Lane congestion degree judgment method and road congestion edge analysis box

Abstract

The embodiment of the invention discloses a lane congestion degree judgment method and a road congestion edge analysis box, the method is applied to the road congestion edge analysis box, the road congestion edge analysis box is connected with front-end equipment, and the method comprises the following steps: receiving front-end real-time data from the front-end equipment, the front-end real-time data comprises at least one of electric card vehicle passing data, radar data and video stream data; analyzing motor vehicle traffic participation elements according to the front-end real-time data; and based on an analysis result, judging a lane congestion degree, and outputting a traffic congestion event result. According to the embodiment of the invention, the motor vehicle traffic participation elements are analyzed according to the front-end real-time data, the intersection traffic object is perceived in real time, the lane congestion degree is further judged, and accurate data support is provided for traffic management.

Description

Technical Field

[0001] The present application belongs to the field of edge computing technology, and specifically relates to a method for determining the degree of lane congestion and a road congestion edge analysis box. Background Art

[0002] With the development of urbanization, the urban population size continues to expand. Today, urban traffic congestion is still a common problem, and cities of different sizes still need various types of construction solutions such as high-end customization or basic transformation to optimize the management of traffic congestion.

[0003] As the number of vehicles in cities increases year by year, road traffic pressure continues to intensify. Existing technology is unable to monitor lane congestion in real time, and thus cannot meet the needs of quickly identifying safety hazards.

[0004] Application Contents

[0005] The purpose of the embodiments of the present application is to provide a method for determining the degree of lane congestion and a road congestion edge analysis box to address the defect that the prior art cannot monitor the degree of lane congestion in real time.

[0006] In order to solve the above technical problems, this application is implemented as follows:

[0007] In a first aspect, a method for determining the degree of lane congestion is provided, which is applied to a road congestion edge analysis box, wherein the road congestion edge analysis box is connected to a front-end device, and the method comprises the following steps:

[0008] Receiving front-end real-time data from the front-end device, the front-end real-time data including at least one of electric card passing data, radar data and video stream data;

[0009] Analyzing the motor vehicle traffic participation elements according to the front-end real-time data;

[0010] Based on the analysis results, the lane congestion level is determined and the traffic congestion event results are output.

[0011] In a second aspect, a road congestion edge analysis box is provided, the road congestion edge analysis box is connected to a front-end device, and the road congestion edge analysis box includes:

[0012] A receiving module, used for receiving front-end real-time data from the front-end device, wherein the front-end real-time data includes at least one of electric card passing data, radar data and video stream data;

[0013] An analysis module, used for analyzing the motor vehicle traffic participation elements according to the front-end real-time data;

[0014] The judgment module is used to judge the lane congestion degree based on the analysis results and output the traffic congestion event results.

[0015] The embodiment of the present application analyzes the elements participating in motor vehicle traffic based on front-end real-time data, perceives traffic objects at intersections in real time, and then determines the degree of lane congestion, providing accurate data support for traffic management. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of a method for determining the degree of lane congestion provided in an embodiment of the present application;

[0017] Figure 2 It is a schematic diagram of the architecture of the traffic road congestion edge analysis box provided in an embodiment of the present application;

[0018] Figure 3 It is a structural schematic diagram of a road congestion edge analysis box provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0020] As the number of urban vehicles increases year by year, road traffic pressure continues to increase. There is an urgent need for edge computing to monitor and analyze traffic violations in real time and quickly identify safety hazards. The road congestion edge analysis box plays an important role in urban road traffic management. It provides data support for intelligent traffic management by analyzing traffic flow and violations in real time. On the other hand, the advancement of smart city construction requires urban traffic management to be more intelligent and efficient. As an important part of smart city traffic management, the road congestion edge analysis box has received great attention from the government and related companies, and has broad market prospects.

[0021] Specifically, the road congestion edge analysis box is based on big data technology and artificial intelligence technology. It is committed to integrating multi-source traffic data, edge computing technology, and vehicle-road collaborative technology to implement a new type of traffic solution of "autonomous learning, intelligent congestion relief, deep cognition, and efficient control" to solve the problem of "easy to congest and difficult to control" in urban traffic.

