Traffic condition analysis method and device

Abstract

The present application discloses a method and device for analyzing traffic conditions, and relates to the field of intelligent traffic technology. The method includes: continuously acquiring information of target traffic participants at each intersection; periodically acquiring the maximum waiting time within the first preset time period based on the first preset time period and the information of target traffic participants at each intersection acquired within the first preset time period; acquiring first traffic information based on the maximum waiting time within the first preset time period acquired within the second preset time period; acquiring second traffic information based on the maximum waiting time within the first preset time period acquired within the second preset time period; acquiring third traffic information based on the maximum waiting time of each intersection direction at each intersection within the first preset time period; and outputting the first traffic information, the second traffic information, and the third traffic information. The present application decomposes a complex algorithm into multiple simple calculations, thereby improving response efficiency and processing capabilities.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation technology, and in particular to a method and device for analyzing traffic conditions. Background Art

[0002] Intelligent transportation is a comprehensive and complex transportation system that effectively integrates and applies advanced information technology, data communication transmission technology, electronic sensor technology, control technology and computer technology to the entire transportation management system.

[0003] Traffic condition analysis at each intersection is an important part of intelligent transportation. It provides a basis for traffic management departments to formulate reasonable traffic management measures, optimize traffic signal timing, improve road conditions, etc. It also helps travelers choose appropriate travel times and routes, and improve the overall operating efficiency and safety of the transportation system.

[0004] Currently, batch processing is used to cache the information of traffic participants over a long period of time, and then calculate the traffic conditions during this period through scheduled tasks. However, when there are too many traffic participants at an intersection, the amount of original visual data will be very large, and this data is disordered. Batch processing also requires spatial calculations, which makes the calculation efficiency very low. Summary of the invention

[0005] In order to overcome the problems existing in the related art, the embodiments of the present application provide a method and device for analyzing traffic conditions. The technical solution is as follows:

[0006] According to a first aspect of an embodiment of the present application, a traffic condition analysis method is provided, the method comprising:

[0007] Continuously obtain information about target traffic participants at each intersection;

[0008] According to the first preset time period and the information of the target traffic participants at each intersection obtained within the first preset time period, periodically obtaining the maximum waiting time of each intersection direction at each intersection within the first preset time period;

[0009] Based on the maximum waiting time of each intersection direction of each intersection obtained within the second preset time period within the first preset time period, obtaining first traffic information, the first traffic information including: a first average waiting time of each intersection direction of each intersection within the second preset time period, a first traffic congestion degree and a first traffic congestion index;

[0010] Based on the maximum waiting time of each intersection direction of each intersection obtained within the second preset time period within the first preset time period, obtaining second traffic information, the second traffic information including: the second average waiting time of each intersection within the second preset time period, the second traffic congestion degree and the second traffic congestion index;

[0011] According to the maximum waiting time of each intersection direction of each intersection within the first preset time period, obtaining third traffic information, the third traffic information including: a third average waiting time, a third traffic congestion degree and a third traffic congestion index of all intersections within the first preset time period;

[0012] The first traffic information, the second traffic information, and the third traffic information are output.

[0013] In one embodiment, the continuously acquiring information of target traffic participants at each intersection includes:

[0014] Continuously obtain image messages from each intersection;

[0015] Acquire information of all traffic participants from the image message; the information of the traffic participants includes: a timestamp when the traffic participants are first recorded at each of the intersections, a timestamp when the traffic participants are last recorded at each of the intersections, and a driving direction of the traffic participants at each of the intersections;

[0016] The information of non-motor vehicles in the information of all traffic participants is filtered out to obtain the information of the target traffic participant.

[0017] In one embodiment, filtering out the information of non-motor vehicles from the information of all traffic participants to obtain the information of the target traffic participant includes:

[0018] Filtering out the information of non-motor vehicles from the information of all traffic participants to obtain the information of candidate traffic participants;

[0019] For each of the intersections, obtaining the waiting time of each of the candidate traffic participants at the current intersection;

[0020] The information of the candidate traffic participants whose waiting time at the current intersection is longer than a preset time is filtered out from the information of the candidate traffic participants to obtain the information of the target traffic participant.

[0021] In one embodiment, the obtaining of the maximum waiting time of each intersection direction at each intersection within the first preset time period includes:

[0022] For each intersection direction of each of the intersections, perform the following steps:

[0023] According to the driving directions of the target traffic participants at the respective intersections acquired within the first preset time period, all the target traffic participants in the current intersection direction of the current intersection are acquired as the traffic participants in the current intersection direction of the current intersection;

[0024] Obtaining the intersection waiting time of each of the traffic participants in the current intersection direction of the current intersection according to the first recorded timestamp and the last recorded timestamp corresponding to each of the traffic participants in the current intersection direction of the current intersection;

[0025] According to the intersection waiting time of each of the traffic participants in the current intersection direction of the current intersection, the maximum waiting time in the current intersection direction of the current intersection within the first preset time period is obtained.

[0026] In one embodiment, the step of obtaining the maximum waiting time of the current intersection direction of the current intersection within the first preset time period according to the intersection waiting time of each of the traffic participants in the current intersection direction of the current intersection includes:

[0027] Obtaining a first minimum value between the waiting time of the first target traffic participant in the current intersection direction of the current intersection and a preset maximum average vehicle delay time as the maximum waiting time;

[0028] The following steps are performed for the waiting time of the remaining target traffic participants in the current intersection direction of the current intersection:

[0029] Obtaining a second minimum value between the waiting time of the current target traffic participant and the preset maximum average vehicle delay time;

[0030] Compare whether the second minimum value is greater than the maximum waiting time calculated previously;

[0031] If it is greater than or equal to, using the second minimum value to overwrite the previously calculated maximum waiting time as the new maximum waiting time, and re-performing the steps of obtaining the second minimum value and comparing for the next target traffic participant;

[0032] If it is less than, the steps of obtaining the second minimum value and comparing are performed again for the next target traffic participant.

