CN113808389A - Vehicle-road cooperation system, edge computing unit, central cloud platform and information processing method - Google Patents
Vehicle-road cooperation system, edge computing unit, central cloud platform and information processing method Download PDFInfo
- Publication number
- CN113808389A CN113808389A CN202110919284.4A CN202110919284A CN113808389A CN 113808389 A CN113808389 A CN 113808389A CN 202110919284 A CN202110919284 A CN 202110919284A CN 113808389 A CN113808389 A CN 113808389A
- Authority
- CN
- China
- Prior art keywords
- data
- traffic
- real
- road
- vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000010365 information processing Effects 0.000 title claims abstract description 30
- 238000003672 processing method Methods 0.000 title claims abstract description 30
- 230000008447 perception Effects 0.000 claims abstract description 86
- 238000012545 processing Methods 0.000 claims abstract description 70
- 238000004458 analytical method Methods 0.000 claims abstract description 20
- 238000004590 computer program Methods 0.000 claims description 12
- 238000000034 method Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 230000004927 fusion Effects 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 206010039203 Road traffic accident Diseases 0.000 description 7
- 238000007405 data analysis Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000007418 data mining Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 230000006698 induction Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 229920003087 methylethyl cellulose Polymers 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/012—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from other sources than vehicle or roadside beacons, e.g. mobile networks
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
- G08G1/0141—Measuring and analyzing of parameters relative to traffic conditions for specific applications for traffic information dissemination
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/091—Traffic information broadcasting
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/06—Selective distribution of broadcast services, e.g. multimedia broadcast multicast service [MBMS]; Services to user groups; One-way selective calling services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
- H04W4/44—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H]
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to a vehicle-road cooperative system, an edge computing unit, a central cloud platform and an information processing method, wherein the information processing method comprises the following steps: acquiring traffic perception data from a plurality of perception devices, and processing the traffic perception data, wherein the traffic perception data comprises vehicle perception data, road perception data and environment perception data; dividing the processed traffic perception data into frontier processed data and/or cloud processed data according to a preset service scene; directly analyzing the side-end processing data to generate a corresponding real-time traffic event, and/or sending the cloud-end processing data to a central cloud platform for analysis to generate a corresponding non-real-time traffic event, and receiving the non-real-time traffic event sent by the central cloud platform; real-time traffic events and/or non-real-time traffic events are broadcast. By implementing the technical scheme of the invention, the problems that the edge computing unit has high real-time requirement and large data volume influences the performance are solved.
Description
Technical Field
The invention relates to the field of Intelligent Transportation Systems (ITS), in particular to a vehicle-road cooperation System, an edge computing unit, a central cloud platform and an information processing method.
Background
With the rapid development of the intelligent networked automobile in the global scope, the mutual integration and cooperation of electromotion, networking and intelligence become the main direction. The vehicle-road cooperation technology becomes an important direction for realizing the cross-type development of the key technology of the automobile industry, and has important significance for improving traffic efficiency, saving resources, reducing pollution, reducing accident rate and improving traffic management.
The vehicle-road cooperation is a safe, efficient and environment-friendly road traffic system which adopts the advanced wireless communication, new generation internet and other technologies, implements vehicle-road dynamic real-time information interaction in all directions, develops vehicle active safety control and road cooperative management on the basis of full-time dynamic traffic information acquisition and fusion, fully realizes effective cooperation of human and vehicle roads, ensures traffic safety and improves traffic efficiency. The vehicle-road cooperation technology is characterized in that smart vehicles, smart roads and powerful clouds are interconnected and intercommunicated through a flexible network, traffic perception information acquired through road-side equipment and global decision-making capability based on a cloud end are used for further improving the reliability and safety of the vehicle auxiliary driving function, and accordingly the improvement of the vehicle auxiliary driving function and the falling of related products are promoted better.
The vehicle-road cooperative system adopts a four-level architecture of 'cloud-pipe-edge-end', wherein 'cloud' comprises V2X cloud control basic service and cloud control application service; the 'management' comprises a private transportation network and a telecommunication network, wherein the private transportation network refers to a private network built by itself or in cooperation with transportation operation and is interconnected with the telecommunication network, and the C-V2X is based on a mobile network and a base station of a telecommunication operator to communicate; the edge comprises a plurality of edge computing nodes and edge computing units, and is deployed by adopting customized server hardware adapted to an edge physical deployment environment on a road side or an edge machine room of an operator; the "end" includes various vehicles, various videos on the road, event monitoring, information, computing terminals, sensors and the like.
The information of the vehicle-road cooperation is calculated and stored through the edge calculating unit, the performance processing and bandwidth requirements of the central cloud platform are reduced, and the problems of large network transmission flow and high cloud processing cost are solved. The edge computing unit usually takes an industrial personal computer as a main part, and the system is closed, so that the advantages of mass resources and elasticity of the cloud cannot be utilized. Meanwhile, a large amount of road side equipment needs to be accessed, the reported data volume is large, the types of sampling are various, the requirement of the trend of real-time from perception analysis to feedback control cannot be met in the aspect of real-time performance, and the problems of real dynamic perception and optimized traffic road traveling are solved.
Disclosure of Invention
The invention aims to solve the technical problem that an edge computing unit in the prior art cannot meet the requirement of high real-time performance.
