69 results about "Traffic reduction" patented technology

The invention discloses a safe driving early warning system based on big data and machine learning, and the system comprises the following steps: S1, data collection: collecting the vehicle position, parking time, vehicle door state, vehicle type and other data in real time through a roadside sensing device, and obtaining environment context information, such as road type, traffic flow, weather condition and other data; s2, data processing and fusion: matching and associating the real-time data acquired in S1 with historical data by using a multi-source data fusion technology, and constructing a complete vehicle behavior data set; s3, establishing a risk assessment model: inputting model related data based on a machine learning algorithm, constructing a door opening risk prediction model, and obtaining a probability value Pdoopen that the model output is a door opening behavior; s4, early warning: when a model early warning value is set to be Pthreshold and a probability value is greater than or equal to the early warning value, early warning about the door opening condition of a front parked vehicle is given to a rear vehicle through a vehicle-road cooperation system; the early warning system can effectively reduce the occurrence of traffic accidents.

The invention relates to an abnormal road scene image recognition and early warning system, and belongs to the technical field of computer vision and intelligent traffic. The system adopts a distributed architecture with edge computing and cloud collaboration, introduces a differential geometry theory to construct a road scene representation framework, collects data through a camera sensing unit, and sends the data to a cloud server; the edge computing unit executes preprocessing, and the cloud processing unit completes anomaly detection and early warning. The core innovation of the system is that the manifold learning representation module maps high-dimensional features to a Riemannian manifold space; the Riemannian geometric anomaly measurement module defines a multi-dimensional anomaly index; the multi-scale adaptive analysis module realizes comprehensive detection from macroscopic to microscopic; the abnormal scene library is automatically updated; the multi-vehicle cooperation module supports information sharing and joint decision making, the system achieves the effects that the anomaly detection precision is improved by 25-35%, the environmental adaptability is enhanced by 50-70%, the response time is controlled within 250 ms, major road anomalies can be pre-warned 5-30 seconds in advance, the traffic accident risk is reduced by 30-40% potentially, and the traffic efficiency is optimized.

The invention belongs to the field of intelligent traffic, and relates to a multi-intersection IVCPS cooperative control test case generalization generation method, which comprises the following steps: S1, constructing a mixed traffic flow fundamental diagram model, and deducing the relationship between traffic flow density and flow under different permeability by combining IDM and CACC models; s2, expanding an IVCPS scene body, and designing a multi-intersection road network scene; s3, adopting an upper-layer and lower-layer distributed cooperative control architecture, wherein the upper layer dynamically adjusts signal timing based on traffic pressure information, and the lower layer provides an optimal path and driving speed suggestion for the CAV; s4, constructing a scene parameter extraction module, and extracting a control algorithm, a vehicle model ratio, traffic flow and CAV permeability; S5, constructing a key calculation module, and calculating a parameter key index; and S6, constructing a test case generation module, and generating a combined test case set by adopting an AETG-S algorithm. According to the invention, the traffic efficiency of a multi-intersection road network can be effectively improved, traffic delay and energy consumption are reduced, and a scientific basis is provided for testing and optimization of an intelligent traffic system.

The embodiment of the invention provides an auxiliary driving control method and device, electronic equipment and a vehicle, and relates to the technical field of intelligent driving, environmental perception information of the advancing direction of a target vehicle in the driving process is obtained, and if it is determined that multiple continuous fixed obstacles exist in the advancing direction of the target vehicle based on the environmental perception information, the target vehicle is driven to move. According to the method and the device, if the traffic warning objects are identified, a plurality of continuous fixed obstacles are virtualized into virtual edges, and then auxiliary driving control is carried out based on the virtual edges, so that the plurality of continuous fixed obstacles are virtualized into the virtual edges, and then the auxiliary driving control is carried out by utilizing the virtual edges, so that missing identification of the traffic warning objects can be reduced; in this way, the effect of auxiliary driving control can be improved in a scene facing a plurality of continuous fixed obstacles, and the risk of collision is reduced.

