WO2022152026A1 - 交通拥堵检测方法、装置、电子设备及存储介质 - Google Patents

交通拥堵检测方法、装置、电子设备及存储介质 Download PDF

Info

Publication number
WO2022152026A1
WO2022152026A1 PCT/CN2022/070351 CN2022070351W WO2022152026A1 WO 2022152026 A1 WO2022152026 A1 WO 2022152026A1 CN 2022070351 W CN2022070351 W CN 2022070351W WO 2022152026 A1 WO2022152026 A1 WO 2022152026A1
Authority
WO
WIPO (PCT)
Prior art keywords
congestion
rsu
road
speed
vehicle
Prior art date
Application number
PCT/CN2022/070351
Other languages
English (en)
French (fr)
Inventor
于宏全
安毅生
黄伟
刘明凤
郭红星
王超
赵振兴
朱晨星
杨志强
Original Assignee
中兴通讯股份有限公司
长安大学
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 中兴通讯股份有限公司, 长安大学 filed Critical 中兴通讯股份有限公司
Priority to JP2023512766A priority Critical patent/JP7576162B2/ja
Priority to EP22738907.9A priority patent/EP4235617A4/en
Priority to US18/038,974 priority patent/US20240005782A1/en
Priority to KR1020227033008A priority patent/KR102800850B1/ko
Publication of WO2022152026A1 publication Critical patent/WO2022152026A1/zh

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
    • G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
    • G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0133—Traffic data processing for classifying traffic situation
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed

Definitions

  • the embodiments of the present application relate to the field of communication technologies, and in particular, to a traffic congestion detection method, device, electronic device, and storage medium.
  • V2V vehicle-to-vehicle
  • V2I Vehicle to Infrastructure
  • V2P Vehicle to People
  • V2C Vehicle to Center
  • Interconnection realizing communication and roaming between vehicle ad hoc networks and various heterogeneous networks, ensuring real-time and serviceability in terms of function and performance, so as to realize vehicle motion control, thereby realizing vehicle motion control and traffic signal control.
  • traffic information processing technology Among them, V2V refers to the interconnection between traffic participants, and V2I refers to the interconnection between traffic participants and transportation infrastructure.
  • traffic congestion has become a common problem faced by major cities.
  • V2V technology is usually used to collect traffic data to detect traffic congestion.
  • An embodiment of the present application provides a traffic congestion detection method, which is applied to a roadside unit, including: acquiring vehicle information of each vehicle entering the RSU detection area of the roadside unit; calculating a first congestion index according to the vehicle information; wherein the first The congestion index is used to represent the traffic congestion in the RSU detection area; multiple first congestion indices of each RSU in the target area are obtained; wherein, the target area includes a plurality of the RSU detection areas; calculated according to the multiple first congestion indices The second congestion index; wherein, the second congestion index is used to represent the traffic congestion in the target area.
  • the embodiment of the present application also provides a traffic congestion detection device, including: a first acquisition module, used to acquire vehicle information of each vehicle entering the RSU detection area of the roadside unit; a first calculation module, used to calculate according to the vehicle information a first congestion index; wherein, the first congestion index is used to indicate traffic congestion in the RSU detection area; a second acquisition module is used to acquire multiple first congestion indexes of each RSU in the target area; wherein the target area includes a plurality of the RSU detection areas; a second calculation module configured to calculate a second congestion index according to a plurality of first congestion indices; wherein, the second congestion index is used to represent the traffic congestion in the target area.
  • a traffic congestion detection device including: a first acquisition module, used to acquire vehicle information of each vehicle entering the RSU detection area of the roadside unit; a first calculation module, used to calculate according to the vehicle information a first congestion index; wherein, the first congestion index is used to indicate traffic congestion in the RSU detection area; a second acquisition module is used to acquire
  • An embodiment of the present application further provides an electronic device, comprising: at least one processor; and a memory connected in communication with the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor.
  • the processors execute to enable at least one processor to execute the traffic congestion detection method as described above.
  • Embodiments of the present application further provide a computer-readable storage medium storing a computer program, and when the computer program is executed, the above-mentioned traffic congestion detection method is implemented.
  • FIG. 1 is a flowchart of a method for detecting traffic congestion according to a first embodiment of the present application
  • FIG. 2 is a schematic diagram of a road network structure in an application scenario of the traffic congestion detection method according to the first embodiment of the present application;
  • FIG. 3 is a flow chart of calculating a first congestion index according to a second embodiment of the present application.
  • FIG. 4 is a function image of the membership function of the average speed of the road section according to the second embodiment of the present application.
  • FIG. 6 is a flow chart of calculating a second congestion index according to the second embodiment of the present application.
  • FIG. 7 is a flowchart of a traffic congestion detection method according to a third embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of a traffic congestion detection device according to a fourth embodiment of the present application.
  • FIG. 9 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present application.
  • the main purpose of the embodiments of the present application is to provide a traffic congestion detection method, device, electronic device, and storage medium, so as to improve the calculation efficiency and stability of traffic data, thereby improving the reliability of traffic congestion level detection results.
  • the traffic congestion detection method proposed in this application is based on the V2I vehicle networking mode, obtains vehicle information in the detection area through the roadside unit, calculates the congestion index in the detection area and uploads the congestion index, and passes through multiple roads in the target area.
  • the congestion index calculated by the side unit calculates the congestion index of the target area to evaluate the traffic congestion in the target area, and does not depend on the information transmission between each traffic participant, so that stable and reliable traffic congestion detection results can be obtained.
  • the first embodiment of the present application relates to a traffic congestion detection method.
  • the specific process is shown in FIG. 1 , including: acquiring vehicle information of each vehicle entering the RSU detection area; calculating a first congestion index according to the vehicle information; wherein, the first The congestion index is used to indicate the traffic congestion in the RSU detection area; obtain multiple first congestion indices of each RSU in the target area; wherein, the target area includes multiple RSU detection areas; calculate the second congestion index according to the multiple first congestion indices A congestion index; wherein, the second congestion index is used to represent the traffic congestion in the target area.
  • the congestion index of the target area is calculated through the congestion index calculated by multiple roadside units in the target area to evaluate the traffic congestion in the target area, which does not depend on the information transmission between various traffic participants, so that stable and reliable traffic can be obtained. Congestion detection results.
  • the executive body in this embodiment is the roadside unit RSU, which is installed on the roadside and communicates with the on-board equipment installed on the vehicle running on the road, that is, the on-board unit OBU, to realize the function of vehicle information exchange.
  • the method flow in this embodiment is shown in Figure 1, and specifically includes:
  • Step 101 Obtain vehicle information of each vehicle entering the RSU detection area.
  • a target area containing multiple road sections in the area is used as the detection object of traffic congestion, and the road sections in the target area are fully covered by the detection area of one or more roadside units.
  • the distance between any two roadside units is set within 200m.
  • the vehicle information mainly includes speed information and the current position, where the speed information may specifically include the instantaneous speed of the vehicle to which the in-vehicle device belongs.
  • the roadside unit saves all vehicle information within the cycle time for subsequent calculation of the congestion index.
  • the communication process of the Internet of Vehicles is that the roadside unit on the road section collects the message sent by the OBU (On Board Unit), and the roadside unit accesses the core wireless network through broadband wireless, mobile base station, satellite and other communication methods , the core wireless network is connected to the Internet to communicate with the intelligent transportation system.
  • OBU On Board Unit
  • Step 102 Calculate a first congestion index according to vehicle information.
  • the roadside unit determines the road section covered by the detection area according to the pre-entered traffic road network data, and then determines the average speed and density of the road section covered by the RSU detection area according to the speed information and position information of each vehicle.
  • the first congestion index is determined according to the average speed of the road section and the average density of the road section. That is, the vehicle information is preliminarily processed, and the average speed of a road section and the average density of the road section in the detection area are calculated from the speed and position information of the vehicle, and then the first congestion index is determined according to the average speed of the road section and the average density of the road section.
  • the average speed of the road section is calculated from the instantaneous speed uploaded by the on-board unit, and the average density of the road section is obtained by the roadside unit using the position information uploaded by the on-board unit to determine the road section where the vehicle is located, and then count the number of vehicles in the road section.
  • the road network structure in the target area is shown in Figure 2.
  • the on-board unit reports its speed and position information to the roadside unit of the road section every second.
  • the time required to pass through the roadside unit detection area is about 36 seconds.
  • the average speed of the vehicle in a period of time is calculated, and the instantaneous speed data The number of samples should not be too small. The greater the number of data, the longer the time period is required.
  • the time period for the vehicle to pass through the detection area is the time period for the roadside unit to calculate the congestion index in this area.
  • the shorter the period the higher the efficiency of the roadside unit.
  • the period is set to 30 seconds, that is, the roadside unit calculates a congestion index in this area every 30s.
  • the roadside unit calculates the average speed v r of the lane r in a time period, and the calculation formula is as follows:
  • the roadside unit calculates the average speed v ave of a certain road section in a time period, and the calculation formula is as follows:
  • the roadside unit calculates the vehicle density in lane r at t second Calculated as follows:
  • l is the total length of the vehicle on lane r in the t second, that is, the distance between the two vehicles closest to the detection edge at both ends of the roadside unit, including the vehicle lengths of the two vehicles.
  • the roadside unit calculates the average density ⁇ r of the lane r in a time period, and the calculation formula is as follows:
  • the roadside unit calculates the average density ⁇ ave of a certain road section in a time period, and the calculation formula is as follows:
  • the first congestion index that is, the congestion index determined according to the average speed of the road section and the average density of the road section
  • different weight indices may be allocated to different road sections according to the road network structure, for example, to the main road. Higher weights and assigning lower weights to secondary roads improve a more accurate measure of overall congestion across all road segments in the area.
  • Step 103 Obtain a plurality of first congestion indices uploaded by each RSU in the target area.
  • the traffic congestion in the target area is used as the object of traffic congestion detection.
  • the target area includes multiple RSU detection areas, that is, the target area covers multiple road sections.
  • the intelligent transportation system will Calculate and upload the first congestion index for statistics, and analyze multiple first congestion indexes according to the road network structure, determine the data fusion center, and calculate the second congestion index.
  • the main road section that is, the roadside unit at the center of the road section with the largest traffic flow, is usually used as the data fusion center.
  • the first congestion index reported by other roadside units in the target area is obtained through the intelligent transportation system.
  • Step 104 Calculate a second congestion index according to the plurality of first congestion indices.
  • the roadside unit determined as the data fusion center obtains the first congestion indices reported by multiple roadside units in the target area, it performs statistical calculation on all the first congestion indices. Since the first congestion index is a parameter representing the congestion in the detection area of a single roadside unit, the congestion in the multiple detection areas can be statistically analyzed to obtain the congestion in the target area composed of multiple detection areas. This implementation In the example, the congestion situation of the target area is represented by the second congestion index.
  • the vehicle information in the detection area is acquired by the roadside unit, the congestion index in the detection area is calculated and the congestion index is uploaded, and then the traffic congestion calculated by the multiple roadside units in the target area is calculated.
  • the index calculates the congestion index of the target area to evaluate the traffic congestion in the target area, so as to obtain stable and reliable traffic congestion detection results.
  • the second embodiment of the present application relates to a traffic congestion detection method.
  • the second embodiment is substantially the same as the first embodiment, with the main difference being that: in the second embodiment, the first congestion index and the second congestion index are both based on DS Evidence theory and fuzzy set theory are calculated.
  • the process of calculating the first congestion index in the traffic congestion detection method in this embodiment is shown in FIG. 3 , including:
  • Step 301 Calculate the average speed and density of road sections in the RSU detection area.
  • the same calculation method as in the first embodiment can be used to determine the average speed of the road section and the average density of the road section, which will not be repeated here.
  • Step 302 based on the DS evidence theory and the fuzzy set theory, generate a basic probability distribution function about the average speed of the road segment and the average density of the road segment.
  • the average speed v ave and the average density ⁇ ave of the road section are matched with the corresponding membership functions respectively, and two sets of information about the speed and density are generated.
  • the basic probability distribution function BPA of the attribute is denoted as m v and m ⁇ , respectively.
  • the two attribute characteristic values of the road congestion index the average speed v ave and the average density ⁇ ave of the road and the membership function, generate two groups of basic probability distribution functions BPA about the speed and density attributes, which are respectively recorded as m v and m ⁇ .
  • BPA basic probability distribution functions
  • the degree of matching between the density attribute and proposition G is:
  • G can represent a single subset proposition or a multiple subset proposition. If the sum of the reliability values of the generated BPA is greater than 1, it is normalized; if the sum is less than 1, the redundant reliability is assigned to the complete set, that is, to the unknown.