The technical scheme adopted by the invention for solving the technical problems is as follows: an information processing method based on vehicle-road cooperation is constructed and applied to an edge computing unit, and the method comprises the following steps:
acquiring traffic perception data from a plurality of perception devices, and processing the traffic perception data, wherein the traffic perception data comprises vehicle perception data, road perception data and environment perception data;
dividing the processed traffic perception data into frontier processed data and/or cloud processed data according to a preset service scene;
directly analyzing the side end processing data to generate a corresponding real-time traffic event, and/or sending the cloud end processing data to a central cloud platform for analysis to generate a corresponding non-real-time traffic event, and receiving the non-real-time traffic event sent by the central cloud platform;
broadcasting the real-time traffic events and/or the non-real-time traffic events.
Preferably, the processing the traffic awareness data comprises:
and carrying out fusion and normalization processing on the traffic perception data to obtain structured traffic perception data.
Preferably, the analysis of the frontend process data directly to generate the corresponding real-time traffic event comprises:
and sending the edge-end processing data into a pre-stored intelligent model, acquiring moving target information according to the output of the intelligent model, and generating a corresponding real-time traffic event according to the moving target information, wherein the moving target information comprises detection information, tracking information and identification information of a moving target.
Preferably, the intelligent model is obtained according to the following manner:
in the model training stage, traffic perception data are obtained from a plurality of perception devices arranged on the road side through road side equipment, and the traffic perception data are processed;
screening out traffic perception data with moving targets from the processed traffic perception data;
sending the screened traffic perception data to a central cloud platform for training an intelligent model;
and receiving the intelligent model issued by the central cloud platform, and updating the stored intelligent model.
Preferably, broadcasting the real-time traffic events and the non-real-time traffic events includes:
and broadcasting the real-time traffic event and the non-real-time traffic event through road side equipment.
Preferably, the sending the cloud processing data to a central cloud platform includes:
and uploading the cloud processing data to the edge computing nodes, so that the edge computing nodes upload the cloud processing data uploaded by the edge computing units to a central cloud platform after collecting the cloud processing data.
The invention also constructs an information processing method based on vehicle-road cooperation, which is applied to a central cloud platform and comprises the following steps:
receiving cloud processing data from a plurality of edge computing units, wherein the cloud processing data is determined by corresponding edge computing units according to preset service scene grades after the corresponding edge computing units process traffic perception data acquired from a plurality of perception devices;
analyzing the received cloud processing data to generate a corresponding non-real-time traffic event;
and issuing the influence range, the influence time and the processing requirement of the non-real-time traffic incident to a corresponding edge calculation unit.
The invention also provides an edge calculation unit of the vehicle-road cooperative system, which comprises a first processor and a first memory, wherein the first memory stores a first computer program, and the first processor realizes the information processing method when executing the first computer program.
The invention also constructs a central cloud platform of the vehicle-road cooperative system, which comprises a second processor and a second memory stored with a second computer program, wherein the second processor realizes the information processing method when executing the second computer program.
The invention also constructs a vehicle-road coordination system, comprising:
a plurality of perception devices;
the edge end equipment comprises an edge computing node and the edge computing unit;
the central cloud platform is connected with the edge equipment through a special traffic network and a telecommunication network.
Preferably, the edge computing node is a server based on a docker container.
According to the technical scheme provided by the invention, the edge computing unit is added with a service scene grading function and a traffic event cooperative scheduling function, so that the cooperation and scheduling of edge end and cloud end processing on different service scenes are realized. Moreover, by utilizing the computing and storing capacity of the edge computing unit and the communication characteristics of low time delay, high reliability and high speed, the real-time traffic state, the road and weather abnormal events are accurately provided for the intelligent networked automobile in real time, the occurrence of traffic accidents is avoided, and the traffic safety and the traffic efficiency are improved; meanwhile, the cloud capability is fully utilized to conduct non-real-time big data mining and analysis, and a processing result is sent to the edge computing unit, so that the requirements of a business scene are met. Therefore, the problems that the edge computing unit has high real-time requirements and large data volume influences performance are solved.
Drawings
In order to illustrate the embodiments of the invention more clearly, the drawings that are needed in the description of the embodiments will be briefly described below, it being apparent that the drawings in the following description are only some embodiments of the invention, and that other drawings may be derived from those drawings by a person skilled in the art without inventive effort. In the drawings:
FIG. 1 is a flowchart of a first embodiment of an information processing method based on vehicle-road coordination according to the present invention;
FIG. 2 is a flowchart of a second embodiment of the information processing method based on vehicle-road coordination according to the present invention;
FIG. 3 is a flowchart of a third embodiment of an information processing method based on vehicle-road coordination according to the present invention;
FIG. 4 is a flowchart of a fourth embodiment of the information processing method based on vehicle-road coordination according to the present invention;
FIG. 5 is a flow chart of a fifth embodiment of the information processing method based on vehicle-road coordination according to the present invention;
FIG. 6 is a logical structure diagram of a first embodiment of the vehicular access cooperative system of the present invention;
FIG. 7 is a schematic diagram of an application scenario of the vehicle-road coordination system of the present invention;
FIG. 8 is a schematic diagram of the vehicle-road coordination system for information interaction according to the present invention;
FIG. 9 is a schematic logical structure diagram of an edge compute node according to a first embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the vehicle-road cooperative system architecture, the scheme is used for grading the importance of various information according to the service requirements and flexibly scheduling tasks according to the grading condition, so that the rapid cooperation of local traffic and the comprehensive management and control of global traffic are realized, the high-real-time traffic events are solved based on the edge computing unit, the service requirements of traffic guidance, traffic universe management and control and the like are solved based on a cloud platform, the cloud capacity is fully utilized to carry out non-real-time big data mining and analysis, and the analysis result is sent to the edge computing unit for processing. Therefore, the scheme can meet the requirement of a vehicle-road cooperative system on the 5G communication network for sensing, analyzing and processing feedback in real time at the level of 50ms, simultaneously reduces the requirements on performance processing and bandwidth of a central cloud platform, shortens emergency response time of an emergency traffic incident, reduces time consumption of incident scheduling, reduces the influence of traffic jam, and improves the processing level of cooperative handling of the emergency traffic incident.