[0022] First, in urban traffic management, it is widely used in key locations such as main roads and intersections in cities, helping traffic management departments to monitor traffic flow in real time, identify congested sections and causes, and take timely measures such as traffic diversion and signal optimization. For example, traffic command centers in some cities have achieved real-time monitoring and intelligent management of urban traffic by deploying edge analysis boxes.

[0023] Secondly, in the intelligent transportation system, it is combined with other equipment and technologies in the intelligent transportation system, such as intelligent traffic lights and electronic police, to form a collaborative traffic management system. The edge analysis box can transmit the analysis results to related equipment in real time to achieve automatic adjustment of traffic signals and automatic capture of traffic violations.

[0024] Finally, in specific scenarios, it is combined with other equipment and technologies in the intelligent transportation system, such as smart traffic lights and electronic police, to form a collaborative traffic management system. The edge analysis box can transmit the analysis results to related equipment in real time to achieve automatic adjustment of traffic signals and automatic capture of traffic violations.

[0025] In the following, in conjunction with the accompanying drawings, a method for determining the degree of lane congestion provided by an embodiment of the present application is described in detail through specific embodiments and application scenarios.

[0026] like Figure 1 As shown, a method for determining the degree of lane congestion provided by an embodiment of the present application is characterized in that it is applied to a road congestion edge analysis box, the road congestion edge analysis box is connected to a front-end device, and the method comprises the following steps:

[0027] Step 101, receiving front-end real-time data from the front-end device, wherein the front-end real-time data includes at least one of electric card passing data, radar data and video stream data.

[0028] Step 102: Analyze the motor vehicle traffic participation elements based on the front-end real-time data.

[0029] Step 103: Based on the analysis results, determine the lane congestion level and output the traffic congestion event result.

[0030] Specifically, for sections with smart card gates and electric police equipment, the lane travel speed and the ratio of travel speed to free flow travel speed can be calculated based on the electric card passing data and road network topology data;

[0031] Accordingly, the following formula can be used to calculate the degree of congestion:

[0032]

[0033] Among them, V freeis the lane free flow speed, V lane is the lane travel speed, LE is the road section length conversion coefficient, which can be calculated by the following formula:

[0034]

[0035] Among them, length lane is the length of the road section in meters.

[0036] In addition, for scenarios where there is no vehicle passing data but radar data is available, the number of lane stops can be calculated using the following formula based on the queue length when the green light is on and the green light duration:

[0037]

[0038] Among them, Q green_start is the queue length when the green light is on, G is the green light duration, N lane Number of stops for driveways;

[0039] According to the lane flow, green light duration and cycle, the lane saturation is calculated using the following formula:

[0040]

[0041] Among them, B lane is the lane saturation, V lane is the lane flow, G is the green light duration, and C is the cycle;

[0042] Accordingly, the lane congestion index can be calculated using the following formula:

[0043] TPI lane =min{2×[(1+B lane )×N lane ],10}

[0044] Among them, B lane is the lane saturation, N lane is the number of lane stops, TPI lane is the lane congestion index;

[0045] When 0≤lane congestion index<4, the lane congestion level is determined to be unobstructed;

[0046] When 4≤lane congestion index<6, the lane congestion level is determined to be basically unobstructed;

[0047] When 6≤lane congestion index<8, the lane congestion level is determined to be slightly unobstructed;

[0048] When 8≤lane congestion index<9, the lane congestion level is determined to be moderate;

[0049] When 9≤lane congestion index≤10, the lane congestion level is determined to be severe.

[0050] In addition, for scenarios where there is no passing vehicle data and no radar data, the received video stream data can be frame-decoded, vehicle targets in the video can be identified by lane and their trajectories can be tracked, vehicle IDs can be recorded, and the time from the start to the end of the vehicle entering the queue area can be counted; the number of vehicles in the lane detection area and the queue positions can be counted and compared with the overall position of the lane to calculate the lane occupancy rate; the average lane occupancy rate in each signal cycle can be counted, the initial queue length distance can be set for different scenarios, and the signal cycle and green light passage time can be obtained from the signal timing plan.

