103 results about "Traffic intersection" patented technology

The invention provides a traffic signal lamp intelligent control method based on a fiber bragg grating sensing network, and relates to the technical field of traffic signal lamps, and the method comprises the steps: obtaining the detection data of each fiber bragg grating sensing line, and enabling the fiber bragg grating sensing lines to be transversely laid at a selected traffic crossroad along a lane, three fiber bragg grating sensing lines parallel to the stop line are laid on each road; determining the length range of the motor vehicle queuing length of each lane according to the detection data of each fiber Bragg grating sensing line; and controlling the working state of the corresponding traffic signal lamp according to the length range of the motor vehicle queuing length of each lane. The actual traffic flow can be determined through the detection data of the fiber Bragg grating sensing lines, the green light time can be dynamically allocated based on the actual traffic flow, the vehicle queuing time is shortened, and the passing efficiency can be effectively improved.

The invention belongs to the field of visual tracking, and relates to a multi-target visual tracking method based on cooperation of a dynamic neural field and a neural network, which takes a cross-modal cooperation architecture as a core and comprises a dynamic neural field module based on multi-target trajectory maintenance and shielding matching and an improved MoESDQ neural network module. Meanwhile, a collaborative decision-making mechanism is designed, when the activation peak value of the dynamic neural field is attenuated to a preset threshold value, neural network feature matching is triggered, and disappearance target reproduction correlation is achieved based on cosine similarity. The objective of the invention is to solve the visual tracking capability under the condition of scene and target motion change in a monitoring range, for example, under an intelligent traffic intersection scene. The problems of high ID switching rate, multi-target misassociation and low tracking precision under a real-time tracking background caused by scene change or frequent shielding of vehicles and pedestrians, similar target appearances, transient disappearance and reproduction of the targets and sudden illumination change are solved.

The invention discloses an automatic driving decision-making method and system for a port mixed traffic intersection based on deep reinforcement learning, and relates to the technical field of automatic driving. Comprising the following steps: acquiring real-time state information of automatic driving transportation equipment in a port mixed traffic intersection environment, and fusing the real-time state information into an automatic driving transportation equipment state vector in a heterogeneous manner; constructing a reinforcement learning decision model based on the DDPG; building a port traffic environment simulation platform; the reinforcement learning decision model based on the DDPG is trained; and solidifying and deploying the trained reinforcement learning decision model based on the DDPG in a vehicle-mounted calculation unit of the automatic driving transportation equipment, and controlling the driving of the automatic driving transportation equipment. The traffic efficiency, stability and safety of the automatic driving transportation equipment at the port intersection can be improved, the unmanned transportation process of the port mixed traffic scene is promoted, and the wharf transformation and operation cost is reduced.

The invention relates to the technical field of automatic driving, in particular to an automatic driving system based on pedestrian motivation and a control method, and the system comprises a data acquisition module, a pedestrian detection module, a pedestrian intention reasoning module and a vehicle control module. The data acquisition module is used for acquiring a video sequence and environment information of a traffic intersection when the intelligent driving vehicle drives to the intersection without the signal lamp. The pedestrian detection module detects pedestrians through video processing and a pedestrian recognition strategy and outputs pedestrian inter-frame images. The pedestrian intention reasoning module classifies pedestrian crossing motivations based on the trajectory and attitude information of pedestrians. The vehicle control module dynamically adjusts the vehicle speed according to the pedestrian motivation type and automatically brakes when necessary so as to ensure that pedestrians safely pass through the intersection. According to the system, self-adaptive comity of the intelligent driving vehicle to pedestrians at the intersection without signal lamps is realized, and the traffic safety and the adaptive capacity of intelligent driving are effectively improved.

Technical problems and their solution are disclosed regarding the location of mobile devices requesting services near a site from a server. Embodiments adapt and / or configure the transmitting device near the site, the mobile device communicating with the transmitting device using a short haul wireless communications protocol to deliver a token based upon a key shared with the server but invisible to the mobile device. The server can determine the proximity of the mobile device to the site to control actuation of the requested service or disable the service request, and possibly flushing the service request from the server. Solutions are disclosed for traffic intersections involving one or more traffic lights, elevators in buildings, fire alarms in buildings and valet parking facilities.