  • Congestion index set ⁇ ⁇ I, II, III, IV ⁇ ;
  • the congestion index I indicates smooth flow, and the qualitative description of the citizens' feelings is: there are few cars on the road, and there is no obstruction; The qualitative description of citizens' feelings is: there is some congestion, but it is not serious; the congestion index IV indicates moderate congestion, and the qualitative description of citizens' feelings is: more serious congestion.
  • the membership function is shown in FIG. 4 and FIG. 5 .
  • the value of 0.1334 is the degree of confidence in the multi-subset proposition ⁇ I, II ⁇ , and the value of the intersection point with I is 0.9 is the degree of confidence in the single-subset proposition I.
  • Step 303 using the evidence combination rule to fuse the average speed and density of each road segment in the detection area to obtain a first congestion index.
  • the average speed of the road sections and the average density of the road sections are fused to obtain the basic probability distribution function m A of the congestion index of the road section A.
  • the specific Dempster combination rules are as follows:
  • the RSU detects that the driving speed and traffic density of the four sections A, B, C and D are (43km/h, 22veh/km), (45km/h, 19veh/km), (40km/ h, 25veh/km), (38km/h, 28veh/km)
  • FIG. 6 The process of calculating the second congestion index in the traffic congestion detection method in this embodiment is shown in FIG. 6 , including:
  • Step 601 the intelligent transportation system determines the weight coefficient of each road section according to the road network structure, and establishes the evidence correlation coefficient matrix SM.
  • Step 602 the intelligent transportation system determines the data fusion center according to the evidence correlation coefficient matrix SM.
  • the weight coefficient of each road section in the target area is obtained; wherein, the weight coefficient of the main road is higher than the weight coefficient of the auxiliary road; the correlation coefficient matrix is established according to the weight coefficient of each road section; wherein, the value of the elements in the matrix Characterize the support degree of the row representing the road segment by the column representing the road segment, and the sum of the element values of each row in the matrix represents the central position of the corresponding road segment in the row in the target area; select the RSU on the corresponding road segment with the highest sum of the row element values as the data fusion center.
  • SM is a symmetric matrix of order s and the value of the i-th row and the j-th column in the matrix SM reflects the similarity between m i and m j , denoted as SM(i, j ). It reflects that the traffic density of road segment i is higher than that of other road segments.
  • the intelligent transportation system selects the roadside unit on road segment i in the area P of the congestion index to be obtained as In the data fusion center, other roadside units in the area P send the basic probability distribution function of the road segment to the roadside unit as the data fusion center.
  • road segment A is the main road
  • road segments B, C and D are secondary roads, so the following evidence correlation matrix SM is designed.
  • the road section A is selected as the secondary fusion center, and the roadside units on the road sections B, C, and D send their respective values m B , m C , and m D to the roadside unit on the road section A.
  • Step 603 Calculate the discount coefficient of the basic probability distribution function of each road segment.
  • the discount coefficient Crd i reflects the degree to which the congestion index of road segment i is supported by the congestion indexes of other road segments, and also serves as the weight of each road segment when calculating the second congestion index.
  • the formula for calculating the discount coefficient Crd i is as follows:
  • Step 604 using the discount coefficient to calculate the average congestion index of each road segment.
  • the evidences of the same proposition on different road sections are weighted and summed using the discount coefficient Crd i to obtain the weighted average evidence m Q .
  • the formula is as follows:
  • Step 605 using the evidence combination rule to fuse the average congestion index itself to obtain a basic probability distribution function.
  • the average evidence m Q is fused three times by itself using the Dempster combination rule to obtain m F , namely
  • Step 606 Convert the basic probability distribution function m F into a probability distribution p, and take the proposition with the largest value as the second congestion index.
  • the basic principle of converting the basic probability distribution function m F to the probability distribution p is to keep the reliability of the single subset proposition unchanged, and to evenly distribute the reliability of the multi-subset propositions to the included single subset propositions.
  • the calculated probability is normalized, and the proposition with the largest value is the congestion index of the area.
  • the congestion index of this area is judged to be II, that is, it is basically unblocked, and the qualitative description of citizens' feelings is: basically unblocked.
  • the first congestion index and the second congestion index are both calculated by data fusion based on the method of evidence theory, which can more accurately perform statistical analysis on the congestion of each road section, so as to obtain a pair of The actual traffic congestion situation reflects a more accurate congestion index.
  • the third embodiment of the present application relates to a method for detecting traffic congestion.
  • the third embodiment is substantially the same as the first embodiment, with the main difference being that: in the third embodiment, the data periodically uploaded by each in-vehicle device in the RSU detection area is acquired.
  • the method further includes: statistical instantaneous speed information in the vehicle information, screening the instantaneous speed information, and eliminating abnormal instantaneous speed information.
  • the implementation details of the traffic congestion detection method in this embodiment will be specifically described below.
  • the flow of the traffic congestion detection method in this embodiment is shown in FIG. 7 , and specifically includes:
  • Step 701 Obtain vehicle information of each vehicle entering the RSU detection area of the roadside unit.
  • Step 701 is the same as step 101 in the first embodiment of the present application, and the relevant implementation details have been specifically described in the first embodiment, which will not be repeated here.
  • step 702 the instantaneous speed information in the vehicle information is counted, the instantaneous speed information is screened, and abnormal instantaneous speed information is eliminated.
  • the roadside unit cannot accurately measure the driving state of the vehicle in the road section only through the instantaneous speed uploaded by the on-board unit. Therefore, the data samples of the instantaneous speed are screened. The average speed of the road segment is calculated using only universal samples of instantaneous speed data.
  • the roadside unit performs a hypothesis test on the speed reported to it by n vehicles on the road segment in the t second.
  • Vehicle V i judges the validity of its own speed v i according to the average speed of other vehicles on the road section in the t second, then the following null and alternative hypotheses are proposed:
  • v represents the real driving speed of the vehicle V i
  • vi represents the detected value of the driving speed of the vehicle V i
  • no significant difference means that there is no significant difference between the actual driving speed and the detected value of the driving speed
  • “there is a significant difference” means The true driving speed is significantly different from the detected driving speed.
  • the roadside unit obtains n-1 vehicle speed sub-samples v 1 , v 2 , v 3 , ... v n-1 in a certain road section. Calculated and the value of S, if:
  • the hypothesis H 0 is rejected, and the hypothesis H 1 is accepted, that is, it is considered that the real speed v is significantly different from v i , and the speed v i detected by the vehicle is considered invalid, so it is discarded. Otherwise if:
  • Step 703 Calculate a first congestion index according to the filtered vehicle information.
  • Step 704 Obtain multiple first congestion indices uploaded by each roadside unit in the target area.
  • Step 705 Calculate a second congestion index according to a plurality of first congestion indices.
  • Steps 703 to 705 are substantially the same as steps 102 to 104 in the first embodiment of the present application, and the relevant implementation details have been specifically described in the first embodiment, and are not repeated here.
  • the traffic congestion detection method in this embodiment after acquiring the speed data uploaded by the on-board unit, the data is screened to obtain the vehicle instantaneous speed data with high confidence, so that the calculated congestion index is more accurate and can be more accurate. Measure traffic congestion in an area.
  • the fourth embodiment of the present application relates to a traffic congestion detection device, the structure is shown in FIG. 8 , and includes:
  • the first acquisition module 801 is used to acquire vehicle information of each vehicle entering the RSU detection area of the roadside unit;
  • a first calculation module 802 configured to calculate a first congestion index according to vehicle information; wherein, the first congestion index is used to represent the traffic congestion in the RSU detection area;
  • the second obtaining module 803 is configured to obtain a plurality of first congestion indices of each RSU in the target area; wherein, the target area includes a plurality of the RSU detection areas;
  • the second calculation module 804 is configured to calculate a second congestion index according to a plurality of first congestion indices; wherein, the second congestion index is used to represent the traffic congestion in the target area.
  • the first calculation module 802 is specifically configured to determine the road segment covered by the RSU detection area; determine the average speed and density of the road segment covered by the RSU detection area according to the speed information and position information of each vehicle; according to the average speed of the road segment and the average density of road sections to determine the first congestion index.
  • the first obtaining module 801 is further configured to perform a hypothesis test on the instantaneous speed information by using a large sub-sample test, and determine whether the instantaneous speed is significantly different from the actual driving speed according to a test threshold;
  • the real driving speed is calculated by the average value of all the instantaneous speeds except the instantaneous speed of the target vehicle, and the test threshold is calculated according to the standard deviation of all the instantaneous speeds except the instantaneous speed of the target vehicle; Instantaneous velocities with significant differences were excluded as abnormal data.
  • the second obtaining module 803 is further configured to obtain multiple first congestion indices uploaded by all roadside units in the target area when the roadside unit is determined as the data fusion center by the intelligent transportation system.
  • the data fusion center is determined by the following methods: obtaining the weight coefficients of each road section in the target area; wherein, the weight coefficient of the main road is higher than that of the auxiliary road; establishing a correlation coefficient matrix according to the weight coefficient of each road section; wherein, the matrix The value of the element in the row represents the degree of support of the road segment represented by the column, and the sum of the element values of each row in the matrix represents the central position of the corresponding road segment in the row in the target area; select the corresponding road segment with the highest sum of row element values.
  • the second calculation module 804 is specifically configured to calculate the discount coefficient of each road section in the target area; the discount coefficient reflects the degree to which the congestion index of the road section is supported by the congestion indexes of other road sections in the target area; Calculate the average congestion index of each road section in the target area according to the discount coefficient; fuse the average congestion index by itself according to the evidence combination rule to obtain a basic probability distribution function; convert the basic probability distribution function into a probability distribution, and determine the second probability distribution according to the probability distribution. Congestion Index.
  • modules involved in this implementation are logical modules.
  • a logical unit may be a physical unit, a part of a physical unit, or multiple physical units. combination implementation.
  • this embodiment does not introduce units that are not closely related to solving the technical problem raised by the present application, but this does not mean that there are no other units in this embodiment.
  • the fifth embodiment of the present application relates to an electronic device, as shown in FIG. 9 , comprising: at least one processor 901 ; and a memory 902 communicatively connected to the at least one processor 901 ; wherein the memory 902 stores data that can be accessed by at least one processor 901 .
  • the memory 902 and the processor 901 are connected by a bus, and the bus may include any number of interconnected buses and bridges, and the bus connects one or more processors 901 and various circuits of the memory 902 together.
  • the bus may also connect together various other circuits, such as peripherals, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein.
  • the bus interface provides the interface between the bus and the transceiver.
  • a transceiver may be a single element or multiple elements, such as multiple receivers and transmitters, providing a means for communicating with various other devices over a transmission medium.
  • the data processed by the processor 901 is transmitted on the wireless medium through the antenna, and further, the antenna also receives the data and transmits the data to the processor 901 .
  • Processor 901 is responsible for managing the bus and general processing, and may also provide various functions including timing, peripheral interface, voltage regulation, power management, and other control functions.
  • the memory 902 may be used to store data used by the processor 901 when performing operations.
  • the sixth embodiment of the present application relates to a computer-readable storage medium storing a computer program.
  • the above method embodiments are implemented when the computer program is executed by the processor. That is, those skilled in the art can understand that all or part of the steps in the method for implementing the above embodiments can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium and includes several instructions to make a device ( It may be a single chip microcomputer, a chip, etc.) or a processor (processor) to execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage medium includes: U disk, removable hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes.