[0051] Accordingly, the following formula can be used to calculate the degree of congestion:

[0052]

[0053] Among them, T m is the time from the vehicle entering the queue area to the end, m is the vehicle ID, N is the number of vehicles passing through the unit signal cycle, R T is the average lane occupancy rate in each signal cycle, T1 is the signal cycle;

[0054] Furthermore, the proportion of congested lanes can be calculated by the following formula:

[0055]

[0056] The intersection congestion index is calculated using the following formula:

[0057]

[0058] Among them, TPI cross is the intersection congestion index, B cross is the intersection saturation, N cross is the average number of stops at the intersection, R is the proportion of congested lanes;

[0059] The proportion of congested road sections is calculated using the following formula:

[0060]

[0061] The road congestion index is calculated using the following formula:

[0062]

[0063] Among them, TPI cross is the road congestion index, V road is the average road travel speed, V freeis the average travel speed of free flow on the road, and R is the proportion of congested road sections.

[0064] Furthermore, for high-altitude bird's-eye view scenes, the video stream of the high-altitude dome camera can be used to identify small target vehicles in the lane and calculate the lane occupancy rate within a unit signal period.

[0065] Accordingly, the following formula can be used to calculate the degree of congestion:

[0066]

[0067] Among them, R T is the lane occupancy rate within a unit signal cycle.

[0068] The embodiment of the present application analyzes the elements participating in motor vehicle traffic based on front-end real-time data, perceives traffic objects at intersections in real time, and then determines the degree of lane congestion, providing accurate data support for traffic management.

[0069] In the embodiment of the present application, the traffic road congestion edge analysis box is an intelligent hardware and software integrated device that integrates a variety of high-tech technologies such as video access, decoding frame extraction, AI intelligent analysis, data storage, etc. It realizes multi-source data collection and fusion, comprehensive traffic evaluation at intersections, etc. based on the access of various sensing devices, aiming to empower two major scenario applications: urban traffic management and vehicle-road collaboration.

[0070] By connecting to road surveillance cameras, the device conducts intelligent analysis of motor vehicle traffic participants in the video, perceives traffic objects at intersections in real time, and outputs the results of traffic congestion events such as long queues, traffic jams, intersection overflows, and intersection deadlocks, thereby building a new generation of transportation infrastructure and providing accurate data support for traffic management.

[0071] Today, urban traffic congestion is still a common problem. Cities of different sizes still need various types of construction solutions such as high-end customization or basic transformation to optimize the management of traffic congestion. The road congestion edge analysis box is based on big data technology and artificial intelligence technology, and is committed to integrating multi-source traffic data, edge computing technology, and vehicle-road collaboration technology to implement a new type of traffic solution of "autonomous learning, intelligent congestion relief, deep cognition, and efficient control" to solve the problem of "easy congestion and difficult control" in urban traffic.

[0072] The traffic road congestion edge analysis box is an industrial-grade integrated hardware and software intelligent device that makes full use of modern communications, AI and other high-tech technologies, accesses front-end intelligent sensing equipment, radar data, front-end monitoring equipment video streams and other data, and performs road congestion detection functions such as long queues, road congestion, intersection overflow, and intersection deadlocks. It provides users in the transportation industry with accurate violation results and supports the construction of a smooth, orderly, civilized and safe road traffic environment.

[0073] The device accesses front-end video data from checkpoints, electric alarms, etc., conducts intelligent analysis of traffic participants in the video, captures events such as congestion and outputs warning signals in a timely manner. It also provides a wealth of interfaces for easy docking with third-party systems, easily realizing the intelligent upgrade of ordinary cameras, and reducing costs and increasing efficiency for traffic management departments.

[0074] The traffic road congestion edge analysis box is an industrial-grade integrated hardware and software edge intelligent device designed for "small and medium-sized" deep learning neural network computing. It integrates a variety of high-tech technologies such as video transmission, encoding and decoding, AI intelligent analysis, and data storage. It has built-in video analysis algorithms, radar fitting algorithms, signal control optimization algorithms and other functions.