Fig. 1 is a flowchart of a first embodiment of an information processing method based on vehicle-road coordination according to the present invention, and the information processing method of the embodiment is applied to an edge computing unit (MEC) having computing and storage capabilities and capable of performing low-latency, high-reliability, and high-speed communication with sensing devices (e.g., a camera, a radar, etc.) and communication devices (e.g., an RSU). The information processing method of this embodiment includes:
s11, acquiring traffic perception data from a plurality of perception devices, and processing the traffic perception data, wherein the traffic perception data comprises vehicle perception data, road perception data and environment perception data;
in this step, the edge computing unit accesses to sensing devices such as high definition cameras, radars, sensing coils, weather instruments, traffic lights, variable information signs, induction screens and the like arranged on the roadside, and supports obtaining of traffic sensing data of continuous time space, including: environment perception information (weather environment information), road perception information (road identification, traffic state, road traffic accident, road construction, etc.), vehicle perception information (vehicle attitude information), and the like.
S12, dividing the processed traffic perception data into frontier processed data and/or cloud processed data according to a preset service scene;
in the step, the edge computing unit can grade the service importance of various traffic perception information according to the service requirements, and the edge computing unit can be used for locally and quickly processing the scenes such as traffic accidents, illegal driving, sprinkled objects on roads, abnormal weather (such as crosswind or cloud) and the like on the road side aiming at the service requirements with high real-time performance; and part of the non-real-time information is gathered to the central cloud platform for global data analysis and global traffic flow control.
S13, directly analyzing the side end processing data to generate a corresponding real-time traffic event, and/or sending the cloud end processing data to a central cloud platform for analysis to generate a corresponding non-real-time traffic event, and receiving the non-real-time traffic event sent by the central cloud platform;
in the step, for a scene with high real-time requirement, the edge computing unit locally processes the edge processing data through image recognition and traffic flow statistics technology to generate a real-time traffic event so as to realize application scenes such as safety early warning, vehicle speed guidance, signal cooperation, multi-vehicle driving path cooperation and the like; for scenes with general real-time requirements, the edge computing units send processed traffic perception data such as traffic flow, snap images and environment perception information to the central cloud platform for processing, the central cloud platform analyzes and processes global data by combining perception information of the edge computing units and perception information of intelligent internet automobiles to generate non-real-time traffic events, and therefore central applications such as analysis and prediction of traffic jam, dynamic prediction of traffic flow, prediction and capacity matching of travel demands, remote configuration of road management strategies, personalized information services and the like are achieved.
And S14, broadcasting the real-time traffic event and/or the non-real-time traffic event.
In the embodiment, on the basis of the existing vehicle-road cooperative system, the edge computing unit is added with a service scene grading function and a traffic event cooperative scheduling function, so that cooperation and scheduling of edge end and cloud end processing on different service scenes are realized. Moreover, by utilizing the computing and storing capacity of the edge computing unit and the communication characteristics of low time delay, high reliability and high speed, the real-time traffic state, the road and weather abnormal events are accurately provided for the intelligent networked automobile in real time, the occurrence of traffic accidents is avoided, and the traffic safety and the traffic efficiency are improved; meanwhile, the cloud capability is fully utilized to conduct non-real-time big data mining and analysis, and a processing result is sent to the edge computing unit, so that the requirements of a business scene are met. Therefore, the problems that the edge computing unit has high real-time requirements and large data volume influences performance are solved.
Further, the processing of the traffic perception data in step S11 includes:
and carrying out fusion and normalization processing on the traffic perception data to obtain structured traffic perception data.
In one embodiment, as shown in fig. 2, an edge computing unit (MEC) accesses intelligent devices, such as a high definition camera, a radar, a sensing coil, a weather meter, a traffic signal lamp, a variable information sign, and an induction screen, disposed on the roadside, and supports acquiring traffic perception data of a continuous time space, including: environmental awareness information (weather environment information), road awareness information (road identification, traffic status, road traffic accidents, road construction, etc.), and vehicle awareness information (vehicle attitude information). After acquiring the traffic perception data, the MEC performs fusion and normalization processing on the data, and then determines whether the data is processed by the edge or the cloud according to the classification of the service scene.
