41 results about "Traffic speed" patented technology

The invention discloses a traffic speed limiting method and device, electronic equipment and a storage medium, and belongs to the technical field of network security. The method comprises the steps of determining a port type of a to-be-configured port under the condition that a port configuration message sent by a control node in the virtual network is received; the port type comprises whether the port belongs to a virtual machine; under the condition that the port type is a virtual machine, determining whether the identifier of the to-be-configured port belongs to a preset white list chain or not; under the condition that the to-be-configured port belongs to the white list chain, adding a permission rule in the white list chain, and releasing the broadcast traffic of the to-be-configured port; and under the condition that the to-be-configured port does not belong to the white list chain, limiting the flow rate of the to-be-configured port according to a speed-limiting chain table rule. The problems that an existing network security technology is not completely suitable for a virtual network environment and is not high in efficiency can be solved.

The invention is applicable to the technical field of intelligent traffic systems, and provides a universal path representation learning method based on multi-modal spatial-temporal feature fusion, which comprises the following steps: firstly, carrying out multi-modal data preprocessing on a road network, a historical traffic speed and a remote sensing image, and constructing basic features; thirdly, through speed-road network fusion modeling, a road topological structure and periodic traffic speed dynamic characteristics are combined, and road path representation is generated; the road path representation and the image path representation are then subjected to fine-grained, medium-grained and coarse-grained semantic alignment at a node level, a sub-path level and a full-path level. And finally, through cross-modal residual fusion based on graph semantic information, integrating roads, images and environment semantic information thereof by using a graph neural network to obtain final path representation with enhanced semantics and stronger discrimination. According to the method, space-time dynamic and visual semantics are effectively fused, and more robust and universal path representation can be provided for downstream tasks such as path planning and traffic prediction.

The invention discloses an asphalt pavement modulus back calculation method and system based on detection data of a traffic speed deflectometer, and relates to the technical field of road engineering nondestructive testing, and the method comprises the following steps: introducing an inertia point theory into a TSD dynamic loading scene, and constructing a TSD finite element mechanical response model based on a multilayer elasticity theory and a double-wheel rolling loading characteristic; by simulating working conditions of different combinations, a direct physical relationship between deflection and the thickness of the soil matrix and the thickness of the superstructure is constructed to determine a unique soil matrix modulus, and by taking the unique soil matrix modulus as a physical boundary condition, a simulated annealing-particle swarm optimization matching method is introduced to realize dynamic modulus back calculation of the superstructure, so that the dynamic modulus of the superstructure is calculated. Therefore, an inverse calculation system based on coupling of a physical rule and intelligent optimization is constructed. According to the method, the back calculation precision and stability can be remarkably improved, the sensitivity to an initial value is reduced, the multi-working-condition adaptability is enhanced, and reliable technical support is provided for application of the TSD in road network level structure evaluation and intelligent maintenance.

The application discloses a traffic speed prediction method based on bidirectional interaction fusion space-time graph prompt, and belongs to the field of traffic speed prediction. First, the road network data and the historical traffic speed observation data of a target region are used to construct traffic space data and a historical traffic speed sequence, and a traffic speed prediction data set is generated by using a sliding time window; a multi-scale time graph prompt is obtained by constructing a multi-scale time subgraph from the historical traffic speed sequence; and a multi-relation space graph prompt is obtained by constructing a multi-relation space subgraph from the traffic space data and the historical traffic speed sequence, the multi-relation space subgraph containing physical neighborhoods and semantic neighborhoods. The two types of prompts are subjected to feature alignment, bidirectional attention interaction and gate fusion to generate a bidirectional interaction fusion space-time graph prompt, a traffic speed prediction backbone model is input with a historical input sequence, and a future traffic speed prediction result is output. The method improves prediction accuracy and generalization ability.

The application discloses a kind of urban traffic speed estimation method based on multi-source crowd-sensing data, which is based on the road pedestrian data and on-road navigation data collected by smart phone, and the final estimated speed is obtained through the steps of missing data filling, self-view speed aggregation and multi-view speed summation.The fine-grained large-scale urban traffic speed estimation method can estimate the speed of all types of roads, including suburban sections and small roads, rather than focusing on the main roads in the city center.The application is based on data-driven, without the need to install additional devices on the road, with low cost, strong universality, stronger practicality, theoretical and applicability compared with prior art, and has important significance for improving traffic management and planning.