[0033] In one embodiment, the first traffic information is obtained, and the first traffic information includes: a first average waiting time, a first traffic congestion degree, and a first traffic congestion index of each intersection direction of each intersection within the second preset time period, including:

[0034] Perform the following steps for each intersection direction at each intersection:

[0035] Obtaining the original waiting time of each target traffic participant in the current intersection direction at the current intersection, wherein the original waiting time is the time difference between the time corresponding to the image message of each target traffic participant just entering the field of view and the time of the previous adjacent image message;

[0036] Obtaining the accumulated number of times each of the target traffic participants is in the current intersection direction of the current intersection, where the accumulated number is the number of image messages corresponding to each of the target traffic participants in the field of view;

[0037] Obtaining the maximum waiting time corresponding to each of the target traffic participants in the current intersection direction of the current intersection within the second preset time period;

[0038] Obtaining a first average waiting time of the current intersection direction of the current intersection within the second preset time period according to the original waiting time of each target traffic participant in the current intersection direction of the current intersection, the accumulated number of times each target traffic participant is in the current intersection direction of the current intersection, and the maximum waiting time corresponding to the current intersection direction of the current intersection within the second preset time period;

[0039] According to the first average waiting time of the current intersection direction of the current intersection within the second preset time period, the first traffic congestion degree and the first traffic congestion index of the current intersection direction of the current intersection within the second preset time period are obtained.

[0040] In one embodiment, the second traffic information is obtained, and the second traffic information includes: the second average waiting time, the second traffic congestion degree and the second traffic congestion index of each intersection within the second preset time period, including:

[0041] For each intersection, perform the following steps:

[0042] Obtaining an average of the first average waiting time of all intersection directions at the current intersection within the second preset time period as the second average waiting time of the current intersection within the second preset time period;

[0043] According to the second average waiting time of the current intersection within the second preset time period, the second traffic congestion degree and the second traffic congestion index of the current intersection within the second preset time period are obtained.

[0044] In one embodiment, third traffic information is obtained, and the third traffic information includes: a third average waiting time, a third traffic congestion degree, and a third traffic congestion index of all intersections within the first preset time period, including:

[0045] Obtaining an average value of maximum waiting times of all intersection directions of all intersections within the first preset time period as a third average waiting time of all intersections within the first preset time period;

[0046] According to the third average waiting time of all the intersections in the first preset time period, the third traffic congestion degree and the third traffic congestion index of all the intersections in the first preset time period are obtained.

[0047] In one embodiment, obtaining the driving direction of the target traffic participant at the intersection from the image message includes:

[0048] Acquiring the heading angle of the target traffic participant at the intersection from the image message;

[0049] The driving direction of the target traffic participant at the intersection is obtained according to the heading angle of the target traffic participant at the intersection.

[0050] According to a second aspect of an embodiment of the present application, a traffic condition analysis device is provided, the traffic condition analysis device comprising:

[0051] The first acquisition module is used to continuously acquire information of target traffic participants at each intersection;

[0052] A second acquisition module, for periodically acquiring the maximum waiting time of each intersection direction at each intersection within the first preset time period according to the first preset time period and the information of the target traffic participants at each intersection acquired within the first preset time period;

[0053] A third acquisition module is used to acquire first traffic information based on the maximum waiting time of each intersection direction of each intersection acquired within the second preset time period within the first preset time period, wherein the first traffic information includes: a first average waiting time of each intersection direction of each intersection within the second preset time period, a first traffic congestion degree and a first traffic congestion index;

[0054] A fourth acquisition module, configured to acquire second traffic information based on the maximum waiting time of each intersection direction of each intersection acquired within the second preset time period within the first preset time period, wherein the second traffic information includes: a second average waiting time, a second traffic congestion degree, and a second traffic congestion index of each intersection within the second preset time period;

[0055] a fifth acquisition module, configured to acquire third traffic information according to the maximum waiting time of each intersection direction of each intersection within the first preset time period, wherein the third traffic information includes: a third average waiting time, a third traffic congestion degree and a third traffic congestion index of all intersections within the first preset time period;

[0056] An output module is used to output the first traffic information, the second traffic information and the third traffic information.

[0057] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application.

[0058] In this application, the batch processing idea is modified to stream processing. When there are many traffic participants at the intersection, the calculation efficiency can be improved by using stream processing, first calculating with the first preset period, and then calculating with the second preset period, and it can be ensured that the excessive data will not be overloaded in the unit time. In addition, in this application, the complex algorithm is disassembled into multiple simple calculations, so as to improve the response efficiency and processing capacity. Because it is through the stream processing method, when the calculation process fails, it is the data processing within a first preset period that fails. In the range of massive data, it will not affect other data, and the data quality problem is guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0060] Figure 1 The figure is a flow chart of a traffic condition analysis method according to an exemplary embodiment.

[0061] Figure 2 is a flowchart of step S101 in a traffic condition analysis method according to an exemplary embodiment.

[0062] Figure 3 is a flowchart of step S102 in the traffic condition analysis method according to an exemplary embodiment.

[0063] Figure 4is a flowchart of step S103 in the traffic condition analysis method according to an exemplary embodiment.

[0064] Figure 5 It is a block diagram of a traffic condition analysis device according to an exemplary embodiment.

[0065] Figure 6 It is a block diagram of a device 90 for analyzing traffic conditions according to an exemplary embodiment. DETAILED DESCRIPTION

[0066] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0067] In the conventional method of calculating road traffic conditions, the information of traffic participants within a period of time is generally cached in a batch processing manner, and then the spatial information of this period is calculated through a scheduled task, and then the traffic conditions are output for storage.

[0068] However, this processing method cannot calculate the traffic conditions at multiple intersections, and if there are too many traffic participants at an intersection, the amount of calculation will be very large, which will lead to low calculation efficiency and the results are not real-time enough.

[0069] Because the information of traffic participants includes spatial information, traffic participant number information, intersection information, speed, and heading angle. Intelligent network data is often massive and high-speed, and is generally reported at a frequency of 10 Hz. For example, if there are currently 10 traffic participants at an intersection, then the intersection will report 100 data in one second, and the intersection will report 6,000 data in one minute. Then, the spatial calculation of these 6,000 data is performed every minute, and the amount of calculation is very huge. In addition, because the coordinates of objects moving do not change much within a few short frames, such spatial calculations consume performance but have little benefit. Comprehensive evaluation is an inefficient task. Considering the amount of data, if there are 10 traffic participants at one intersection, it is already such a large amount of data. If it is an intersection with a larger flow of people and vehicles, and hundreds or thousands of intersections need to be calculated in parallel, the amount of original visual data will be huge, and when calculating uncontrollable data in a certain time window, the robustness of the system cannot be guaranteed.

[0070] In order to solve the problems in the related art, the present application provides a traffic condition analysis method and device.

