CN117354347A - Vehicle-road cooperative control method and device for multifunctional intelligent lamp post of Internet of things - Google Patents
Vehicle-road cooperative control method and device for multifunctional intelligent lamp post of Internet of things Download PDFInfo
- Publication number
- CN117354347A CN117354347A CN202311654483.2A CN202311654483A CN117354347A CN 117354347 A CN117354347 A CN 117354347A CN 202311654483 A CN202311654483 A CN 202311654483A CN 117354347 A CN117354347 A CN 117354347A
- Authority
- CN
- China
- Prior art keywords
- road
- target
- vehicle
- data
- traffic flow
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000004088 simulation Methods 0.000 claims abstract description 64
- 238000012360 testing method Methods 0.000 claims abstract description 58
- 238000004458 analytical method Methods 0.000 claims abstract description 51
- 239000013598 vector Substances 0.000 claims description 36
- 239000000463 material Substances 0.000 claims description 27
- 230000005540 biological transmission Effects 0.000 claims description 16
- 238000010276 construction Methods 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 3
- 230000006855 networking Effects 0.000 claims 2
- 230000008569 process Effects 0.000 description 11
- 230000007613 environmental effect Effects 0.000 description 9
- 206010039203 Road traffic accident Diseases 0.000 description 8
- 230000003993 interaction Effects 0.000 description 7
- 239000010426 asphalt Substances 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 4
- 230000005855 radiation Effects 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000012351 Integrated analysis Methods 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering 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
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
-
- 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]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
- Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection
Abstract
The invention relates to the technical field of the Internet of things, and discloses a vehicle-road cooperative control method and device for a multifunctional intelligent lamp post of the Internet of things, which are used for improving the accuracy of the vehicle-road cooperative control for the multifunctional intelligent lamp post of the Internet of things. Comprising the following steps: collecting road parameter information of a target road section through a plurality of multifunctional intelligent lamp poles installed in the target road section; constructing a digital twin body of the target road section through the road parameter information to obtain a target digital twin road; carrying out heterogeneous traffic flow simulation on the digital twin road to obtain test traffic flow data; based on the test traffic flow data, performing real-time image acquisition on the target road section through a plurality of multifunctional intelligent lamp poles to obtain a real-time image set; carrying out multi-target spatial position relation analysis on the real-time image set to obtain spatial position relation description information; and predicting the vehicle running parameters of the test traffic flow data and the spatial position relation description information to obtain the running parameters of the target vehicle.
Description
Technical Field
The invention relates to the technical field of the Internet of things, in particular to a vehicle-road cooperative control method and device for a multifunctional intelligent lamp post of the Internet of things.
Background
In the field of urban traffic management and traffic flow optimization, a multifunctional intelligent lamp post is an emerging form of urban infrastructure and has various sensing, communication and computing functions. By installing the intelligent lamp posts on the road, the city can monitor traffic conditions, control traffic lights in real time, provide real-time data support and enhance the intellectualization of the city. This is expected to improve traffic management, reduce traffic congestion, improve road safety, and provide more data support for city decision-making.
In the prior art, positioning is a key component of a vehicle-road cooperative system for tracking the position of vehicles and pedestrians. However, satellite positioning systems (e.g., GPS) or other positioning technologies are affected by signal interference, terrain, buildings, etc., resulting in reduced accuracy of vehicle location information, thereby affecting the accuracy of traffic management and navigation. Vehicles and intelligent transportation devices typically use various sensors to sense the surrounding environment, including radar, cameras, lidar, and the like. These sensors produce errors in different meteorological conditions, light conditions or road surface conditions, resulting in inaccurate perception of the surrounding conditions. Data communication between the vehicle and the roadside equipment is typically required through a wireless network, which introduces delays. This results in insufficient timeliness and accuracy of the information.
Disclosure of Invention
The invention provides a vehicle-road cooperative control method and device for an internet of things multifunctional intelligent lamp post, which are used for improving accuracy of vehicle-road cooperative control for the internet of things multifunctional intelligent lamp post.
The first aspect of the invention provides a vehicle-road cooperative control method for an internet of things multifunctional intelligent lamp post, which comprises the following steps: collecting road parameter information of a preset target road section through a plurality of preset multifunctional intelligent lamp poles installed in the target road section;
carrying out digital twin body construction on the target road section through the road parameter information to obtain a target digital twin road;
carrying out heterogeneous traffic flow simulation on the digital twin road to obtain test traffic flow data;
based on the test traffic flow data, performing real-time image acquisition on the target road section through a plurality of multifunctional intelligent lamp rods to obtain a real-time image set;
performing multi-target spatial position relation analysis on the real-time image set to obtain spatial position relation description information;
and predicting the vehicle running parameters of the test traffic flow data and the spatial position relation description information to obtain target vehicle running parameters, and transmitting the target vehicle running parameters to a preset data transmission terminal.
With reference to the first aspect, in a first implementation manner of the first aspect of the present invention, the collecting, by a plurality of preset multifunctional intelligent lamp poles installed in a preset target road segment, road parameter information of the target road segment includes:
collecting infrared parameter information of the target road section through infrared sensors in a plurality of multifunctional intelligent lamp poles;
extracting the road temperature of the infrared parameter information to obtain the road temperature data of the target road section;
collecting sound wave parameter information of the target road section through sound wave sensors in a plurality of multifunctional intelligent lamp poles;
collecting radar positioning data of the target road section through microwave radars in a plurality of multifunctional intelligent lamp poles;
and combining the road temperature data, the acoustic parameter information and the radar positioning data into the road parameter information.
With reference to the first implementation manner of the first aspect, in a second implementation manner of the first aspect of the present invention, the performing digital twin construction on the target road section through the road parameter information to obtain a target digital twin road includes:
carrying out road material matching on the road temperature data to obtain target road material data;
Carrying out vehicle position distribution analysis on the radar positioning data to obtain vehicle distribution data;
carrying out environment parameter construction on the target road section by the sound wave parameter information to obtain an environment parameter set;
and constructing a digital twin body of the target road section based on the target road material data, the vehicle distribution data and the environment parameter set to obtain a target digital twin road.
With reference to the first aspect, in a third implementation manner of the first aspect of the present invention, the performing heterogeneous traffic flow simulation on the digital twin road to obtain test traffic flow data includes:
calculating the route length of the digital twin road to obtain a target route length;
generating a simulation time period and a simulation time step by the target route length;
and based on the target route length, carrying out heterogeneous traffic flow simulation on the digital twin road through the simulation time period and the simulation time step to obtain test traffic flow data.
With reference to the first aspect, in a fourth implementation manner of the first aspect of the present invention, the performing, based on the test traffic flow data, real-time image acquisition on the target road section through a plurality of the multifunctional intelligent light bars to obtain a real-time image set includes:
Carrying out road capacity calculation on the test traffic flow data to obtain road capacity data;
carrying out safety vehicle distance analysis on the road capacity data to obtain a safety vehicle distance corresponding to the road capacity data;
performing image acquisition frequency matching through the safety distance to obtain target image acquisition frequency;
and carrying out real-time image acquisition on the target road section through the target image acquisition frequency and the multifunctional intelligent lamp poles to obtain a real-time image set.