The invention discloses an urban road multi-lane real-time traffic state reconstruction method and device, and belongs to the technical field of intelligent traffic. Matching the vehicle license plate data with the road network topology information, and extracting path information and steering historical features; a training soft label is generated through a soft label fusion mechanism, the steering probability of an individual vehicle is predicted through an LSTM (Long Short-Term Memory) network, and macroscopic steering flow is obtained; with the matched vehicle as a reference point, estimating a lane cumulative arrival flow from the reference point to the current moment and a corresponding lane cumulative arrival curve through a DNN deep neural network; a Newell simplified motion wave model is adopted to reconstruct a lane traffic speed, the traffic speed is introduced into an IDM intelligent driving model as a constraint, a microscopic car-following track of an individual vehicle is reconstructed, and then a lane-level real-time queuing state and a traffic state are identified; the invention aims to reconstruct a continuous and fine traffic state of a whole road section from limited point detection data.

A system receives GPS data and on-board sensor data from several connected vehicles indicating locations of nearby vehicles and objects. The system processes the data to create a shared-world model that includes locations and velocities of the connected vehicles and nearby vehicles and objects, and the system determines whether driving hazards exist, such as potential collisions. The system may transmit an alert to at least one of the connected vehicles, to cause the connected vehicle or a mobile device to present a warning message to a driver, such as a visual, audio, or haptic message, or to cause the connected vehicle to implement an action to avoid the driving hazard, such as activating emergency braking or altering course. The system may create, and transmit to a connected vehicle or mobile device, a lane-level traffic model indicating traffic density, traffic speed, and traffic throughput.

The application discloses a kind of intersection traffic speed planning method, computer equipment, readable storage medium and motor vehicle, it is related to automatic driving technical field, comprising the following steps: determining the availability of navigation map;Judge whether vehicle is close to intersection;According to signal light, judge vehicle to stop or pass intersection, and obtain the speed of road element and its rolling distance window;According to the speed of road element and its rolling distance window, the speed of passing intersection is calculated.The application does not depend on high-precision map of advanced auxiliary driving, only through navigation map, without changing the burden of road construction, effectively improve the traffic efficiency of crossroad.

The invention provides a flow rate control method and system for highway mixed traffic confluence, and relates to the technical field of traffic control, and the method comprises the steps: constructing a highway cell grid, and calculating the density information of vehicles in cells according to the lateral flow rate, the longitudinal flow rate and the ramp cell confluence flow rate from adjacent cells to a target cell; calculating the permeability of each type of vehicles in the cells and the traffic speed of the cells based on the density information of the vehicles in the target cells, and constructing a lane changing rate model according to the traffic speed and the vehicle distance information in the cells; based on the density information and a lane change rate model, constructing a lane change demand function and a cellular supply function of each type of vehicles, and updating a lateral flow rate; calculating the traffic capacity of cells based on the traffic speed, the permeability and the vehicle type information, and calculating a flow rate balance target ratio between upstream lanes of the confluence area according to the traffic capacity of the cells; and based on the flow rate balance target ratio, the lane change rate of the human-driven vehicle and the ramp cell convergence flow rate, calculating the lane change demand of the automatic driving vehicle in the upstream cell of the convergence area, and generating an automatic driving lane change strategy. According to the method, lane-level traffic is accurately modeled, and the inter-lane flow rate of the upstream of the confluence area is dynamically managed by using the active cooperative control function of the automatic driving vehicle.

The application discloses a kind of based on quantification total risk loss Large-scale city bridge tunnel network evaluation method, the method is: one, to open source geographic platform crawler, obtain road network topology data and establish bridge tunnel network model;Two, according to road grade and intersection situation, the edge and node of bridge tunnel network model are simplified;Three, traffic speed data is converted, and daily traffic volume data is obtained;Four, the monomer structure score data in detection report is converted, and monomer structure failure probability is obtained;Five, define spatial non-homogeneous Markov chain simulation structure state evolution;Six, define the direct and indirect total loss quantification formula considering structure failure, casualties, traffic closed detour and additional carbon emission;Seven, the long-term annual total risk loss of a city large-scale bridge tunnel network is quantified and evaluated.The method solves the current evaluation bridge tunnel network method only concerns safety loss and lacks consideration of functional loss, and is suitable for efficient management and maintenance of large-scale bridge tunnel network.