[0075] like Figure 2 The figure shows the architecture of the edge analysis box for traffic congestion. First, access the front-end real-time video stream of the front-end device, import the data into the data source processing module of the device through different hardware interfaces, and perform H264 format encoding and decoding operations through the underlying codec chip to process it into subsequent algorithm output data. Secondly, it is compatible with the mainstream ecology of CUDA and OpenCL, integrates the computing framework of X86 and GPU, initializes the resources of the hardware box, divides the computing, storage, and network transmission resource blocks, releases the model computing resources, and ensures the model reasoning effect. Finally, bind the signal transmission module of the hardware device, and output the alarm information in the form of video, audio, etc. through HDMI and alarm interface.

[0076] The traffic road congestion edge analysis box supports the connection of multiple front-end device data such as vehicle passing data, radar data, video data, etc., and supports congestion judgment for low-altitude and high-altitude scenes. In terms of usage scenarios, for low-altitude scenes, it is suitable for tunnels, intersections, road sections, highways, expressways and other scenes; for high altitude scenes, it is suitable for high-altitude bird's-eye view gimbal cameras. At the same time, it supports linkage with signal machines, intelligently generates signal optimization timing plans, and supports the distribution of plans, thereby realizing precise signal control.

[0077] In low-altitude scenarios, for sections of roads equipped with smart card gates and electric police equipment, the travel speed is calculated through the electric card passing data and road network topology data. At the same time, the ratio of travel speed to free-flow travel speed is calculated to determine lane congestion.

[0078] Specifically, based on the passing data, considering that the shorter the section length, the greater the speed change caused by the same delay time, and the free flow speed of the section is greatly affected by the road, the calculation method is as follows:

[0079]

[0080] Among them, V free is the lane free flow speed, V laneis the lane travel speed, LE is the road section length conversion coefficient, which can be calculated by the following formula:

[0081]

[0082] Among them, length lne is the length of the road section in meters.

[0083] For scenarios where there is no passing vehicle data but radar data is available, the lane congestion situation is judged by the radar queue length and green light release time, combined with lane saturation.

[0084] Specifically, the number of lane stops is calculated using the following formula based on the queue length when the green light is on and the green light duration:

[0085]

[0086] Among them, Q green_start is the queue length when the green light is on, G is the green light duration, N lane Number of stops for driveways;

[0087] According to the lane flow, green light duration and cycle, the lane saturation is calculated using the following formula:

[0088]

[0089] Among them, B lane is the lane saturation, V lane is the lane flow, G is the green light duration, and C is the cycle;

[0090] The lane congestion index is calculated using the following formula:

[0091] TPI lane =min{2×[(1+B lane )×N lane ],10}

[0092] Among them, B lane is the lane saturation, N lane is the number of lane stops, TPI lane is the lane congestion index;

[0093] It can be seen that the lane congestion index can be calculated by the number of lane stops and the lane saturation, and the range is [0,10]. Furthermore, the lane congestion index is used to determine the lane congestion degree according to different ranges:

[0094] When 0≤lane congestion index<4, the lane congestion level is determined to be unobstructed;

[0095] When 4≤lane congestion index<6, the lane congestion level is determined to be basically unobstructed;

[0096] When 6≤lane congestion index<8, the lane congestion level is determined to be slightly unobstructed;

[0097] When 8≤lane congestion index<9, the lane congestion level is determined to be moderate;

[0098] When 9≤lane congestion index≤10, the lane congestion level is determined to be severe.

[0099] For scenarios where there is no vehicle passing data or radar data, the video stream data is accessed and analyzed, and the vehicle queue length, lane occupancy, and vehicle travel time are calculated based on the traffic light timing plan and video analysis results to determine lane congestion.

