CN109191850B - Data fusion method of stop line detector and queuing detector based on time window - Google Patents

Data fusion method of stop line detector and queuing detector based on time window Download PDF

Info

Publication number
CN109191850B
CN109191850B CN201811227670.1A CN201811227670A CN109191850B CN 109191850 B CN109191850 B CN 109191850B CN 201811227670 A CN201811227670 A CN 201811227670A CN 109191850 B CN109191850 B CN 109191850B
Authority
CN
China
Prior art keywords
data
detector
stop line
vehicle
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.)
Expired - Fee Related
Application number
CN201811227670.1A
Other languages
Chinese (zh)
Other versions
CN109191850A (en
Inventor
王云鹏
王子睿
于海洋
任毅龙
杨阳
王飞
张力
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.)
Beihang University
Original Assignee
Beihang 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 Beihang University filed Critical Beihang University
Priority to CN201811227670.1A priority Critical patent/CN109191850B/en
Publication of CN109191850A publication Critical patent/CN109191850A/en
Application granted granted Critical
Publication of CN109191850B publication Critical patent/CN109191850B/en
Expired - Fee Related 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
    • G08G1/0133—Traffic data processing for classifying traffic situation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Traffic Control Systems (AREA)

Abstract

The patent discloses a data fusion method of a stop line detector and a queuing detector based on a time window, which comprises the following steps: step 1: acquiring data; step 2: fusing data; utilizing a time window method in the fusion process of the data, and step 3: matching of the stop line detector data with the vehicle queue detector data. The data detected by the stop line detector and the queuing detector are fused by the method, so that more accurate road information data is obtained. To estimate a more accurate traffic state. The time window method is provided, the data range of the stop line detector data which needs to be matched is narrowed, compared with the prior art, the calculated amount of data matching is reduced, the efficiency of data matching is improved, and the traffic state is acquired more quickly.