The invention discloses a non-motor vehicle passenger-vehicle identification method and system in a crowded scene, and belongs to the technical field of intelligent traffic management. In order to solve the problem of accurate recognition of non-motor vehicles, persons and vehicles in a crowded scene, image data of a traffic intersection is collected through a traffic camera, target detection processing is performed on the image data by using a target detection model, and a person target and a non-motor vehicle target are detected to obtain a person target frame and a non-motor vehicle target frame; judging whether the scene category to which the image data of the traffic intersection belongs is a crowded scene or not to obtain crowded scene image data; personnel key points and non-motor vehicle key points in the crowded scene image data are extracted; associating the personnel key points with the non-motor vehicle key points to determine personnel key points associated with the non-motor vehicle key points to obtain a personnel-vehicle association target; and identifying whether the person-vehicle associated target has traffic violation behaviors or not through an image tracking technology, and if so, identifying the identity information of the person target for traffic violation early warning and processing.

The invention relates to the technical field of traffic monitoring. The traffic flow dynamic monitoring method and device, the equipment and the medium are provided, and the method comprises the steps that independent game nodes are arranged at key traffic intersections of a target road network in a distributed node deployment mode, and a remote game control framework is constructed; collecting real-time traffic flow data and associated environment parameters, and generating an initial signal control strategy; performing cross-regional information exchange on the initial signal control strategy to generate a traffic resource allocation game model; performing iterative optimization on the traffic resource allocation game model by adopting a distributed Nash equilibrium algorithm to generate a global coordination signal timing scheme; performing scenarized strategy customization on the global coordination signal timing scheme according to the road function partition features to obtain a scenarized signal control instruction; and issuing the scenarized signal control instruction to an execution terminal of a corresponding intersection so as to improve the multi-intersection collaborative decision-making capability, enhance the scenarized strategy adaptability and optimize the dynamic optimization real-time performance.

The application discloses a traffic signal lamp trigger type countdown control output method, comprising the following steps: S100, configuring signal lamp fixed time countdown time length and configuring current cycle phase information; S200, reading the cycle phase information of the traffic signal lamp at the current time node and the signal lamp fixed time countdown time length, and generating a running phase chain table; S300, judging whether the time before the non-traffic light color of the current lost traffic right phase meets the configured fixed time countdown time length; S400, if the configured fixed time countdown time length is met, triggering the corresponding countdown timer; if the configured fixed time countdown time length is not met, performing countdown correction and calculating the countdown extension time; and S500, repeating steps S200-S400. The application can generate a running phase chain table under the condition that traffic intersection parameters are pre-configured, pre-add, real-time update and calculate signal control data to achieve accurate control of the time when the trigger signal triggers the countdown timer, and realize the trigger type pulse control countdown algorithm.

The invention relates to the technical field of image recognition, and provides a computer-aided infrared imaging target simulation recognition method and device, and the method comprises the steps: carrying out the clustering analysis of all vehicle heat source regions based on a driving correlation index, and obtaining an independent vehicle heat source region and a suspected adhesion vehicle heat source region; according to the position distribution of the vehicle heat source area in the independent vehicle heat source area, obtaining a corrected structural element size of the independent vehicle heat source area; according to the adhesion suspicion degree, the corrected structural element size of the suspected adhesion vehicle heat source area is obtained; enhancement is carried out based on the corrected structure element size, and an enhanced traffic intersection monitoring infrared image is obtained; and vehicle target identification is carried out based on the enhanced traffic intersection monitoring infrared image. According to the invention, the accuracy of vehicle segmentation in a complex traffic scene is improved, and the accuracy of vehicle target identification and the integrity of a vehicle target structure are ensured.

The invention relates to the field of path planning, in particular to a vehicle path planning method based on road network division and graph reinforcement learning, comprising the following steps: forming a directed graph according to a traffic road network, nodes in the graph representing traffic intersections, and edges representing connections between the intersections; dividing the real-time traffic flow data into a plurality of control regions according to the directed graph, assigning adjacent nodes among the regions as control nodes, and endowing each edge with a weight according to the real-time traffic flow data; inputting the directed graph into the graph convolutional network, extracting a road condition flow characteristic matrix, and combining the flow characteristic matrix, the current position matrix and the destination position matrix to obtain the current state of the intelligent agent; and the intelligent agent selects the advancing direction according to the decision network in the current state, updates the state according to the selected action, and optimizes the driving route. According to the method, efficient path planning can be realized in a complex and dynamically changing traffic environment, and the method is suitable for optimizing a vehicle driving route in real time.