If the data is processed by the edge end, the MEC directly analyzes the processed data of the edge end to generate a real-time traffic event, for example, a traffic event which is related to application scenes such as safety early warning, vehicle speed guidance, signal cooperation, multi-vehicle driving path cooperation and the like and has high real-time requirement.
If the traffic jam occurs, the central cloud analyzes the cloud processing data to generate a non-real-time traffic event, and sends the non-real-time traffic event to the multiple MECs, and specifically, the central cloud analyzes and processes global data by combining the sensing information of the multiple edge computing units and the sensing information of the intelligent networked automobiles to generate the non-real-time traffic event related to analysis and prediction of traffic jam, dynamic prediction of traffic flow, prediction and capacity matching of travel demand, remote configuration of road management strategies, personalized information services and the like.
The MEC gathers real-time traffic events and non-real-time traffic events and broadcasts the gathered traffic events, so that the traffic events are issued to the road side RSU.
Further, in an optional embodiment, the sending the cloud processing data to a central cloud platform includes: and uploading the cloud processing data to the edge computing nodes, so that the edge computing nodes upload the cloud processing data uploaded by the edge computing units to a central cloud platform after collecting the cloud processing data.
Fig. 3 is a flowchart of a third embodiment of the information processing method based on vehicle-road coordination according to the present invention, where the information processing method of the embodiment is applied to a central cloud platform, and specifically includes:
step S21, receiving cloud processing data from a plurality of edge computing units, wherein the cloud processing data are determined by the corresponding edge computing units according to preset service scene grading after processing traffic perception data acquired from a plurality of perception devices;
s22, analyzing the received cloud processing data to generate a corresponding non-real-time traffic event;
in the step, the central cloud platform performs global data analysis and processing by combining the perception information of the edge computing units and the perception information of the intelligent networked automobile to generate a non-real-time traffic event so as to realize central applications such as analysis and prediction of traffic jam, dynamic prediction of traffic flow, prediction and capacity matching of travel demand, remote configuration of road management strategies, personalized information services and the like.
And S23, issuing the influence range, the influence time and the processing requirement of the non-real-time traffic incident to a corresponding edge calculation unit according to the influence range, the influence time and the processing requirement of the non-real-time traffic incident.
In this embodiment, the edge computing unit adds a service scene grading function and a traffic event coordination scheduling function, and realizes coordination and scheduling of edge end and cloud processing for different service scenes. Moreover, the cloud capability is fully utilized to carry out non-real-time big data mining and analysis, and the processing result is sent to the edge computing unit, so that the requirement of a business scene is met.
In a specific embodiment, the edge computing unit is connected with the edge computing node and the central cloud platform by adopting a private transportation network in an optical fiber mode or by adopting a 4G/5G mobile communication network. As shown in fig. 4, the task scheduling process of the edge computing unit and the central cloud platform is as follows:
the edge computing unit A collects and analyzes the perception data, and aiming at a service scene with low real-time requirement, the edge computing unit A sends an analysis result to an edge computing node, the central cloud platform collects an accessed edge end analysis result and information of an external system, and carries out big data analysis on traffic data collected by a road side and a vehicle end, potential cause and effect relation among the traffic data is analyzed through strong computing and storage capacity of the central cloud platform, big data theme analysis and data mining are carried out, deep analysis and prediction are realized on traffic events, and central application such as analysis and prediction of traffic jam, dynamic prediction of traffic flow, prediction and capacity matching of travel demand, remote configuration of road management strategies, personalized information service and the like is realized.
And the central cloud platform actively issues the traffic event information to a plurality of edge computing nodes, an edge computing unit A and an edge computing unit B on the road side according to the influence range, the influence time and the processing requirement of the event.
Further, in an optional embodiment, the analyzing the frontend processing data directly in step S13 to generate the corresponding real-time traffic event includes:
and sending the edge-end processing data into a pre-stored intelligent model, acquiring moving target information according to the output of the intelligent model, and generating a corresponding real-time traffic event according to the moving target information, wherein the moving target information comprises detection information, tracking information and identification information of a moving target.
Moreover, the intelligent model is obtained according to the following manner:
in the model training stage, traffic perception data are obtained from a plurality of perception devices arranged on the road side through road side equipment, and the traffic perception data are processed;
screening out traffic perception data with moving targets from the processed traffic perception data;
sending the screened traffic perception data to a central cloud platform for training an intelligent model;
and receiving the intelligent model issued by the central cloud platform, and updating the stored intelligent model.
In a specific embodiment, as shown in fig. 5, the edge computing unit obtains sensing data through a sensing device accessed by the roadside, performs intelligent analysis on the data, performs preprocessing on the sensing data to achieve consistency of time and space, screens the sensing data with a moving target, including images, videos, 3D point cloud data, and the like, and then performs intelligent segment storage. And uploading the screened sensing data to a central cloud platform through edge computing nodes, and performing data training of an intelligent algorithm by the central cloud platform to realize intelligent algorithm optimization and version upgrading including moving target detection, moving target tracking, moving target identification and the like, so as to obtain a model file. And the central cloud platform issues the acquired model file to the accessed edge computing unit through the edge computing node, and the edge computing unit updates the model file to realize intelligent algorithm upgrading of the perception data.