[0071] First, the technical terms used in this application are explained:

[0072] Traffic congestion: A traffic phenomenon in which vehicles are forced to slow down or stop due to traffic demand exceeding the road capacity or due to traffic incidents, causing the vehicle backlog to exceed a certain level.

[0073] Traffic congestion degree: measures the degree of traffic congestion, which is divided into Level I, Level II, Level III and Level IV, representing severe congestion, moderate congestion, slight congestion and smooth traffic respectively.

[0074] Average intersection delay: the average time loss incurred by vehicles in passing through an intersection.

[0075] Queue length: The length of the vehicle queue from the intersection stop line or the queue start to the end of the queue

[0076] Intersection queue time: The time it takes for vehicles queuing at an intersection to stop for the first time and pass the stop line of the entrance lane.

[0077] Queuing time index: the ratio of vehicle queuing time at a signal-controlled intersection to the signal control cycle.

[0078] Calculation method:

[0079] Intersection evaluation indicators:

[0080] The evaluation indicators of intersection traffic congestion include the maximum average vehicle delay and the maximum queue time index. This application calculates the congestion situation by calculating the maximum average vehicle delay.

[0081] The calculation method of the maximum average vehicle delay is shown in formula (1):

[0082]

[0083] Where: Indicates the maximum average vehicle delay, in seconds (s); It represents the average delay time of vehicles in the i-th entrance lane within a certain time interval, in seconds; n represents the total number of entrance lanes.

[0084] The calculation method of the maximum queuing time index is shown in formula (2):

[0085]

[0086] Where: QTI max Indicates the maximum queue time index; QTI i represents the queuing time index of the i-th entrance within a certain time interval; T irepresents the intersection queue time of vehicles at the i-th entrance lane within a certain time interval, in seconds (s); C represents the length of the signal control cycle, and the average value of the three consecutive cycles before the cycle when the vehicle passes the stop line is obtained, in seconds (s).

[0087] For signalized intersections, the maximum average vehicle delay or the maximum queue time index can be selected as the evaluation index of traffic congestion. The corresponding relationship between each index and traffic congestion is shown in Table 1.

[0088] In Table 1, when the maximum average vehicle delay is between [0,55), the corresponding traffic congestion is smooth; when the maximum average vehicle delay is between [55,100), the corresponding traffic congestion is light; when the maximum average vehicle delay is between [100,145), the corresponding traffic congestion is moderate; when the maximum average vehicle delay is greater than or equal to 145, the corresponding traffic congestion is severe; or, when the maximum queuing time index is between [0,0.8), the corresponding traffic congestion is smooth; when the maximum queuing time index is between [0.8,1.5), the corresponding traffic congestion is light; when the maximum queuing time index is between [1.5,2.1), the corresponding traffic congestion is moderate; when the maximum queuing time index is greater than or equal to 2.1, the corresponding traffic congestion is severe.

[0089] In Table 1, when the traffic congestion degree is smooth, the corresponding color is green, and the corresponding traffic congestion level is IV; when the traffic congestion degree is light, the corresponding color is yellow, and the corresponding traffic congestion level is III; when the traffic congestion degree is moderate, the corresponding color is orange, and the corresponding traffic congestion level is II; when the traffic congestion degree is severe, the corresponding color is red, and the corresponding traffic congestion level is I.

[0090] Table 1

[0091]

[0092] The evaluation index of traffic congestion at unsignalized intersections is the maximum average vehicle delay, and its corresponding relationship with traffic congestion is shown in Table 2.

[0093] In Table 2, when the maximum average delay per vehicle is between [0,35), the corresponding traffic congestion is smooth; when the maximum average delay per vehicle is between [35,50), the corresponding traffic congestion is mild; when the maximum average delay per vehicle is between [50,70), the corresponding traffic congestion is moderate; when the maximum average delay per vehicle is greater than or equal to 70, the corresponding traffic congestion is severe.

[0094] In Table 2, when the traffic congestion degree is smooth, the corresponding color is green, and the corresponding traffic congestion level is IV; when the traffic congestion degree is light, the corresponding color is yellow, and the corresponding traffic congestion level is III; when the traffic congestion degree is moderate, the corresponding color is orange, and the corresponding traffic congestion level is II; when the traffic congestion degree is severe, the corresponding color is red, and the corresponding traffic congestion level is I.

[0095] Table 2

[0096]

[0097]

[0098] Figure 1 is a flow chart of a traffic condition analysis method according to an exemplary embodiment. Figure 1 As shown, the method includes the following steps S101-S106:

[0099] In step S101, information of target traffic participants at each intersection is continuously obtained.

[0100] In one embodiment, Figure 2 As shown, step S101 includes the following sub-steps S1011-S1013:

[0101] S1011. Continue to obtain image messages from each intersection.

[0102] The PTC (Positive Train Control) message is a communication message used in a train control system. The image message of the present application may be in the form of a PTC message.

[0103] The data source of the image message is the structured data of traffic participants uploaded by the intelligent intersection monitoring camera.

[0104] S1012. Obtain information of all traffic participants from the image message; the information of traffic participants includes: a timestamp when the traffic participant is first recorded at each intersection, a timestamp when the traffic participant is last recorded at each intersection, and a driving direction of the traffic participant at each intersection.

[0105] After the image message is obtained, the information of all traffic participants is obtained from the image message through image processing and other methods.

[0106] Among them, the heading angle of the target traffic participant at the intersection can be obtained from the image message, and then the driving direction of the target traffic participant at the intersection is obtained according to the heading angle of the target traffic participant at the intersection.

[0107] S1013. Filter out the information of non-motor vehicles in the information of all traffic participants to obtain the information of the target traffic participant.

[0108] Since the data of non-motor vehicles do not have a significant impact on the calculation of traffic conditions, in order to reduce the amount of data, a large amount of invalid data of non-motor vehicles can be filtered out to initially reduce the amount of subsequent calculation data to improve calculation efficiency. In this application, the target traffic participants refer to motor vehicles.

[0109] In one embodiment, step S1013 includes the following sub-steps S10131-S10134:

[0110] S10131. Filter out the information of non-motor vehicles from the information of all traffic participants to obtain the information of candidate traffic participants.

[0111] First, the information of non-motor vehicles is filtered out from the information of all traffic participants, and then the information of the remaining traffic participants is filtered.

[0112] S10132. For each intersection, obtain the waiting time of each candidate traffic participant at the current intersection.