Description

Data fusion method of stop line detector and queuing detector based on time window
Technical Field
The invention relates to the field of traffic engineering, in particular to a data fusion method based on a stop line detector and a queuing detector.
Background
The acquisition of the traffic state is a precondition for effective traffic management and control, and the acquisition accuracy of important traffic parameters such as vehicle speed, traffic flow and the like on a road directly influences the identification and judgment of the traffic state. The traffic parameter acquisition mode is various, and the trackside fixed equipment gathers, bayonet socket data acquisition, modes such as surveillance video acquisition. And the roadside equipment mainly collects the data through a stop line detector, a queue detector and the like.
The stop line detector and the queuing detector are both annular coil detectors and belong to magnetic frequency detectors; based on the electromagnetic principle, when a vehicle passes through the detector, the loop inductance is changed, so that whether the vehicle exists or passes is judged. Compared with detectors such as video detectors and microwave detectors, the annular coil detector has the advantages of mature technology, easiness in installation and control, high detection precision, simple data format, convenience in data storage and the like.
Conventional intersection upstream traffic information processing is often based on analysis of data from a single detector, such as a queue detector or a stop line detector. Due to the fact that data detected by a single detector are inaccurate, data are missing, data cannot be matched and the like, the obtained traffic information is greatly different from actual traffic conditions and cannot be used, and accurate collection and processing of the traffic information are greatly influenced.
The invention adopts a data fusion method considering the stop line detector and the queuing detector, so that the data detected by the two types of detectors are complementary, and the accuracy of information extraction and data is improved. And a time window method is provided, when the data collected by the two detectors are matched, a certain matching range is defined, the data range needing to be matched is narrowed, the time required by data matching is reduced, and the data matching efficiency is improved. The acquired traffic parameters such as vehicle speed, traffic flow and the like are more accurate, and the traffic information is better reflected.
Disclosure of Invention
The invention aims to provide a data fusion method based on a stop line detector and a queuing detector, which realizes data fusion of stop line detection data at an intersection and queuing detector data before the intersection.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention relates to a data fusion method based on a stop line detector and a queuing detector, which comprises the following steps: step 1: data acquisition
Acquiring data of a stop line detector at an intersection, including time of arrival at the stop line detector and the like; acquiring data of a vehicle queue detector at an upstream of the intersection, wherein the data comprises time for reaching the parked vehicle queue detector and the like; we assume that all vehicles do not have lane changing activity on the road segment between the stop line detector and the in-line detector.
Step 2: data fusion
In the process of data fusion, a time window method is utilized, and the time window method is as follows:
the information stored by the vehicle queue detector includes the time (T) at which the vehicle has stepped on the detectoriAI vehicle) and occupancy time (t)iA) The effective vehicle length (l) was assumed in the studyeff) Is a fixed value, the effective vehicle length is the length of the vehicle and the length of the coil detector (l)D) The sum, which is generally 7.5 meters. Assuming that the maximum acceleration of braking and acceleration are both amax(ii) a The distance between the vehicle queue detector and the stop line detector is DAS(ii) a Extracting the time t for the vehicle to pass the queue detectoriAThe speed of the vehicle passing through the in-line detector can be calculated by equation 1.
Figure BDA0001836192120000021
The maximum and minimum travel times required for the vehicle to travel from the in-line detector to the stop line detector are then estimated, and a "time window" is thus determined in the stop line detector data, which is used to search for and match the data.
Calculating the maximum travel time Tmax：
Assuming that the uniform deceleration measure is taken until the vehicle completely stops near the stop line after passing through the queue detector, the calculation formula is as follows,
Figure BDA0001836192120000022
calculating the minimum travel time:
suppose a vehicle is driven with amaxThe maximum acceleration of the vehicle is calculated as follows.
Figure BDA0001836192120000023
In the formula, TmaxAnd TminRespectively, the maximum travel time and the minimum travel time required for the vehicle to travel from the in-line detector to the stop-line detector.
And step 3: matching of stop line detector data with vehicle queue detector data:
1) if a piece of time data that can be matched with the stop line detector data can be searched within the above calculated "time window", the piece of stop line detector data is directly matched with the data of the vehicle queue detector for corresponding data.
2) If a plurality of pieces of time data that can be matched with the stop line data can be searched within the calculated 'time window' is found, the ideal travel time for matching each stop line detector data is calculated using formula (4), respectively.
Figure BDA0001836192120000024
And the percentage error between the actual travel time and the ideal travel time when matching is performed is calculated by using equation (5), and the stop line detector data with the minimum error is selected as final matching data.
Figure BDA0001836192120000031
The invention has the advantages that:
(1) and fusing the data detected by the stop line detector and the queuing detector to obtain more accurate road information data. To estimate a more accurate traffic state.
(2) The time window method is provided, the data range of the stop line detector data which needs to be matched is narrowed, compared with the prior art, the calculated amount of data matching is reduced, the efficiency of data matching is improved, and the traffic state is acquired more quickly.
Drawings
In order to more clearly illustrate the technical solution to be implemented in the present invention, the drawings that are required to be used in the present invention will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that for those skilled in the art, other related drawings can be obtained from these drawings without inventive effort.
Fig. 1 shows a schematic diagram of an intersection device based on a stop line detector and a queue detector according to the invention.
FIG. 2 shows a schematic diagram of the "time window" method of the present invention.
Fig. 3 illustrates a method of matching stop line detector data and queue detector data in accordance with the present invention.
Detailed Description
The invention provides a data fusion method based on stop line detection and a vehicle queue detector, which can match and fuse data of the vehicle queue detector at the upstream of an intersection and the stop line detector at the intersection.
Specifically, the data fusion method of the stop line detector and the queue detector in the invention is as follows:
we define vehicle arrival as an event.
Step one, a vehicle queuing detector is positioned at the upstream of a signalized intersection, and the specific position is shown in figure 1; the stop line detector is positioned at a stop line of the signalized intersection, and the specific position is shown in figure 1;
the vehicle queuing detector adopts a loop coil detector, when a vehicle passes through a coil embedded position, the vehicle is positioned in an alternating magnetic field of the loop coil, and therefore induced electromotive force can be generated in the vehicle and induced current can be formed. The vehicle queuing detector can not only sense whether a vehicle passes through or not, record the time point when the vehicle reaches the queuing detector, but also calculate the time when the vehicle passes through the vehicle queuing detector.
So we extract the information stored by the vehicle queue detector including the time of arrival (T) of the vehicle at the detectoriAWhere i represents the i-th vehicle arriving at the detector) and the i-th vehicle is occupied by the vehicle in-line detectorTime of use (t)iA). And through the data collected by the vehicle queuing detector, the instantaneous speed of the vehicle passing through the vehicle queuing detector can be calculated by using a formula (1), wherein the formula is as follows:
Figure BDA0001836192120000041
in the calculation, the general length of the automobile is analyzed, the automobile length of the automobile is assumed to be a fixed value, and the length of the coil detector is lDIs also a fixed value, so the effective vehicle length is the sum of the vehicle length and the length of the coil detector, using leffIs expressed as ieff＝l+lDWhere l denotes the length of the vehicle, in practice leffTypically 7.5 meters. V obtained by calculationiAI.e. the instantaneous speed of the vehicle as it passes the vehicle detector.
Step two, a calculation method of a time window:
after calculating the instantaneous speed of the vehicle at the vehicle queue detector, it is necessary to estimate the maximum travel time and the minimum travel time required for the vehicle to travel from the queue detector to the stop line detector, and to use the difference between the maximum travel time and the minimum travel time as a "time window" to be used as a range for searching and matching data. The "time window" method is as follows:
we assume that all vehicles do not have lane change behavior on the road segment between the stop line detector and the queue detector; assuming that the maximum acceleration of braking and acceleration are both amaxThe distance between the vehicle queue detector and the stop line detector is DAS；
Calculating the maximum travel time Tmax：
Assuming that the vehicle takes uniform deceleration measures after passing through the queue detector until completely stopping near the stop line, the calculation formula is as follows:
Figure BDA0001836192120000042
calculating the minimum travel time:
suppose a vehicle is driven with amaxThe maximum acceleration of the vehicle is calculated as follows.
Figure BDA0001836192120000043
In the formula, TmaxAnd TminRespectively, the maximum travel time and the minimum travel time required for the vehicle to travel from the in-line detector to the stop-line detector. As shown in fig. 2, the maximum travel time and the minimum travel time calculated by the above formulas form a time window on the graph. The time window defines the time range of the stop line detector that needs to be matched.
Step three, matching the data of the stop line detector with the data of the vehicle queue detector:
the time of the vehicle passing through the vehicle detector detected by the stop line detector is extracted and is subjected to data matching with the calculated 'time window', so that the aim of matching the stop line detector data with the vehicle queue detector data is fulfilled. As shown in fig. 3, the matching method is as follows:
1) the time span calculated by the "time window" method described above is looked up in the stop line detector data at the corresponding time. If within the time span, only one stop line detector data is found and meets the condition, then the stop line detector data is directly matched with the data that generated the "time window" vehicle in-line detector. So as to achieve the purpose of data matching and fusion.
As shown in FIG. 3, at event A1, the predicted lines of minimum and maximum travel times are formed with a blue dashed line and time window 1 is formed. Then in the data of the stop line detector a time window 1 is spanned, within which time window there is one and only one piece of data that can be matched. The piece of data is data of event a1 arriving at the stop line detector, and the matching is successful.
2) If a plurality of pieces of time data that can be matched with the stop line data can be searched within the above calculated "time window", ideal travel times for matching of the respective stop line detector data are calculated using the following formula (4), respectively. Parking line detector data corresponding to the plurality of vehicle queue detector data is obtained and calculated by equation (5).
Figure BDA0001836192120000051
The actual travel time measured by a plurality of stop line detectors in the time window is compared with the ideal travel time by the percentage error of the ideal travel time in formula 4, and the data with the minimum error is selected as the final matching data.
Figure BDA0001836192120000052