[0100] Specifically, the received video stream data is decoded by frame extraction, the vehicle targets in the video are identified by lanes and tracked, the vehicle ID is recorded, and the time from the start to the end of the vehicle entering the queue area is counted; the number of vehicles in the lane detection area is counted and the queue position is compared with the overall position of the lane to calculate the lane occupancy rate; the average lane occupancy rate in each signal cycle is counted, the initial queue length distance is set for different scenarios, and the signal cycle and green light passage time are obtained from the signal timing plan;

[0101] Use the following formula to calculate the congestion level:

[0102]

[0103] Among them, T m is the time from the vehicle entering the queue area to the end, m is the vehicle ID, N is the number of vehicles passing through the unit signal cycle, R T is the average lane occupancy rate in each signal cycle, T1 is the signal cycle;

[0104] Based on the lane congestion determination results, the congestion level of the lane is taken into account, the comprehensive proportion of congested lanes is calculated, and then the intersection congestion index is generated. The calculation formula is as follows:

[0105]

[0106] Among them, TPI cross is the intersection congestion index, B cross is the intersection saturation, N cross is the average number of stops at the intersection, R is the proportion of congested lanes;

[0107] Based on the lane congestion determination results, the congestion situation of each road section is calculated; then the congestion degree of the road section is considered, and the comprehensive proportion of the congested road sections is calculated to generate the road congestion index. The calculation formula is as follows:

[0108]

[0109] The road congestion index is calculated using the following formula:

[0110]

[0111] Among them, TPI cross is the road congestion index, V road is the average road travel speed, V free is the average travel speed of free flow on the road, and R is the proportion of congested road sections.

[0112] For the aerial bird's-eye view scene, the aerial dome camera video stream is mainly used to identify small target vehicles in the lane. Since the vehicle target is small, it is not suitable for target tracking. Therefore, only the lane occupancy rate within the unit signal cycle is calculated. The congestion judgment formula is as follows:

[0113]

[0114] Among them, R T is the lane occupancy rate within a unit signal cycle.

[0115] The embodiments of the present application have the following advantages:

[0116] 1. Easy deployment: 1U standard rack-mount aluminum alloy chassis, 505mm deep, flexible and lightweight, easy to deploy. Connected through Gigabit Ethernet chip, providing Gigabit electrical port to the outside, and expandable 4G / 5G communication. With wide temperature design, passive heat dissipation, stable dust resistance, it is suitable for a variety of industrial-grade scenarios and can easily achieve intelligent upgrades.

[0117] 2. Equipment reuse: Supports connection with multi-brand common traffic police and checkpoint cameras to fully utilize the original video resources. It can provide unified support for various business models such as reuse, new construction, and combination of old and new, and easily complete the intelligent upgrade of common cameras.

[0118] 3. Superior performance: Supports 15 AI algorithm functions, supports access to 24 / 48-channel high-definition video streams for real-time analysis; supports concurrent analysis of more than 10 illegal detection algorithms for the same video stream, and provides users with highly automated, real-time, and reliable illegal capture results.

[0119] 4. End-cloud collaboration: The cloud-based intelligent management platform not only supports easy management of edge nodes, but also supports efficient management of algorithm models, task scheduling, alarm mechanisms, etc., greatly improving the speed of intelligent iteration through one-click publishing and seamless deployment. It has rich interfaces and flexible docking, which facilitates third-party system integration and application.

[0120] like Figure 3 FIG. 1 is a schematic diagram of the structure of a road congestion edge analysis box provided in an embodiment of the present application. The road congestion edge analysis box is connected to a front-end device, and the road congestion edge analysis box includes:

[0121] The receiving module 310 is used to receive front-end real-time data from the front-end device, and the front-end real-time data includes at least one of electric card passing data, radar data and video stream data.

[0122] The analysis module 320 is used to analyze the motor vehicle traffic participation elements according to the front-end real-time data.

[0123] The judgment module 330 is used to judge the lane congestion degree based on the analysis result and output the traffic congestion event result.

[0124] Specifically, the analysis module 320 is used to calculate the lane travel speed and the ratio of the travel speed to the free flow travel speed based on the electric card passing data and the road network topology data for the road sections equipped with smart card gates and electric police equipment.