The invention relates to the technical field of motor vehicle testing, and discloses an intelligent vehicle speed auxiliary testing method, system and device and a storage medium, and the method comprises the steps: obtaining driving video data collected on a target region road, and inputting the driving video data to a perception input module, the to-be-tested automatic driving controller carries out traffic speed limit information identification based on the driving video data and generates a corresponding control response; driving the virtual vehicle to operate in a simulation environment based on the control response, and feeding back the vehicle state information in the operation process to the automatic driving controller to form a closed-loop simulation test; and determining an intelligent vehicle speed auxiliary test result according to whether the automatic driving controller correctly recognizes the subsequent traffic speed limiting information in the continuous driving process and makes corresponding control actions.

1. Name of the product in this design: Radar Tester. 2. Application of this product: This product is used for traffic speed measurement and control. It can measure and capture the speed of vehicles in both directions, identify license plates, vehicle models and body colors, and achieve data cloud storage and synchronization through network cable or 4G. It can present data in real time and generate visual reports, and is suitable for construction areas and other scenarios. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: a 3D model.

This invention belongs to the field of intelligent transportation, specifically relating to a road network comprehensive resilience assessment method based on a dual-component neural rough differential equation. The method includes the following steps: Step 1: Constructing high- and low-frequency dual-component feature information based on historical traffic speed data and topology data of the urban road network; Step 2: Constructing a dual-component neural rough differential equation model, solving for high-frequency and low-frequency spatiotemporal feature representations, fusing the high- and low-frequency dual-component spatiotemporal features, and outputting speed prediction results; Step 3: Constructing a road network comprehensive resilience index; Step 4: Road network comprehensive resilience assessment. Experimental results show that, compared with other prediction methods, this invention not only has superior traffic speed prediction performance but also provides more comprehensive, dynamic, and reliable road network resilience assessment results, providing effective technical support for management decisions and resilience enhancement of urban transportation systems under extreme weather conditions.

The application discloses a traffic speed prediction method based on high-order principal component decomposition space-time graph convolution, constructs a spatial correlation adjacency matrix of nodes based on the distance between site nodes, and the node attribute comes from the average speed of vehicles driving at the site represented by the node; in addition, the attribute of the node has dynamic time sequence, and the whole traffic network is modeled as a space-time graph structure; the traffic space-time graph is decomposed into a core tensor and a factor matrix in each dimension based on high-order principal component decomposition, the expression form of the space-time graph convolution network after high-order principal component decomposition is inferred, and a space-time graph convolution network model of unified space-time correlation modeling is realized. The application first applies the high-order principal component decomposition algorithm to the space-time graph convolution network, starts from the perspective of high-dimensional correlation modeling in the tensor space, proposes a space-time graph convolution model based on high-order principal component truncated decomposition, and has the advantages of reducing data dimension, parallel computing and noise suppression.

The application relates to the technical field of cloud computing networks, and provides a traffic speed-limiting system, a traffic speed-limiting method and a traffic speed-limiting device. The system comprises a network element proxy unit, a monitoring unit, a speed-limiting configuration unit, a program loading unit, a speed-limiting execution tool and a filter proxy unit. When the monitoring unit detects that the life cycle of the network element proxy unit or the bandwidth configuration strategy changes, the monitoring unit triggers the speed-limiting configuration unit to obtain a bandwidth speed-limiting execution mode and a bandwidth information configuration file according to the bandwidth configuration strategy; the program loading unit updates ip address bandwidth mapping data in a filter speed-limiting program file through the speed-limiting execution tool and the bandwidth information configuration file; the program loading unit further acquires and loads the filter speed-limiting program file into an operating system kernel, so that the speed-limiting execution tool realizes traffic speed-limiting according to ip mapping data and bandwidth mapping data in the above file and the bandwidth speed-limiting execution mode. The system can improve the scalability.