Claims (3)

1. A method for data fusion based on a stop line detector and a queue detector, the method comprising the steps of:
step 1: data acquisition
Acquiring data of a stop line detector at an intersection, including the time of arrival at the stop line detector; acquiring data of a vehicle queue detector upstream of the intersection, including the time of arrival at the parked vehicle queue detector;
step 2: data fusion
A time window method is utilized in the fusion process of data, and the time window method comprises the following steps: first, the information stored by the vehicle queue detector includes the time T when the ith vehicle steps on the detectoriAAnd the occupied time tiASetting the effective vehicle length to leffSetting the maximum acceleration of braking and acceleration to be amax(ii) a The distance between the vehicle queue detector and the stop line detector is DAS(ii) a Extracting the time t for the vehicle to pass the queue detectoriABy the formula
Figure FDA0002363885970000011
Calculating the speed v of the vehicle passing the queue detectoriA(ii) a Then estimating the maximum travel time and minimum travel time required for the vehicle to travel from the queue detector to the stop line detector and thereby determining in the stop line detector data a "time window" to be used to search for and match the data; recalculating the maximum travel time and minimum travel time T for a vehicle to travel from a queue detector to a stop line detectormaxAnd Tmin，
Figure FDA0002363885970000012
The T ismaxAnd TminThe time between is the time window;
and step 3: matching of stop line detector data with vehicle queue detector data
When a piece of time data which can be matched with the stop line detector data can be searched in the time window calculated in the step 2, directly matching the stop line detector data with the data of the vehicle queue detector; when a plurality of pieces of time data which can be matched with the stop line data can be searched in the time window calculated in the step 2, the time window is utilized
Figure FDA0002363885970000013
Respectively calculating ideal travel time TI of each stop line detector data for matchingi，viSThe speed at which the stop line detector is stepped on for the vehicle; and use
Figure FDA0002363885970000014
Calculating the percentage error, T, of the actual travel time to the ideal travel time when matching is performediSTime to step on the stop line detector for the vehicle; the stop line detector data with the smallest error is selected as the final matching data.
2. The method of claim 1, wherein the effective vehicle length is the length of the vehicle and the length l of the coil detectorDAnd (4) summing.
3. The data fusion method based on the stop line detector and the queue detector as claimed in claim 2, wherein the effective vehicle length is 7.5 m.
CN201811227670.1A 2018-10-22 2018-10-22 Data fusion method of stop line detector and queuing detector based on time window Expired - Fee Related CN109191850B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811227670.1A CN109191850B (en) 2018-10-22 2018-10-22 Data fusion method of stop line detector and queuing detector based on time window