[0125] Accordingly, the determination module 330 is specifically configured to:

[0126] Use the following formula to calculate the congestion level:

[0127]

[0128] Among them, V free is the lane free flow speed, V lane is the lane travel speed, and LE is the road section length conversion coefficient, which can be calculated by the following formula:

[0129]

[0130] Among them, length lane is the length of the road section in meters.

[0131] In addition, the analysis module 320 is specifically used to calculate the number of lane stops according to the queue length and green light duration when the green light is on, for a scenario where there is no passing vehicle data but radar data is available, using the following formula:

[0132]

[0133] Among them, Q green_start is the queue length when the green light is on, G is the green light duration, N lane Number of stops for driveways;

[0134] According to the lane flow, green light duration and cycle, the lane saturation is calculated using the following formula:

[0135]

[0136] Among them, B lane is the lane saturation, V lane is the lane flow, G is the green light duration, and C is the cycle.

[0137] Accordingly, the determination module 330 is specifically configured to:

[0138] The lane congestion index is calculated using the following formula:

[0139] TPI lane =min{2×[(1+B lane )×N lane ],10}

[0140] Among them, B lane is the lane saturation, N lane is the number of lane stops, TPI lane is the lane congestion index;

[0141] When 0≤lane congestion index<4, the lane congestion level is determined to be unobstructed;

[0142] When 4≤lane congestion index<6, the lane congestion level is determined to be basically unobstructed;

[0143] When 6≤lane congestion index<8, the lane congestion level is determined to be slightly unobstructed;

[0144] When 8≤lane congestion index<9, the lane congestion level is determined to be moderate;

[0145] When 9≤lane congestion index≤10, the lane congestion level is determined to be severe.

[0146] In addition, the analysis module 320 is specifically used to extract frames and decode the accessed video stream data for scenarios where there is no vehicle passing data and no radar data, identify vehicle targets in the video by lane and track their trajectories, record vehicle IDs, and count the time from the start to the end of the vehicle entering the queue area; count the number of vehicles in the lane detection area and the queue position, compare it with the overall position of the lane, and calculate the lane occupancy rate; count the average lane occupancy rate in each signal cycle, set the initial queue length distance for different scenarios, and obtain the signal cycle and green light passing time from the signal timing plan;

[0147] Accordingly, the determination module 330 is specifically configured to:

[0148] Use the following formula to calculate the congestion level:

[0149]

[0150] Among them, T m is the time from the vehicle entering the queue area to the end, m is the vehicle ID, N is the number of vehicles passing through the unit signal cycle, R T is the average lane occupancy rate in each signal cycle, T1 is the signal cycle;

[0151] Furthermore, the judgment module 330 is further configured to calculate the proportion of congested lanes by the following formula:

[0152]

[0153] The intersection congestion index is calculated using the following formula:

[0154]

[0155] Among them, TPI cross is the intersection congestion index, B cross is the intersection saturation, N cross is the average number of stops at the intersection, R is the proportion of congested lanes;

[0156] The proportion of congested road sections is calculated using the following formula:

[0157]

[0158] The road congestion index is calculated using the following formula:

[0159]

[0160] Among them, TPI cross is the road congestion index, V road is the average road travel speed, V free is the average travel speed of free flow on the road, and R is the proportion of congested road sections.

[0161] In addition, the analysis module 320 is specifically used to identify small target vehicles in the lane using the video stream of the high-altitude ball camera for the high-altitude bird's-eye view scene, and calculate the lane occupancy rate within the unit signal cycle;

[0162] Accordingly, the determination module 330 is specifically configured to:

[0163] Use the following formula to calculate the congestion level:

[0164]

[0165] Among them, R T is the lane occupancy rate within a unit signal cycle.

[0166] The embodiment of the present application analyzes the elements participating in motor vehicle traffic based on front-end real-time data, perceives traffic objects at intersections in real time, and then determines the degree of lane congestion, providing accurate data support for traffic management.