Further, the broadcasting the real-time traffic events and the non-real-time traffic events in step S14 includes: broadcasting the real-time traffic events and the non-real-time traffic events through a Road Side Unit (RSU). In the embodiment, the edge computing unit and the RSU are simultaneously deployed on the road side, so that rapid information interaction can be realized, the edge computing unit broadcasts various traffic events which are subjected to fusion analysis through a C-V2X technology, the communication delay can be controlled within 30 milliseconds, the real-time performance of the traffic event broadcast and the road state notification is greatly increased, and short-time decision of vehicles can be guided.
The present invention also constructs an edge calculation unit of a vehicle-road cooperation system, the edge calculation unit including a first processor and a first memory storing a first computer program, the first processor implementing the above vehicle-road cooperation-based information processing method applied to the edge calculation unit when executing the first computer program.
The invention also constructs a central cloud platform of the vehicle-road cooperation system, which comprises a second processor and a second memory stored with a second computer program, wherein the second processor realizes the information processing method based on the vehicle-road cooperation applied to the central cloud platform when executing the second computer program.
Fig. 6 is a logic structure diagram of a first embodiment of the vehicle-road coordination system of the present invention, where the vehicle-road coordination system of the embodiment includes: sensing devices 11 and 12, an edge device, and a central cloud platform 30, where the central cloud platform 30 is connected to the edge device through a private transportation network and a telecommunication network, the edge device includes an edge computing unit 21 and an edge computing node 22, and the logical structures of the edge computing unit 21 and the central cloud platform 30 may refer to the foregoing description and are not described herein again.
Fig. 7 is a schematic diagram of an application scenario of the vehicle-road cooperative system, in which an edge computing unit and various sensing devices (such as a high-definition camera, a radar, a sensing coil, a weather meter, a traffic signal lamp, a variable information sign, and an induction screen) are arranged on a road side to support acquisition of traffic sensing data of a continuous time space, and the edge computing unit includes: environmental awareness information (weather environment information), road awareness information (road identification, traffic status, road traffic accidents, road construction, etc.), and vehicle awareness information (vehicle attitude information). The edge computing nodes are close to the road side RSU equipment or a nearby base station machine room, the advantages of low time delay, reduction of computing load of a cloud end, reduction of bandwidth overhead of the whole network and the like can be fully utilized, and meanwhile, sensing data and traffic events are continuously uploaded to the central cloud platform.
With reference to fig. 8, the intelligent internet automobiles and the edge computing units disposed at the road side can both sense traffic information in real time, and for the edge computing units, the intelligent internet automobiles can report the road information to the central cloud platform and receive the road information broadcast from the central cloud platform in an optical fiber communication manner; for the intelligent networked automobile, the road information can be reported to the central cloud platform and the road information broadcast can be received from the central cloud platform in a 4G/5G communication mode, and the road information can be broadcast to the automobile by the edge computing unit in a C-V2X mode.
On the basis of the existing vehicle-road cooperative system, the vehicle-road cooperative system adopts an edge computing unit to apply and add a software module to realize a processing and scheduling solution for grading a service scene and integrating real-time and non-real-time service requirements. The service scenes are various in types, the application is complex, and the requirements on the system are different. For emergencies such as road sprinkles, traffic accidents, illegal driving, emergency lane parking, road surface collapse, road crosswind, road fog and the like, the vehicles in the road need to be warned in time. This requires a fast information exchange mechanism between the edge computing unit and the RSU and a corresponding message push scheme for specific events. The service scenario rating table is shown as the following table:
and realizing real-time traffic event edge processing and non-real-time traffic event cloud processing grading by a business demand classification mode, wherein 10 high real-time business scenes, 13 common real-time business scenes and 4 non-real-time business scenes are obtained.
Further, as shown in fig. 9, the edge computing node is a server based on a Docker container, that is, the edge computing node adopts a new distributed network resource model, adopts a Docker container technology, and builds an application based on a micro-service architecture, specifically including: the method comprises the steps of service registration, edge cloud cooperation, resource management, algorithm management, safety certification, perception data fusion, operation monitoring, traffic event collection analysis, service scene configuration and traffic event release. The edge computing node is intelligently deployed at any position of the edge and the cloud according to business requirements, flexible access of application between the edge computing node and the cloud platform is achieved, and the task scheduling goal is achieved, and the working process of the edge computing node comprises the following steps: and collecting the perception data, and obtaining the structured perception data under unified time and space through preprocessing, modeling analysis and discrete data normalization. And then, according to the grading according to the scenes, calculating and distributing and adjusting the storage resources according to the requirements of the service scenes, realizing the scheduling and management of the resources, supporting the localized decision analysis of the edge end, and issuing the traffic events or the scheduling information.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims (11)
1. An information processing method based on vehicle-road cooperation is applied to an edge computing unit and is characterized by comprising the following steps:
acquiring traffic perception data from a plurality of perception devices, and processing the traffic perception data, wherein the traffic perception data comprises vehicle perception data, road perception data and environment perception data;
dividing the processed traffic perception data into frontier processed data and/or cloud processed data according to a preset service scene;
directly analyzing the side end processing data to generate a corresponding real-time traffic event, and/or sending the cloud end processing data to a central cloud platform for analysis to generate a corresponding non-real-time traffic event, and receiving the non-real-time traffic event sent by the central cloud platform;
broadcasting the real-time traffic events and/or the non-real-time traffic events.