[0113] After obtaining the information of the candidate traffic participants, for each intersection, the waiting time of the candidate traffic participants at the current intersection can be obtained through the timestamp when the candidate traffic participants were first recorded at the current intersection and the timestamp when the candidate traffic participants were last recorded at each intersection.

[0114] S10133. Filter out the information of candidate traffic participants whose waiting time at the current intersection is longer than a preset time from the information of candidate traffic participants to obtain the information of the target traffic participant.

[0115] Among them, if there are many illegally parked vehicles at an intersection, it may affect the results, because too many illegally parked vehicles will lead to long queues at the intersection. The judgment of the preset time length is to exclude the influence of illegally parked motor vehicles on the calculation results. For example, the preset time length can be 600 seconds, that is, a car that has not left the field of vision for 600 seconds is set as an illegally parked vehicle and does not need to participate in the calculation.

[0116] Redis (Remote Dictionary Server) is an open source, high-performance key-value storage system. The information of the target traffic participants in this application can be stored in the form of Redis, and the data structure is hash, as shown in Table 3. In Table 3, only traffic participants of the type of motor vehicles with a certain speed are stored. The storage result is a key-value structure, the key is the ID of a traffic participant at a certain intersection, the value is the timestamp of the first time the traffic participant was recorded (the time when the PTC message was reported when the key was created), the timestamp of the last time it was recorded (the time when each PTC message was reported to be received), and the direction value calculated according to the heading angle of the traffic participant.

[0117] It is worth noting that the data in this application is stored in redis, so it will not be lost, and the system can continue to calculate even if it crashes and restarts.

[0118] Table 3

[0119]

[0120]

[0121]

[0122] The heading angle refers to the angle between the longitudinal axis (generally the forward direction) of the carrier (such as an aircraft, ship, vehicle, etc.) and a reference direction. The calculation method of the direction value calculated based on the heading angle of the traffic participant includes:

[0123] When the key in Table 3 is first created, a direction is divided into 8 equal parts and the angles in the polar coordinate system can be used to represent these 8 directions. Generally speaking, these 8 directions can be represented as: 0° for (east), 45° for (northeast), 90° for (north), 135° for (northwest), 180° for (west), 225° for (southwest), 270° for (south), and 315° for (southeast).

[0124] If the heading angle θ is given, the following steps can be used to find the corresponding direction index value:

[0125] Step 1, convert the angle θ into a value within the range of 0-360°, that is, the above θ should be in degrees;

[0126] Step 2: Formula The calculated value is rounded down, and the resulting integer is the direction index value.

[0127] After obtaining the direction index value, one of the eight directions corresponding to θ can be found according to the direction index table shown in Table 4:

[0128] Table 4

[0129]

[0130]

[0131] For example: if the calculated direction index value is 7, then set it to 7; if the calculated direction index value is 8, then set it to 0, and so on.

[0132] When the calculated direction index value is greater than 7, the current direction index value is determined according to N-7M-1, where 0≤N-7M-1≤7 and M is an integer greater than 0. For example, the calculated direction index value is 28, then N is 28. When M is 1, 28-7×1-1=20, which is greater than 7 and does not meet the requirements. When M is 2, 28-7×2-1=13, which is greater than 7 and does not meet the requirements. When M is 3, 28-7×3-1=6, which is less than 7 and meets the requirements. At this time, the calculated direction index value 28 is set to 6.

[0133] In Table 3, the intersection ID and data status flag (value=0, 1, 2) are also recorded, where 0 means only saving; 1 means the next step of calculation can be performed; and 2 means not participating in the calculation.

[0134] For example, when the waiting time exceeds 600 seconds, it is set to 2 (considered as parking time too long).

[0135] This application uses simple calculations to analogize a two-dimensional coordinate system. Under the premise that the position of each stop line at each intersection is known, a simple greater than or less than comparison can be used to determine whether the participant has passed the stop line. If so, the state of the object can be temporarily modified to mark it as "driving out", that is, if the coordinates are judged to have crossed the stop line, then it is set to 1;

[0136] Specific:

[0137] When the direction is 0, the latitude < the stop line latitude 0, then it is determined that the stop line has been crossed;

[0138] It can be understood as: the XY axis of the two-dimensional coordinate system, if the coordinates of the two ends of the parking line are now (0, 0) (10, 0), assuming that the point is moving along the positive direction of the Y axis, when the participant's coordinates are (4, -5), it means that it has not crossed the parking line. When the participant's coordinates are (4, 6), it means that it has crossed the parking line, because -5<0, and 6>0, so when the Y coordinate is greater than the Y coordinate of the parking line, it has crossed the parking line.

[0139] When the direction is 1, the latitude < the stop line latitude 1 and the longitude < the stop line longitude 1, then it is determined that the stop line has been crossed;

[0140] When the direction is 2, the longitude < the stop line longitude 2, then it is determined that the stop line has been crossed;

[0141] When the direction is 3, the latitude > the stop line latitude 3 and the longitude < the stop line longitude 3, then it is determined that the stop line has been crossed;

[0142] When the direction is 4, the latitude > the stop line latitude 4, then it is determined that the stop line has been crossed;

[0143] When the direction is 5, the latitude > the stop line latitude 5 and the longitude > the stop line longitude 5, then it is determined that the stop line has been crossed;

[0144] When the direction is 6, the longitude > the stop line longitude 6, then it is determined that the stop line has been crossed;

[0145] When the direction is 7, latitude < stop line latitude 7 and longitude > stop line longitude 7, it is determined that the stop line is crossed.

[0146] In step S102, based on the first preset time period and the information of the target traffic participant at each intersection obtained within the first preset time period, the maximum waiting time of each intersection direction at each intersection within the first preset time period is periodically obtained.

[0147] For example, the first preset time period can be at the minute level, for example: the first time period can be 1 minute, 2 minutes, etc., and 1 minute is taken as an example for explanation. With 1 minute as a period, the maximum waiting time of each direction of each intersection within 1 minute is obtained based on the information of the target traffic participants at each intersection obtained within 1 minute. For example, after obtaining the information of the target traffic participants at each intersection within 1 minute from 4:24:00 to 4:24:60, the maximum waiting time within 1 minute from 4:24:00 to 4:24:60 will be calculated. Continuing, after obtaining the information of the target traffic participants at each intersection within 1 minute from 4:25:00 to 4:25:60, the maximum waiting time within 1 minute from 4:25:00 to 4:25:60 will be calculated, and so on.