With reference to the first aspect, in a fifth implementation manner of the first aspect of the present invention, the performing multi-target spatial location relationship analysis on the real-time image set to obtain spatial location relationship description information includes:
inputting the real-time image set into an object detection unit in a preset position relation recognition model to detect objects, and obtaining a plurality of target objects corresponding to the real-time image set;
extracting feature vectors of a plurality of target objects to obtain a feature vector set;
calibrating the spatial position relationship of a plurality of target objects to obtain corresponding position relationship data between every two target objects;
based on the corresponding position relation data between every two target objects, each feature vector in the feature vector set is encoded to obtain an encoded vector set;
And inputting the coding vector set into a text decoding unit in the position relation recognition model to generate a position relation description text, so as to obtain the spatial position relation description information.
With reference to the first aspect, in a sixth implementation manner of the first aspect of the present invention, the predicting the vehicle running parameter for the test traffic flow data and the spatial location relationship description information to obtain a target vehicle running parameter, and transmitting the target vehicle running parameter to a preset data transmission terminal includes:
carrying out vehicle congestion degree analysis on the test traffic flow data to obtain corresponding first vehicle congestion degree data;
carrying out vehicle congestion degree analysis on the spatial position relation description information to obtain corresponding second vehicle congestion degree data;
the congestion degree analysis is carried out on the first vehicle congestion degree data and the second vehicle congestion degree data to obtain target vehicle congestion degree data;
performing position relation traversal on the spatial position relation description information to obtain traversal text information;
extracting current traffic condition data from the traversal text information to obtain a target traffic condition;
and inputting the target traffic condition and the target vehicle congestion data into a preset vehicle running parameter prediction model to predict the vehicle running parameters, obtaining the target vehicle running parameters, and transmitting the target vehicle running parameters to a preset data transmission terminal.
The second aspect of the invention provides a vehicle-road cooperative control device for an internet of things multifunctional intelligent lamp post, which comprises:
the acquisition module is used for acquiring road parameter information of a preset target road section through a plurality of preset multifunctional intelligent lamp poles installed in the target road section;
the construction module is used for constructing a digital twin body of the target road section through the road parameter information to obtain a target digital twin road;
the simulation module is used for simulating the heterogeneous traffic flow of the digital twin road to obtain test traffic flow data;
the acquisition module is used for acquiring real-time images of the target road section through a plurality of multifunctional intelligent lamp bars based on the test traffic flow data to obtain a real-time image set;
the analysis module is used for carrying out multi-target spatial position relation analysis on the real-time image set to obtain spatial position relation description information;
and the prediction module is used for predicting the vehicle running parameters of the test traffic flow data and the spatial position relation description information to obtain target vehicle running parameters, and transmitting the target vehicle running parameters to a preset data transmission terminal.
In the technical scheme provided by the invention, road parameter information of a target road section is collected through a plurality of multifunctional intelligent lamp poles installed in the target road section; constructing a digital twin body of the target road section through the road parameter information to obtain a target digital twin road; carrying out heterogeneous traffic flow simulation on the digital twin road to obtain test traffic flow data; based on the test traffic flow data, performing real-time image acquisition on the target road section through a plurality of multifunctional intelligent lamp poles to obtain a real-time image set; carrying out multi-target spatial position relation analysis on the real-time image set to obtain spatial position relation description information; and predicting the vehicle running parameters of the test traffic flow data and the spatial position relation description information to obtain the target vehicle running parameters, and transmitting the target vehicle running parameters to the data transmission terminal. In the scheme, the actual condition of the target road section can be better obtained through digital twin body construction and heterogeneous traffic flow simulation, so that the accuracy of vehicle running parameter prediction is improved. The multifunctional intelligent lamp post and the real-time image acquisition allow real-time monitoring of road section conditions. The method can be used for traffic management, accident detection, congestion analysis and the like, and helps cities to respond to traffic problems better. Through real-time data and space position relation description information, traffic signal lamp control can be better optimized, congestion is reduced, and traffic flow efficiency is improved. By analyzing the real-time image and the traffic flow data, potential traffic accident signs can be found in advance, so that better safety is provided, and the accuracy of the vehicle-road cooperative control for the multifunctional intelligent lamp post of the Internet of things is further improved.
Drawings
FIG. 1 is a schematic diagram of an embodiment of a vehicle-road cooperative control method for a multifunctional intelligent lamp post of the Internet of things in an embodiment of the invention;
FIG. 2 is a flow chart of digital twin construction of a target road segment through road parameter information in an embodiment of the present invention;
FIG. 3 is a flow chart of a heterogeneous traffic flow simulation for a digital twinned road in an embodiment of the invention;
FIG. 4 is a flowchart of real-time image acquisition of a target road segment through a plurality of multifunctional intelligent lamp poles in an embodiment of the invention;
fig. 5 is a schematic diagram of an embodiment of a vehicle-road cooperative control device for a multifunctional intelligent lamp post of the internet of things in an embodiment of the invention.
Detailed Description
The embodiment of the invention provides a vehicle-road cooperative control method and device for an internet of things multifunctional intelligent lamp post, which are used for improving the accuracy of vehicle-road cooperative control for the internet of things multifunctional intelligent lamp post.
The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
For easy understanding, a specific flow of an embodiment of the present invention is described below, referring to fig. 1, and an embodiment of a vehicle-road cooperative control method for a multifunctional intelligent lamp post of the internet of things in the embodiment of the present invention includes:
s101, acquiring road parameter information of a target road section through a plurality of preset multifunctional intelligent lamp poles installed in the preset target road section;
it can be understood that the execution body of the invention can be a vehicle-road cooperative control device for the multifunctional intelligent lamp post of the internet of things, and can also be a terminal or a server, and the implementation body is not limited in the specific point. The embodiment of the invention is described by taking a server as an execution main body as an example.
Specifically, the multifunctional intelligent lamp post collects infrared parameter information of a target road section through an infrared sensor arranged in the multifunctional intelligent lamp post. These sensors can detect heat distribution on the road surface, including heat release from vehicles and pedestrians. From these data, the system analyzes traffic density and pedestrian traffic for the target road segment. For example, during peak hours, these sensors may detect traffic congestion, triggering adjustment of traffic lights to reduce congestion. Road temperature information is extracted from data acquired by the infrared sensors, which can be used to evaluate the surface condition of the road. The temperature data is helpful for identifying dangerous situations such as icing, snow accumulation or road slippery. In addition, the sound wave sensor is also installed in multi-functional wisdom lamp pole for gather the sound wave parameter information of target highway section. These sensors may detect traffic noise levels, such as engine noise, whistling, and road friction of the vehicle. By analyzing these sound data, the system evaluates the condition of road traffic, including vehicle speed and location of traffic congestion. For example, if the noise level increases significantly, the system determines that there is a traffic accident or congestion and notifies the traffic management center. Meanwhile, the multifunctional intelligent lamp post is further provided with a microwave radar for collecting radar positioning data. Microwave radar can detect the position, speed and direction of the vehicle and thus can provide more accurate traffic flow data. By analyzing the radar positioning data, the system monitors the running track of the vehicle in real time and counts the vehicles. For example, the system tracks vehicle movement on roads, helping traffic management centers adjust the timing of traffic lights to optimize traffic flow. Integration and analysis of these data sources allows the system to generate comprehensive road parameter information including traffic density, vehicle speed, noise level, and road surface conditions. And combining the road temperature data, the sound wave parameter information and the radar positioning data into the road parameter information. The comprehensive information provides more references for cooperative control of the vehicle and the road, and can support a traffic management center to better plan and coordinate traffic flow. For example, when the system detects a congested or dangerous road condition, it can adjust the rhythm of traffic lights, improve the traffic fluency and reduce the risk of traffic accidents. In addition, the system may also provide real-time traffic information to the driver, helping them make more intelligent route choices, thereby reducing commute time and fuel consumption.