The invention discloses a multi-agent collaborative highway variable speed limit control method in a complex environment, and belongs to the technical field of highway traffic speed limit control. The method comprises the following steps: dividing an expressway into a plurality of control road sections, and obtaining traffic state data of the plurality of control road sections in the expressway in each control period and weather information and event information corresponding to the control road sections; calculating a context awareness feature vector for each control road section; constructing a multi-agent cooperative variable speed limit control model; training the Actor network and the Critic network based on the collaborative reward to obtain a trained Actor network; and during online control, calling the trained Actor network in each control period, outputting a speed limiting action according to the traffic state data and the context awareness feature vector of each control road section, converting the speed limiting action into a speed limiting control instruction, and issuing the speed limiting control instruction to a variable speed limiting sign, a road side unit or a traffic control platform for execution.

The invention relates to the technical field of traffic assistance, in particular to an unmanned aerial vehicle cooperative traffic accident handling system and a control method, and the method comprises the following steps: starting the system and entering peak daily patrol; the VSDM continuously collects and uploads the traffic flow speed and density of each road section, and the system generates a traffic flow density thermodynamic diagram according to the speed and plans a gridding fixed patrol route for the unmanned aerial vehicle; when the VSDM detects that the average speed of the road section is reduced to exceed a preset threshold value in a preset time window or the unmanned aerial vehicle returns an image to detect that the vehicle is static for a long time, triggering suspected accident early warning and recording an early warning position and associated traffic flow data; if not, returning to S2 to continue patrol; and sending a quick response instruction to the unmanned aerial vehicle closest to the early warning position. According to the invention, the problems of lagging accident discovery and confirmation, low disposal efficiency, insufficient module collaboration and low decision subjectivity are solved.

The application provides a kind of road rut fine measurement method based on structured light, first to the road point cloud data collected is denoised, slope and two-dimensional gridding processing, then the various features of point cloud data in gridding are mapped to gray scale image, finally based on image recognition and multi-feature fusion method realizes the identification and fine measurement of rut. Since the point cloud data collection is carried out by using the vehicle-mounted structured light collection equipment, the measurement of the degree of road rut under the dynamic traffic speed can be supported, and more rapid and fine rut detection and fine evaluation can be realized. At the same time, more fine road damage conditions are provided for the road maintenance department, and basis is provided for maintenance fund allocation and measure selection. Also, since the point cloud data is processed by two-dimensional gridding, the calculation amount of point cloud data processing and the dependence on artificial or high-precision instruments are greatly reduced, which has important significance for large-scale road performance high-frequency digital detection.

This invention discloses a dynamic scheduling method for the entire lifecycle of a bus fleet based on hierarchical reinforcement learning, belonging to the field of dynamic intelligent scheduling technology for urban public transport systems. The method first constructs a bus information collection module to acquire real-time operational data throughout the entire lifecycle, building a virtual scheduling environment that matches actual operational rules. Then, the entire bus operation cycle is decomposed into three levels: upper-level departure timetable scheduling, middle-level joint scheduling of stops and operating speeds, and lower-level joint scheduling of intersection signal priority and traffic speeds, constructing independent Markov decision processes for each level. Next, through a hierarchical progressive training framework, the strategies of each level are trained sequentially, first the lower level, then the middle level, and finally the upper level, to obtain a full-cycle collaborative scheduling model. Finally, based on the model, a real-time scheduling strategy is output, achieving closed-loop optimization of the entire bus lifecycle. This invention can effectively suppress bus queueing and delay propagation, significantly improve bus punctuality, reduce passenger waiting time, and has strong engineering applicability.

A method, apparatus and computer program product are provided to estimate a road segment traffic tendency determination value. A current traffic speed pattern data object may be generated for an initial location of a vehicle and a future traffic speed pattern data object may be generated for an estimated downstream location of the vehicle. A road segment traffic tendency determination value may then be estimated based at least in part on the current traffic speed pattern data object and the future traffic speed pattern data object. A road segment traffic tendency notification may be provided to the vehicle.