2. The information processing method based on vehicle-road cooperation according to claim 1, wherein the processing of the traffic perception data comprises:
and carrying out fusion and normalization processing on the traffic perception data to obtain structured traffic perception data.
3. The information processing method based on vehicle-road cooperation according to claim 1, wherein directly analyzing the frontend processing data to generate a corresponding real-time traffic event comprises:
and sending the edge-end processing data into a pre-stored intelligent model, acquiring moving target information according to the output of the intelligent model, and generating a corresponding real-time traffic event according to the moving target information, wherein the moving target information comprises detection information, tracking information and identification information of a moving target.
4. The information processing method based on vehicle-road cooperation according to claim 3, wherein the intelligent model is obtained according to the following manner:
in the model training stage, traffic perception data are obtained from a plurality of perception devices arranged on the road side through road side equipment, and the traffic perception data are processed;
screening out traffic perception data with moving targets from the processed traffic perception data;
sending the screened traffic perception data to a central cloud platform for training an intelligent model;
and receiving the intelligent model issued by the central cloud platform, and updating the stored intelligent model.
5. The information processing method based on vehicle-road coordination according to claim 1, wherein broadcasting the real-time traffic event and the non-real-time traffic event comprises:
and broadcasting the real-time traffic event and the non-real-time traffic event through road side equipment.
6. The information processing method based on vehicle-road cooperation according to claim 1, wherein the sending of the cloud-processed data to a central cloud platform comprises:
and uploading the cloud processing data to the edge computing nodes, so that the edge computing nodes upload the cloud processing data uploaded by the edge computing units to a central cloud platform after collecting the cloud processing data.
7. An information processing method based on vehicle-road cooperation is applied to a central cloud platform and is characterized by comprising the following steps:
receiving cloud processing data from a plurality of edge computing units, wherein the cloud processing data is determined by corresponding edge computing units according to preset service scene grades after the corresponding edge computing units process traffic perception data acquired from a plurality of perception devices;
analyzing the received cloud processing data to generate a corresponding non-real-time traffic event;
and issuing the influence range, the influence time and the processing requirement of the non-real-time traffic incident to a corresponding edge calculation unit.
8. An edge calculation unit of a vehicle-road cooperative system, comprising a first processor and a first memory in which a first computer program is stored, wherein the first processor implements the information processing method according to any one of claims 1 to 6 when executing the first computer program.
9. A central cloud platform of a vehicle-road cooperation system, comprising a second processor and a second memory storing a second computer program, wherein the second processor implements the information processing method according to claim 7 when executing the second computer program.
10. A vehicle-road coordination system, comprising:
a plurality of perception devices;
an edge device comprising an edge compute node and the edge compute unit of claim 8;
the central cloud platform of claim 9, and the central cloud platform and the edge devices are connected through a private transportation network and a telecommunication network.
11. The vehicle road coordination system according to claim 10, wherein said edge computing node is a server based on a docker container.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110919284.4A CN113808389A (en) | 2021-08-11 | 2021-08-11 | Vehicle-road cooperation system, edge computing unit, central cloud platform and information processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110919284.4A CN113808389A (en) | 2021-08-11 | 2021-08-11 | Vehicle-road cooperation system, edge computing unit, central cloud platform and information processing method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113808389A true CN113808389A (en) | 2021-12-17 |
Family
ID=78893542
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110919284.4A Pending CN113808389A (en) | 2021-08-11 | 2021-08-11 | Vehicle-road cooperation system, edge computing unit, central cloud platform and information processing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113808389A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114500222A (en) * | 2021-12-30 | 2022-05-13 | 中智行(上海)交通科技有限公司 | Deployment mode of vehicle-road cooperation field network and computing architecture |