Landscapes

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

Abstract

一种交通拥堵检测方法、装置、电子设备及存储介质。交通拥堵检测方法应用于路侧单元RSU，包括：获取驶入路侧单元RSU检测区域内各车辆(V i)的车辆信息；根据车辆信息计算第一拥堵指数；其中，第一拥堵指数用于表示RSU检测区域的交通拥堵情况；获取目标区域内各RSU的多个第一拥堵指数；其中，目标区域包括多个RSU检测区域；根据多个第一拥堵指数计算第二拥堵指数；其中，第二拥堵指数用于表示目标区域的交通拥堵情况。

Description

交通拥堵检测方法、装置、电子设备及存储介质
交叉引用
本申请基于申请号为“202110032765.3”、申请日为2021年1月12日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此以引入方式并入本申请。
技术领域
本申请实施例涉及通信技术领域，特别涉及一种交通拥堵检测方法、装置、电子设备及存储介质。
背景技术
随着通信技术的发展，车辆网技术逐渐得到广泛的应用。车联网技术包括：车与车(V2V，Vehicle to Vehicle)、车与路(V2I，Vehicle to Infrastructure)、车与人(V2P，Vehicle to People)、车与中心(V2C，Vehicle to Center)等的互联互通，实现车辆自组网及多种异构网络之间的通信与漫游，在功能和性能上保障实时性与可服务性，从而实现车辆运动控制，从而实现车辆运动控制、交通信号的控制以及交通信息处理的技术。其中V2V是指在交通参与者之间进行互联互通、V2I是指交通参与者与交通基础设施之间的互联互通。近年来交通拥堵成为各大城市面临的共同难题，通常采用V2V技术来进行交通数据的搜集从而实现交通拥堵情况的检测。
然而，在实际的交通拥堵检测场景下，由于实际路网中车辆众多，导致各个交通参与者之间的通讯总量过于庞大，同时部分信息需要在各个交通参与者之间进行传递，使得信息传递过程可靠性与稳定性都得不到较好的保证，最终影响交通拥堵检测的效率与精度。
发明内容
本申请实施例提供了一种交通拥堵检测方法，应用于路侧单元，包括：获取驶入路侧单元RSU检测区域内各车辆的车辆信息；根据车辆信息计算第一拥堵指数；其中，第一拥堵指数用于表示RSU检测区域的交通拥堵情况；获取目标区域内各RSU的多个第一拥堵指数；其中，所述目标区域包括多个所述RSU检测区域；根据多个第一拥堵指数计算第二拥堵指数；其中，第二拥堵指数用于表示目标区域的交通拥堵情况。
本申请实施例还提供了一种交通拥堵检测装置，包括：第一获取模块，用于获取驶入路侧单元RSU检测区域内各车辆的车辆信息；第一计算模块，用于根据车辆信息计算第一拥堵指数；其中，第一拥堵指数用于表示RSU检测区域的交通拥堵情况；第二获取模块，用于获取目标区域内各RSU的多个第一拥堵指数；其中，所述目标区域包括多个所述RSU检测区域；第二计算模块，用于根据多个第一拥堵指数计算第二拥堵指数；其中，第二拥堵指数用于表示目标区域的交通拥堵情况。
本申请实施例还提供了一种电子设备，包括：至少一个处理器；以及，与至少一个处理器通信连接的存储器；其中，存储器存储有可被至少一个处理器执行的指令，指令被至少一个处理器执行，以使至少一个处理器能够执行如上述的交通拥堵检测方法。
本申请实施例还提供了一种计算机可读存储介质，存储有计算机程序，计算机程序被执行时实现上述的交通拥堵检测方法。
附图说明
图1是根据本申请第一实施例中交通拥堵检测方法的流程图；
图2是根据本申请第一实施例中交通拥堵检测方法应用场景中路网结构的示意图；
图3是根据本申请第二实施例中计算第一拥堵指数的流程图；
图4是根据本申请第二实施例中路段平均速度隶属度函数的函数图像；
图5是根据本申请第二实施例中路段平均密度隶属度函数的函数图像；
图6是根据本申请第二实施例中计算第二拥堵指数的流程图；
图7是根据本申请第三实施例中交通拥堵检测方法的流程图；
图8是根据本申请第四实施例中交通拥堵检测装置的结构示意图；
图9是根据本申请第五实施例中电子设备的结构示意图。
具体实施方式
为使本申请实施例的目的、技术方案和优点更加清楚，下面将结合附图对本申请的各实施例进行详细的阐述。然而，本领域的普通技术人员可以理解，在本申请各实施例中，为了使读者更好地理解本申请而提出了许多技术细节。但是，即使没有这些技术细节和基于以下各实施例的种种变化和修改，也可以实现本申请所要求保护的技术方案。以下各个实施例的划分是为了描述方便，不应对本申请的具体实现方式构成任何限定，各个实施例在不矛盾的前提下可以相互结合相互引用。
本申请实施例的主要目的在于提出一种交通拥堵检测方法、装置、电子设备及存储介质，使得交通数据的计算效率和稳定性提升，从而提高交通拥堵水平检测结果的可靠性。
本申请提出的交通拥堵检测方法，基于V2I的车联网模式，通过路侧单元获取检测区域内的车辆信息，计算出检测区域内的拥堵指数并将拥堵指数上传后，通过目标区域内多个路侧单元计算得到的拥堵指数计算出目标区域的拥堵指数来评估目标区域的交通拥堵情况，不依赖于各个交通参与者之间的信息传递，从而可以得到稳定可靠的交通拥堵检测结果。
本申请第一实施例涉及一种交通拥堵检测方法，具体流程如图1所示，包括：获取驶入RSU检测区域内各车辆的车辆信息；根据车辆信息计算第一拥堵指数；其中，第一拥堵指数用于表示RSU检测区域的交通拥堵情况；获取目标区域内各RSU的多个第一拥堵指数；其中，目标区域包括多个RSU检测区域；根据所述多个第一拥堵指数计算第二拥堵指数；其中，所述第二拥堵指数用于表示所述目标区域的交通拥堵情况。通过目标区域内多个路侧单元计算得到的拥堵指数计算出目标区域的拥堵指数来评估目标区域的交通拥堵情况，不依赖于各个交通参与者之间的信息传递，从而可以得到稳定可靠的交通拥堵检测结果。
下面对本实施例中的交通拥堵检测方法的实现细节进行具体的说明，以下内容仅为方便理解提供的实施细节，并非实施本方案的必须。
本实施例中的执行主体为路侧单元RSU，是一种安装在路侧，与路上行驶的车辆上安装的车载设备，即车载单元OBU进行通讯，实现车辆信息交互的功能。本实施例中的方法流程如图1所示，具体包括：
步骤101，获取驶入RSU检测区域内各车辆的车辆信息。
具体地说，本实施例以区域内包含有多条路段的目标区域作为交通拥堵的检测对象，目标区域中的路段由一个或多个路侧单元的检测区域进行全覆盖，同时根据路侧单元与车载设备通信的特点，将任意两个路侧单元的距离设置在200m以内。在路侧单元部署完毕后，与自身检测区域内路段上的车载设备建立通讯连接，开始进行交通拥堵检测，周期性地获取车载设备所上报的车辆信息。
在一个例子中，车辆信息主要包括速度信息与当前的位置，其中，速度信息可以具体包括车载设备所属车辆的瞬时速度。路侧单元在周期时间内保存所有车辆信息供后续计算拥堵指数使用。
在实际的应用场景中，车联网通信过程是路段上的路侧单元收集车载单元OBU(On Board Unit)发送的消息，路侧单元通过宽带无线、移动基站、卫星等通信方式接入核心无线网络，由核心无线网络接入互联网与智能交通系统进行通讯。
步骤102，根据车辆信息计算第一拥堵指数。
具体地说，首先路侧单元根据预先录入的交通路网数据确定检测区域所覆盖的路段，然后根据各车辆的速度信息和位置信息确定RSU检测区域所覆盖路段的路段平均速度和路段平均密度，根据路段平均速度和路段平均密度确定第一拥堵指数。即先对车辆信息进行初步处理，通过车辆的速度、位置信息计算出检测区域内某一路段的路段平均速度以及路段平均密度，然后根据路段平均速度和所述路段平均密度确定第一拥堵指数。
其中，路段平均速度通过车载单元上传的瞬时速度计算得到，路段平均密度由路侧单元通过车载单元上传的位置信息确定车辆所处路段，然后统计路段内的车辆数量得到。
在一个具体实现中，目标区域内的路网结构如图2所示，当车辆行驶入检 测范围时，通过车载单元将自身的速度以及位置信息每隔一秒向该路段的路侧单元上报一次。假设城市道路车辆平均速度大约为40km/h，则穿过路侧单元检测区域(以半径200m为例)所需时间大约为36秒，根据车辆瞬时速度求一时间段内车辆平均速度，瞬时速度数据样本数量不宜过少，数据个数越多则要求该时间段越长，在计算中忽略传输延迟等误差，以汽车通过检测区域的时间时长为路侧单元计算该区域拥堵指数的时间周期，时间周期越短则路侧单元效率越高，假设将该周期时长设置为30秒，即路侧单元每隔30s计算得到一个该区域拥堵指数。
进一步地，假定30秒内，车辆V i向路侧单元上报t组数据(t<＝30)，计算路段平均速度v ave的过程如下：
S11：假定当前存在t′(t′≤30)个有效速度，根据车辆i的j个瞬时速度计算车辆V i一个时间周期内的平均速度v i，计算公式如下：
Figure PCTCN2022070351-appb-000001
S12：路侧单元计算一个时间周期内车道r的平均速度v r，计算公式如下：
Figure PCTCN2022070351-appb-000002
其中，n r表示车道r上的车辆数，则有n＝∑n r。
S13：路侧单元计算一个时间周期内某一路段的平均速度v ave，计算公式如下：
Figure PCTCN2022070351-appb-000003
其中，s r表示该路段车道总数，本实例中s r＝4。
计算路段平均密度ρ ave的过程如下：
S21：路侧单元计算第t秒车道r车辆密度
Figure PCTCN2022070351-appb-000004
计算公式如下：
Figure PCTCN2022070351-appb-000005
其中l为第t秒车道r上车辆占道总长，即为距离路侧单元两端检测边缘最近的两辆车之间的距离，包括这两辆车的车长。
S22：路侧单元计算一个时间周期内车道r的平均密度ρ r，计算公式如下：