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811227670.1A CN109191850B (en) 2018-10-22 2018-10-22 Data fusion method of stop line detector and queuing detector based on time window

Publications (2)

Publication Number Publication Date
CN109191850A CN109191850A (en) 2019-01-11
CN109191850B true CN109191850B (en) 2020-06-05

Family

ID=64946032

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811227670.1A Expired - Fee Related CN109191850B (en) 2018-10-22 2018-10-22 Data fusion method of stop line detector and queuing detector based on time window

Country Status (1)

Country Link
CN (1) CN109191850B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114241749B (en) * 2021-11-26 2022-12-13 深圳市戴升智能科技有限公司 Video beacon data association method and system based on time sequence
CN114241776B (en) * 2021-12-31 2023-01-31 连云港杰瑞电子有限公司 Road section parking frequency dynamic estimation method based on rolling time window

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103106801A (en) * 2013-01-14 2013-05-15 上海应用技术学院 Self-organizing traffic signal coordination control method
CN104778837A (en) * 2015-04-14 2015-07-15 吉林大学 Multi-time scale forecasting method for road traffic running situation
CN107886744A (en) * 2017-11-01 2018-04-06 西南交通大学 One kind is used for subway station adjacent to intersection public transport priority signal control method
CN108492562A (en) * 2018-04-12 2018-09-04 连云港杰瑞电子有限公司 Intersection vehicles trajectory reconstruction method based on fixed point detection with the alert data fusion of electricity

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9129519B2 (en) * 2012-07-30 2015-09-08 Massachussetts Institute Of Technology System and method for providing driver behavior classification at intersections and validation on large naturalistic data sets

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103106801A (en) * 2013-01-14 2013-05-15 上海应用技术学院 Self-organizing traffic signal coordination control method
CN104778837A (en) * 2015-04-14 2015-07-15 吉林大学 Multi-time scale forecasting method for road traffic running situation
CN107886744A (en) * 2017-11-01 2018-04-06 西南交通大学 One kind is used for subway station adjacent to intersection public transport priority signal control method
CN108492562A (en) * 2018-04-12 2018-09-04 连云港杰瑞电子有限公司 Intersection vehicles trajectory reconstruction method based on fixed point detection with the alert data fusion of electricity

Also Published As

Publication number Publication date
CN109191850A (en) 2019-01-11

Similar Documents

Publication Publication Date Title
CN108806296B (en) Road traffic incident detection early warning method and detection early warning system based on vehicle-road cooperation
Li et al. Real-time queue length estimation for signalized intersections using vehicle trajectory data
CN101739824B (en) Data fusion technology-based traffic condition estimation method
US20100309022A1 (en) Driving support device, driving support method, and driving support program
CN108091137B (en) Method and device for evaluating signal lamp control scheme
CN104318770A (en) Method for detecting traffic jam state of expressway in real time based on mobile phone data
CN107590999B (en) Traffic state discrimination method based on checkpoint data
CN107146409B (en) The identification of equipment detection time exception and true time difference evaluation method in road network
CN104750963A (en) Intersection delay time estimation method and device
CN109191850B (en) Data fusion method of stop line detector and queuing detector based on time window
CN105336166A (en) Traffic characteristic parameter extraction method based on vehicle Bluetooth
US20220413005A1 (en) Method for vehicle speed estimation using multiple geomagnetic sensors
Tian et al. A vehicle re-identification algorithm based on multi-sensor correlation
CN103971516A (en) Traffic data preprocessing method and road condition detection method
CN114495520B (en) Counting method and device for vehicles, terminal and storage medium
Bhaskar et al. Estimation of travel time on urban networks with midlink sources and sinks
CN101976508A (en) Traffic signal artery phase difference optimization method based on license plate recognition data
CN104616495A (en) Bus GPS (Global Positioning System) probe vehicle based urban traffic state recognition method
CN110610118A (en) Traffic parameter acquisition method and device
US20120253648A1 (en) Apparatus and method for generating traffic information
Liu et al. Pattern recognition of vehicle types and reliability analysis of pneumatic tube test data under mixed traffic condition
CN102819957B (en) Road section queue tracing identification method based on upstream coil detector information
Brunauer et al. Deriving driver-centric travel information by mining delay patterns from single GPS trajectories
CN114674458A (en) Temperature detection method, device and system of magnetic suspension train and server
Ma et al. A new online travel time estimation approach using distorted automatic vehicle identification data

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
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20200605

Termination date: 20211022