S102, constructing a digital twin body of a target road section through road parameter information to obtain a target digital twin road;
the road material matching is performed on the road temperature data. The road temperature data is matched to known road material properties to determine the material characteristics of the target road segment. As the type of material of the road affects the thermal conductivity, durability and reflectivity of the road. By matching road temperature data, the system obtains target road material data, providing a basis for material characteristics for digital twinning roads. For example, if by temperature data analysis, the system concludes that the temperature of a section of road surface is rising, and the material of that section of road is matched to asphalt, this indicates that there is road damage or asphalt quality problem. This information may be used in decisions for road maintenance, such as repairing a road surface or making a resurface. And carrying out vehicle position distribution analysis on the radar positioning data. Radar location data provides information on the location of vehicles on the road, allows the system to track the location and distribution of vehicles, can help determine vehicle density, identify congestion points, and provide critical information for traffic light control. For example, if radar location data analysis indicates that the vehicle density is abnormally high on a certain road segment, the system deduces that traffic congestion is present. This will trigger the traffic management center to take action, such as adjusting the signal timing, to reduce congestion. And then, constructing the environment parameters of the acoustic parameter information. The acoustic parameter information reflects the sound level in the environment and the location of the sound source, such as a noisy road segment, a noise source, or a sound pollution area. For example, acoustic parameter information analysis indicates that an area is a high noise area, and the system uses this information to support traffic management decisions, such as taking noise reduction measures or limiting the runtime of the noise source. Based on the target road material data, the vehicle distribution data, and the set of environmental parameters, the system performs digital twin construction. This digital twin road is a virtual replica that reflects the reality of the target road segment, including road material characteristics, vehicle location distribution, and environmental conditions. For example, the system builds a digital twin road based on the information from the analysis, which shows that on a certain stretch of road the road material is asphalt, the vehicles are densely distributed and the surrounding environment is very noisy. This digital twin road helps to simulate the effects of different traffic management strategies, for example by adjusting signal lights to improve traffic flow, or taking noise reduction measures to improve the resident's living environment.
S103, carrying out heterogeneous traffic flow simulation on the digital twin road to obtain test traffic flow data;
specifically, route length calculation is performed on the digital twin road to obtain the length of the target route, and the actual length of the road section to be simulated is determined. This step may be implemented by map data or GPS information for quantifying the length of the target link. For example, assume that the system has a target segment that is 10 km in length. This length information will be used as a basis for simulation for subsequent traffic flow simulation. Next, based on the length of the target route, the system generates a simulation time period and a simulation time step. The simulation time period refers to the total time range of the simulation, typically in hours or minutes, to ensure that the simulation covers enough time to evaluate traffic flow. The analog time step is the time interval in the analog, typically in seconds, that determines the time resolution of the analog. For example, if the target link length is 10 km, the system chooses to simulate a period of one hour, and then sets the simulation time step to 10 seconds for simulation at a higher time resolution. The system then performs heterogeneous traffic flow simulation based on the target route length, the simulation time period, and the simulation time step to generate test traffic flow data. In this simulation, the system will take into account the different types of vehicles, their speed, density and driving behaviour. This helps simulate mixed traffic on actual roads, including small cars, buses, trucks, etc. For example, during simulation, the system considers that during peak hours, traffic flow is greater and vehicle speed is slower, while during night hours, traffic flow is less and vehicle speed is faster. By modeling these different conditions, the system generates detailed traffic flow data, including vehicle position, speed, and lane occupancy. These generated test traffic flow data facilitate traffic management and decision making. For example, it may help traffic management centers predict congestion, adjust the timing of traffic lights to optimize traffic flow.
S104, based on the test traffic flow data, performing real-time image acquisition on the target road section through a plurality of multifunctional intelligent lamp poles to obtain a real-time image set;
it should be noted that, the system performs road capacity calculation by using the test traffic flow data to obtain the road capacity data. Road capacity refers to the number of vehicles that a road segment can accommodate over a period of time. This helps to determine the load situation of the road, i.e. the relation between traffic flow and road capacity. For example, if the test traffic flow data shows that the traffic flow of a certain road segment is very high, approaching or exceeding the road capacity, this means a potential traffic jam. The road capacity data may be used to determine whether traffic management measures, such as adjusting signal lights or limiting vehicle access, need to be taken. Next, the system performs a safe distance analysis on the road capacity data to obtain a safe distance corresponding to the data. The safe distance is the minimum distance that the vehicle should maintain while traveling on the road to ensure safety. This value is typically dependent on the speed of the vehicle and the road conditions. For example, if the road capacity data indicates a high vehicle density, the system may use the corresponding safe distance value to ensure that there is sufficient distance between the vehicles to prevent collisions and reduce the risk of traffic accidents. Based on the calculated safe distance, the system will determine the target image acquisition frequency. This refers to the frequency at which real-time images are acquired at multiple frequencies to ensure that vehicle position and driving conditions are captured and to monitor whether a safe vehicle distance is maintained. For example, if the calculation of the safe distance between vehicles shows that a distance of 2 seconds should be maintained between vehicles, the system sets the image acquisition frequency to acquire real-time images every 2 seconds to detect whether the distance between vehicles meets the safety standards. Through the target image acquisition frequency, the system configures a plurality of multifunctional intelligent lamp poles to acquire real-time images of a target road section at a specific frequency, so that a real-time image set is obtained. These real-time images can be used to analyze whether traffic flow, vehicle position, and safe distance meet criteria to better understand road conditions. For example, the multifunctional intelligent lamp post can regularly shoot real-time images on road sections according to set frequencies. These images can be used to monitor the driving situation of the vehicle, such as whether a sufficient safe distance is maintained, and whether traffic congestion exists.