[0148] This step is used to calculate the maximum waiting time of each direction at each intersection within the first preset time period, as shown in Table 5. Taking the first preset time period as minutes as an example, the data can also be stored in Redis, and the structure is also a key-value structure. The key is the intersection ID-direction, and the value is the maximum waiting time for the direction of the intersection at a specific minute.

[0149] Table 5

[0150]

[0151] Specifically, Figure 3 As shown, the following steps S1021-S1023 are performed for each intersection direction of each intersection:

[0152] S1021. According to the driving directions of the target traffic participants at the respective intersections acquired within the first preset time period, all the target traffic participants in the current intersection direction of the current intersection are acquired as the traffic participants in the current intersection direction of the current intersection.

[0153] Obtain target traffic participants in the current intersection direction from massive data.

[0154] S1022. Obtain the intersection waiting time of each traffic participant in the current intersection direction of the current intersection according to the first recorded timestamp and the last recorded timestamp corresponding to each traffic participant in the current intersection direction of the current intersection.

[0155] Based on the last recorded timestamp of each target traffic participant in the current intersection direction minus the first recorded timestamp of the corresponding target traffic participant, the intersection waiting time of each traffic participant in the current intersection direction can be obtained.

[0156] S1023. According to the intersection waiting time of each target traffic participant in the current intersection direction of the current intersection, obtain the maximum waiting time in the current intersection direction of the current intersection within the first preset time period.

[0157] In Table 5, an explanation of the maximum waiting time is also given.

[0158] Maximum waiting time: Min ((end time - start time), 145) of the waiting time of each target traffic participant is compared with the maximum waiting time. If it exceeds, it is overwritten. Specifically, step S1023 includes the following sub-steps:

[0159] S10231. Obtain a first minimum value between the waiting time of the first target traffic participant in the current intersection direction of the current intersection and a preset maximum average vehicle delay time as the maximum waiting time.

[0160] In Table 5, the preset maximum average vehicle delay is 145s. The preset maximum average vehicle delay can be adjusted according to the actual scenario, and the present disclosure does not limit it. Table 5 is only an example.

[0161] Select any one of all the target traffic participants in the current intersection direction of the current intersection as the first target traffic participant to start the calculation, first determine the first minimum value min1 between the waiting time of the first target traffic participant and the preset maximum average vehicle delay time, and use this value as the maximum waiting time at this time.

[0162] It is worth noting that if there is only one target traffic participant in the current intersection direction of the current intersection, then the first minimum value min1 calculated at this time is the maximum waiting time in the current intersection direction of the current intersection. If there are multiple target traffic participants in the current intersection direction of the current intersection, then the first minimum value min1 calculated at this time is not necessarily the maximum waiting time in the current intersection direction of the current intersection. At this time, the following steps are performed for the waiting time of the remaining target traffic participants in the current intersection direction of the current intersection:

[0163] S10232. Obtain the second minimum value between the waiting time of the current target traffic participant and the preset maximum average vehicle delay time.

[0164] S10233. Compare whether the second minimum value is greater than the maximum waiting time calculated previously.

[0165] S10234. If it is greater than or equal to, use the second minimum value to overwrite the previously calculated maximum waiting time as the new maximum waiting time, and re-execute the steps of obtaining the second minimum value and comparing for the next target traffic participant.

[0166] S10235: If it is less than, re-execute the steps of obtaining the second minimum value and comparing for the next target traffic participant.

[0167] For example, the second minimum value min2 between the waiting time of the second target traffic participant and the preset maximum average vehicle delay time is obtained, and min2 is compared to see whether it is greater than the previously calculated maximum waiting time min1. If it is greater than or equal to, min2 is used to overwrite the previously calculated maximum waiting time min2 as the new maximum waiting time, and the steps of obtaining the second minimum value and comparing are repeated for the third target traffic participant. At this time, the second minimum value min3 of the third target traffic participant is compared with the above-mentioned new maximum waiting time min2. If it is less than, the previously calculated maximum waiting time min1 is not updated, and then the steps of obtaining the second minimum value and comparing are repeated for the third target traffic participant.

[0168] In step S103, first traffic information is obtained based on the maximum waiting time of each intersection direction at each intersection within the first preset time period obtained within the second preset time period, and the first traffic information includes: a first average waiting time of each intersection direction at each intersection within the second preset time period, a first traffic congestion degree and a first traffic congestion index.

[0169] For example, the second preset time period may be in hours.

[0170] In this step, the first average waiting time, the first traffic congestion degree and the first traffic congestion index of each intersection direction at each hour level are calculated. As shown in Table 6, the data calculated in this step can also be stored in Redis, and the structure is a key-value structure, where the key is the intersection ID-direction, and the value is the accumulated number of times, the first average waiting time, the first congestion degree and the first traffic congestion index.

[0171] Table 6

[0172]

[0173]

[0174] In step S103, Figure 4 As shown, the following steps S1031-S1035 are performed for each intersection direction of each intersection:

[0175] S1031. Obtain the original waiting time of each target traffic participant in the current intersection direction at the current intersection, where the original waiting time is the time difference between the time corresponding to the image message of each target traffic participant just entering the field of view and the time of the previous adjacent image message.

[0176] S1032. Obtain the accumulated number of times each target traffic participant is at the current intersection direction, where the accumulated number is the number of image messages corresponding to each target traffic participant in the field of view.

[0177] The number of image messages corresponding to each target traffic participant in the field of view is obtained as the cumulative number.

[0178] S1033. Obtain the maximum waiting time corresponding to each target traffic participant in the second preset time period in the current intersection direction of the current intersection.

[0179] The maximum waiting time corresponding to the second preset time period is the maximum value of the maximum waiting time calculated in all the first preset time periods included in the second preset time period.

[0180] S1034. Obtain the first average waiting time of the current intersection direction of the current intersection within the second preset time period based on the original waiting time of each target traffic participant in the current intersection direction of the current intersection, the accumulated number of times of each target traffic participant in the current intersection direction of the current intersection and the maximum waiting time corresponding to the current intersection direction of the current intersection within the second preset time period.

[0181] That is, the first average waiting time=(original waiting time×accumulated number of times+corresponding maximum waiting time within the second preset time period) / (accumulated number of times+1).

[0182] S1035. Obtain a first traffic congestion degree and a first traffic congestion index in the current intersection direction within the second preset time period based on the first average waiting time in the current intersection direction within the second preset time period.