Figure PCTCN2022070351-appb-000006
S23：路侧单元计算一个时间周期内某一路段的平均密度ρ ave，计算公式如下：
Figure PCTCN2022070351-appb-000007
在一个例子中，在计算第一拥堵指数(即根据路段的平均速度以及路段平均密度所确定的拥堵指数)时，可以根据路网结构为不同的路段分配不同的权重指数，例如为主路分配较高的权重以及为次路分配较低的权重，从而提高更加准确地衡量区域内所有路段总体的拥堵情况。
步骤103，获取目标区域内各RSU上传的多个第一拥堵指数。
具体地说，本实施例中以目标区域的交通拥堵情况作为交通拥堵检测的对象，目标区域包括多个RSU检测区域，即在目标区域内涵盖多个路段，同一时间智能交通系统将路侧单元计算并上传的第一拥堵指数进行统计，并根据路网结构对多个第一拥堵指数进行分析，确定数据融合中心，进行第二拥堵指数的计算。一般来说，通常将主要路段，即车流量最大的路段上处于中心位置的路侧单元作为数据融合中心。但在本实例中，以执行前述步骤101、102的路侧单元被确定为数据融合中心为例，通过智能交通系统获取目标区域内其他路侧单元上报的第一拥堵指数。
步骤104，根据多个第一拥堵指数计算第二拥堵指数。
具体地说，当被确定为数据融合中心的路侧单元获取到目标区域内多个路侧单元上报的第一拥堵指数后，对所有第一拥堵指数进行统计计算。由于第一拥堵指数是表示单个路侧单元检测区域内拥堵情况的参数，那么将多个检测区域的拥堵情况进行统计分析，则可以得到由多个检测区域组成的目标区域的拥堵情况，本实施例中通过第二拥堵指数来表示目标区域的拥堵情况。
本实施例中的交通拥堵检测方法，通过路侧单元获取检测区域内的车辆信息，计算出检测区域内的拥堵指数并将拥堵指数上传后，通过目标区域内多个路侧单元计算得到的拥堵指数计算出目标区域的拥堵指数来评估目标区域的交通拥堵情况，从而得到稳定可靠的交通拥堵检测结果。
需要说明的是，本实施例中的上述各示例均为方便理解进行的举例说明，并不对本申请的技术方案构成限定。
本申请的第二实施例涉及一种交通拥堵检测方法，第二实施例与第一实施例大致相同，主要的区别在于：第二实施例中，第一拥堵指数以及第二拥堵指 数均基于DS证据理论和模糊集理论计算得到。
下面对本实施例中的交通拥堵检测方法的实现细节进行具体的说明，本实施例中的交通拥堵检测方法中计算第一拥堵指数的流程如图3所示，包括：
步骤301，计算RSU检测区域的路段平均速度和路段平均密度。
具体地说，本实施例中可以采用与第一实施例中的计算方法确定路段平均速度和路段平均密度，在此不再赘述。
在另一个例子中，路段平均速度还可以通过车辆经过路侧单元的时间t以及路侧单元覆盖路段的距离d计算得到，即v ave＝d/t。采用这种方式计算能够避免车辆在行驶过程中因特殊情况产生的加速或减速，从而导致车辆上传无法准确表达路段真实情况的瞬时速度样本。
步骤302，基于DS证据理论和模糊集理论，生成关于路段平均速度和路段平均密度的基本概率分配函数。
具体地说，在计算得到v ave和ρ ave以后，基于DS证据理论和模糊集理论，分别匹配路段平均速度v ave和路段平均密度ρ ave与对应的隶属度函数，生成两组关于速度、密度属性的基本概率分配函数BPA，分别记为m v、m ρ。设拥堵指数构成的辨识框架为Θ，假设G是辨识框架下的某个命题，μ G(x)为命题G的隶属度函数，表征属性x从属于命题G的程度，分别匹配上述步骤所得判断路段拥堵指数的两个属性特征值：路段平均速度v ave和路段平均密度ρ ave与隶属度函数，生成两组关于速度、密度属性的基本概率分配函数BPA,分别记为m v、m ρ。则定义速度属性与命题G间的匹配程度为：
Figure PCTCN2022070351-appb-000008
密度属性与命题G间的匹配程度为:
Figure PCTCN2022070351-appb-000009
其中，G可以表示单子集命题或多子集命题。若生成的BPA的信度值之和大于1，则对其进行归一化处理；若其和小于1，则把冗余的信度分配给全集，也就是分配给未知。
拥堵指数集合Θ＝{Ⅰ，Ⅱ，Ⅲ，Ⅳ}；
其中，拥堵指数Ⅰ表示畅通，市民感受的定性描述为：路上车很少，畅行无阻；拥堵指数Ⅱ表示基本畅通，市民感受的定性描述为：基本还是畅通的； 拥堵指数Ⅲ表示轻度拥堵，市民感受的定性描述为：有一些拥堵，但不严重；拥堵指数Ⅳ表示中度拥堵，市民感受的定性描述为：拥堵较严重。
本实施例中，隶属度函数如图4和图5所示。本实施例中，假定路段A检测得到路段平均速度v A＝43km/h，路段平均密度ρ A＝22veh/km。
根据速度v A和密度ρ A各自对应的函数，查图4，速度v A＝43km/h时与拥堵指数为Ⅰ，Ⅱ，Ⅲ的函数相交；查图5，ρ A＝22veh/km时与拥堵指数为Ⅰ，Ⅱ的函数相交。由图4可知：v A＝43km/h时，从下往上看，与Ⅲ的交点值0.1333为对多子集命题{Ⅰ，Ⅱ，Ⅲ}的信任度，与Ⅰ的交点值0.15为对多子集命题{Ⅰ，Ⅱ}的信任度，与Ⅱ的交点值0.85为对单子集命题Ⅱ的信任度，相同的，ρ A＝22veh/km时，从下往上看，与Ⅱ的交点值0.1334为对多子集命题{Ⅰ，Ⅱ}的信任度，与Ⅰ的交点值0.9为对单子集命题Ⅰ的信任度。归一化处理v A和ρ A，得到路段A速度和密度两个属性下拥堵指数基本概率分配函数BPA如下：
Figure PCTCN2022070351-appb-000010
步骤303，采用证据组合规则融合检测区域内各路段的路段平均速度和路段平均密度，得到第一拥堵指数。
具体地说，假定检测区域内包含x个路段，将x个路段的路段平均速和路段平均密度进行融合，得到路段A的拥堵指数基本概率分配函数m A。其中，路段i的拥堵指数所对应的基本概率分配函数记为m i，i＝1，2，…，x。具体的Dempster组合规则如下：
Figure PCTCN2022070351-appb-000011
在具体的实现中，计算m A的过程如下：
Figure PCTCN2022070351-appb-000012
Figure PCTCN2022070351-appb-000013
Figure PCTCN2022070351-appb-000014
Figure PCTCN2022070351-appb-000015
Figure PCTCN2022070351-appb-000016
Figure PCTCN2022070351-appb-000017
检测周期内，若A、B、C、D四个路段RSU检测到其行驶速度和所在车流密度分别为(43km/h，22veh/km)，(45km/h,19veh/km),(40km/h,25veh/km),(38km/h,28veh/km)该区域四个路段的拥堵指数集合分别为：{m A(Ⅰ)＝0.3763，mAⅡ＝0.2792，mAⅠ,Ⅱ＝0.0931，mAθ＝0.0193，mBⅠ＝0.8261，mBθ＝0.0116，mCⅡ＝0.7618，mCθ＝0.0159，mDⅡ＝1。
本实施例中的交通拥堵检测方法中计算第二拥堵指数的流程如图6所示，包括：
步骤601，智能交通系统根据路网结构确定各路段的权重系数，建立证据关联系数矩阵SM。
步骤602，智能交通系统依据证据关联系数矩阵SM确定数据融合中心。
具体地说，获取所述目标区域内各路段的权重系数；其中，主路的权重系数高于辅路的权重系数；根据各路段的权重系数建立关联系数矩阵；其中，所 述矩阵中元素的值表征所在行代表路段被所在列代表路段的支持程度，所述矩阵中各行元素值的总和表征该行对应路段在所述目标区域的中心地位；选取行元素值总和最高的对应路段上的RSU作为所述数据融合中心。
例如，假定目标区域有s个路段，则SM为s阶对称矩阵且矩阵SM中的第i行第j列的值反映了m i和m j之间的相似度，记作SM(i，j)。
Figure PCTCN2022070351-appb-000018
反映了路段i相较其他路段车流密度较高，此时，智能交通系统接收到各路侧单元上传的第一拥堵指数后，在待求拥堵指数区域P中选取路段i上的路侧单元为数据融合中心，区域P的其他路侧单元将路段基本概率分配函数发给作为数据融合中心的路侧单元。
在一个具体实现中，如图2的路网结构所示，路段A为主干道，路段B、C和D为次干道，故设计如下证据关联矩阵SM。
Figure PCTCN2022070351-appb-000019
据
Figure PCTCN2022070351-appb-000020
可知，选取路段A为二次融合中心，路段B、C、D上的路侧单元将各自的值m B、m C、m D发送至路段A上的路侧单元。
步骤603，计算各路段基本概率分配函数的折扣系数。
具体地说，折扣系数Crd i反映路段i拥堵指数被其他路段拥堵指数所支持的程度，同时也作为计算第二拥堵指数时各路段的权重。折扣系数Crd i的计算公式如下：
Figure PCTCN2022070351-appb-000021
在具体的实现中，以图2所示的路网结构为例，四个路段对应折扣系数如下：
Figure PCTCN2022070351-appb-000022
Figure PCTCN2022070351-appb-000023
Figure PCTCN2022070351-appb-000024
Figure PCTCN2022070351-appb-000025
步骤604，利用折扣系数计算各路段的平均拥堵指数。
具体地说，利用折扣系数Crd i对不同路段上相同命题的证据进行加权求和，得到加权后的平均证据m Q。公式如下：
Figure PCTCN2022070351-appb-000026
对于本实例，计算过程如下：
Figure PCTCN2022070351-appb-000027
Figure PCTCN2022070351-appb-000028
Figure PCTCN2022070351-appb-000029
Figure PCTCN2022070351-appb-000030