S105, carrying out multi-target spatial position relation analysis on the real-time image set to obtain spatial position relation description information;
specifically, the real-time image set is input into an object detection unit in a preset position relation recognition model to perform object detection, so as to obtain a plurality of target objects corresponding to the real-time image set, such as automobiles, pedestrians, bicycles and the like. Object detection typically relies on computer vision and deep learning techniques to identify and target objects in the image. For example, assume that the real-time image set contains vehicles on a road. The object detection unit may identify and mark the position and contour of these vehicles. Then, feature vector extraction is performed on the plurality of target objects. A feature vector is a mathematical representation describing each target object and generally includes features of color, shape, size, etc. These feature vectors help to distinguish between different target objects and support subsequent positional relationship analysis. And then, calibrating the spatial position relationship of the plurality of target objects. This step aims at determining the relative positional relationship, such as distance, direction, overlap, etc., between each two target objects. These relationship data facilitate an understanding of interactions and spatial arrangements between the target objects. For example, if two vehicles are detected in the image, the spatial positional relationship calibration may determine the distance and relative direction between them, such as one vehicle in front of or behind the other. Each feature vector in the set of feature vectors is encoded based on positional relationship data between each two target objects. The aim is to associate the positional relationship information with the feature vectors, thereby forming a set of encoded vectors. The set of encoding vectors includes the characteristics of each target object and its relative positional relationship with other target objects. For example, if the positional relationship data between two vehicles indicates that they are closely spaced, the encoded vector may reflect this relationship, indicating that the two vehicles are potentially at risk for collision. And inputting the coded vector set into a text decoding unit in the position relation recognition model to generate a position relation description text. The text decoding unit translates the encoded vectors into natural language or descriptive text to provide information about the spatial positional relationship between the target objects.
S106, predicting the vehicle running parameters of the test traffic flow data and the spatial position relation description information to obtain the target vehicle running parameters, and transmitting the target vehicle running parameters to a preset data transmission terminal.
It should be noted that, the system performs a vehicle congestion degree analysis on the test traffic flow data to obtain corresponding first vehicle congestion degree data. The degree of vehicle congestion refers to a measure of the density of vehicles on a road, and is typically determined by calculating the number of vehicles in a certain area. This value helps to assess the congestion of the road. For example, if a very large number of vehicles are found in a certain road section in the test traffic flow data, the system calculates that the degree of vehicle congestion in the area is high. Next, the system performs a vehicle congestion degree analysis on the spatial relationship description information to obtain corresponding second vehicle congestion degree data. This analysis involves considering the positional relationship between the target objects to understand the interactions and alignment between the target vehicles. For example, if the positional relationship description information indicates that the distance between the target vehicles is very close, there is a case of traffic jam or high congestion. Then, the system performs congestion level analysis on the first vehicle congestion level data and the second vehicle congestion level data to obtain target vehicle congestion level data. This step allows the system to integrate congestion information from different data sources to more accurately assess the congestion condition of the target vehicle. For example, if the first vehicle congestion data indicates that the vehicle density is high for a certain road segment, and the positional relationship description information indicates that the distance between the vehicles is very close, the system integrates the information to derive that the target vehicle is traveling in a highly congested environment. The system performs a positional relationship traversal to obtain traversal text information. The positional relationship traversal refers to analyzing the spatial positional relationship description information to extract information related to the current traffic condition. This step helps determine the relationship between the specific location of the target vehicle and the surrounding vehicles. For example, through positional relationship traversal, the system understands whether the target vehicle is surrounded by other vehicles or is in the vicinity of a certain exit on the expressway. The system then performs current traffic condition data extraction on the traversal text information to obtain the target traffic condition. This step allows the system to learn about the actual traffic conditions at the location of the target vehicle, including whether there is congestion, whether there is an accident or other factors that may affect vehicle travel. For example, by extracting the traversal text information, the system knows that a traffic accident is occurring in the area where the target vehicle is located, resulting in a closed road segment. And inputting the target traffic condition and the target vehicle congestion data into a preset vehicle running parameter prediction model. This model will take into account these data in combination and estimate the driving parameters of the target vehicle, such as speed, time of arrival, driving path, etc., based on algorithms and predictive models. For example, if the model finds that there is traffic congestion at the location of the target vehicle, it predicts that the target vehicle will be slower and the arrival time will be delayed. Finally, the predicted driving parameters of the target vehicle are transmitted to a preset data transmission terminal for use by a traffic management center or other related parties.
In the embodiment of the invention, the road parameter information of the target road section is collected through a plurality of multifunctional intelligent lamp poles installed in the target road section; constructing a digital twin body of the target road section through the road parameter information to obtain a target digital twin road; carrying out heterogeneous traffic flow simulation on the digital twin road to obtain test traffic flow data; based on the test traffic flow data, performing real-time image acquisition on the target road section through a plurality of multifunctional intelligent lamp poles to obtain a real-time image set; carrying out multi-target spatial position relation analysis on the real-time image set to obtain spatial position relation description information; and predicting the vehicle running parameters of the test traffic flow data and the spatial position relation description information to obtain the target vehicle running parameters, and transmitting the target vehicle running parameters to the data transmission terminal. In the scheme, the actual condition of the target road section can be better obtained through digital twin body construction and heterogeneous traffic flow simulation, so that the accuracy of vehicle running parameter prediction is improved. The multifunctional intelligent lamp post and the real-time image acquisition allow real-time monitoring of road section conditions. The method can be used for traffic management, accident detection, congestion analysis and the like, and helps cities to respond to traffic problems better. Through real-time data and space position relation description information, traffic signal lamp control can be better optimized, congestion is reduced, and traffic flow efficiency is improved. By analyzing the real-time image and the traffic flow data, potential traffic accident signs can be found in advance, so that better safety is provided, and the accuracy of the vehicle-road cooperative control for the multifunctional intelligent lamp post of the Internet of things is further improved.
In a specific embodiment, the process of executing step S101 may specifically include the following steps:
(1) Collecting infrared parameter information of a target road section through infrared sensors in a plurality of multifunctional intelligent lamp poles;
(2) Extracting the road temperature of the infrared parameter information to obtain the road temperature data of the target road section;
(3) Collecting sound wave parameter information of a target road section through sound wave sensors in a plurality of multifunctional intelligent lamp poles;
(4) Radar positioning data of a target road section are collected through microwave radars in a plurality of multifunctional intelligent lamp poles;
(5) And combining the road temperature data, the sound wave parameter information and the radar positioning data into road parameter information.