[0183] After obtaining the first average waiting time, the first average waiting time can be used as the maximum average vehicle delay in Table 2 and Table 3 to obtain the first traffic congestion degree, and then the first average waiting time is divided by 14.5 and rounded to get the first traffic congestion index. It is worth noting that when the calculated value is greater than 10, the first traffic congestion index is 10, where the larger the value of the first traffic congestion index, the more congested it is.

[0184] That is, when the first average waiting time is between [0,55), the corresponding first traffic congestion degree is unblocked; when the first average waiting time is between [55,100), the corresponding first traffic congestion degree is lightly congested; when the first average waiting time is between [100,145), the corresponding first traffic congestion degree is moderately congested; and when the first average waiting time is greater than or equal to 145, the corresponding first traffic congestion degree is severely congested.

[0185] In step S104, based on the maximum waiting time of each intersection direction at each intersection obtained within the second preset time period within the first preset time period, second traffic information is obtained, and the second traffic information includes: the second average waiting time of each intersection within the second preset time period, the second traffic congestion degree and the second traffic congestion index.

[0186] In this step, the scheduled task service is used to calculate the traffic conditions of each intersection every hour, and the corresponding values ​​are obtained from the redis in Table 5. The calculated values ​​are also stored in redis in the form of key-value, where the key is the year, month, day and time, and the value is the second average waiting time, the second traffic congestion degree and the second traffic congestion index.

[0187] Table 7

[0188]

[0189]

[0190] In Table 7, the second average waiting time is obtained by calculating the arithmetic mean of the first average waiting time in all directions (0-7) of all intersections. Specifically, in step S104, the following steps S1041-S1042 are performed for each intersection:

[0191] S1041. Obtain an average value of the first average waiting time of all intersection directions at the current intersection within the second preset time period as the second average waiting time of the current intersection within the second preset time period.

[0192] S1042. Obtain a second traffic congestion degree and a second traffic congestion index of the current intersection within a second preset time period according to a second average waiting time of the current intersection within a second preset time period.

[0193] After obtaining the second average waiting time, the second average waiting time can be used as the maximum average vehicle delay in Table 2 and Table 3 to obtain the second traffic congestion degree, and then the second average waiting time is divided by 14.5 and rounded to get the second traffic congestion index. It is worth noting that when the calculated value is greater than 10, the second traffic congestion index is 10.

[0194] That is, when the second average waiting time is between [0,55), the corresponding second traffic congestion degree is unblocked; when the second average waiting time is between [55,100), the corresponding second traffic congestion degree is lightly congested; when the second average waiting time is between [100,145), the corresponding second traffic congestion degree is moderately congested; and when the second average waiting time is greater than or equal to 145, the corresponding second traffic congestion degree is severely congested.

[0195] In step S105, the third traffic information is obtained according to the maximum waiting time of each intersection direction at each intersection within the first preset time period, and the third traffic information includes: the third average waiting time of all intersections within the first preset time period, the third traffic congestion degree and the third traffic congestion index.

[0196] In this step, the congestion situation of each intersection is calculated in batches every minute through the scheduled task service, and the value is obtained from the redis in Table 5. After calculation, it is also stored in redis and stored in the form of key-value as shown in Table 8. The key is the year, month, day, hour and minute (accurate to minutes), and the value is the third average waiting time, the third traffic congestion degree and the third traffic congestion index.

[0197] Table 8

[0198]

[0199] In one embodiment, step S105 includes the following sub-steps S1051-S1052:

[0200] S1051. Obtain an average value of maximum waiting times in all directions of all intersections within a first preset time period as a third average waiting time for all intersections within the first preset time period.

[0201] S1052. Obtain a third traffic congestion degree and a third traffic congestion index for all intersections within the first preset time period according to the third average waiting time for all intersections within the first preset time period.

[0202] After obtaining the third average waiting time, the third average waiting time can be used as the maximum average vehicle delay in Table 2 and Table 3 to obtain the third traffic congestion degree, and then the third average waiting time is divided by 14.5 and rounded to get the third traffic congestion index. It is worth noting that when the calculated value is greater than 10, the third traffic congestion index is 10.

[0203] That is, when the third average waiting time is between [0,55), the corresponding third traffic congestion degree is unblocked; when the third average waiting time is between [55,100), the corresponding third traffic congestion degree is lightly congested; when the third average waiting time is between [100,145), the corresponding third traffic congestion degree is moderately congested; and when the third average waiting time is greater than or equal to 145, the corresponding third traffic congestion degree is severely congested.

[0204] In step S106 , the first traffic information, the second traffic information, and the third traffic information are output.

[0205] This application adopts a stream processing approach, first calculating at the minute level and then at the hour level, which can improve computing efficiency.

[0206] Specifically, in this application, the batch processing idea is modified to stream processing. The uncontrollability of batch processing in related technologies is reflected in the following aspects: there may be many traffic participants at the intersection. When this scenario occurs, the data processed in batches at the same time exceeds the computing load of the system, which will affect the computing efficiency or paralyze the system. The core idea of ​​stream processing is to calculate every piece of data received by the system. And the complex algorithm is disassembled. That is, each piece of data is processed separately, which can ensure that the excessive data will not be overloaded in the unit time. However, the complexity of the algorithm is too high, and the high-frequency data will also make the computer unable to respond in time. Disassembling complex algorithms into multiple simple calculations can improve the system response efficiency and improve the system processing capabilities.

[0207] Furthermore, each piece of data will be parsed and stored when it enters the system for processing, such as updating the participant's current time, the participant's intersection and direction, and other information. And through simple calculations (analogous to a two-dimensional coordinate system, under the premise of knowing the position of each stop line at each intersection, a simple greater than or less than comparison can be used to determine whether the participant has passed the stop line. If passed, the state of the object can be temporarily modified to mark it as "driving out". Then, according to the batch calculation of the participant's consumption time, the travel time of the intersection can be calculated. The calculation of this batch processing is relatively simple and can also be calculated at a high frequency. Here is the minute level, that is, all intersections are calculated once a minute. Then the minute-level data can be aggregated into the hour level by more advanced batch processing, and the data of each direction of the intersection can be aggregated into the intersection level.

[0208] Through the above analysis, it can be seen that this application can achieve the following effects for the traffic industry in calculating the traffic conditions of multiple intersections under the premise of clear stop lines:

[0209] 1) Availability: When there are many intersections and the number of traffic participants is uncontrollable, the computing tasks cannot be executed in time due to batch processing computing power and computing efficiency in related technologies. This application converts batch processing into stream processing to calculate each piece of data to ensure the executability of the calculation.