[0167] The embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, each process of the above-mentioned lane congestion determination method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. The computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0168] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0169] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0170] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A method for determining the degree of lane congestion, characterized in that: Applied to a road congestion edge analysis box, the road congestion edge analysis box is connected to a front-end device, and the method comprises the following steps: Receiving front-end real-time data from the front-end device, the front-end real-time data including at least one of electric card passing data, radar data and video stream data; Analyzing the motor vehicle traffic participation elements according to the front-end real-time data; Based on the analysis results, the lane congestion level is determined and the traffic congestion event results are output.

2. The method according to claim 1, characterized in that The analyzing of the motor vehicle traffic participation elements according to the front-end real-time data specifically includes: For roads equipped with smart card gates and electric police equipment, the lane travel speed and the ratio of travel speed to free flow travel speed are calculated based on the electric card passing data and road network topology data; The judging of the lane congestion degree based on the analysis result specifically includes: Use the following formula to calculate the congestion level: Among them, V free is the lane free flow speed, V lane is the lane travel speed, LE is the road section length conversion coefficient, which can be calculated by the following formula: Among them, length lane is the length of the road section in meters.

3. The method according to claim 1, characterized in that The analyzing of the motor vehicle traffic participation elements according to the front-end real-time data specifically includes: For scenarios where there is no vehicle passing data but radar data is available, the number of lane stops is calculated using the following formula based on the queue length when the green light is on and the green light duration: Among them, Q green_start is the queue length when the green light is on, G is the green light duration, N lane Number of stops for driveways; According to the lane flow, green light duration and cycle, the lane saturation is calculated using the following formula: Among them, B lane is the lane saturation, V lane is the lane flow, G is the green light duration, and C is the cycle; The judging of the lane congestion degree based on the analysis result specifically includes: The lane congestion index is calculated using the following formula: TPI lane =min{2×[(1+B lane )×N lane ],10} Among them, B lane is the lane saturation, N lane is the number of lane stops, TPI lane is the lane congestion index; When 0≤lane congestion index<4, the lane congestion level is determined to be unobstructed; When 4≤lane congestion index<6, the lane congestion level is determined to be basically unobstructed; When 6≤lane congestion index<8, the lane congestion level is determined to be slightly unobstructed; When 8≤lane congestion index<9, the lane congestion level is determined to be moderate; When 9≤lane congestion index≤10, the lane congestion level is determined to be severe.

4. The method according to claim 1, characterized in that: The analyzing of the motor vehicle traffic participation elements according to the front-end real-time data specifically includes: For scenarios where there is no vehicle passing data or radar data, the system extracts frames from the incoming video stream and decodes them, identifies vehicle targets in the video by lane, tracks their trajectories, records vehicle IDs, and counts the time it takes for vehicles to enter the queuing area. Count the number of vehicles in the lane detection area and compare them with the overall position of the lane to calculate the lane occupancy rate; Count the average lane occupancy rate in each signal cycle, set the initial queue length distance for different scenarios, and obtain the signal cycle and green light time from the signal timing plan; The judging of the lane congestion degree based on the analysis result specifically includes: Use the following formula to calculate the congestion level: Among them, T m is the time from the vehicle entering the queue area to the end, m is the vehicle ID, N is the number of vehicles passing through the unit signal cycle, R T is the average lane occupancy rate in each signal cycle, T1 is the signal cycle; The method further comprises: The proportion of congested lanes is calculated using the following formula: The intersection congestion index is calculated using the following formula: Among them, TPI cross is the intersection congestion index, B cross is the intersection saturation, N cross is the average number of stops at the intersection, R is the proportion of congested lanes; The proportion of congested road sections is calculated using the following formula: The road congestion index is calculated using the following formula: Among them, TPI cross is the road congestion index, V road is the average road travel speed, V free is the average travel speed of free flow on the road, and R is the proportion of congested road sections.

5. The method according to claim 1, characterized in that The analyzing of the motor vehicle traffic participation elements according to the front-end real-time data specifically includes: For aerial bird's-eye view scenes, use the video stream of the aerial dome camera to identify small target vehicles in the lane and calculate the lane occupancy rate within a unit signal cycle; The judging of the lane congestion degree based on the analysis result specifically includes: Use the following formula to calculate the congestion level: Among them, R T is the lane occupancy rate within a unit signal cycle.