Specifically, infrared parameter information of a target road section is collected through infrared sensors in a plurality of multifunctional intelligent lamp poles. The infrared sensor may detect infrared radiation in the surrounding environment, which changes as the temperature of the object changes. These sensors are typically distributed on top of a multi-function smart light pole to cover a wide area on the road. For example, if a vehicle is traveling on a target road, the infrared sensor may detect the thermal radiation of the vehicle, thereby providing information about the vehicle's location and density. Next, by processing the infrared parameter information, road temperature data can be extracted. This is achieved by analyzing the intensity and spectrum of the infrared radiation. The road temperature data is helpful in understanding the condition of the road because it can indicate whether there is ice or snow coverage, whether the road is dry or wet, and whether ice formation is occurring. For example, if the infrared sensor detects high temperature radiation on the target road segment, the system deduces that the road temperature is high, which indicates that the road surface is hot, and measures need to be taken to reduce the effect of the road surface temperature on the vehicle. In addition, the multifunctional intelligent lamp post also collects sound wave parameter information of the target road section through the sound wave sensor. The acoustic wave sensor can detect the reflection time of the acoustic wave, thereby determining the position and distance of the object. In a vehicle-road cooperative control system, these sensors are typically used to monitor traffic flow and vehicle position. For example, if a vehicle passes through a target section, the acoustic wave sensor may capture the time of reflection of the acoustic wave and calculate the distance between the vehicle and the light pole, thereby providing real-time vehicle position data. In addition, the microwave radar in the multifunctional intelligent lamp post is used for collecting radar positioning data. The microwave radar may transmit a microwave signal and measure its reflection time to determine the position and velocity of the object. This technique is commonly used to monitor the speed and direction of travel of a vehicle. For example, when a vehicle enters a target segment, microwave radar may detect the position and speed of the vehicle and provide radar location data associated with the vehicle. The road temperature data, acoustic parameter information and radar positioning data will be combined into road parameter information. The integrated data set contains integrated information about road conditions, vehicle position and speed, and provides basic data for the vehicle-road cooperative control system. For example, if the road temperature data indicates that the road surface temperature is low, the acoustic parameter information indicates that the vehicle density is high, and the radar location data provides vehicle speed information, the system integrates this information to predict road conditions, such as potential icing or congestion.
In a specific embodiment, as shown in fig. 2, the process of executing step S102 may specifically include the following steps:
s201, road material matching is carried out on the road temperature data, and target road material data are obtained;
s202, carrying out vehicle position distribution analysis on radar positioning data to obtain vehicle distribution data;
s203, constructing environmental parameters of the target road section according to the acoustic parameter information to obtain an environmental parameter set;
s204, constructing a digital twin body of the target road section based on the target road material data, the vehicle distribution data and the environment parameter set, and obtaining the target digital twin road.
The road material matching is performed on the road temperature data to obtain the target road material data. The purpose of this step is to determine the type of road material used for the target road segment, as different road materials respond differently to temperature. For example, asphalt pavement and cement pavement differ in temperature response, so it is necessary to match temperature data with road materials to obtain more accurate information. For example, if the road temperature data indicates that the temperature of a road segment is low, the system correlates to the asphalt face by matching the temperature range, thereby deriving that the target road material is asphalt. Then, vehicle position distribution analysis is performed on the radar positioning data to obtain vehicle distribution data. The radar location data provides accurate position and speed information of the vehicle so that the distribution of the vehicle over the road can be determined. For example, if the radar location data indicates that there are multiple vehicles on the target road segment, the system generates vehicle profile data, including the position and speed of each vehicle. Meanwhile, the sound wave parameter information is used for constructing environment parameters of the target road section. The acoustic wave sensor can capture the travel time of the acoustic wave to determine the location and distance of the object. In a vehicle-road cooperative control system, acoustic wave sensors are commonly used to monitor obstacles, pedestrians, and vehicles in the environment, thereby helping to construct environmental parameters. For example, if the sonic sensor detects a pedestrian or obstacle on the target road segment, the system uses this information to construct environmental parameters to indicate a potential traffic obstacle. Based on the target road material data, the vehicle distribution data and the environmental parameter set, the system performs digital twin construction to obtain a target digital twin road. The digital twin is a virtual model of the road and vehicle, reflecting the conditions on the actual road, including road conditions, vehicle distribution, environmental factors, etc. For example, the system uses road material data to determine the type of road, vehicle distribution data to determine the position and speed of the vehicle on the road, and environmental parameters to construct a traffic environment, thereby constructing a virtual model of the target digital twin road.
In a specific embodiment, as shown in fig. 3, the process of executing step S103 may specifically include the following steps:
s301, calculating the route length of the digital twin road to obtain a target route length;
s302, generating a simulation time period and a simulation time step through the target route length;
s303, based on the target route length, carrying out heterogeneous traffic flow simulation on the digital twin road through the simulation time period and the simulation time step to obtain test traffic flow data.
The route length calculation is performed for the digital twin road. The objective is to determine the actual length of the target link so as to accurately reflect the scale and distance of the road in the simulation. The route length is typically expressed in units of distance (e.g., meters or kilometers) to describe the total distance traveled by the vehicle. For example, assuming that the target road segment is a highway, the system calculates the total length of the highway to provide the underlying data for subsequent simulation. Next, a simulation time period and a simulation time step are generated by the target route length. These parameters are key factors in the simulation process and determine the time span and granularity of the simulation. The simulation time period is typically expressed as a start time and an end time, with the simulation time step representing the time interval of each simulation advance. For example, if the target road segment is an urban road, the system will set the simulation time period to 7 am to 7 pm for a total of 12 hours, and the simulation time step to 1 minute, indicating that the system simulates traffic conditions once per minute. Based on the target route length, the simulation time period and the simulation time step, the system performs heterogeneous traffic flow simulation to obtain test traffic flow data. The simulation process simulates the traffic condition on the road based on different vehicle types, speed distribution, traffic density and other factors so as to better understand the running condition of the actual road. For example, in the simulation of urban roads, the system considers different types of vehicles, such as cars, buses and bicycles, as well as their operating speeds and traffic densities over different time periods. Through simulation, the system generates various traffic scenes including the conditions of congestion in peak periods, smooth off-peak periods and the like. The simulation data can be used for evaluating the effectiveness of traffic management strategies, optimizing signal lamp control, relieving traffic jams, improving decision making in aspects of road safety and the like.
In a specific embodiment, as shown in fig. 4, the process of executing step S104 may specifically include the following steps:
s401, calculating the road capacity of the test traffic flow data to obtain the road capacity data;
s402, analyzing the safety vehicle distance of the road capacity data to obtain the safety vehicle distance corresponding to the road capacity data;
s403, performing image acquisition frequency matching through a safe vehicle distance to obtain a target image acquisition frequency;
s404, performing real-time image acquisition on the target road section through a plurality of multifunctional intelligent lamp poles according to the target image acquisition frequency to obtain a real-time image set.
Specifically, road capacity calculation is performed on the test traffic flow data. The purpose is to evaluate the busyness and throughput of the road. Road capacity represents the number of vehicles passing through a road over a period of time, typically expressed in Vehicles Per Hour (VPH). This calculation helps determine the load level of the road and whether there is a potential traffic congestion problem. For example, if the test traffic flow data shows that the number of vehicles passing through the target road segment is high for a period of time, the system calculates the road capacity for that period of time to see if the maximum throughput of the road is approaching or exceeded. Next, safety distance analysis is performed on the road capacity data in order to ensure that a sufficient safety distance is maintained between vehicles to reduce the risk of traffic accidents. The safe distance refers to the minimum distance that should be maintained between vehicles in order to safely stop the vehicle in an emergency. For example, if the road capacity data indicates a high density of vehicles on the road, the system calculates a corresponding safe distance from the road type and the vehicle speed, ensuring sufficient space between the vehicles to brake and avoid collisions. And performing image acquisition frequency matching through the safety vehicle distance. The purpose is to ensure that the timing of the real-time image acquisition matches the traffic conditions. Different traffic conditions require different image acquisition frequencies to capture accurate information about vehicle position, speed and behaviour. For example, at high traffic densities, the system increases the image acquisition frequency to monitor the distance and speed between vehicles in real time. And when the traffic is smooth, the image acquisition frequency can be reduced so as to reduce the data transmission and storage cost. Through the target image acquisition frequency, the system acquires real-time images of the target road sections through a plurality of multifunctional intelligent lamp poles so as to obtain a real-time image set. These real-time images capture the actual position and behavior of the vehicle on the road segment and can be used for traffic monitoring, accident detection and decision support. For example, the system increases the image acquisition frequency during peak hours to capture traffic conditions between vehicles, to discover congestion or accidents in time, and to inform traffic management centers to take necessary actions.