The application provides a traffic intersection vehicle trajectory fusion method and device, electronic equipment and medium, and relates to the technical field of intelligent transportation, which comprises the following steps: standardizing and preprocessing the perception data of a millimeter wave radar and a camera to obtain effective data; matching single-camera and multi-camera fusion prediction targets to determine a visual measurement state vector; combining Mahalanobis distance and target binding ID to complete target association; performing adaptive Kalman filtering fusion tracking to obtain fusion target state data; performing new birth and disappearance judgment on unassociated targets after clustering to obtain an effective fusion tracking target set; extracting a preliminary trajectory, matching the preliminary trajectory with a new birth trajectory after interrupting trajectory prediction in a ROI (Region of Interest) of the intersection, and performing interpolation completion to obtain an optimized trajectory; and improving multi-target tracking accuracy, trajectory speed and position consistency, adapting to complex traffic scenarios at the intersection, and providing reliable trajectory data for traffic management and vehicle-road cooperation.

The invention provides a traffic road ghost probe warning lamp, and relates to the technical field of traffic signals. The warning lamp comprises a detection device, a warning device and a control device. The detection device comprises at least two groups of laser correlation sensors, an ultrasonic distance measuring sensor and a networking monitoring camera, and is used for detecting approaching conditions of pedestrians, non-motor vehicles and vehicles at an intersection. The warning device comprises an LED lamp strip, a full-color LED dot matrix display screen and a motor vehicle display screen and is used for carrying out real-time early warning on passing vehicles and pedestrians. The control device comprises a control circuit board and a power management circuit. According to the invention, through a plurality of sensor fusion technologies, accurate detection of pedestrians and vehicles at the intersection is realized, and real-time early warning is carried out on passing vehicles and pedestrians by using the LED lamp strip and the display screen, so that traffic accidents caused by a ghost probe phenomenon are effectively prevented, the safety and traffic efficiency of the traffic intersection are improved, and accident risks are reduced.

This invention discloses a perception-driven intelligent multi-modal traffic signal optimization method and system, belonging to the field of traffic signal optimization technology. The method includes: collecting traffic flow data; constructing a multi-modal traffic flow model; connecting multiple traffic lights within a target area to obtain street light control signals; predicting traffic flow trends based on the traffic flow data and the street light control signals, using the multi-modal traffic flow model; and configuring a timing optimization scheme for multiple traffic lights within the target area based on the traffic flow trend prediction results. This invention solves the technical problem in the prior art where traffic light timing schemes cannot be accurately adjusted dynamically based on real-time traffic conditions and multi-modal traffic behavior interactions, leading to low traffic intersection efficiency. It achieves the technical effect of optimizing traffic light timing in a target area based on prediction results, effectively improving the traffic intersection efficiency.

The invention relates to the technical field of traffic control, and discloses a traffic intersection adaptive control traffic signal machine and a traffic control method, and the method comprises the steps: obtaining local point cloud data of a to-be-turned vehicle through a multi-frame image collection and three-dimensional reconstruction technology; according to the geometrical characteristics of the vehicle local point cloud, dynamically distributing weight coefficients of shape completion and semantic completion, and fusing the two completion results to generate a high-precision vehicle global point cloud; and then the vehicle length value is calculated through bounding box fitting, and when the number of vehicles meeting the length condition reaches a threshold value, the system automatically prolongs the green light duration of the U-turn signal lamp. According to the scheme, the problem of size calculation errors caused by local missing of vehicle images in a traditional method is effectively solved, accurate recognition and passing demand matching of large turning-around vehicles (such as long-wheelbase trucks) are achieved, the intersection space-time resource utilization rate in a complex traffic scene is remarkably improved, and the overall passing efficiency and safety are improved.