步骤605，利用证据组合规则对平均拥堵指数自身进行融合，得到基本概率分配函数。
具体地说，将平均证据m Q用Dempster组合规则自身融合三次，得到m F，即
Figure PCTCN2022070351-appb-000031
三次融合结果如下表所示：
Figure PCTCN2022070351-appb-000032
步骤606，将基本概率分配函数m F转换为概率分布p，取数值最大的命题作为第二拥堵指数。
具体地说，将基本概率分配函数m F转换为概率分布p的基本原理为保持单子集命题的信度不变，将多子集命题的信度平均分配给所包含的单子集命题。本实施例中，对计算得到的概率进行归一化处理，将数值最大的命题为该区域的拥堵指数。
在具体的实现中，p(Ⅰ)＝0.0332p(Ⅱ)＝0.1135，经归一化处理后，p(Ⅰ)＝0.2263p(Ⅱ)＝0.7736，p(Ⅱ)>p(Ⅰ),故该区域拥堵指数判定为Ⅱ，即基本畅通，市民感受的定性描述为：基本还是畅通的。
本实施例中的交通拥堵检测方法，通过第一拥堵指数与第二拥堵指数均采用基于证据理论的方法进行数据融合计算，能够更加准确的对各个路段的拥堵情况进行统计分析，从而得到一个对实际交通拥堵情况反映更加准确的拥堵指数。
本申请的第三实施例涉及一种交通拥堵检测方法，第三实施例与第一实施例大致相同，主要区别在于：第三实施例中，在获取RSU检测区域内各车载设备周期性上传的车辆信息之后，根据车辆信息计算第一拥堵指数之前，还包括：统计车辆信息中的瞬时速度信息，对瞬时速度信息进行筛选，剔除异常的瞬时速度信息。
下面对本实施例中的交通拥堵检测方法的实现细节进行具体的说明，本实施例中交通拥堵检测方法的流程如图7所示，具体包括：
步骤701，获取驶入路侧单元RSU检测区域内各车辆的车辆信息。
步骤701与本申请第一实施例中的步骤101相同，相关的实施细节已在第一实施例中具体说明，在此不再赘述。
步骤702，统计车辆信息中的瞬时速度信息，对瞬时速度信息进行筛选，剔除异常的瞬时速度信息。
具体地说，由于车辆在路段中的行驶状态具有一定的不确定性，路侧单元仅通过车载单元上传的瞬时速度无法准确衡量车辆在路段中行驶状态，因此对瞬时速度的数据样本进行筛选，仅采用具有普适性的瞬时速度数据样本来计算路段的平均速度。
在具体的实现中，基于大子样假设检验，路侧单元对第t秒内该路段上n辆车向其上报的速度做假设检验。车辆V i根据第t秒该路段上其他车辆平均速度判断自身速度v i的有效性，则提出以下零假设和备择假设方案：
H 0：v＝v i,无显著差异
H 1：v≠v i,有显著差异
上式中，v表示车辆V i真实的行驶速度，v i表示车辆V i行驶速度检测值，“无显著差异”表示真实的行驶速度与行驶速度检测值无显著差异，“有显著差异”表示真实的行驶速度与行驶速度检测值有显著差异。
若该路段上除车辆V i外，其余n-1辆车上报速度分别为：v 1、…v i-1、v i+1…v n-1,依据中心极限定理和基于大子样的假设检验知：路段上车辆数量很多，即此时n值很大，统计量v近似地服从标准正态分布，v计算公式如下：
其中S和
Figure PCTCN2022070351-appb-000033
分别为该路段其余n-1辆车上报速度的标准差和平均值，v i为车辆V i的上报速度。
给定显著性水平α，存在
Figure PCTCN2022070351-appb-000034
使得：
Figure PCTCN2022070351-appb-000035
即：
Figure PCTCN2022070351-appb-000036
路侧单元得到某路段n-1辆车速度子样值v 1、v 2、v 3、…v n-1。计算得到
Figure PCTCN2022070351-appb-000037
和S的数值，若：
Figure PCTCN2022070351-appb-000038
则拒绝假设H 0，接受假设H 1，即认为真实的速度v与v i有显著差异，认为该车辆检测得到的速度v i无效，故舍去。否则若：
Figure PCTCN2022070351-appb-000039
则接受假设H 0，拒绝假设H 1，即认为真实的速度v与v i无显著差异，认为该车辆检测得到的速度v i有效，且置信概率为1-α，本文选定α＝0.1。对路段内n辆车作如此假设检验，可以将在该秒速度过快和过慢的数据剔除，剔除数据反映的可能是正在路边选择停车位的车辆或正在超速的车辆。
步骤703，根据筛选后的车辆信息计算第一拥堵指数。
步骤704，获取目标区域内各路侧单元上传的多个第一拥堵指数。
步骤705，根据多个第一拥堵指数计算第二拥堵指数。
步骤703至步骤705与本申请第一实施例中的步骤102至步骤104大致相同，相关的实施细节已在第一实施例中具体说明，在此不再赘述。
本实施例中的交通拥堵检测方法，在获取到车载单元上传的速度数据后，对数据进行筛选，得到置信度高的车辆瞬时速度数据，从而使得计算得到的拥堵指数更加准确，能够更加准确地衡量区域内的交通拥堵情况。
上面各种方法的步骤划分，只是为了描述清楚，实现时可以合并为一个步骤或者对某些步骤进行拆分，分解为多个步骤，只要包括相同的逻辑关系，都在本专利的保护范围内；对算法中或者流程中添加无关紧要的修改或者引入无关紧要的设计，但不改变其算法和流程的核心设计都在该专利的保护范围内。
本申请的第四实施例涉及一种交通拥堵检测装置，结构如图8所示，包括：
第一获取模块801，用于获取驶入路侧单元RSU检测区域内各车辆的车辆信息；
第一计算模块802，用于根据车辆信息计算第一拥堵指数；其中，第一拥堵指数用于表示RSU检测区域的交通拥堵情况；
第二获取模块803，用于获取目标区域内各RSU的多个第一拥堵指数；其中，所述目标区域包括多个所述RSU检测区域；
第二计算模块804，用于根据多个第一拥堵指数计算第二拥堵指数；其中， 第二拥堵指数用于表示目标区域的交通拥堵情况。
在一个例子中，第一计算模块802具体用于确定RSU检测区域所覆盖的路段；根据各车辆的速度信息和位置信息确定RSU检测区域覆盖路段的路段平均速度和路段平均密度；根据路段平均速度和路段平均密度确定第一拥堵指数。
在另一个例子中，第一获取模块801还用于采用大子样检验对所述瞬时速度信息进行假设检验，根据检验阈值确定所述瞬时速度与真实的行驶速度是否有显著差异；其中，所述真实行驶速度通过除目标车辆的瞬时速度以外所有瞬时速度的平均值计算得到，所述检验阈值根据所述除目标车辆的瞬时速度以外所有瞬时速度的标准差计算得到；将与真实的行驶速度有显著差异的瞬时速度作为异常数据剔除。
在一个例子中，第二获取模块803还用于在路侧单元被智能交通系统确定为数据融合中心时，获取目标区域内所有路侧单元上传的多个第一拥堵指数。其中，数据融合中心通过以下方式确定：获取目标区域内各路段的权重系数；其中，主路的权重系数高于辅路的权重系数；根据各路段的权重系数建立关联系数矩阵；其中，所述矩阵中元素的值表征所在行代表路段被所在列代表路段的支持程度，所述矩阵中各行元素值的总和表征该行对应路段在所述目标区域的中心地位；选取行元素值总和最高的对应路段上的RSU作为所述数据融合中心。
在一个例子中，第二计算模块804具体用于计算所述目标区域内各路段的折扣系数；所述折扣系数反映路段的拥堵指数被所述目标区域内其他路段的拥堵指数所支持的程度；根据折扣系数计算所述目标区域内各路段的平均拥堵指数；根据证据组合规则对平均拥堵指数进行自身融合，得到基本概率分配函数；将基本概率分配函数转换为概率分布，根据概率分布确定第二拥堵指数。
值得一提的是，本实施中所涉及到的各模块均为逻辑模块，在实际应用中，一个逻辑单元可以是一个物理单元，也可以是一个物理单元的一部分，还可以以多个物理单元的组合实现。此外，为了突出本申请的创新部分，本实施例中并没有将与解决本申请所提出的技术问题关系不太密切的单元引入，但这并不表明本实施例中不存在其它的单元。
本申请的第五实施例涉及一种电子设备，如图9所示，包括：至少一个处 理器901；以及，与至少一个处理器901通信连接的存储器902；其中，存储器902存储有可被至少一个处理器901执行的指令，指令被至少一个处理器901执行，以使至少一个处理器901能够执行第一、第二或第三实施例中的交通拥堵检测方法。其中，存储器902和处理器901采用总线方式连接，总线可以包括任意数量的互联的总线和桥，总线将一个或多个处理器901和存储器902的各种电路连接在一起。总线还可以将诸如外围设备、稳压器和功率管理电路等之类的各种其他电路连接在一起，这些都是本领域所公知的，因此，本文不再对其进行进一步描述。总线接口在总线和收发机之间提供接口。收发机可以是一个元件，也可以是多个元件，比如多个接收器和发送器，提供用于在传输介质上与各种其他装置通信的单元。经处理器901处理的数据通过天线在无线介质上进行传输，进一步，天线还接收数据并将数据传送给处理器901。处理器901负责管理总线和通常的处理，还可以提供各种功能，包括定时，外围接口，电压调节、电源管理以及其他控制功能。而存储器902可以被用于存储处理器901在执行操作时所使用的数据。
本申请第六实施例涉及一种计算机可读存储介质，存储有计算机程序。计算机程序被处理器执行时实现上述方法实施例。即，本领域技术人员可以理解，实现上述实施例方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序存储在一个存储介质中，包括若干指令用以使得一个设备(可以是单片机，芯片等)或处理器(processor)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-OnlyMemory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。本领域的普通技术人员可以理解，上述各实施例是实现本申请的具体实施例，而在实际应用中，可以在形式上和细节上对其作各种改变，而不偏离本申请的精神和范围。