| CN114595271A (en) * | 2022-02-24 | 2022-06-07 | 贵州具京网络科技有限公司 | Big data mining method and system |
| CN114664092A (en) * | 2022-05-18 | 2022-06-24 | 阿里巴巴达摩院(杭州)科技有限公司 | Traffic event detection system, event detection method and device |
| CN114743382A (en) * | 2022-06-13 | 2022-07-12 | 浙江大云物联科技有限公司 | Vehicle violation behavior identification method and device based on intelligent lamp pole system |
| CN115063969A (en) * | 2022-04-26 | 2022-09-16 | 阿里云计算有限公司 | Data processing method, device, medium, roadside cooperative device and system |
| CN115100854A (en) * | 2022-06-17 | 2022-09-23 | 上海市城市建设设计研究总院（集团）有限公司 | Data storage method for intelligent network connection road edge node |
| CN115457759A (en) * | 2022-07-22 | 2022-12-09 | 中智行(苏州)科技有限公司 | Road traffic real-time road condition information analysis system and method based on vehicle-road cooperation |
| CN116033387A (en) * | 2022-11-30 | 2023-04-28 | 西部科学城智能网联汽车创新中心(重庆)有限公司 | Road environment collaborative perception decision-making method and device |
| CN117765721A (en) * | 2023-11-14 | 2024-03-26 | 安徽交控信息产业有限公司 | Highway transaction special condition processing method and system based on cloud platform |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110349423A (en) * | 2019-06-28 | 2019-10-18 | 京东数字科技控股有限公司 | A kind of road side system based on bus or train route collaboration |
| CN111371904A (en) * | 2020-03-18 | 2020-07-03 | 交通运输部公路科学研究院 | Cloud-side-end-coordinated highway cloud control system and control method |
| CN111477010A (en) * | 2020-04-08 | 2020-07-31 | 图达通智能科技(苏州)有限公司 | Device for intersection holographic sensing and control method thereof |
| CN111787481A (en) * | 2020-06-17 | 2020-10-16 | 北京航空航天大学 | Road-vehicle coordination high-precision sensing method based on 5G |
| CN111915907A (en) * | 2020-08-18 | 2020-11-10 | 河南中天高新智能科技股份有限公司 | Multi-scale traffic information publishing system and method based on vehicle-road cooperation |
| CN112071063A (en) * | 2020-09-15 | 2020-12-11 | 苏州映赛智能科技有限公司 | Roadside sensing system |
| CN212160931U (en) * | 2020-04-02 | 2020-12-15 | 深圳市金溢科技股份有限公司 | ETC-X system for vehicle-road cooperation |
| CN112289059A (en) * | 2020-10-22 | 2021-01-29 | 中电智能技术南京有限公司 | Vehicle-road cooperative road traffic system |
| CN112289054A (en) * | 2020-09-29 | 2021-01-29 | 深圳市金溢科技股份有限公司 | Road safety early warning method, OBU, RSU, MEC equipment and system |
| WO2021062792A1 (en) * | 2019-09-30 | 2021-04-08 | 华为技术有限公司 | Wakeup signal monitoring method and apparatus |
| CN112633120A (en) * | 2020-12-18 | 2021-04-09 | 北京理工大学重庆创新中心 | Intelligent roadside sensing system based on semi-supervised learning and model training method |
| CN112750326A (en) * | 2021-01-05 | 2021-05-04 | 北京中交国通智能交通系统技术有限公司 | Generalized vehicle-road cooperation system and method |
| CN112925657A (en) * | 2021-01-18 | 2021-06-08 | 国汽智控(北京)科技有限公司 | Vehicle road cloud cooperative processing system and method |
| CN113178076A (en) * | 2021-06-30 | 2021-07-27 | 中移(上海)信息通信科技有限公司 | Vehicle-road cooperation system and vehicle-road cooperation method |
-
2021
- 2021-08-11 CN CN202110919284.4A patent/CN113808389A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110349423A (en) * | 2019-06-28 | 2019-10-18 | 京东数字科技控股有限公司 | A kind of road side system based on bus or train route collaboration |
| WO2021062792A1 (en) * | 2019-09-30 | 2021-04-08 | 华为技术有限公司 | Wakeup signal monitoring method and apparatus |
| CN111371904A (en) * | 2020-03-18 | 2020-07-03 | 交通运输部公路科学研究院 | Cloud-side-end-coordinated highway cloud control system and control method |
| CN212160931U (en) * | 2020-04-02 | 2020-12-15 | 深圳市金溢科技股份有限公司 | ETC-X system for vehicle-road cooperation |
| CN111477010A (en) * | 2020-04-08 | 2020-07-31 | 图达通智能科技(苏州)有限公司 | Device for intersection holographic sensing and control method thereof |
| CN111787481A (en) * | 2020-06-17 | 2020-10-16 | 北京航空航天大学 | Road-vehicle coordination high-precision sensing method based on 5G |
| CN111915907A (en) * | 2020-08-18 | 2020-11-10 | 河南中天高新智能科技股份有限公司 | Multi-scale traffic information publishing system and method based on vehicle-road cooperation |
| CN112071063A (en) * | 2020-09-15 | 2020-12-11 | 苏州映赛智能科技有限公司 | Roadside sensing system |
| CN112289054A (en) * | 2020-09-29 | 2021-01-29 | 深圳市金溢科技股份有限公司 | Road safety early warning method, OBU, RSU, MEC equipment and system |
| CN112289059A (en) * | 2020-10-22 | 2021-01-29 | 中电智能技术南京有限公司 | Vehicle-road cooperative road traffic system |
| CN112633120A (en) * | 2020-12-18 | 2021-04-09 | 北京理工大学重庆创新中心 | Intelligent roadside sensing system based on semi-supervised learning and model training method |
| CN112750326A (en) * | 2021-01-05 | 2021-05-04 | 北京中交国通智能交通系统技术有限公司 | Generalized vehicle-road cooperation system and method |
| CN112925657A (en) * | 2021-01-18 | 2021-06-08 | 国汽智控(北京)科技有限公司 | Vehicle road cloud cooperative processing system and method |
| CN113178076A (en) * | 2021-06-30 | 2021-07-27 | 中移(上海)信息通信科技有限公司 | Vehicle-road cooperation system and vehicle-road cooperation method |