The application relates to the field of data processing, and in particular to a method and device for reconstructing an expressway in an interchange area, equipment and a medium. The method comprises the following steps: the application accurately determines the interchange type by comprehensively considering the traffic engineering diagram of the current expressway, historical accident data, location information and reconstruction reasons, deeply analyzes the structural influence of the reconstruction on the existing road network, combines the current turning traffic volume and the long-term predicted traffic volume, scientifically formulates the geometric layout optimization scheme and the road technical index, and finally generates a targeted reconstruction plan, which effectively improves the foresight, rationality and safety of the reconstruction project, ensures that the expressway can better adapt to future traffic demand after reconstruction, optimizes the road network structure, and reduces the risk of traffic accidents, so that the effectiveness of the reconstruction is improved through comprehensive and detailed data analysis and design optimization.

The application belongs to the technical field of transportation, and particularly relates to a traffic prediction method based on multi-graph gated convolution and Conv-LSTM. The DTWN similarity value filling module is used to calculate the similarity between time series, and the average value of K data with high similarity is taken to fill in the missing data, so as to ensure the integrity of the traffic data. The traffic data is decomposed into approximate coefficients and detail coefficients through DWT. The approximate coefficients reflect the long-term trend of traffic flow, and the detail coefficients contain short-term fluctuation information. Different models are combined to process the data obtained through DWT. The detail coefficients are processed through the multi-graph gated dilated convolution MGDCN to capture the short-term fluctuation, and the approximate coefficients are processed through the Conv-LSTM to capture the long-term trend. Compared with the existing traffic prediction model, the application can fully fill in the missing data, capture the short-term fluctuation and long-term trend of traffic, effectively reduce the error in traffic prediction, and improve the accuracy of traffic prediction.

A processor-implemented method for managing bus traffic of a system-on-chip (SoC) includes receiving a mixed signal in a computing device including the SoC. One or more polarity changes in a slope of a waveform corresponding to the mixed signal are detected. One or more of an analog-to-digital converter (ADC) or a portion of SoC bus traffic associated with ADC operation is selectively disabled between one or more polarity changes in a slope of a waveform.

A processor-implemented method for managing bus traffic of a system-on-a-chip (SoC) includes receiving a mixed signal in a computing device including the SoC. One or more polarity changes of a slope of a waveform corresponding to the mixed signal are detected. One or more of an analog-to-digital converter (ADC) or a portion of SoC bus traffic related to ADC operation are selectively disabled between one or more polarity changes in the slope of the waveform.

This invention relates to the field of road management, specifically to a data-driven road traffic risk control system and method, comprising: a road monitoring module, a vehicle management module, an accident analysis module, a traffic focusing module, and a dispatching and allocation module. The road monitoring module is used to establish a road network model; the vehicle management module is used to plan the optimal driving route; the accident analysis module is used to determine the type of accident; the traffic focusing module is used to optimize patrol routes; and the dispatching and allocation module is used to build an exchange service platform for command and dispatch. This invention can improve traffic operation efficiency, reduce accident risks, build an intelligent traffic management system, enhance the perception and management level of urban traffic, improve the accuracy of traffic accident target detection, improve traffic infrastructure construction, enhance road network safety, optimize the allocation of human and material resources, and reduce traffic management costs.

The invention provides a user flow and city flow reduction method and device and a readable storage medium, and the method comprises the steps: carrying out the information analysis of NetFlow flow and AAA flow, and obtaining a NetFlow analysis result and an AAA analysis result; performing flow calculation according to the NetFlow analysis result to obtain a NetFlow flow calculation result, and performing flow calculation according to the AAA analysis result to obtain an AAA flow calculation result; carrying out city matching according to the NetFlow flow calculation result and the AAA flow calculation result, and carrying out city flow reduction to obtain NetFlow city reduction flow; and according to the NetFlow flow calculation result and the AAA flow calculation result, carrying out user internet protocol IP address matching, and carrying out user flow reduction to obtain NetFlow user reduction flow. The method can effectively reduce the flow reduction error.