Claims (10)

  1. 一种交通拥堵检测方法，应用于路侧单元，包括：
    获取驶入路侧单元RSU检测区域内各车辆的车辆信息；
    根据所述车辆信息计算第一拥堵指数；其中，所述第一拥堵指数用于表示所述RSU检测区域的交通拥堵情况；
    获取目标区域内各RSU的多个所述第一拥堵指数；其中，所述目标区域包括多个所述RSU检测区域；
    根据所述多个第一拥堵指数计算第二拥堵指数；其中，所述第二拥堵指数用于表示所述目标区域的交通拥堵情况。
  2. 根据权利要求1所述的交通拥堵检测方法，其中，所述车辆信息至少包括：速度信息和位置信息；
    所述根据所述车辆信息计算第一拥堵指数，包括：
    确定所述RSU检测区域内所覆盖的路段；
    根据所述各车辆的速度信息和位置信息确定所述RSU检测区域所覆盖路段的路段平均速度和路段平均密度；
    根据所述路段平均速度和所述路段平均密度确定所述第一拥堵指数。
  3. 根据权利要求2所述的交通拥堵检测方法，其中，所述根据所述路段平均速度和所述路段平均密度确定所述第一拥堵指数，包括：
    基于DS证据理论和模糊集理论确定所述路段平均速度以及所述路段平均密度对应的基本概率分配函数；
    根据所述基本概率分配函数采用证据组合规则融合得到所述第一拥堵指数。
  4. 根据权利要求2所述的交通拥堵检测方法，其中，所述速度信息包括车辆的瞬时速度信息；
    在所述根据所述各车辆的速度信息和位置信息确定所述RSU检测区域所覆盖路段的路段平均速度和路段平均密度之前，还包括：
    采用大子样检验对所述瞬时速度信息进行假设检验，根据检验阈值确定所 述瞬时速度与真实的行驶速度是否有显著差异；其中，所述真实行驶速度通过除目标车辆的瞬时速度以外所有瞬时速度的平均值计算得到，所述检验阈值根据所述除目标车辆的瞬时速度以外所有瞬时速度的标准差计算得到；
    将与真实的行驶速度有显著差异的瞬时速度作为异常数据剔除。
  5. 根据权利要求1至4中任一项所述的交通拥堵检测方法，其中，在所述获取目标区域内各RSU的多个所述第一拥堵指数之前，还包括：
    当被智能交通系统确定为数据融合中心时，执行所述获取目标区域内各RSU上传的多个所述第一拥堵指数。
  6. 根据权利要求5所述的交通拥堵检测方法，其中，所述数据融合中心通过以下方式确定：
    获取所述目标区域内各路段的权重系数；其中，主路的权重系数高于辅路的权重系数；
    根据所述各路段的权重系数建立关联系数矩阵；其中，所述矩阵中元素的值表征所在行代表路段被所在列代表路段的支持程度，所述矩阵中各行元素值的总和表征该行对应路段在所述目标区域的中心地位；
    选取行元素值总和最高的对应路段上的RSU作为所述数据融合中心。
  7. 根据权利要求1至6中任一项所述的交通拥堵检测方法，其中，所述根据所述多个第一拥堵指数计算第二拥堵指数，包括：
    计算所述目标区域内各路段的折扣系数；所述折扣系数反映路段的拥堵指数被所述目标区域内其他路段的拥堵指数所支持的程度；
    根据所述折扣系数计算所述目标区域内各路段的平均拥堵指数；
    根据证据组合规则对所述平均拥堵指数进行自身融合，得到基本概率分配函数；
    将基本概率分配函数转换为概率分布，根据所述概率分布确定所述第二拥堵指数。
  8. 一种交通拥堵检测装置，包括：
    第一获取模块，用于获取驶入路侧单元RSU检测区域内各车辆的车辆信息；
    第一计算模块，用于根据所述车辆信息计算第一拥堵指数；其中，所述第一拥堵指数用于表示所述RSU检测区域的交通拥堵情况；
    第二获取模块，用于获取目标区域内各RSU的多个所述第一拥堵指数；其中，所述目标区域包括多个所述RSU检测区域；
    第二计算模块，用于根据所述多个第一拥堵指数计算第二拥堵指数；其中，所述第二拥堵指数用于表示所述目标区域的交通拥堵情况。
  9. 一种电子设备，包括：
    至少一个处理器；以及，
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行如权利要求1至7中任一项所述的交通拥堵检测方法。
  10. 一种计算机可读存储介质，存储有计算机程序，所述计算机程序被处理器执行时实现权利要求1至7中任一项所述的交通拥堵检测方法。
PCT/CN2022/070351 2021-01-12 2022-01-05 交通拥堵检测方法、装置、电子设备及存储介质 WO2022152026A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
JP2023512766A JP7576162B2 (ja) 2021-01-12 2022-01-05 交通渋滞検出方法、装置、電子デバイス及び記憶媒体
EP22738907.9A EP4235617A4 (en) 2021-01-12 2022-01-05 TRAFFIC CONGESTION DETECTION METHOD AND APPARATUS, ELECTRONIC DEVICE AND STORAGE MEDIUM
US18/038,974 US20240005782A1 (en) 2021-01-12 2022-01-05 Traffic congestion detection method and apparatus, electronic device and storage medium
KR1020227033008A KR102800850B1 (ko) 2021-01-12 2022-01-05 교통 혼잡 감지 방법, 장치, 전자 장치 및 저장 매체

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110032765.3 2021-01-12
CN202110032765.3A CN112382098B (zh) 2021-01-12 2021-01-12 交通拥堵检测方法、装置、电子设备及存储介质

Publications (1)

Publication Number Publication Date
WO2022152026A1 true WO2022152026A1 (zh) 2022-07-21

Family

ID=74591068

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/070351 WO2022152026A1 (zh) 2021-01-12 2022-01-05 交通拥堵检测方法、装置、电子设备及存储介质

Country Status (6)

Country Link
US (1) US20240005782A1 (zh)
EP (1) EP4235617A4 (zh)
JP (1) JP7576162B2 (zh)
KR (1) KR102800850B1 (zh)
CN (1) CN112382098B (zh)
WO (1) WO2022152026A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115691141A (zh) * 2022-11-10 2023-02-03 无锡市德宁节能科技有限公司 一种基于护栏的城市交通管理方法和系统

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112382098B (zh) * 2021-01-12 2021-07-06 中兴通讯股份有限公司 交通拥堵检测方法、装置、电子设备及存储介质
CN115691095B (zh) * 2021-07-27 2024-09-06 海信集团控股股份有限公司 交通事件分析设备及方法
CN115705770A (zh) * 2021-08-04 2023-02-17 丰图科技(深圳)有限公司 道路拥堵的确定方法、装置、计算机设备及存储介质
CN114613137B (zh) * 2022-03-07 2023-02-21 同盾科技有限公司 应用于高速公路的拥堵指数确定方法、装置、介质及设备
CN114944058B (zh) * 2022-05-11 2023-06-23 福勤智能科技（昆山）有限公司 拥堵区域距离确定方法、装置、预警设备和存储介质
CN114999148B (zh) * 2022-05-16 2024-10-22 国汽智图(北京)科技有限公司 拥堵程度监测方法、装置、计算机设备和存储介质
CN114999155B (zh) * 2022-05-26 2024-03-19 南斗六星系统集成有限公司 一种车辆轨迹的拥堵评价方法、装置、设备及存储介质
CN114999164B (zh) * 2022-08-05 2022-11-04 深圳支点电子智能科技有限公司 智能交通预警处理方法及相关设备
CN115985091B (zh) * 2022-12-05 2025-07-11 讯飞智元信息科技有限公司 一种路段拥堵优化方法及装置、电子设备、存储介质
US12272237B2 (en) * 2022-12-27 2025-04-08 Itron, Inc. Pedestrian and vehicle congestion relief system
CN119296328B (zh) * 2024-12-11 2025-03-04 辽宁交投艾特斯技术股份有限公司 一种交通数据的融合方法及融合装置
CN119832742A (zh) * 2025-03-14 2025-04-15 陕西中交信通网络科技有限公司 智慧交通中目标道路拥堵确定方法及系统

Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010009366A (ja) * 2008-06-27 2010-01-14 Ihi Corp 円滑走行支援システム
CN103761876A (zh) * 2014-01-10 2014-04-30 山东大学 基于车路协同的道路交通信息采集与状态评价的方法
CN105023434A (zh) * 2015-07-03 2015-11-04 信融源大数据科技(北京)有限公司 一种高速公路拥堵指数的获取方法
CN105303850A (zh) * 2015-10-20 2016-02-03 北京长峰金鼎科技有限公司 道路交通路口的交通信号灯的控制方法
KR101615970B1 (ko) * 2014-11-07 2016-04-28 한국건설기술연구원 도로교통 전용통신-기반 노변장치 및 차량단말기를 이용한 도로공사구간 교통정보 제공 시스템 및 그 방법
CN106023626A (zh) * 2016-06-17 2016-10-12 深圳市元征科技股份有限公司 一种交通拥堵提示方法、服务器及车载设备
CN107622309A (zh) * 2017-08-18 2018-01-23 长安大学 一种基于VANETs和改进的D‑S证据理论的道路拥堵检测方法
CN108492555A (zh) * 2018-03-20 2018-09-04 青岛海信网络科技股份有限公司 一种城市路网交通状态评价方法及装置
CN108765939A (zh) * 2018-05-11 2018-11-06 贵阳信息技术研究院（中科院软件所贵阳分部） 基于聚类算法的动态交通拥堵指数计算方法
CN110570674A (zh) * 2019-09-06 2019-12-13 杭州博信智联科技有限公司 车路协同数据交互方法、系统、电子设备及可读存储介质
US20190392712A1 (en) * 2018-06-20 2019-12-26 Cavh Llc Connected automated vehicle highway systems and methods related to heavy vehicles
CN111081019A (zh) * 2019-12-23 2020-04-28 华南理工大学 一种基于路段权重系数的路网交通运行状况评价方法
CN111489548A (zh) * 2020-02-28 2020-08-04 广东中科臻恒信息技术有限公司 动态道路交通信息采集方法及系统、存储介质
CN111583641A (zh) * 2020-04-30 2020-08-25 北京嘀嘀无限科技发展有限公司 道路拥堵分析方法、装置、设备和存储介质
CN112382098A (zh) * 2021-01-12 2021-02-19 中兴通讯股份有限公司 交通拥堵检测方法、装置、电子设备及存储介质