The invention discloses an intelligent traffic resource dynamic allocation method and system based on cloud side-end collaborative element reinforcement learning, and the method comprises the steps: obtaining a traffic flow and a traffic control state of a traffic intersection, and a self equipment load and communication state, and constructing a state vector; the edge node adopts reinforcement learning to generate each terminal action according to the state vector; after the action is executed, obtaining a state vector of the edge node at the next moment and calculating an environment feedback reward; the edge node uses a local experience tuple to train a local reinforcement learning model; the cloud side simulates one-step'virtual update 'of a global model based on a training set gradient uploaded by an edge node, and calculates element loss on an independent verification set based on a virtual parameter, thereby obtaining an element gradient of a discount factor gamma. And the cloud updates the gamma and issues the gamma to each edge server according to the gamma, so that the system can adaptively switch strategies of'attention to short-term 'and'attention to long-term' in a non-stable traffic environment, thereby improving the resource utilization rate and reducing the average delay.

1. Name of the product in this design: Two-way license plate recognition machine. 2. Application of this design: This design is used in traffic intersections or parking lots to recognize license plates of vehicles entering and exiting, provide voice announcements, and display text and image information (payment QR codes). 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: 3D view 1. 5. Other notes: Area A in 3D diagram 1 is a display screen, and area B is an LED light.

The application provides a lane and traffic light association method and device, a storage medium and an electronic device, wherein the method comprises the following steps: identifying traffic light information and lane information of a vehicle at a current traffic intersection; filtering traffic lights at non-current traffic intersections according to the traffic light information and the lane information to obtain a target traffic light group matched with the current traffic intersection; and associating each lane of the current traffic intersection with a matched traffic light in the target traffic light group. Through the embodiment of the application, traffic signal lights at non-current vehicle driving roads and non-current intersections can be effectively filtered, and the technical problem of inaccurate association of traffic lights and lanes in the related art is solved.

A heterogeneous regional traffic flow prediction method, comprising the following steps: S1: a traffic monitoring module monitors; S2: a feature analysis module is transmitted to a neural network traffic prediction module; S3: the neural network traffic prediction module comprises: S31: a strip-shaped convolution layer is used for pre-processing spatial data; S32: an extended causal convolution is used as a time convolution layer to obtain the time correlation between road network nodes; S33: the adaptive graph convolution layer is used to imitate the road connection relationship between heterogeneous regions, analyze the spatial features, and use the space-time aggregation module when facing the traffic intersection area selection, so that the adaptive graph convolution layer focuses on the time information change combined with the space-time aggregation module; S34: the cross-channel space attention layer is used to learn the connectivity relationship of adjacent roads; S35: the residual connection and the fully connected layer are used to aggregate the space and time information to obtain the traffic prediction result; S4: a traffic information visualization module is displayed; the application improves the traffic prediction accuracy and prediction speed, and the method has strong compatibility.

The application discloses a traffic intersection traffic light control method, including collecting real-time data, presetting pedestrian quantity range, presetting vehicle flow length range, calculating special vehicle intersection, special vehicle active regulation communication light, traffic accident dredging. The application obtains the latitude and longitude coordinate information of the special vehicle position and the latitude and longitude coordinate information of the intersection center position captured by the corresponding Beidou positioning equipment of the vehicle detector through the signal control machine, calculates the special vehicle driving path intersection, controls the traffic signal lamp of the special vehicle driving direction intersection to be green by the signal control machine, timely opens the green channel for the special vehicle, provides more efficient and safe driving route for the special vehicle, improves the emergency response speed and rescue efficiency; according to the vehicle flow and the pedestrian flow, the traffic intersection traffic light is regulated, the change of the traffic flow can be responded in real time, and the road traffic capacity and the traffic management level are improved.

Procedure for determining the reliability of the modeling of the dynamics of a traffic intersection, comprising the steps: S1 - Recording sensor data regarding the movement of road users at the traffic junction; S2 - Using a trained deep learning network model with the sensor data, wherein the deep learning network model includes at least one echo-state network unit (ESN), and wherein a result of the deep learning network model is a model of the dynamics of the traffic node; S3 - Determining a learned regularization coefficient of the deep learning network model, where the regularization coefficient indicates the reliability of the modeling of the dynamics of the traffic junction.