The invention discloses a port ship traffic organization optimization and regulation and control method, which belongs to the technical field of waterway traffic optimization and intelligent management and control, and comprises the following steps: collecting port data, constructing an information physical system framework, and dynamically managing a port by using the port data through the information physical system framework. The method comprises the following steps of: extracting and quantizing, performing uniform feature fusion, obtaining a judgment result by utilizing an event triggering mechanism, updating a system state, predicting the updated system state by utilizing a model prediction control algorithm to obtain a system step length, predicting the system step length in real time by utilizing a self-adaptive vision field mechanism to obtain a real-time step length, and calculating the real-time step length according to the real-time step length. And solving by utilizing a multiplier alternating direction method according to the judgment result and the real-time step length to obtain a port ship traffic scheduling control strategy. According to the invention, high-efficiency ship traffic scheduling and resource optimization can be realized in a complex and changeable port environment, the port transportation efficiency is obviously improved, traffic congestion is reduced, and the self-adaptive capability of the system is enhanced.

The application discloses a port ship traffic organization optimization and regulation method, and belongs to the technical field of waterway traffic optimization and intelligent management and control. The method comprises the following steps: collecting port data, constructing an information physical system framework, using the information physical system framework to realize dynamic management of the port, uniformly fusing features after extraction and quantization, using an event triggering mechanism to obtain a judgment result, updating a system state, using a model prediction control algorithm to predict the system step length, using an adaptive horizon mechanism to obtain a real-time step length, using a multiplier alternating direction method to solve according to the judgment result and the real-time step length, and obtaining a port ship traffic scheduling control strategy. The application can realize efficient ship traffic scheduling and resource optimization in a complex and changeable port environment, significantly improve port transportation efficiency, reduce traffic congestion, and enhance the adaptive ability of the system.

The application provides a kind of underground mine truck scheduling method and device based on state machine and reinforcement learning, it is related to underground mine transportation system scheduling optimization technical field.The method comprises: obtaining the scene model of underground mine transportation system, constructs topological structure model, constructs the underground mine truck fleet operation problem according to topological structure model and conflict type, and then constructs the fleet scheduling decision model based on state machine and reinforcement learning;Wherein, each truck is regarded as the agent of fleet scheduling decision model, and the state machine is equipped for the agent;With the goal of maximizing transportation efficiency, reducing waiting time and reducing conflict, the fleet scheduling decision model is solved, and the scheduling result of mine truck in the underground transportation working face with bidirectional single lane driving characteristics is obtained.The application realizes the intelligent scheduling of underground mine truck fleet by combining state machine and reinforcement learning technology, to improve transportation efficiency, reduce traffic conflict and reduce energy consumption.

In order to improve passenger satisfaction with a transportation service and to provide an operation plan creation means capable of reducing operating costs for a transportation service provider, an operation plan creation device comprises: a transportation leg network generation unit that generates transportation leg network information that defines each transportation leg of the transportation service; a cancellation determination unit that generates transportation leg cancellation possibility information that indicates whether or not cancellation of each transportation leg of the transportation service is possible; a travel route candidate determination unit that generates travel route candidate information that indicates a travel route candidate for each travel plan in passenger travel plan information; a people flow prediction unit that generates people flow prediction information that indicates a predicted people flow in the transportation service; and an operation plan generation unit that generates new operation plan information in which certain transportation legs of the transportation service are eliminated.

The application provides an implementation method for detecting vehicle left turn, which comprises the following steps: monitoring the motion state of the vehicle by using a six-axis inertial measurement unit (IMU); performing data processing and six-axis fusion algorithm processing on the collected three-axis acceleration and three-axis angular velocity data to obtain three-axis Euler angles of the vehicle; performing integral and angle change calculation on the stored yaw angle and Z-axis angular velocity data to obtain the angle change when the vehicle turns; comparing the real-time calculated Z-axis angle change value with a preset left turn angle threshold value, and if the threshold value is exceeded, it is judged that the vehicle is left turning; introducing a time window mechanism; after the vehicle starts left turning, the Z-axis angle change of the vehicle in each data sampling period is continuously monitored, and when the Z-axis angular velocity decreases and tends to zero, it is judged that the left turning action is completed. Through accurate identification of the left turning action of the vehicle, the application reduces the occurrence of traffic accidents and provides more intelligent decision support for the traffic management system.