Family Cites Families (25)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4461977B2 (ja) * 2004-09-21 2010-05-12 株式会社デンソー 道路混雑度予測システムおよび道路混雑度予測装置
JP2006105686A (ja) 2004-10-01 2006-04-20 Matsushita Electric Ind Co Ltd 経路探索装置
US8014936B2 (en) * 2006-03-03 2011-09-06 Inrix, Inc. Filtering road traffic condition data obtained from mobile data sources
JP2010061336A (ja) * 2008-09-03 2010-03-18 Kyosan Electric Mfg Co Ltd 情報提供システム及び情報提供方法
JP2010191614A (ja) * 2009-02-17 2010-09-02 Sumitomo Electric Ind Ltd 交通情報推定システム、推定方法、提供システムおよびコンピュータプログラム
CN103310642A (zh) * 2012-03-16 2013-09-18 捷达世软件（深圳）有限公司 道路状况预警系统以及道路状况预警方法
JP6244625B2 (ja) * 2012-12-19 2017-12-13 日本電気株式会社 渋滞検出システム及び渋滞検出方法
WO2014162169A1 (en) * 2013-04-01 2014-10-09 Qatar University Qstp-B Methods and systems for estimating road traffic
CN103280098B (zh) * 2013-05-23 2015-06-10 北京交通发展研究中心 交通拥堵指数计算方法
JP2016133942A (ja) 2015-01-19 2016-07-25 住友電気工業株式会社 交通指標算出装置、交通指標算出方法及びコンピュータプログラム
WO2017033799A1 (ja) * 2015-08-26 2017-03-02 京セラ株式会社 無線通信装置及び網側装置
JP6610669B2 (ja) * 2015-08-27 2019-11-27 日本電気株式会社 渋滞予防システム、渋滞予防方法、及び、プログラム
CN106530684B (zh) * 2015-09-11 2019-08-20 杭州海康威视系统技术有限公司 处理交通道路信息的方法及装置
CN106778883A (zh) * 2016-12-23 2017-05-31 贵州电网有限责任公司电力科学研究院 一种基于模糊集合的证据理论智能巡检信息融合方法
CN106781488B (zh) * 2016-12-28 2019-11-15 安徽科力信息产业有限责任公司 基于车流密度和车速融合的交通运行状态评价方法
CN107301774A (zh) * 2017-06-30 2017-10-27 深圳市金溢科技股份有限公司 交通拥堵预警方法、系统、车载单元和路侧单元
CN108198412B (zh) * 2017-12-06 2020-02-07 广东交通职业技术学院 车联网下基于mfd的过饱和路网多层控制边界动态划分方法
EP3764364A4 (en) * 2018-03-29 2021-12-15 Tanita Corporation COMPONENT DETERMINATION DEVICE, COMPONENT DETERMINATION PROCESS AND PROGRAM
WO2019189218A1 (ja) * 2018-03-29 2019-10-03 日本電気株式会社 交通監視装置、交通監視システム、交通監視方法及びプログラムが格納された非一時的なコンピュータ可読媒体
US20210027619A1 (en) * 2018-03-29 2021-01-28 Nec Corporation Traffic monitoring apparatus, traffic monitoring system, traffic monitoring method, and non-transitory computer readable medium storing program
US12136339B2 (en) * 2018-03-29 2024-11-05 Nec Corporation Traffic monitoring apparatus, traffic monitoring system, traffic monitoring method, and non-transitory computer readable medium storing program
CN109615867A (zh) * 2019-01-28 2019-04-12 大连海事大学 一种面向交通疏导的智能道路系统
CN110310476B (zh) * 2019-05-06 2020-10-20 平安国际智慧城市科技股份有限公司 道路拥堵程度的评估方法、装置、计算机设备及存储介质
US20230110089A1 (en) * 2020-03-27 2023-04-13 Nec Corporation Information collection device, roadside device, and road condition obtaining method
US20210319691A1 (en) * 2021-06-25 2021-10-14 Arvind Merwaday Collaborative detection and avoidance of phantom traffic jams

Patent Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010009366A (ja) * 2008-06-27 2010-01-14 Ihi Corp 円滑走行支援システム
CN103761876A (zh) * 2014-01-10 2014-04-30 山东大学 基于车路协同的道路交通信息采集与状态评价的方法
KR101615970B1 (ko) * 2014-11-07 2016-04-28 한국건설기술연구원 도로교통 전용통신-기반 노변장치 및 차량단말기를 이용한 도로공사구간 교통정보 제공 시스템 및 그 방법
CN105023434A (zh) * 2015-07-03 2015-11-04 信融源大数据科技(北京)有限公司 一种高速公路拥堵指数的获取方法
CN105303850A (zh) * 2015-10-20 2016-02-03 北京长峰金鼎科技有限公司 道路交通路口的交通信号灯的控制方法
CN106023626A (zh) * 2016-06-17 2016-10-12 深圳市元征科技股份有限公司 一种交通拥堵提示方法、服务器及车载设备
CN107622309A (zh) * 2017-08-18 2018-01-23 长安大学 一种基于VANETs和改进的D‑S证据理论的道路拥堵检测方法
CN108492555A (zh) * 2018-03-20 2018-09-04 青岛海信网络科技股份有限公司 一种城市路网交通状态评价方法及装置
CN108765939A (zh) * 2018-05-11 2018-11-06 贵阳信息技术研究院（中科院软件所贵阳分部） 基于聚类算法的动态交通拥堵指数计算方法
US20190392712A1 (en) * 2018-06-20 2019-12-26 Cavh Llc Connected automated vehicle highway systems and methods related to heavy vehicles
CN110570674A (zh) * 2019-09-06 2019-12-13 杭州博信智联科技有限公司 车路协同数据交互方法、系统、电子设备及可读存储介质
CN111081019A (zh) * 2019-12-23 2020-04-28 华南理工大学 一种基于路段权重系数的路网交通运行状况评价方法
CN111489548A (zh) * 2020-02-28 2020-08-04 广东中科臻恒信息技术有限公司 动态道路交通信息采集方法及系统、存储介质
CN111583641A (zh) * 2020-04-30 2020-08-25 北京嘀嘀无限科技发展有限公司 道路拥堵分析方法、装置、设备和存储介质
CN112382098A (zh) * 2021-01-12 2021-02-19 中兴通讯股份有限公司 交通拥堵检测方法、装置、电子设备及存储介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4235617A4

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115691141A (zh) * 2022-11-10 2023-02-03 无锡市德宁节能科技有限公司 一种基于护栏的城市交通管理方法和系统
CN115691141B (zh) * 2022-11-10 2024-01-30 无锡市德宁节能科技有限公司 一种基于护栏的城市交通管理方法和系统及网络侧服务端

Also Published As

Publication number Publication date
JP7576162B2 (ja) 2024-10-30
EP4235617A1 (en) 2023-08-30
US20240005782A1 (en) 2024-01-04
CN112382098B (zh) 2021-07-06
CN112382098A (zh) 2021-02-19
KR20220144856A (ko) 2022-10-27
EP4235617A4 (en) 2024-08-28
JP2023538141A (ja) 2023-09-06
KR102800850B1 (ko) 2025-04-24

Similar Documents

Publication Publication Date Title
WO2022152026A1 (zh) 交通拥堵检测方法、装置、电子设备及存储介质
CN108430069B (zh) 一种v2x网络性能测试及综合评价分析方法
Jiang et al. Investigating macro-level hotzone identification and variable importance using big data: A random forest models approach
CN108597227B (zh) 高速公路收费站下道交通流量预测方法
CN108629973A (zh) 基于固定检测设备的路段交通拥堵指数计算方法
CN116524712A (zh) 融合时空关联数据的高速公路拥堵预测方法、系统及装置
CN113870564B (zh) 一种封闭路段交通拥堵分类方法、系统、电子设备及存储介质
CN111144446B (zh) 一种基于时空网格的司机身份识别方法和系统
CN117894181B (zh) 一种全域通行异常状况集成监测方法及系统
CN116631186A (zh) 基于危险驾驶事件数据的高速公路交通事故风险评估方法、系统
CN114973659A (zh) 一种高速公路的间接事件检测的方法、装置及系统
CN112507624B (zh) 一种城际公路出行方式识别模型构建、识别方法及装置
CN111476449B (zh) 基于改进k均值聚类算法的地铁车站运营时段划分方法
CN118918707B (zh) 一种雷视融合系统质量综合测定方法
KR102739468B1 (ko) 교통 정보를 생성하는 서버, 방법 및 컴퓨터 프로그램
CN118522173B (zh) 智慧云平台停车引导管理系统及方法
CN116092037B (zh) 融合轨迹空间-语义特征的车辆类型识别方法
CN108665705B (zh) 交通诱导统计模型校对方法及装置
CN114092897A (zh) 道路分类方法与设备
CN117831287B (zh) 高速公路拥堵指数的确定方法、装置、设备和存储介质
CN113990069B (zh) 一种基于卫星联动技术的城市交通管理方法及系统
CN119418550B (zh) 一种基于建筑智能化的数据控制系统及方法
CN109785622B (zh) 一种基于车载电子标签技术的拥堵区域识别方法
JP3500134B2 (ja) 区間移動所要時間算出方法及び装置と、区間移動所要時間算出処理用プログラム及びそのプログラムの記録媒体
KR101060673B1 (ko) 교통 정보 데이터 프레임 실행방법과 이를 저장하고 컴퓨터로 판독 가능한 기록매체

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22738907

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 20227033008

Country of ref document: KR

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2023512766

Country of ref document: JP

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 18038974

Country of ref document: US

ENP Entry into the national phase

Ref document number: 2022738907

Country of ref document: EP

Effective date: 20230523

NENP Non-entry into the national phase

Ref country code: DE