In a specific embodiment, the process of executing step S105 may specifically include the following steps:
(1) Inputting the real-time image set into an object detection unit in a preset position relation recognition model to perform object detection to obtain a plurality of target objects corresponding to the real-time image set;
(2) Extracting feature vectors of a plurality of target objects to obtain a feature vector set;
(3) Calibrating the spatial position relationship of a plurality of target objects to obtain corresponding position relationship data between every two target objects;
(4) Based on the corresponding position relation data between every two target objects, each feature vector in the feature vector set is encoded to obtain an encoded vector set;
(5) And inputting the coded vector set into a text decoding unit in the position relation recognition model to generate a position relation description text, so as to obtain the spatial position relation description information.
Specifically, the real-time image set is input to an object detection unit in a preset position relation recognition model to perform object detection. This step aims at identifying and extracting various objects on the road, including vehicles, pedestrians, bicycles, etc., from the real-time images. Object detection utilizes computer vision techniques, such as Convolutional Neural Networks (CNNs), etc., to identify different objects in an image. Next, feature vector extraction is performed on the plurality of target objects. Each target object is represented as a set of feature vectors that describe the appearance, shape, size, and other visual characteristics of the object. Feature vector extraction helps abstract objects from the image for subsequent analysis. For example, for identified cars, pedestrians, and bicycles, the system may generate a corresponding feature vector for each object to describe their appearance and shape. And calibrating the spatial position relationship of the plurality of target objects to obtain position relationship data between every two target objects. This step aims at analysing the relative position between objects, for example whether they are adjacent, overlap or remain at a distance. For example, if an automobile and a pedestrian are detected in the real-time image, the system determines the relative position between them to see if the pedestrian is in front of or to the side of the automobile. Each feature vector in the set of feature vectors is encoded based on positional relationship data between each two target objects. Coding is the process of converting positional relationship information between objects into numerical or symbolic representations. Encoding helps to convert visual information into processable data. For example, the system encodes the positional relationship between the automobile and the pedestrian as "pedestrian in front of the automobile" and converts it into a corresponding data representation. And inputting the coded vector set into a text decoding unit in the position relation recognition model to generate a position relation description text so as to obtain spatial position relation description information. This step converts the encoded data into natural language descriptions that are easy to understand and use to support traffic management and security decisions.
In a specific embodiment, the process of executing step S106 may specifically include the following steps:
(1) Carrying out vehicle congestion degree analysis on the test traffic flow data to obtain corresponding first vehicle congestion degree data;
(2) Carrying out vehicle congestion degree analysis on the spatial relationship description information to obtain corresponding second vehicle congestion degree data;
(3) The congestion degree analysis is carried out on the first vehicle congestion degree data and the second vehicle congestion degree data to obtain target vehicle congestion degree data;
(4) Performing position relation traversal on the spatial position relation description information to obtain traversal text information;
(5) Extracting current traffic condition data from the traversal text information to obtain a target traffic condition;
(6) And inputting the target traffic condition and the target vehicle congestion data into a preset vehicle running parameter prediction model to predict the vehicle running parameters, obtaining the target vehicle running parameters, and transmitting the target vehicle running parameters to a preset data transmission terminal.
Specifically, vehicle congestion degree analysis is performed on the test traffic flow data. The purpose of this step is to evaluate the degree of congestion on the road based on the density of the actual vehicle. Congestion level analysis may be accomplished by identifying the number of vehicles on a particular road segment. This requires analysis of vehicle speed, spacing and flow in the traffic flow data. For example, assuming that the number of vehicles on a certain road section is high and the interval between vehicles is small in the test traffic flow data for a certain period of time, it is possible to obtain that the congestion degree of the road section is high. Next, vehicle congestion degree analysis is performed on the spatial relationship description information. The purpose of this step is to use the spatial positional relationship information to learn the interactions and relationships between vehicles on the road to further evaluate the degree of congestion. This may include the relative position between vehicles, interactions between vehicles, and relationships between different vehicle types on the road. For example, if the positional relationship information between vehicles indicates that there is a close interaction between some vehicles, and the distance between the vehicles is small, this indicates that the degree of congestion is high. Congestion degree analysis is performed on the first vehicle congestion degree data and the second vehicle congestion degree data. This step aims at comprehensively considering the test traffic flow data and the spatial position relation description information to generate a more comprehensive crowdedness analysis result. For example, if the test traffic flow data indicates that the vehicle density is high for a road segment and the spatial location relationship description information indicates that the interaction between the vehicles is tight, then the integrated analysis may determine that the congestion level for the road segment is high. Next, the spatial relationship description information is subjected to positional relationship traversal. This step is to identify and record the positional relationship between vehicles, including the distance, relative speed, and interaction between vehicles. For example, by traversing the spatial positional relationship description information, the system determines which vehicles present a potential collision risk or emergency braking nature between them. And inputting the target traffic condition and the target vehicle congestion data into a preset vehicle running parameter prediction model. The vehicle travel parameter prediction model will take into account current traffic conditions, vehicle congestion, and other factors to generate travel parameters of the vehicle, such as speed, acceleration, and travel path. For example, by inputting current traffic conditions and vehicle congestion data into a predictive model, the system estimates the optimal speed of the vehicle to avoid congestion or dangerous situations and controls traffic lights or provides navigational advice accordingly.
The above describes a vehicle-road cooperative control method for an internet of things multifunctional intelligent lamp post in the embodiment of the present invention, and the following describes a vehicle-road cooperative control device for an internet of things multifunctional intelligent lamp post in the embodiment of the present invention, referring to fig. 5, one embodiment of the vehicle-road cooperative control device for an internet of things multifunctional intelligent lamp post in the embodiment of the present invention includes:
the acquisition module 501 is used for acquiring road parameter information of a preset target road section through a plurality of preset multifunctional intelligent lamp poles installed in the target road section;
the construction module 502 is configured to perform digital twin construction on the target road section according to the road parameter information to obtain a target digital twin road;
the simulation module 503 is configured to perform heterogeneous traffic flow simulation on the digital twin road to obtain test traffic flow data;
the acquisition module 504 is configured to acquire real-time images of the target road section through a plurality of the multifunctional intelligent light bars based on the test traffic flow data, so as to obtain a real-time image set;
the analysis module 505 is configured to perform multi-target spatial position relationship analysis on the real-time image set to obtain spatial position relationship description information;
And the prediction module 506 is configured to predict the vehicle running parameter for the test traffic flow data and the spatial position relationship description information, obtain a target vehicle running parameter, and transmit the target vehicle running parameter to a preset data transmission terminal.