The application provides a traffic state determination method based on multi-source heterogeneous data, which can be applied to the technical field of intelligent transportation. The determination method comprises the following steps: performing anomaly detection on a plurality of initial traffic data in an initial traffic data sequence according to the distance between each initial traffic data arranged according to time information and a preset data and the abnormal value of each initial traffic data, to obtain abnormal traffic data; performing denoising on the initial traffic data sequence according to the abnormal traffic data, to obtain a target traffic data sequence; performing feature extraction on the target traffic data sequence based on the time information of the target traffic data sequence and the traffic correlation relationship between a plurality of traffic intersections, to obtain the time feature and the space feature of a target traffic intersection; and determining the traffic state of the target traffic intersection based on the time feature and the space feature.

The invention relates to the technical field of data processing, and provides a traffic signal intelligent optimization method based on key intersection identification, and the method comprises the steps: obtaining key intersections in an urban traffic intersection network; constructing a deep reinforcement learning agent corresponding to each key intersection; acquiring traffic state information of each key intersection to obtain a traffic state information set; and determining a traffic signal control scheme corresponding to each key intersection by adopting a deep reinforcement learning agent corresponding to the key intersection and the traffic state information set, so that the traffic signal control scheme can be generated according to the identified key intersection in combination with the deployed deep reinforcement learning agent. And the accuracy of generating the traffic signal control scheme is improved.

The application provides a traffic intersection lane direction adaptive switching control method and system, wherein the method comprises the following steps: obtaining a straight congestion coefficient and a left-turn congestion coefficient of an entering lane of a traffic intersection; and switching the lane direction of a variable lane on the entering lane based on the straight congestion coefficient and the left-turn congestion coefficient. According to the application, the straight congestion coefficient and the left-turn congestion coefficient of an entering lane of a traffic intersection are obtained, and the lane direction of a variable lane on the entering lane is switched based on the straight congestion coefficient and the left-turn congestion coefficient, so that the variable lane can be flexibly controlled in real time and accurately according to the traffic flow of each turning direction at the intersection, the turning function of the variable lane can be dynamically switched according to real-time traffic demand, the traffic efficiency of the urban road is improved, and the traffic congestion degree of the urban road is reduced.

The application provides a traffic participant trajectory prediction method, comprising: preprocessing a historical trajectory sequence to obtain a space-time category graph; encoding a time sequence of a to-be-predicted pedestrian to obtain a pedestrian time sequence hidden state; learning an interaction influence of different category intelligent agents on the pedestrian from the space-time category graph; learning interaction weight information of different intelligent agents in a surrounding area of the to-be-predicted pedestrian; splicing the above three feature vectors into a hidden vector of a specific dimension; encoding the hidden vector, splicing the obtained encoding vector with Gaussian noise, and decoding the obtained splicing vector into a Gaussian distribution parameter vector of a future trajectory as an output of trajectory prediction. The application not only considers the time and space interaction features of traffic intersection intelligent agents, but also fully utilizes the state category information of the traffic intersection intelligent agents, so that the prediction accuracy on an experimental data set is greatly improved, and good stability is shown.

This application discloses a method, device, equipment, storage medium, and program product for vehicle braking reminders, belonging to the field of vehicles. The method includes: acquiring the driving information of a first vehicle and the predicted state of traffic lights at an intersection; predicting a second reference duration for the first vehicle to pass through the intersection when the color and predicted state of the traffic lights meet reference conditions; when the second reference duration is less than a first threshold duration, generating an actual braking signal or a virtual braking signal based on at least one of the braking state of the first vehicle and relevant information of vehicles behind the first vehicle, wherein the actual braking signal is used to control the braking of the first vehicle and generate braking reminder information, and the virtual braking signal is used to generate braking reminder information to remind vehicles behind; and generating braking reminder information based on the actual braking signal or the virtual braking signal. This method can promptly remind vehicles behind, improving vehicle safety during driving.

The application relates to the technical field of device control, and discloses a traffic signal lamp control method and device, a terminal device and a storage medium. The method comprises the following steps: acquiring driving state data of each vehicle at a traffic intersection, wherein the driving state data comprises a future driving direction of the corresponding vehicle at the traffic intersection; inputting the driving state data into a trained signal lamp control model for processing; and controlling the signal lamp at the traffic intersection by using a state action value function output by the signal lamp control model; wherein the signal lamp control model is a graph neural network trained based on a deep reinforcement learning algorithm, the nodes of the graph neural network are various phases of the signal lamp, the feature data of each node is the driving state data of the vehicles on all passable lanes under the corresponding phase, the state of the deep reinforcement learning algorithm is the driving state data of the vehicles, and the action is each phase of the signal lamp. The method can improve the accuracy of signal lamp timing, thereby improving the vehicle passing efficiency.