The application discloses a signal control and CAV trajectory planning method based on a pre-signal lamp, and comprises the following steps: acquiring intersection phase information and first information according to a pre-signal lamp arranged in a signal area; acquiring second information in a regulation area and a special lane area; performing first model processing on the first information and the second information, predicting a vehicle motion trajectory, and acquiring a total number and a type of vehicles in the regulation area; performing second model and third model processing on the intersection phase information, the vehicle motion trajectory, the total number and the type of vehicles, and predicting a best phase duration and a best CAV trajectory. The application significantly improves the traffic capacity of the intersection, obviously reduces the average fuel consumption and the number of lane changes of the CAV, and obviously improves the traffic speed and delay of the heterogeneous traffic flow.

The application relates to the technical field of artificial intelligence, in particular to a road recognition method and device, an electronic device and a storage medium, which can be applied to a vehicle-mounted scene, and based on candidate through traffic flow and deviated traffic flow corresponding to each historical time period of a to-be-recognized road, a deviated traffic parameter of the to-be-recognized road in a corresponding historical time period is determined, based on candidate traffic speed and candidate through traffic flow corresponding to each historical time period of the to-be-recognized road, a traffic impedance parameter of the to-be-recognized road is determined, and based on each traffic deviated parameter and the traffic impedance parameter, a traffic difficulty category of the to-be-recognized road is obtained. In this way, the road is recognized through the candidate through traffic flow, the deviated traffic parameter and the candidate traffic speed of the to-be-recognized road, so that the efficiency and accuracy of road recognition can be improved.

A traffic speed prediction apparatus may include: a communication device configured to receive probe data from a probe vehicle driving on a road; a storage configured to store data and algorithms for predicting a traffic speed; and at least one processor electrically connected to the communication device and the storage. The processor may be configured to predict the traffic speed on the road using traffic speed data, traffic volume data, and congestion data obtained based on probe data, and to obtain the congestion data by creating a target road network including a target collection section where the probe data is collected and determining a congestion matrix of the target road network.

The application discloses a kind of minimum clear distance calculation method and system of urban expressway under heterogeneous traffic flow, the method includes the following steps: according to the driving speed of each lane vehicle of current urban expressway traffic speed regulation setting, calculate the critical safety vehicle distance between the front and rear vehicles of target lane in the lane changing process of lane changing vehicle;According to the type of lane changing vehicle and the front and rear vehicles of target lane, several lane changing scenarios are constructed, the minimum lane changing gap between the front and rear vehicles of target lane and lane changing vehicle under each lane changing scenario is calculated according to the critical safety vehicle distance, the minimum lane changing gap is used as the driving constraint of lane changing vehicle, the driving scene of lane changing vehicle and the front and rear vehicles of target lane under all lane changing scenarios is simulated;According to the simulation result, the minimum clear distance under all lane changing scenarios is calculated, and the maximum value in all minimum clear distances is taken as the minimum clear distance of current urban expressway.The minimum clear distance calculated by the application fully considers the difference of driving vehicle type, and is more practical.

The application discloses a kind of distributed road weight training methods.The method is first obtained target area motor vehicle travel trajectory and is converted into learning target section sequence using map matching algorithm;Subsequently, the road section characteristic vector containing multi-dimensional objective attributes such as road grade, type and real-time traffic speed is constructed, and the training set containing positive and negative samples is constructed in combination with temporarily generated temporary coefficient;The training set is hashed into fragments using distributed computing architecture, the local update result of each training node is summarized by parameter server, and the global road weighting coefficient is generated based on road network topology constraint to perform gradient arbitration;Before outputting the final coefficient, construct virtual traffic to perform road network load balancing deduction, and use the penalty mask fed back to correct the feature dimension that causes abnormal aggregation by weighting reduction.The application realizes the accurate inversion of large-scale road network traffic cost by deep ordering learning and distributed parallel computing, effectively improves the rationality of path planning and the balance of road network flow.