The invention relates to the technical field of traffic monitoring and management, and particularly discloses a traffic flow abnormity intelligent identification and early warning method and system based on deep learning. According to the method, after traffic monitoring video data is obtained and processed, information such as vehicle tracks is extracted to generate traffic state feature data, a traffic feature combination matrix and dominant feature parameters are determined, a traffic flow dynamic feature sequence is generated, traffic flow states are classified, the traffic abnormal degree is determined, and a corresponding management and control strategy is generated. According to the invention, accurate identification and timely early warning of traffic flow anomalies can be realized, the traffic management efficiency is improved, and the probability of occurrence of traffic accidents is reduced.

This invention relates to the field of vehicle control technology, and more specifically to a multi-vehicle system model for non-signal-controlled intersections. Through third-order linear transformation, the nonlinear system model can be converted into a third-order linear state-space model. This simplifies the model while meeting the requirements of vehicle motion control. Considering parameter mismatch and bounded acceleration, it more realistically reflects the longitudinal dynamics data of vehicles during actual driving, making it suitable for more realistic vehicle and traffic conditions. This provides more accurate data for vehicle control systems to control vehicles. By analyzing the vehicle terminal dynamics data through a multi-vehicle control system, it is possible to better control the current vehicle to maintain a certain and appropriate distance from surrounding vehicles to ensure safe driving. Simultaneously, it can alleviate traffic congestion, reduce traffic accidents, and increase traffic capacity.

The embodiment of the application provides a traffic congestion discrimination method and device based on map coordinates and vehicle big data, fully utilizes high-precision coordinate information provided by modern map services and massive vehicle driving data, and realizes rapid and accurate discrimination of a traffic congestion state through comprehensive analysis of multidimensional data such as vehicle driving directions and speeds, thereby providing timely and reliable decision support for a traffic management department, optimizing traffic flow management, improving road passing efficiency, and reducing traffic delay and environmental pollution. The method innovatively combines map geometric analysis and vehicle big data processing, overcomes many limitations of traditional methods, and has remarkable application value and popularization prospect.

A system, a method and a computer program product are provided to determine a left turn decision for a user or autonomous vehicle attempting to turn at an intersection of a road. For example, the system obtains contextual features and / or sensor data related to the intersection of the road. An optimal location on the road is determined for the user or autonomous vehicle to position the vehicle to make the left turn decision, based on the contextual features and / or the sensor data. A left turn risk factor is determined based on the location on the road for the user or autonomous vehicle to position the vehicle to make a left turn. An alert is presented to the user or autonomous vehicle regarding the left turn risk factor with a left turn advisory message.

The invention discloses a multi-source traffic data driven signal lamp accurate control method and system, and the method comprises the following steps: S1, collecting multi-source traffic data, and carrying out the data preprocessing, and forming a multi-source traffic original data set; s2, according to a flow conservation relationship, performing unification processing on the original data, and outputting calibrated traffic state data; s3, utilizing a shock wave neural operator module to predict motorcade wavefront arrival time and queuing emptying time of each entrance lane; s4, constructing a sequential logic constraint set and an uncertainty scene set; s5, through distributed robust optimization solution, generating a signal control scheme satisfying constraints, and generating a plan time axis; and S6, a control scheme is issued to a signal controller, adaptive phase switching is implemented, and after execution, recovery data are updated online. According to the accurate signal lamp control method driven by the multi-source traffic data, signal lamp scheduling is optimized in real time, the traffic flow management efficiency is improved, and traffic congestion is reduced.

The invention provides an anti-fatigue driving reminding method and system and electronic equipment, and belongs to the technical field of automobile anti-fatigue driving. The method comprises the steps that face information of a driver is acquired; judging whether the driver has a fatigue driving behavior or not according to the facial information; when it is judged that the driver is in fatigue driving, calling interaction reminding is conducted on the driver; and when an interactive response of the driver is not received within a first preset duration after calling interactive reminding is carried out on the driver, automatic driving is started to take over the vehicle. Whether the driver has the fatigue driving behavior or not can be detected, interesting interaction operation such as call reminding can be carried out through the voice assistant, the driving experience of the driver is not affected, the driver can be helped to improve attention, and traffic accidents are reduced. According to the invention, after the interaction function of the intelligent AI voice assistant is used for reminding, the automatic driving mode is entered when the user fails to correctly interact, so that the accident risk is reduced.