The application discloses a target tracking method and device based on radar and video fusion, a storage medium and equipment. The method comprises the following steps: acquiring video data of a plurality of video devices and radar data of a plurality of radar devices at a traffic intersection, extracting target video frames and target radar frames containing target objects, obtaining target video pixel coordinates and target latitude and longitude information, performing plane coordinate conversion to obtain geodetic plane coordinates, obtaining time synchronization frame data sets according to time stamps of the target video frames and the target radar frames and the geodetic plane video coordinates and the geodetic plane radar coordinates, fusing target object coordinates of the target video frames and target object coordinates of the target radar frames at the same time to obtain cross-device radar and video fusion results, and finally matching cross-device fusion coordinates of each target object in the cross-device radar and video fusion results at different times to corresponding track trackers to obtain tracking tracks of each target object, so that accurate and efficient multi-sensor target fusion is realized.

The application provides a roadside laser radar-camera-UTM coordinate system joint calibration method and system, and the method comprises the following steps: selecting GNSS RTK equipment collection points, and obtaining a UTM coordinate sequence P UTM ; sequentially extracting the GNSS RTK equipment collection points in a laser radar point cloud, and obtaining a coordinate sequence P Lidar under a laser radar coordinate system; sequentially extracting the GNSS RTK equipment collection points in a camera image, and obtaining a coordinate sequence P Pixel under a pixel coordinate system; based on P UTM , P Lidar and P Pixel , an external parameter transformation relationship among the laser radar coordinate system, the camera coordinate system and the UTM coordinate system is calculated through nonlinear optimization, so that the joint external parameter calibration of the roadside laser radar-camera-UTM coordinate system can be more convenient, economical and accurate. The application avoids the high cost of obtaining a high-precision map, and the calibration precision is not lost, and the collection can be carried out for many times at different traffic intersections, the normal traffic is not disturbed, and the safety hidden danger of collection personnel is reduced.

The application belongs to the technical field of intelligent traffic, and specifically discloses an intelligent traffic management and control method, system and program product, which extracts image ROI and detects moving targets through collecting monitoring image sequences of each traffic direction at an intersection, so as to determine the moving target information in the corresponding interval, then establishes the moving track of each moving target to calculate the congestion index of the corresponding traffic direction, and finally determines the green light passing time of each traffic direction according to the comprehensive congestion index of each traffic direction, so as to realize fine and dynamic adjustment of the signal light time of the traffic intersection. The application allocates the signal light time of the intersection based on the congestion index, can more accurately determine the congestion of each traffic direction at the traffic intersection, makes the signal light timing capable of responding to the change of the traffic demand of each direction in real time, significantly improves the overall passing efficiency of the intersection, and is highly adaptable, can comprehensively evaluate the congestion of the vehicle flow and the pedestrian flow, and is suitable for mixed traffic scenes.

The invention discloses a method and a system for predicting red light running behaviors of pedestrians in a sparse scene, and belongs to the technical field of intelligent traffic control. In order to solve the problem that pedestrian red light running behaviors in a sparse scene are judged in advance, a first area and a second area are arranged in a traffic camera acquisition range of a traffic intersection; performing real-time target detection processing on the first area, performing static behavior detection on the pedestrian by using a behavior detection model to determine a target pedestrian, and obtaining an image sequence of the target pedestrian in the first area and an image sequence of the target pedestrian in the second area; performing trajectory extraction to obtain trajectory data of the target pedestrian, and performing behavior extraction to obtain a behavior sequence of the target pedestrian; according to the speed trend of the trajectory data of the target pedestrian, calculating a behavior probability value of the target pedestrian to judge whether the target pedestrian is a red light running intention, and constructing a positive sample and a negative sample of red light running; and constructing a red light running prediction model to obtain a trained red light running prediction model for predicting the red light running behavior of the pedestrian in the sparse scene.