A system receives, from a plurality of connected vehicles, respective GPS data indicating an absolute location of a respective connected vehicle and on-board sensor data indicating locations of nearby vehicles and objects relative to the respective connected vehicle. The system processes the data to create a shared-world model that includes at least the locations of the plurality of connected vehicles and the nearby vehicles and objects. Some implementations of the shared-world model further include the speeds and trajectories of each of the plurality of connected vehicles and the nearby vehicles and objects. The system transmits a representation of the shared-world model to one or more of the plurality of connected vehicles, which may utilize the shared-world model to provide advanced warnings for drivers or to provide improved path planning for autonomous vehicles. Some representations of the shared-world model include lane-level traffic functions such as traffic density, traffic speed, and traffic throughput.

This invention relates to the field of intelligent transportation technology and provides a congestion analysis method and system based on vehicle operating status. The congestion analysis method and system provided by this invention establishes intermittent flow operation models and continuous flow operation models, combines interfering vehicles into operating units, and performs combined analysis to obtain the traffic volume and the speed and density of moving units on a road segment based on the current traffic flow state. Furthermore, the road segment is segmented into sections to analyze changes in traffic volume and moving unit density. Based on the analysis results, the road congestion status is determined, thus solving the problems that current simple average traffic speed cannot accurately represent congestion, and that the calculation of the capacity of intersections and road segments is also relatively idealized, subject to many disturbance factors, and cannot closely reflect reality.

The invention discloses a data-driven highway frequent traffic congestion bottleneck rapid identification method, which comprises the following steps: acquiring historical traffic flow speed data of a highway section, estimating the traffic flow speed based on a traffic state space-time reconstruction technology guided by physical information, and constructing a daily traffic speed space-time diagram; performing traffic state research and judgment on each time-space block; constructing a daily traffic state space-time diagram and a traffic jam occurrence probability space-time diagram, and accurately identifying a common traffic jam space-time block in combination with a data-driven automatic probability threshold segmentation method; and carrying out segmentation extraction on the time-space region of the frequent traffic jam, and accurately identifying the bottleneck of the frequent traffic jam. According to the method, frequent traffic congestion and accidental traffic congestion can be effectively distinguished, key technical support is provided for expressway refined traffic control, the degree of dependence on artificial experience and the labor cost are remarkably reduced, and the reliability and stability of traffic congestion bottleneck identification and the automatic and intelligent level of expressway control are improved.

The invention belongs to the technical field of multi-vehicle cooperative supervision, and particularly relates to a multi-vehicle cooperative monitoring management platform supporting dynamic priority scheduling, comprising: a multi-source space-time prediction module outputting probability distribution of traffic speed and communication quality in a future time domain; the dynamic priority decision module constructs a multi-scene set based on probability distribution, generates a Pareto optimal strategy set through a multi-objective evolutionary algorithm, and decouples a dynamic priority weight vector of each vehicle from an optimal strategy through reverse optimization and marginal contribution analysis after greedy-robustness screening; the communication link management module pre-distributes a future time period strategy to a target vehicle and a relay adjacent vehicle before the vehicle enters a communication weak area based on communication prediction; and the distributed execution control module takes the priority weight as an optimization weighting coefficient, generates a smooth instruction through distributed model prediction control, realizes consistent collaboration through vehicle-vehicle communication iterative negotiation, and ensures the autonomous collaboration capability under communication abnormity.

The invention relates to the technical field of traffic management, in particular to a road traffic flow prediction method and system, and the method comprises the following steps: obtaining a traffic topological graph, analyzing speed change, calculating propagation time delay, obtaining a compensation coefficient, collecting a track analysis node feature prediction path, extracting speed density vehicle distance fluctuation, and judging a disturbance level. And simulating traffic distribution, evaluating pressure and predicting traffic flow, and comparing actual measurement errors to adjust parameter feedback results. According to the method, a propagation time delay calculation mechanism based on node passing speed and peak time difference is introduced, a time delay compensation coefficient is obtained, a stability score is constructed in combination with path preference and stay duration, a travel intention is deduced, the passing speed, density and vehicle distance data are fused to identify disturbance synchronism, and traffic loads under different guide modes are simulated. A node pressure index is calculated, a spatial distribution trend is judged, error starting point identification and parameter adjustment are combined, a simulation prediction and error feedback chain is formed, and the space-time identification capability of traffic flow prediction is improved.