Non-Patent Citations (3)
| Title |
|---|
| 刘睿健: "云边协同 构建交通"大脑"与"神经末梢" 交通云平台与边缘计算初探", 《中国交通信息化》, no. 6, 30 June 2021 (2021-06-30) * |
| 王勇: "基于5G边缘计算技术的智慧交通分级决策系统", 《信息与电脑(理论版)》, vol. 31, no. 18, 30 September 2019 (2019-09-30) * |
| 程婕;陈建峰: "一种基于5G的车路协同自动驾驶技术架构", 《信息通信》, no. 12, 31 December 2019 (2019-12-31) * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114500222A (en) * | 2021-12-30 | 2022-05-13 | 中智行(上海)交通科技有限公司 | Deployment mode of vehicle-road cooperation field network and computing architecture |
| CN114500222B (en) * | 2021-12-30 | 2024-06-07 | 中国电信股份有限公司 | Deployment mode of network and computing architecture in vehicle-road cooperation field and application thereof |
| CN114595271A (en) * | 2022-02-24 | 2022-06-07 | 贵州具京网络科技有限公司 | Big data mining method and system |
| CN114595271B (en) * | 2022-02-24 | 2022-12-13 | 北京中数睿智科技有限公司 | Big data mining method and system |
| CN115063969A (en) * | 2022-04-26 | 2022-09-16 | 阿里云计算有限公司 | Data processing method, device, medium, roadside cooperative device and system |
| CN114664092A (en) * | 2022-05-18 | 2022-06-24 | 阿里巴巴达摩院(杭州)科技有限公司 | Traffic event detection system, event detection method and device |
| CN114743382B (en) * | 2022-06-13 | 2022-10-28 | 浙江大云物联科技有限公司 | Vehicle violation behavior identification method and device based on intelligent lamp pole system |
| CN114743382A (en) * | 2022-06-13 | 2022-07-12 | 浙江大云物联科技有限公司 | Vehicle violation behavior identification method and device based on intelligent lamp pole system |
| CN115100854A (en) * | 2022-06-17 | 2022-09-23 | 上海市城市建设设计研究总院（集团）有限公司 | Data storage method for intelligent network connection road edge node |
| CN115457759A (en) * | 2022-07-22 | 2022-12-09 | 中智行(苏州)科技有限公司 | Road traffic real-time road condition information analysis system and method based on vehicle-road cooperation |
| CN116033387A (en) * | 2022-11-30 | 2023-04-28 | 西部科学城智能网联汽车创新中心(重庆)有限公司 | Road environment collaborative perception decision-making method and device |
| CN116033387B (en) * | 2022-11-30 | 2023-08-25 | 西部科学城智能网联汽车创新中心(重庆)有限公司 | Road environment collaborative perception decision-making method and device |
| CN117765721A (en) * | 2023-11-14 | 2024-03-26 | 安徽交控信息产业有限公司 | Highway transaction special condition processing method and system based on cloud platform |
| CN117765721B (en) * | 2023-11-14 | 2024-06-14 | 安徽交控信息产业有限公司 | Highway transaction special condition processing method and system based on cloud platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113808389A (en) | Vehicle-road cooperation system, edge computing unit, central cloud platform and information processing method | |
| Munir et al. | IFCIoT: Integrated Fog Cloud IoT: A novel architectural paradigm for the future Internet of Things | |
| CN108198439B (en) | Urban intelligent traffic control method based on fog calculation | |
| CN113965568B (en) | Edge computing system for urban road C-V2X network | |
| US12022353B2 (en) | Vehicle to everything dynamic geofence | |
| CN109377778B (en) | Collaborative automatic driving system and method based on multipath RDMA and V2X | |
| US11102630B2 (en) | Method for service placement in a multi-access/mobile edge computing (MEC) system | |
| EP4198944A1 (en) | Roadside sensing system and traffic control method | |
| CN114179829A (en) | Multi-end cooperative vehicle driving method, device, system and medium | |
| CN115116257A (en) | Vehicle scheduling method, device, equipment and medium based on edge cloud service | |
| Ramesh et al. | Smart traffic congestion model in IoT-A review | |
| WO2019040024A2 (en) | System and method for dissemination by carrying and processing of traffic warning information to notify a driver | |
| Kheder et al. | Real-time traffic monitoring system using IoT-aided robotics and deep learning techniques | |
| CN112839319A (en) | Method, device and system for processing information of cellular internet of vehicles, terminal and storage medium | |
| CN112950929B (en) | All-weather real-time traffic information monitoring and QOS hierarchical control system and method | |
| US11516032B2 (en) | Methods and systems for billing of metadata in a network of moving things | |
| CN114913501A (en) | Attention-driven streaming system | |
| CN116758746A (en) | Expressway data collection and sharing method and platform | |
| CN112233419A (en) | Data processing method, device, equipment and storage medium | |
| Farhat et al. | A novel cooperative collision avoidance system for vehicular communication based on deep learning | |
| CN115909716A (en) | Traffic intersection scheduling system, method and equipment based on internet cloud control platform | |
| CN113781809A (en) | Unmanned early warning method and device based on big data platform | |
| EP4070260A1 (en) | Methods and systems for gathering, classification, accounting, and billing of metadata in a network of moving things | |
| CN105448114A (en) | Intelligent traffic intersection information system | |
| Čolaković et al. | Adaptive Traffic Management Systems Based on the Internet of Things (IoT) |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211217 |