6. A road congestion edge analysis box, characterized in that: The road congestion edge analysis box is connected to the front-end device, and the road congestion edge analysis box includes: A receiving module, used for receiving front-end real-time data from the front-end device, wherein the front-end real-time data includes at least one of electric card passing data, radar data and video stream data; An analysis module, used for analyzing the motor vehicle traffic participation elements according to the front-end real-time data; The judgment module is used to judge the lane congestion degree based on the analysis results and output the traffic congestion event results.

7. The road congestion edge analysis box according to claim 6, characterized in that: The analysis module is specifically used to calculate the lane travel speed and the ratio of the travel speed to the free flow travel speed based on the electric card passing data and the road network topology data for the road sections equipped with smart card gates and electric police equipment; The judgment module is specifically used for: Use the following formula to calculate the congestion level: Among them, V free is the lane free flow speed, V lane is the lane travel speed, LE is the road section length conversion coefficient, which can be calculated by the following formula: Among them, length lane is the length of the road section in meters.

8. The road congestion edge analysis box according to claim 6, characterized in that: The analysis module is specifically used to calculate the number of lane stops based on the queue length and green light duration when the green light is on, for scenarios where there is no vehicle passing data but radar data is available, using the following formula: Among them, Q green_start is the queue length when the green light is on, G is the green light duration, N lane Number of stops for driveways; According to the lane flow, green light duration and cycle, the lane saturation is calculated using the following formula: Among them, B lane is the lane saturation, V lane is the lane flow, G is the green light duration, and C is the cycle; The judgment module is specifically used for: The lane congestion index is calculated using the following formula: TPI lane =min{2×[(1+B lane )×N lane ],10} Among them, B lane is the lane saturation, N lane is the number of lane stops, TPI lane is the lane congestion index; When 0≤lane congestion index<4, the lane congestion level is determined to be unobstructed; When 4≤lane congestion index<6, the lane congestion level is determined to be basically unobstructed; When 6≤lane congestion index<8, the lane congestion level is determined to be slightly unobstructed; When 8≤lane congestion index<9, the lane congestion level is determined to be moderate; When 9≤lane congestion index≤10, the lane congestion level is determined to be severe.

9. The road congestion edge analysis box according to claim 6, characterized in that: The analysis module is specifically used to extract frames and decode the received video stream data for scenarios where there is no vehicle passing data and no radar data, identify vehicle targets in the video by lane and track their trajectories, record vehicle IDs, and count the time from the start to the end of the vehicle entering the queuing area; Count the number of vehicles in the lane detection area and compare them with the overall position of the lane to calculate the lane occupancy rate; Count the average lane occupancy rate in each signal cycle, set the initial queue length distance for different scenarios, and obtain the signal cycle and green light time from the signal timing plan; The judgment module is specifically used for: Use the following formula to calculate the congestion level: Among them, T m is the time from the vehicle entering the queue area to the end, m is the vehicle ID, N is the number of vehicles passing through the unit signal cycle, R T is the average lane occupancy rate in each signal cycle, T1 is the signal cycle; The judgment module is also used to calculate the proportion of congested lanes using the following formula: The intersection congestion index is calculated using the following formula: Among them, TPI cross is the intersection congestion index, B cross is the intersection saturation, N cross is the average number of stops at the intersection, R is the proportion of congested lanes; The proportion of congested road sections is calculated using the following formula: The road congestion index is calculated using the following formula: Among them, TPI cross is the road congestion index, V road is the average road travel speed, V free is the average travel speed of free flow on the road, and R is the proportion of congested road sections.

10. The road congestion edge analysis box according to claim 6, characterized in that: The analysis module is specifically used to identify small target vehicles in the lane using the video stream of the high-altitude dome camera for the high-altitude bird's-eye view scene, and calculate the lane occupancy rate within a unit signal cycle; The judgment module is specifically used for: Use the following formula to calculate the congestion level: Among them, R T is the lane occupancy rate within a unit signal cycle.

Images