[0210] 2) Efficiency: When processing massive amounts of high-velocity data, time-consuming calculations are converted into streaming calculations that are output as soon as they are received, greatly shortening the entire data life cycle and improving computing efficiency.

[0211] 3) Stability: Because each piece of data is calculated separately, when a failure occurs in the calculation process, it is only a failure in the processing of one piece of data. In the scope of massive data, it will not affect other data, and data quality issues are guaranteed.

[0212] Among them, because the time of data entering the system will be recorded and updated, each frame of data will be updated, and the minute-level data is aggregated. The source of the minute-level is that the scheduled task runs in batches every minute. If it runs once every 30 seconds, it is 30 seconds, and if it runs once every 15 seconds, it can be 15 seconds. Here, for each traffic participant, there is a specific ID at the corresponding intersection. The intersection + participant ID is unique, and each frame of data will be updated to the corresponding intersection: the time information of the participant ID can be calculated in batch processing.

[0213] 4) Scalability: The processing efficiency can be linearly improved by horizontally expanding the processing equipment.

[0214] In summary, by introducing this application, an efficient algorithm for calculating traffic conditions is provided in smart transportation, smart cities, and autonomous driving demonstration areas to enhance the infrastructure capabilities of the industry.

[0215] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application.

[0216] Figure 5 is a block diagram of a traffic condition analysis device according to an exemplary embodiment. Figure 5 As shown, the traffic condition analysis device includes:

[0217] A first acquisition module 11 is used to continuously acquire information of target traffic participants at each intersection;

[0218] A second acquisition module 12 is used to periodically acquire the maximum waiting time of each intersection direction at each intersection within the first preset time period according to the first preset time period and the information of the target traffic participants at each intersection acquired within the first preset time period;

[0219] The third acquisition module 13 is used to acquire first traffic information based on the maximum waiting time of each intersection direction of each intersection acquired within the second preset time period within the first preset time period, wherein the first traffic information includes: a first average waiting time of each intersection direction of each intersection within the second preset time period, a first traffic congestion degree and a first traffic congestion index;

[0220] The fourth acquisition module 14 is used to acquire second traffic information based on the maximum waiting time of each intersection direction of each intersection acquired within the second preset time period within the first preset time period, wherein the second traffic information includes: a second average waiting time, a second traffic congestion degree, and a second traffic congestion index of each intersection within the second preset time period;

[0221] A fifth acquisition module 15 is used to acquire third traffic information according to the maximum waiting time of each intersection direction of each intersection within the first preset time period, and the third traffic information includes: a third average waiting time, a third traffic congestion degree and a third traffic congestion index of all intersections within the first preset time period;

[0222] The output module 16 is configured to output the first traffic information, the second traffic information and the third traffic information.

[0223] The present application also provides a traffic condition analysis device, comprising:

[0224] processor;

[0225] a memory for storing processor-executable instructions;

[0226] The processor is configured as follows:

[0227] Continuously obtain information about target traffic participants at each intersection;

[0228] According to the first preset time period and the information of the target traffic participants at each intersection obtained within the first preset time period, periodically obtaining the maximum waiting time of each intersection direction at each intersection within the first preset time period;

[0229] Based on the maximum waiting time of each intersection direction of each intersection obtained within the second preset time period within the first preset time period, obtaining first traffic information, the first traffic information including: a first average waiting time of each intersection direction of each intersection within the second preset time period, a first traffic congestion degree and a first traffic congestion index;

[0230] Based on the maximum waiting time of each intersection direction of each intersection obtained within the second preset time period within the first preset time period, obtaining second traffic information, the second traffic information including: the second average waiting time of each intersection within the second preset time period, the second traffic congestion degree and the second traffic congestion index;

[0231] According to the maximum waiting time of each intersection direction of each intersection within the first preset time period, obtaining third traffic information, the third traffic information including: a third average waiting time, a third traffic congestion degree and a third traffic congestion index of all intersections within the first preset time period;

[0232] The first traffic information, the second traffic information, and the third traffic information are output.

[0233] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0234] Figure 6 is a block diagram of a device 90 for traffic condition analysis according to an exemplary embodiment. For example, the device 90 can be provided as a server. The device 90 includes a processing component 902, which further includes one or more processors, and a memory resource represented by a memory 903, which is used to store instructions that can be executed by the processing component 902, such as an application. The application stored in the memory 903 can include one or more modules, each of which corresponds to a set of instructions. In addition, the processing component 902 is configured to execute instructions to perform the above method.

[0235] The device 90 may also include a power supply component 906 configured to perform power management of the device 90, a wired or wireless network interface 905 configured to connect the device 90 to a network, and an input / output (I / O) interface 908. The device 90 may operate based on an operating system stored in the memory 903, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™ or the like.

[0236] A non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by the processor of the device 90, enables the device 90 to perform the above-mentioned traffic condition analysis method.

[0237] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the application disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0238] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A traffic condition analysis method, characterized in that: The method comprises: Continuously obtain information about target traffic participants at each intersection; According to a first preset time period and information of target traffic participants at each intersection obtained within the first preset time period, periodically obtaining a maximum waiting time of each intersection direction at each intersection within the first preset time period; Based on the maximum waiting time of each intersection direction of each intersection obtained within the second preset time period within the first preset time period, obtaining first traffic information, the first traffic information including: a first average waiting time of each intersection direction of each intersection within the second preset time period, a first traffic congestion degree and a first traffic congestion index; Based on the maximum waiting time of each intersection direction of each intersection obtained in the second preset time period in the first preset time period, obtaining second traffic information, the second traffic information including: the second average waiting time of each intersection in the second preset time period, the second traffic congestion degree and the second traffic congestion index; According to the maximum waiting time of each intersection direction of each intersection within the first preset time period, third traffic information is obtained, wherein the third traffic information includes: a third average waiting time, a third traffic congestion degree and a third traffic congestion index of all intersections within the first preset time period; The first traffic information, the second traffic information, and the third traffic information are output.

2. The method according to claim 1, characterized in that The continuously acquiring information of target traffic participants at each intersection includes: Continuously acquiring image messages of each intersection; Acquire information of all traffic participants from the image message; the information of the traffic participants includes: a timestamp when the traffic participants are first recorded at each intersection, a timestamp when the traffic participants are last recorded at each intersection, and a driving direction of the traffic participants at each intersection; The information of non-motor vehicles in the information of all traffic participants is filtered out to obtain the information of the target traffic participant.