The road parameter information of the target road section is collected through the cooperation of the components and a plurality of multifunctional intelligent lamp poles installed in the target road section; constructing a digital twin body of the target road section through the road parameter information to obtain a target digital twin road; carrying out heterogeneous traffic flow simulation on the digital twin road to obtain test traffic flow data; based on the test traffic flow data, performing real-time image acquisition on the target road section through a plurality of multifunctional intelligent lamp poles to obtain a real-time image set; carrying out multi-target spatial position relation analysis on the real-time image set to obtain spatial position relation description information; and predicting the vehicle running parameters of the test traffic flow data and the spatial position relation description information to obtain the target vehicle running parameters, and transmitting the target vehicle running parameters to the data transmission terminal. In the scheme, the actual condition of the target road section can be better obtained through digital twin body construction and heterogeneous traffic flow simulation, so that the accuracy of vehicle running parameter prediction is improved. The multifunctional intelligent lamp post and the real-time image acquisition allow real-time monitoring of road section conditions. The method can be used for traffic management, accident detection, congestion analysis and the like, and helps cities to respond to traffic problems better. Through real-time data and space position relation description information, traffic signal lamp control can be better optimized, congestion is reduced, and traffic flow efficiency is improved. By analyzing the real-time image and the traffic flow data, potential traffic accident signs can be found in advance, so that better safety is provided, and the accuracy of the vehicle-road cooperative control for the multifunctional intelligent lamp post of the Internet of things is further improved.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
The integrated units, if implemented in the form of software functional units and sold or passed as separate products, may be stored in a computer readable storage medium. Based on the understanding that the technical solution of the present invention may be embodied in essence or in a part contributing to the prior art or in whole or in part in the form of a software product stored in a storage medium, comprising instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, or other various media capable of storing program codes.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. The vehicle-road cooperative control method for the multifunctional intelligent lamp post of the Internet of things is characterized by comprising the following steps of:
collecting road parameter information of a preset target road section through a plurality of preset multifunctional intelligent lamp poles installed in the target road section;
carrying out digital twin body construction on the target road section through the road parameter information to obtain a target digital twin road;
carrying out heterogeneous traffic flow simulation on the digital twin road to obtain test traffic flow data;
based on the test traffic flow data, performing real-time image acquisition on the target road section through a plurality of multifunctional intelligent lamp rods to obtain a real-time image set;
Performing multi-target spatial position relation analysis on the real-time image set to obtain spatial position relation description information;
and predicting the vehicle running parameters of the test traffic flow data and the spatial position relation description information to obtain target vehicle running parameters, and transmitting the target vehicle running parameters to a preset data transmission terminal.
2. The vehicle-road cooperative control method for internet of things multifunctional intelligent lamp post according to claim 1, wherein the collecting road parameter information of a preset multifunctional intelligent lamp post installed in a preset target road segment through the preset multifunctional intelligent lamp post comprises:
collecting infrared parameter information of the target road section through infrared sensors in a plurality of multifunctional intelligent lamp poles;
extracting the road temperature of the infrared parameter information to obtain the road temperature data of the target road section;
collecting sound wave parameter information of the target road section through sound wave sensors in a plurality of multifunctional intelligent lamp poles;
collecting radar positioning data of the target road section through microwave radars in a plurality of multifunctional intelligent lamp poles;
and combining the road temperature data, the acoustic parameter information and the radar positioning data into the road parameter information.
3. The vehicle-road cooperative control method for the internet of things multifunctional intelligent lamp post according to claim 2, wherein the constructing the digital twin body for the target road section through the road parameter information to obtain the target digital twin road comprises:
carrying out road material matching on the road temperature data to obtain target road material data;
carrying out vehicle position distribution analysis on the radar positioning data to obtain vehicle distribution data;
carrying out environment parameter construction on the target road section by the sound wave parameter information to obtain an environment parameter set;
and constructing a digital twin body of the target road section based on the target road material data, the vehicle distribution data and the environment parameter set to obtain a target digital twin road.
4. The vehicle-road cooperative control method for an internet of things multifunctional intelligent lamp post according to claim 1, wherein the performing heterogeneous traffic flow simulation on the digital twin road to obtain test traffic flow data comprises:
calculating the route length of the digital twin road to obtain a target route length;
generating a simulation time period and a simulation time step by the target route length;
And based on the target route length, carrying out heterogeneous traffic flow simulation on the digital twin road through the simulation time period and the simulation time step to obtain test traffic flow data.
5. The vehicle-road cooperative control method for a multifunctional intelligent lamp post of the internet of things according to claim 1, wherein the performing real-time image acquisition on the target road section through a plurality of the multifunctional intelligent lamp posts based on the test traffic flow data to obtain a real-time image set comprises:
carrying out road capacity calculation on the test traffic flow data to obtain road capacity data;
carrying out safety vehicle distance analysis on the road capacity data to obtain a safety vehicle distance corresponding to the road capacity data;
performing image acquisition frequency matching through the safety distance to obtain target image acquisition frequency;
and carrying out real-time image acquisition on the target road section through the target image acquisition frequency and the multifunctional intelligent lamp poles to obtain a real-time image set.
6. The vehicle-road cooperative control method for the internet of things multifunctional intelligent lamp post according to claim 1, wherein the performing the multi-target spatial position relationship analysis on the real-time image set to obtain spatial position relationship description information comprises:
Inputting the real-time image set into an object detection unit in a preset position relation recognition model to detect objects, and obtaining a plurality of target objects corresponding to the real-time image set;
extracting feature vectors of a plurality of target objects to obtain a feature vector set;
calibrating the spatial position relationship of a plurality of target objects to obtain corresponding position relationship data between every two target objects;
based on the corresponding position relation data between every two target objects, each feature vector in the feature vector set is encoded to obtain an encoded vector set;
and inputting the coding vector set into a text decoding unit in the position relation recognition model to generate a position relation description text, so as to obtain the spatial position relation description information.
7. The vehicle-road cooperative control method for an internet of things multifunctional intelligent lamp post according to claim 1, wherein the predicting the vehicle running parameter for the test traffic flow data and the spatial position relationship description information to obtain a target vehicle running parameter, and transmitting the target vehicle running parameter to a preset data transmission terminal comprises:
Carrying out vehicle congestion degree analysis on the test traffic flow data to obtain corresponding first vehicle congestion degree data;
carrying out vehicle congestion degree analysis on the spatial position relation description information to obtain corresponding second vehicle congestion degree data;
the congestion degree analysis is carried out on the first vehicle congestion degree data and the second vehicle congestion degree data to obtain target vehicle congestion degree data;
performing position relation traversal on the spatial position relation description information to obtain traversal text information;
extracting current traffic condition data from the traversal text information to obtain a target traffic condition;
and inputting the target traffic condition and the target vehicle congestion data into a preset vehicle running parameter prediction model to predict the vehicle running parameters, obtaining the target vehicle running parameters, and transmitting the target vehicle running parameters to a preset data transmission terminal.