The application discloses a traffic flow prediction fused traffic light adaptive control method and system, and relates to the technical field of intelligent traffic, comprising: obtaining real-time traffic flow data of a target intersection; obtaining a current traffic light control strategy of the target intersection; obtaining a traffic flow prediction result; performing change degree evaluation according to the real-time traffic flow data and the traffic flow prediction result, obtaining a traffic flow change coefficient, and whether it is greater than or equal to a traffic flow change threshold; if the traffic flow change coefficient is greater than or equal to the traffic flow change threshold, generating a traffic light adjustment instruction, adjusting the current traffic light control strategy according to the traffic flow prediction result, generating a future traffic light control strategy, and performing traffic light adaptive control of the target intersection. The application solves the technical problems of inaccurate traffic flow prediction and inflexible traffic light control strategy in the prior art, and achieves the technical effects of improving traffic efficiency, reducing traffic congestion and optimizing traffic light control.

The utility model discloses a zebra crossing intersection reminding device with a traffic guiding function, which relates to the technical field of auxiliary traffic devices and comprises a base, two symmetrical vertical plates are arranged above the base, and a height adjusting mechanism is arranged between the two vertical plates and the base. A human body sensing sensor and a buzzer are arranged on the opposite faces of the two vertical plates correspondingly, a mounting groove is formed in the upper surface of the base, a blocking mechanism is arranged in the mounting groove, and the blocking mechanism comprises a blocking plate arranged in the mounting groove. According to the zebra crossing intersection reminding device with the traffic guiding function, the blocking plate is arranged, the two threaded blocks drive the two supporting plates to move under the rotation of the two-way threaded rod, the blocking plate is supported and jacked up through the movement of the two supporting plates, the blocking effect on pedestrians can be achieved, meanwhile, the traffic guiding function is achieved, and the traffic guiding function is achieved. When a pedestrian forcibly crosses the blocking plate, the human body sensing sensor controls the buzzer to operate, sound is made to remind the pedestrian of civilized traffic, and traffic accidents are reduced.

The utility model belongs to the technical field of barrier gates, and relates to a barrier gate rod offset damage early warning device for a barrier gate, which comprises a mounting plate, one end of the mounting plate is provided with a data processing main body, the middle part of the mounting plate is provided with an interrupting type microwave sensor, and the interrupting type microwave sensor is electrically connected with the data processing main body. A rotating groove is formed in the end, away from the data processing body, of the mounting plate, a driving shaft is rotationally connected into the rotating groove, and a barrier gate rod is mounted on the driving shaft. Under the condition that the barrier gate rod is damaged, the device can timely inform background customer service to report and repair through the data processing main body, meanwhile, the standby barrier gate rod of the device is started to intercept charging, normal operation of the parking lot charging barrier gate can be ensured, and especially in the peak period, traffic jam can be reduced, and the service life of the parking lot charging barrier gate is prolonged. The passing efficiency of the parking lot is improved, and meanwhile management disorder and income loss caused by barrier gate damage are reduced.

The application provides a smart public security comprehensive management information system and a reporting method, relates to the technical field of smart public security, and is a smart public security comprehensive management information system, which comprises a monitoring and collecting module, a two-dimensional coordinate system is arranged on a monitoring road surface image, and monitoring road surface image data is collected; the application sets up monitoring on the monitoring road surface, collects image data, analyzes and calculates the right turn of a vehicle, analyzes the right turn path of the vehicle by setting the coordinate system, and compares with the pedestrian coordinates; when the pedestrian coordinates are on the upper side of the right turn path of the vehicle, the voice broadcast device is used to remind the pedestrian to avoid, which can greatly reduce the probability of traffic security accidents, specifically, the conversion speed, acceleration and turning angle of the vehicle are analyzed, the vehicle offset point is generated, the vehicle control point is generated, the actual situation is more fitted, the output is more accurate, the Bezier curve is used to analyze the right turn trajectory of the vehicle, and finally, the trajectory related formula is output.

The application discloses a kind of multi-source data interaction's traffic light control optimization method and system, it is related to intelligent transportation technology field, including: obtaining the real-time traffic information dataset of target section;Based on real-time traffic information dataset, construct real-time traffic twin model, and embed traffic prediction model, carry out traffic jam prediction, obtain congestion result;Dynamically determine vehicle traffic priority, generate traffic light control target based on congestion result and vehicle traffic priority;Different signal timing schemes are simulated randomly by real-time traffic twin model, determine traffic efficiency index evaluation result set, select optimal control strategy according to traffic efficiency index evaluation result set;Based on optimal control strategy, adjust the traffic light signal of target section.The application solves the technical problems that traffic light signal timing is not flexible and cannot adapt to traffic flow changes in real time in the prior art, achieves the technical effects of improving traffic flow efficiency, reducing traffic congestion and improving the priority passing capacity of emergency vehicles.

The invention discloses a traffic control method and a traffic control system, and relates to the technical field of traffic control, and the method comprises the steps: collecting all-time video data in all directions through an intersection camera device, carrying out the standardization, training a flow prediction model with a vehicle arrival rate as a target through a neural network algorithm, and carrying out the optimization of the traffic prediction model; the traffic light cycle suitability is analyzed in combination with historical videos, and the queuing length in each direction of the next cycle is predicted by fusing a model prediction value and lane saturation traffic rate multi-dimensional data; and triggering a hierarchical control instruction according to a comparison result of the actually measured queuing length and a preset threshold value, and finally linking multiple devices to execute the instruction to execute a feedback optimization model and a threshold value parameter so as to realize accurate and efficient traffic control. According to the scheme, the predicted value of the queuing length is output by training the flow prediction model, and the traffic jam and the adjustment hysteresis are reduced by combining dynamically associated traffic light timing and hierarchical control instructions and matching with a multi-module cooperative execution and closed-loop feedback optimization mechanism.

The invention relates to an AR-HUD-based intelligent pedestrian interaction system, method and device, and belongs to the technical field of intelligent driving. The method comprises the steps of collecting multi-modal data of a target vehicle in real time through multiple sensors; inputting the multi-modal data into the trained deep learning model, detecting and identifying pedestrians and zebra crossings to obtain augmented reality information, and displaying the augmented reality information through HUD projection; wherein the augmented reality information comprises zebra crossing positions, pedestrian directions and vehicle yielding states; when it is detected that the pedestrian approaches the zebra crossing, safety reminding is sent to the pedestrian in combination with the environment sensing information. According to the scheme, pedestrians and zebra crossings can be accurately detected and recognized in various complex environments, so that the robustness and reliability of the system are improved, and traffic accidents can be effectively reduced and the street crossing safety of the pedestrians can be improved through accurate pedestrian detection and an efficient interaction mechanism when the system interacts with the pedestrians.

The application discloses a traffic accident prediction method, comprising: acquiring a vehicle-mounted video and preprocessing to obtain continuous image frames, extracting time features and space features from the continuous image frames, and performing mid-term fusion on the time-space features; performing position weighting on the object-level features based on a graph structure; performing spatial attention on the weighted object-level features; splicing the object-level features and full-frame features, and performing frame-level aggregation and time period-level aggregation to sufficiently learn traffic scene context information; performing space-time relationship reasoning on the obtained double-layer aggregated information to obtain a hidden state representation of a current time step; inputting the hidden state representation of the current time step into a full connection network to obtain an accident score, and giving a warning signal when the accident score exceeds a predetermined threshold. The method can successfully predict the occurrence of a traffic accident 2-4 seconds in advance, thereby giving a driving system or a driver sufficient reaction time, and thus greatly reducing the possibility of traffic accidents.

Embodiments of the present application provide a radar communication method, system, device, equipment and storage medium, relating to the technical field of radar communication, and applied to a slave radar in radar communication networking, which further comprises a master radar. The method comprises detecting a command action of a user of the master radar, and sending the command action to other slave radars in the radar communication networking, so as to remind the user of the slave radar to control a vehicle according to the command action. The present application detects and transmits the command action of the user of the master radar in real time, so that the user of the slave radar behind can obtain the intention of the user of the master radar in time, and thus can take corresponding measures in advance, reduce the probability of traffic accidents, and further improve the safety and user experience of travel. In addition, the automatic radar detection and information transmission reduce the dependence on visual observation or language communication, so that the radar user can more focusedly control the vehicle, and further enhance the safety and user experience of travel.