3. The method according to claim 2, characterized in that The filtering out the information of non-motor vehicles from the information of all traffic participants to obtain the information of the target traffic participant includes: Filtering out the information of non-motor vehicles from the information of all traffic participants to obtain the information of candidate traffic participants; For each of the intersections, obtaining the waiting time of each of the candidate traffic participants at the current intersection; The information of the candidate traffic participants whose waiting time at the current intersection is longer than a preset time is filtered out from the information of the candidate traffic participants to obtain the information of the target traffic participant.

4. The method according to claim 3, characterized in that The obtaining of the maximum waiting time of each intersection direction at each intersection within the first preset time period includes: For each intersection direction of each of the intersections, perform the following steps: According to the driving directions of each of the target traffic participants at each intersection obtained within the first preset time period, all the target traffic participants in the current intersection direction of the current intersection are obtained as traffic participants in the current intersection direction of the current intersection; Obtaining the intersection waiting time of each of the traffic participants in the current intersection direction of the current intersection according to the first recorded timestamp and the last recorded timestamp corresponding to each of the traffic participants in the current intersection direction of the current intersection; According to the intersection waiting time of each of the traffic participants in the current intersection direction of the current intersection, the maximum waiting time in the current intersection direction of the current intersection within the first preset time period is obtained.

5. The method according to claim 4, characterized in that The step of obtaining the maximum waiting time of the current intersection direction of the current intersection within the first preset time period according to the intersection waiting time of each of the traffic participants in the current intersection direction of the current intersection includes: Obtaining a first minimum value between the waiting time of the first target traffic participant in the current intersection direction of the current intersection and a preset maximum average vehicle delay time as the maximum waiting time; The following steps are performed for the waiting time of the remaining target traffic participants in the current intersection direction of the current intersection: Obtaining a second minimum value between the waiting time of the current target traffic participant and the preset maximum average vehicle delay time; Compare whether the second minimum value is greater than the maximum waiting time calculated previously; If it is greater than or equal to, using the second minimum value to overwrite the previously calculated maximum waiting time as the new maximum waiting time, and re-performing the steps of obtaining the second minimum value and comparing for the next target traffic participant; If it is less than, the steps of obtaining the second minimum value and comparing are performed again for the next target traffic participant.

6. The method according to claim 5, characterized in that The first traffic information is obtained, wherein the first traffic information includes: a first average waiting time, a first traffic congestion degree and a first traffic congestion index of each intersection direction of each intersection within the second preset time period, including: Perform the following steps for each intersection direction at each intersection: Obtaining the original waiting time of each of the target traffic participants in the current intersection direction of the current intersection, wherein the original waiting time is the time difference between the time corresponding to the image message of each of the target traffic participants just entering the field of view and the time of the previous adjacent image message; wherein the field of view is the shooting range corresponding to the image acquisition device used to acquire the image message; Obtaining the accumulated number of times each of the target traffic participants is in the current intersection direction of the current intersection, where the accumulated number is the number of image messages corresponding to each of the target traffic participants in the field of view; Obtaining the maximum waiting time corresponding to each of the target traffic participants in the current intersection direction of the current intersection within the second preset time period; Obtaining a first average waiting time of the current intersection direction of the current intersection within the second preset time period according to the original waiting time of each target traffic participant in the current intersection direction of the current intersection, the accumulated number of times each target traffic participant is in the current intersection direction of the current intersection, and the maximum waiting time corresponding to the current intersection direction of the current intersection within the second preset time period; According to the first average waiting time of the current intersection direction of the current intersection within the second preset time period, the first traffic congestion degree and the first traffic congestion index of the current intersection direction of the current intersection within the second preset time period are obtained.

7. The method according to claim 6, characterized in that The obtaining of the second traffic information, wherein the second traffic information includes: the second average waiting time, the second traffic congestion degree and the second traffic congestion index of each intersection within the second preset time period, includes: For each intersection, perform the following steps: Obtaining an average of the first average waiting time of all intersection directions at the current intersection within the second preset time period as the second average waiting time of the current intersection within the second preset time period; According to the second average waiting time of the current intersection within the second preset time period, the second traffic congestion degree and the second traffic congestion index of the current intersection within the second preset time period are obtained.

8. The method according to claim 7, characterized in that Acquire third traffic information, the third traffic information including: a third average waiting time, a third traffic congestion degree and a third traffic congestion index of all intersections within the first preset time period, including: Obtaining an average value of maximum waiting times of all intersection directions of all intersections within the first preset time period as a third average waiting time of all intersections within the first preset time period; According to the third average waiting time of all the intersections in the first preset time period, the third traffic congestion degree and the third traffic congestion index of all the intersections in the first preset time period are obtained.

9. The method according to claim 2, characterized in that: The obtaining the driving direction of the target traffic participant at the intersection from the image message includes: Acquiring the heading angle of the target traffic participant at the intersection from the image message; The driving direction of the target traffic participant at the intersection is obtained according to the heading angle of the target traffic participant at the intersection.

10. A traffic condition analysis device, characterized in that: The traffic condition analysis device comprises: The first acquisition module is used to continuously acquire information of target traffic participants at each intersection; A second acquisition module, for periodically acquiring the maximum waiting time of each intersection direction at each intersection within the first preset time period according to the first preset time period and the information of the target traffic participants at each intersection acquired within the first preset time period; A third acquisition module is used to acquire first traffic information based on the maximum waiting time of each intersection direction of each intersection acquired within the second preset time period within the first preset time period, wherein the first traffic information includes: a first average waiting time of each intersection direction of each intersection within the second preset time period, a first traffic congestion degree and a first traffic congestion index; a fourth acquisition module, configured to acquire second traffic information based on the maximum waiting time of each intersection direction of each intersection acquired within the second preset time period within the first preset time period, wherein the second traffic information includes: a second average waiting time of each intersection within the second preset time period, a second traffic congestion degree, and a second traffic congestion index; a fifth acquisition module, configured to acquire third traffic information according to the maximum waiting time of each intersection direction of each intersection within the first preset time period, wherein the third traffic information includes: a third average waiting time, a third traffic congestion degree and a third traffic congestion index of all intersections within the first preset time period; An output module is used to output the first traffic information, the second traffic information and the third traffic information.

Images