historical contemporaneous average travel time; SD is the standard deviation of the historical travel time; k is a parameter for setting a threshold value, and the travel time threshold UD is different in value according to different values of K, so that different road traffic states are identified;
s8: comparing the actual measurement travel time in the time period to be monitored with all the travel time thresholds UD corresponding to the time period, and judging the traffic state of the time period;
i.e. comparing said current journey time ATT with said journey time threshold UD;
if the current travel time ATT does not exceed the abnormal state range identified by the travel time threshold UD, the traffic state of the road section to be monitored is a normal condition, and no alarm is given;
otherwise, sending out an early warning, wherein the traffic of the road section to be monitored enters the abnormal delay state;
s9: resetting the starting time TB of the monitoring time, circularly executing the steps S1-S9, and monitoring the traffic state of the road section to be monitored in real time.
2. The method for recognizing the abnormal traffic state of the road section based on the license plate data as claimed in claim 1, wherein the method comprises the following steps: the link travel time T in step S6jThe calculation method of (2) is as follows:
al, from the starting time TB to the end of the time period d to be monitored, extracting the vehicle identification data from the upstream bayonet;
a2, identifying all the vehicles to be analyzed, and sharing m vehicles to be analyzed; acquiring the time T1 for m vehicles to be analyzed to pass through the upstream gatej；
a3, taking the license plate number of the vehicle to be analyzed as a basis, extracting the vehicle identification data from the downstream gate, and obtaining the time T2 when the vehicle to be analyzed passes through the downstream gatej；
a4 by T2jMinus T1jCalculating and obtaining all the corresponding stations of the vehicles to be analyzedSaid section travel time Tj。
3. The method for recognizing the abnormal traffic state of the road section based on the license plate data as claimed in claim 1, wherein the method comprises the following steps: in step S6, the method for calculating the current trip time ATT is as follows:
b 1: m of the road section travel time TjSorting according to the sequence from small to large;
b 2: taking all T within 15-85%jCalculating the average value, namely the current travel time ATT;
Figure FDA0002622296630000021
wherein p is T at the 15% position after sorting in step b1jQ is T at 85% positionjThe serial number of (2);
p and q are positive integers, and p is more than or equal to 1 and less than or equal to q and less than or equal to m.
4. The method for recognizing the abnormal traffic state of the road section based on the license plate data as claimed in claim 1, wherein the method comprises the following steps: in step S7, the abnormal delay state is subdivided according to the state of the road congestion at different times, and the travel time threshold of the abnormal delay state includes: an abnormal delay threshold UD1 and an abnormal long delay threshold UD 2; the abnormal delay threshold UD1 and the abnormal long-time delay threshold UD2 correspond to different parameters K respectively;
wherein the abnormal delay state UD1 is: the corresponding K value is 1.04 when the travel time is not more than 85% of the historical travel time;
the abnormal long-time delay state UD2 is: the corresponding K value is 1.65 when the travel time is not more than 95% of the historical travel time.
5. The method for recognizing the abnormal traffic state of the road section based on the license plate data as claimed in claim 1, wherein the method comprises the following steps: in step S8, the detailed steps include:
c 1: based on the historical travel time T of the road sectioniCalculating and obtaining the abnormal delay threshold UD1_ h and the abnormal long delay threshold UD2_ h corresponding to the road section to be monitored according to the corresponding average travel time TTA _ h and standard deviation SD _ h;
c 2: comparing the down-trip time ATT with the abnormal delay threshold UD1_ h and the abnormal long delay threshold UD2_ h;
if the ATT is less than or equal to UD1_ h, the state is normal, and no alarm is given;
if ATT > UD1_ h and ATT < UD2_ h, an early warning is given: the traffic of the road section to be monitored enters the abnormal delay state;
if ATT ≧ UD2_ h, a warning is issued: and the traffic of the road section to be monitored enters the abnormal long-time delay state.
6. The method for recognizing the abnormal traffic state of the road section based on the license plate data as claimed in claim 1, wherein the method comprises the following steps: in step S4, H takes 30 days.
7. The method for recognizing the abnormal traffic state of the road section based on the license plate data as claimed in claim 1, wherein the method comprises the following steps: and the value of the time period d to be monitored is 5 minutes.
CN202010786823.7A 2020-08-07 2020-08-07 Road section traffic abnormal state identification method based on license plate data Active CN111932877B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010786823.7A CN111932877B (en) 2020-08-07 2020-08-07 Road section traffic abnormal state identification method based on license plate data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010786823.7A CN111932877B (en) 2020-08-07 2020-08-07 Road section traffic abnormal state identification method based on license plate data

Publications (2)

Publication Number Publication Date
CN111932877A true CN111932877A (en) 2020-11-13
CN111932877B CN111932877B (en) 2022-06-17

Family

ID=73306907

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010786823.7A Active CN111932877B (en) 2020-08-07 2020-08-07 Road section traffic abnormal state identification method based on license plate data

Country Status (1)

Country Link
CN (1) CN111932877B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113256967A (en) * 2021-04-25 2021-08-13 广州方纬智慧大脑研究开发有限公司 Road traffic incident detection method, device and medium based on checkpoint data

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107146409A (en) * 2017-06-01 2017-09-08 东方网力科技股份有限公司 The abnormal identification of equipment detection time and true time difference evaluation method in road network
CN108335482A (en) * 2017-01-20 2018-07-27 亚信蓝涛（江苏）数据科技有限公司 A kind of urban transportation Situation Awareness method and method for visualizing
CN108346292A (en) * 2018-04-17 2018-07-31 吉林大学 City expressway real-time traffic index calculation method based on bayonet data
CN109035772A (en) * 2018-08-08 2018-12-18 上海工程技术大学 The recognition methods of freeway traffic operation situation and device based on charge data
CN110363985A (en) * 2019-06-27 2019-10-22 北京易华录信息技术股份有限公司 A kind of traffic data analyzing method, apparatus, storage medium and equipment

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108335482A (en) * 2017-01-20 2018-07-27 亚信蓝涛（江苏）数据科技有限公司 A kind of urban transportation Situation Awareness method and method for visualizing
CN107146409A (en) * 2017-06-01 2017-09-08 东方网力科技股份有限公司 The abnormal identification of equipment detection time and true time difference evaluation method in road network
CN108346292A (en) * 2018-04-17 2018-07-31 吉林大学 City expressway real-time traffic index calculation method based on bayonet data
CN109035772A (en) * 2018-08-08 2018-12-18 上海工程技术大学 The recognition methods of freeway traffic operation situation and device based on charge data
CN110363985A (en) * 2019-06-27 2019-10-22 北京易华录信息技术股份有限公司 A kind of traffic data analyzing method, apparatus, storage medium and equipment

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113256967A (en) * 2021-04-25 2021-08-13 广州方纬智慧大脑研究开发有限公司 Road traffic incident detection method, device and medium based on checkpoint data

Also Published As

Publication number Publication date
CN111932877B (en) 2022-06-17

Similar Documents

Publication Publication Date Title
CN106846801B (en) Method for detecting abnormal behavior of regional loitering based on vehicle track
CN107798876B (en) Road traffic abnormal jam judging method based on event
CN106887137B (en) Congestion event prompting method and device
WO2011060727A1 (en) Road traffic condition predicting method and device thereof
CN105336162B (en) The method for early warning and early warning system of vehicle abnormality aggregation
CN103258430A (en) Road traveling time calculating and traffic road condition judging method and road traveling time calculating and traffic road condition judging device
CN109360415B (en) Road traffic flow abnormal data identification method
CN110942640B (en) Method for actively discovering suspect vehicle illegally engaged in network car booking passenger transportation
CN110288823B (en) Traffic violation misjudgment identification method based on naive Bayesian network
US20220383738A1 (en) Method for short-term traffic risk prediction of road sections using roadside observation data
CN102426783B (en) Low flow road traffic incident detection method based on vehicle tracking
CN109979193B (en) Data anomaly diagnosis method based on Markov model
CN113269042B (en) Intelligent traffic management method and system based on driving vehicle violation identification
CN111754786A (en) System for identifying traffic vehicle passing events on highway
CN111932877B (en) Road section traffic abnormal state identification method based on license plate data
CN108681717B (en) Quality detection method for urban traffic video detection equipment
CN116994428A (en) Intersection entrance road traffic accident identification method based on parameter change rate
CN106910334B (en) Method and device for predicting road section conditions based on big data
CN109887285B (en) Method and device for determining parking reason
CN109190924B (en) Video number plate data quality analysis method
CN110060370B (en) Equivalent statistical method for times of rapid acceleration and rapid deceleration of vehicle
CN114550459A (en) Method for accurately predicting bus arrival based on big data and dynamic multidimensional
CN113112803A (en) Urban traffic road traffic flow data acquisition and analysis processing system based on video monitoring
Sese et al. Cloud based Detection and Real-Time Communication of Number Coding Violators through Character Recognition and Image Processing
CN110619745B (en) Data processing method and device for preventing traffic jam

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