8. A vehicle road cooperative control device for multi-functional wisdom lamp pole of thing networking, a serial communication port, a vehicle road cooperative control device for multi-functional wisdom lamp pole of thing networking includes:
the acquisition module is used for acquiring road parameter information of a preset target road section through a plurality of preset multifunctional intelligent lamp poles installed in the target road section;
The construction module is used for constructing a digital twin body of the target road section through the road parameter information to obtain a target digital twin road;
the simulation module is used for simulating the heterogeneous traffic flow of the digital twin road to obtain test traffic flow data;
the acquisition module is used for acquiring real-time images of the target road section through a plurality of multifunctional intelligent lamp bars based on the test traffic flow data to obtain a real-time image set;
the analysis module is used for carrying out multi-target spatial position relation analysis on the real-time image set to obtain spatial position relation description information;
and the prediction module is used for predicting the vehicle running parameters of the test traffic flow data and the spatial position relation description information to obtain target vehicle running parameters, and transmitting the target vehicle running parameters to a preset data transmission terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311654483.2A CN117354347B (en) | 2023-12-05 | 2023-12-05 | Vehicle-road cooperative control method and device for multifunctional intelligent lamp post of Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311654483.2A CN117354347B (en) | 2023-12-05 | 2023-12-05 | Vehicle-road cooperative control method and device for multifunctional intelligent lamp post of Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117354347A true CN117354347A (en) | 2024-01-05 |
| CN117354347B CN117354347B (en) | 2024-02-20 |
Family
ID=89367119
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311654483.2A Active CN117354347B (en) | 2023-12-05 | 2023-12-05 | Vehicle-road cooperative control method and device for multifunctional intelligent lamp post of Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117354347B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106297274A (en) * | 2016-10-09 | 2017-01-04 | 上海五零盛同信息科技有限公司 | Wisdom lamp stand and urban traffic situation Forecasting Methodology |
| CN111754794A (en) * | 2020-05-14 | 2020-10-09 | 深圳市奥拓电子股份有限公司 | Highway traffic information display method, device and system based on intelligent lamp pole |
| CN113442929A (en) * | 2021-06-21 | 2021-09-28 | 国汽智控(北京)科技有限公司 | Vehicle control method, device, equipment and computer readable storage medium |
| CN114153220A (en) * | 2022-02-10 | 2022-03-08 | 深圳市爱云信息科技有限公司 | Remote control method for automatic driving based on artificial intelligence Internet of things platform |
| CN115578699A (en) * | 2022-10-25 | 2023-01-06 | 中山市联兆照明有限公司 | Multi-functional wisdom lamp pole control system based on 5G communication |
| CN117057656A (en) * | 2023-08-17 | 2023-11-14 | 广东飞翔云计算有限公司 | Digital twinning-based smart city management method and system |
-
2023
- 2023-12-05 CN CN202311654483.2A patent/CN117354347B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106297274A (en) * | 2016-10-09 | 2017-01-04 | 上海五零盛同信息科技有限公司 | Wisdom lamp stand and urban traffic situation Forecasting Methodology |
| CN111754794A (en) * | 2020-05-14 | 2020-10-09 | 深圳市奥拓电子股份有限公司 | Highway traffic information display method, device and system based on intelligent lamp pole |
| CN113442929A (en) * | 2021-06-21 | 2021-09-28 | 国汽智控(北京)科技有限公司 | Vehicle control method, device, equipment and computer readable storage medium |
| CN114153220A (en) * | 2022-02-10 | 2022-03-08 | 深圳市爱云信息科技有限公司 | Remote control method for automatic driving based on artificial intelligence Internet of things platform |
| CN115578699A (en) * | 2022-10-25 | 2023-01-06 | 中山市联兆照明有限公司 | Multi-functional wisdom lamp pole control system based on 5G communication |
| CN117057656A (en) * | 2023-08-17 | 2023-11-14 | 广东飞翔云计算有限公司 | Digital twinning-based smart city management method and system |
Non-Patent Citations (2)
| Title |
|---|
| 张宇琳;尚可;张飞舟: "基于数字孪生技术的异质交通流安全性研究", 北京大学学报(自然科学版), vol. 58, no. 005, pages 888 - 896 * |
| 臧锋等: ""基于智慧灯杆系统的关键技术发展路径研究"", 《照明工程学报》, vol. 33, no. 6, pages 107 - 116 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117354347B (en) | 2024-02-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11847908B2 (en) | Data processing for connected and autonomous vehicles | |
| Chen et al. | Analysis of factors affecting the severity of automated vehicle crashes using XGBoost model combining POI data | |
| Ghanim et al. | A case study for surrogate safety assessment model in predicting real-life conflicts | |
| CN113345237A (en) | Lane-changing identification and prediction method, system, equipment and storage medium for extracting vehicle track by using roadside laser radar data | |
| CN112258841A (en) | Intelligent vehicle risk assessment method based on vehicle track prediction | |
| Nesamani et al. | Estimating impacts of emission specific characteristics on vehicle operation for quantifying air pollutant emissions and energy use | |
| Choi et al. | Proactive strategy for variable speed limit operations on freeways under foggy weather conditions | |
| CN115081508B (en) | Traffic running risk parallel simulation system based on traffic digital twin | |
| CN115618932A (en) | Traffic incident prediction method and device based on internet automatic driving and electronic equipment | |
| KR100865939B1 (en) | Traffic information guiding system and method | |
| Alrassy et al. | Driver behavior indices from large-scale fleet telematics data as surrogate safety measures | |
| Hawas et al. | Optimized multistage fuzzy-based model for incident detection and management on urban streets | |
| CN112017428B (en) | Road side vehicle networking device, viaduct road section identification method and vehicle-mounted vehicle networking device | |
| Chen et al. | A Novel Background Filtering Method with Automatic Parameter Adjustment for Real-Time Roadside LiDAR Sensing System | |
| Miqdady et al. | In search of severity dimensions of traffic conflicts for different simulated mixed fleets involving connected and autonomous vehicles | |
| CN117354347B (en) | Vehicle-road cooperative control method and device for multifunctional intelligent lamp post of Internet of things | |
| CN116461546A (en) | Vehicle early warning method, device, storage medium and processor | |
| KR20230063080A (en) | Traffic light operation system according to the results of analysis of road surface conditions and traffic patterns at signal intersections to increase traffic volume | |
| CN113128847A (en) | Entrance ramp real-time risk early warning system and method based on laser radar | |
| Golze et al. | Impact analysis of accidents on the traffic flow based on massive floating car data | |
| Rabbouch et al. | Traffic Sensing and Assessing in Digital Transportation Systems | |
| Ye et al. | Dynamic Queue Prediction at Signalized Intersections with Fusing Sensory Information and Connected Vehicles | |
| CN116168542B (en) | Early warning method and system based on behavior monitoring of large vehicle | |
| KR102477885B1 (en) | Safety analysis management server for evaluating autonomous driving roads | |
| Nateghinia et al. | A LiDAR-based methodology for monitoring and collecting microscopic bicycle flow parameters on bicycle facilities |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |