193 results about "Intelligent transportation system its" patented technology

The invention discloses a roadside sensing system based on vehicle-road cooperation and a vehicle control method using the same. The system comprises intelligent roadside equipment, the intelligent roadside equipment comprises a roadside sensing module, a roadside processing module and a roadside communication module, the roadside sensing module comprises a sensor and is used for collecting surrounding environment information of a target vehicle, the roadside processing module is used for carrying out fusion processing on the collected surrounding environment information to form road environment information, the roadside communication module is used for sending the road environment information to the target vehicle, the target vehicle comprises a driving behavior decision module, and the driving behavior decision module is used for carrying out path planning according to the road environment information and carrying out automatic driving according to a path planning result. Therefore,a common vehicle on a road can realize automatic driving by interacting with the intelligent roadside equipment, the whole vehicle cost of configuring a sensing system on the vehicle is effectively reduced, and the cost of an intelligent traffic system is effectively reduced.

The invention provides a vehicle interval measurement method based on visible-light communication. Vehicle interval measurement is a basic function needed in an intelligent transportation system. The method adopts the visible-light communication and an image processing method to measure interval between vehicles. A pair of LED tail lights of a front vehicle transmits a modulation optical signal comprising an identity mark, the width of a vehicle body, the interval between the tail lights and other information backwards; a back vehicle utilizes an area-array photoelectric sensor to acquire an image of the front vehicle and receives the optical signal transmitted by the front vehicle; and the interval, relative velocity and relative position between two vehicles are calculated according to extracted communication information and the positions of two vehicle lights in the image.

The invention discloses a traffic accident automatic identification processing method and system based on videos. The traffic accident automatic identification processing method and system based on the videos comprises the steps of respectively setting up three-dimensional feature libraries of different vehicle types, obtaining road video image sequences, carrying out foreground vehicle separation based on background modeling, carrying out static target judgment based on target centroid displacement, recognizing the vehicle types based on a vehicle outer contour recognition algorithm of three-dimensional modeling, judging whether a traffic accident occurs or not according to whether contour deformation occurs or not, extracting improved SIFT feature points of the vehicles based on an improved SIFT feature recognition algorithm of vehicles of the three-dimensional modeling, and judging whether a traffic accident occurs or not according to comparison results of the improved SIFT feature points. The traffic accident automatic identification processing method and system based on the videos judges whether vehicles on a current road are driven safely or not by analyzing images collected by a camera, collects information of a traffic accident scene in first time of a traffic accident, and transfers the information to a commanding monitoring centre. Workers can effectively and timely work by watching the videos, and the traffic accident automatic identification processing method and system based on the videos plays a huge role in perfecting a whole intelligent traffic system.

The invention discloses an intelligent traffic system based on light emitting diode (LED) visible light communication, and belongs to the field of intelligent traffic systems. The intelligent traffic system comprises LED traffic lamps, a light emitter and a light receiver, wherein the light receiver and the light emitter are arranged on one vehicle; the light receiver on a back vehicle receives a signal sent by the light emitter on a front vehicle; signals sent by the LED traffic lamps comprise a road condition and traffic lamp conditions; the signal sent by the light emitter comprises a distance between the front vehicle and the rear vehicle and a warning signal; and the light receiver receives the signals sent by the LED traffic lamps and the light emitter. Due to the method, a visible light intelligent traffic network is formed, so that road condition information, the distance between the front vehicle and the rear vehicle, the warning signal and the traffic lamp conditions which are sent by the LED traffic lamps can be received immediately; and therefore, the traffic safety is guaranteed, and the probability of traffic accidents is reduced.

The invention provides a control method for managing parking spaces in an intelligent traffic system, which comprises the following steps that: a. whether the parking spaces to be used need to be reserved is judged; and b. if the parking spaces to be used do not need to be reserved, the parking spaces to be used can be used is determined. The invention also provides a control device for managing the parking spaces in the intelligent traffic system. The invention also provides an auxiliary control device for managing the parking spaces in a third party system which is associated with the intelligent traffic system. Optimally, the invention is particularly applicable in the parking space management of various residential communities, can effectively use the parking spaces, so as to bring great convenience for community owners who fixedly use special parking spaces and do not have fixed parking spaces and car owners of external vehicles.

The invention discloses an intersection centralized scheduling method for a multiple-unmanned-vehicle formation. For aiming at a cooperative intelligent traffic system in which unmanned vehicles are used as a mobile service carrier, the method is characterized in that centralized scheduling on the multiple-unmanned-vehicle formation is performed based on vehicle-to-infrastructure communication (V2I); and the disposition in a scheduling computer of each intersection is performed. According to the method, before reaching the intersection by each unmanned vehicle, reserving information for passing the intersection must be performed to the scheduling computer through an on-vehicle wireless network. The scheduling computer utilizes a principle that a high-weight lane has higher priority, thereby performing multiple-vehicle authorization scheduling on the unmanned vehicles in each lane. According to the intersection centralized scheduling method, passing scheduling efficiency of the unmanned vehicle is further improved in a formation scheduling manner, and particularly passing efficiency of the unmanned vehicle with high priority is improved as possible, thereby effectively supporting design of a service-oriented intelligent traffic system, and similar multiple-intelligent-mobile-robot systems for intelligent warehousing and dispensing, etc.

The invention discloses an intelligent traffic system and a monitoring control method thereof, belonging to the technical fields of traffic system optimization and monitoring control. In the invention, the intelligent traffic system is divided into n Zigbee network modules with the same structure, every Zigbee network module comprises m fixed nodes with the same hardware structure, every platform and every intersection are respectively provided with a fixed node, and every bus is provided with a vehicular moving node. The method adopts the technical scheme that a center node is established in every Zigbee network module to manage the Zigbee network; the vehicular moving nodes collect the running information of a vehicle and transmit the running information to roadside fixed nodes in time; and the roadside fixed nodes quickly transmit the information to backward direction intersection fixed nodes and display the situation information of the running road sections of a bus on an intersection electronic display screen. The invention has good modularization, interference resistance, low cost, good real-time property, distributing type regulation and control and high positioning precision of the vehicle.

The invention proposes a traffic flow prediction method based on firefly algorithm and RBF neural network. The method comprises: performing normalization to the sample data so that the input data and output data are on the same order of magnitude; initializing the firefly algorithm parameters; utilizing the random method to initialize the firefly populations and encoding each individual in the populations; using the firefly algorithm to train the RBF neural network to obtain the best individual in the populations; decoding the best individual in the populations to obtain the trained RBF neural network; and utilizing the trained RBF neural network to predict the traffic flow data sample. Compared with the traditional traffic flow prediction method, the method of the invention makes full use of the advantages of the firefly algorithm in the RBF neural network training so that the RBF network possesses a more accurate prediction capability, achieves even faster training efficiency and better generalization capability. The invention belongs to the traffic transportation information engineering technology field and can be used for the predictions of road traffic flows in an intelligent traffic system.

The invention discloses a vehicle type identification method and system. The method comprises a process of classifier generation by machine training and a process of determination of a to-be-measured picture. During the process of classifier generation, an image range needed in a picture of a training set is determined based on a licence plate; the determined image range is divided into several areas; feature information in all areas is selected; all feature information in respective selected areas are inputted into a machine training unit to generate classifiers corresponding to all areas one by one; single-area determination is carried out on a to-be-measured picture by the generated classifiers; and according to the single-area determination result, a vehicle type identification result is obtained by multi-area confidence coefficient fusion determination. With the method and system, the precision of vehicle type identification is enhanced effectively and detailed information like a vehicle manufacture can be identified. The method and system can be applied to the intelligent traffic system especially and the strong evidence can be provided for dealing with a traffic accident.

The invention relates to a hybrid electric vehicle energy management method based on traffic information. The method comprises a traffic information data acquisition step, a driving condition information prediction step and a required power calculation and distribution step. Traffic information obtained by an intelligent traffic system is used in energy management of a hybrid electric vehicle, excellent distribution of power between different power sources is achieved, and fuel economy and tail gas emission performance of the vehicle are improved. Hybrid electric vehicle energy optimization control is carried out by adopting a layered structure design, vehicle demand power is more efficiently calculated, and excellent control is realized; future driving condition information of the vehicleis predicted by using a Markov chain algorithm based on a network connection environment so as to obtain the optimal required power of the vehicle; and a lower-layer controller based on a global dynamic programming algorithm is adopted to control a state of charge SOC and a state of energy SOE of a power battery within a preset reasonable range, and optimal control of vehicle energy management iscarried out.

The invention discloses an intelligent transportation system based on a networked communication technology. The intelligent transportation system comprises a traffic signal light, a traffic signal light controller, a camera system, a regional traffic control center, a cloud platform, a portable networkable device and a vehicle-mounted networked communication device. According to the intelligent transportation system based on the networked communication technology and a control method thereof, the best travel route can be selected, so that a traffic congestion road section is avoided; and a reasonable vehicle speed is selected to pass an intersection to avoid the red light so as to shorten the time for waiting for the red light and the time of slow travelling during traffic jams, and the fuel consumption is reduced. The intelligent transportation system has small manual intervention workloads and low costs in the case of real-time traffic flexibility.

The invention provides a traffic jam analysis method and device, the method can be applied to an intelligent traffic or intelligent transport system (ITS), and the traffic jam analysis method can comprise the following steps: obtaining a first road section with jam in a traffic network and a first time period with jam in the first road section; determining an identity label of a vehicle running onthe first road section in a first time period; acquiring travel features of the vehicle in a first area in N statistical time periods; and on the basis of the travel characteristics of the vehicle, analyzing the congestion of the first road section in the first time period to obtain a jam analysis result. By adopting the traffic jam analysis method provided by the invention, refined analysis of traffic jam can be realized.

An aftermarket vehicle communication device engageable to a vehicle for providing location information associated with the vehicle to a V2X data stream. The device includes a housing configured to be detachably engageable to the vehicle. A GPS circuit is coupled to the housing and is disposable in communication with a GPS system to receive a GPS signal therefrom, with the received GPS signal being representative of a location of the vehicle when the housing is engaged to the vehicle. An antenna circuit is also coupled to the housing and is in communication with the GPS circuit. The antenna circuit is configured to receive the GPS signal from the GPS circuit and communicate the GPS signal to the V2X data stream.

The invention discloses a PHEV adaptive optimization energy management control method based on driving condition prediction, and the method comprises the steps: obtaining future path information through an intelligent traffic system and a vehicle-mounted navigation system, and generating an energy consumption equivalent prediction condition of a future path; establishing a reference ECMS control model, and searching for an optimal ECMS equivalent factor lambda opt and a reference SOCref by taking the energy consumption equivalent prediction working condition as input and taking the lowest oilconsumption as an optimization target; on the basis of the optimal equivalent factor lambda opt and a reference SOCref, correcting the optimal equivalent factor lambda opt according to the actual SOCand the reference SOCref under the actual driving working condition to form a self-adaptive ECMS control model, and calculating the engine torque and the motor torque with optimal oil consumption; andtransmitting the target torques of the engine and the motor and a switching instruction to a bottom layer controller, and distributing the power of the whole vehicle to realize PHEV energy managementand control.

The invention belongs to the technical field of air-ground integrated Internet of Vehicles communication, and discloses an air-ground integrated Internet of Vehicles relay selection method based on state transition probability. The method comprises the steps of constructing an air-ground integrated Internet of Vehicles model composed of V vehicle nodes and U unmanned aerial vehicle nodes; constructing an information transmission mechanism between the mobile nodes based on the air-ground integrated Internet of Vehicles model; constructing a state transition probability between the mobile nodesbased on the information transmission mechanism between the mobile nodes; based on the state transition probability between the mobile nodes, constructing an information identification method based ona multiple-input-multiple-output technology; and constructing a relay selection method based on the state transition probability on the basis of the information transmission mechanism between the mobile nodes, the state transition probability and the information identification method. The method can be applied to an urban intelligent traffic system, the relation among vehicles, unmanned aerial vehicles and users is enhanced, and a real-time, accurate and efficient comprehensive transportation and information transmission system is built.

The invention discloses an intelligent transportation system for relieving congestion, and an operation method thereof. The intelligent transportation system for relieving congestion comprises a datamanagement module, a vehicle monitoring module, a weather monitoring module, a variable lane management module, an electronic speed limit display screen and a power supply module, wherein the vehiclemonitoring module is laid on a photovoltaic road surface to monitor the vehicle driving speed and the road traffic flow information, thus being able to effectively monitor whether a vehicle is speeding and identify the information of an illegal vehicle through a radio frequency identification technology so as to effectively supervise the traffic order; the variable lane management module is used to adaptively change left turn, right turn or going straight of the vehicle according to the congestion condition of an intersection; the weather monitoring module is used to monitor the weather condition in real time; and when bad weather appears, such as rain, snow, fog and haze, the data management module correspondingly adjusts the speed limit indicator and displays through the electronic speedlimit display screen to prevent the situation that a driver drives the vehicle overspeed when he or she cannot see a speed limit board because of poor visibility caused by bad weather, thus reducingoccurrence of traffic accidents.

The invention belongs to the technical field of ITS intelligent traffic systems, and particularly relates to an adaptive full-chain urban area network signal control optimization method. Traffic flow parameters are collected by utilizing a machine vision technology, traffic flow prediction is carried out based on a pre-trained traffic flow prediction algorithm by using obtained data, a microscopic traffic simulation model is constructed according to predicted traffic flow data, an original signal timing scheme and traffic network basic data, and a network-level signal optimization model is constructed. Active optimization is carried out on the network-level signal optimization model by adopting a Bayesian optimization algorithm so as to obtain an optimal signal timing scheme of the target area network. The method has good integration, an inner and outer circulation feedback closed loop is formed, an inner and outer circulation feedback mechanism can achieve interaction of a network signal optimization model and a microscopic traffic simulation model, it can be guaranteed that an optimization result scheme adapts to dynamic changes of the external environment, and then instantaneous dynamic optimization and long-term steady-state optimization are achieved.

The invention discloses a privacy protection model aggregation system and method based on federated learning in the Internet of Vehicles. The system comprises a TA (Trusted Authority), a CS (Cloud Server), a Fog Node FN (Fog Node) and a V (Vehicle). The method comprises the four steps of system initialization, vehicle data collection, training to generate a local model and aggregation to generate a global model. According to the invention, under the condition that the privacy information of the vehicle is not leaked, the cloud server can effectively generate the global model of the Internet of Vehicles, Meanwhile, the privacy of the local model and the global model in the aggregation process is ensured. The method can promote stable operation of the intelligent traffic system and has good practicability.

The invention discloses a road traffic condition detection method based on vehicle-mounted camera shooting, and the method fully considers the dynamics and uncertainty of road traffic through employing a vehicle detection theory based on deep learning. Traffic condition estimation assists the vehicle in dynamically describing the current traffic condition, so that the traffic efficiency in intelligent traffic is improved. The invention provides the traffic condition detection method based on vehicle-mounted camera shooting in allusion to an intelligent traffic system so as to assist the vehicle in estimating the traffic condition through the traffic information collected by the vehicle-mounted camera shooting equipment. By integrating with edge computing and V2X networks, additional computing and communication resources may be obtained to accurately estimate traffic conditions at which the vehicle arrives. The invention provides the road traffic condition detection method based on vehicle-mounted camera shooting to count the number of vehicles running on different lanes. And finally, the fine-grained estimation is carried out on the road traffic condition.

The invention discloses a method for predicting the travel time of a vehicle passing through an intersection based on a neural network, belongs to the field of intelligent traffic systems, and mainly aims to accurately predict the time of the vehicle passing through the intersection under the condition that the vehicle is jammed at the intersection and under the influence of traffic lights. The method comprises the following steps of: (1) dividing urban roads; (2) performing intersection data collection; (3) performing data processing; and (4) inputting processed data to a BP neural network to carry out iterative learning of the model, and obtaining a relationship between traffic parameters and travel time, thereby achieving the purpose of predicting time. According to the method, the complex condition of the intersection is fully considered, the advantages of the neural network model are utilized, the travel time of the vehicle passing through the intersection is predicted, and reliable information can be provided for subsequent driving route selection of a driver.

The embodiment of the invention discloses an intelligent pedestrian violation behavior management method and a related product, the intelligent pedestrian violation behavior management method is applied to an intelligent traffic system, the intelligent traffic system is connected with at least one camera, the method comprises the steps: acquiring a pedestrian image through the at least one camera,wherein the pedestrian image comprises at least one person; determining a target person in the at least one person according to the pedestrian image, wherein the target person is a violation person;tracking the target person to obtain a video image of the target person; inputting the video image into a preset neural network model to obtain a target face template corresponding to the target person, and obtaining identity information corresponding to the target face template, the preset neural network model being obtained by training a large number of face template images; and sending alarm information to the target person according to the identity information. By adopting the embodiment of the invention, the pedestrian violation behavior management efficiency can be improved.

The invention provides an urban road network dynamic division method and device, computer equipment and a storage medium. According to the method, potential traffic state modes and multi-dimensional change characteristics in road network traffic state data are deeply mined, the traffic space-time correlation and the connectivity of the space structure of the road network are introduced, and dynamic division is carried out on the road network, therefore, each sub-road network has similar spatio-temporal evolution characteristics, the difference of traffic modes among the different sub-road networks is maximized, scientific division of the large-scale road network can be realized, and the fine management level of the road network is improved. The method can be used for intelligent traffic control of the large-scale road network, and adopts real-time traffic guidance and control strategies for the different sub-road networks, thereby realizing macroscopic regulation and control of traffic flow of the whole road network, and providing basic technical support for an intelligent traffic system driven by data.

The invention relates to an intelligent park management system. As an important composition of an intelligent traffic system, the system is an application of ITS in the field of parking. Based on accurate and real-time stall detection and a variable and multi-stage information issuing screen as a carrier, the system provides information such as specific positions of the park and current stall real-time data to a traveler to guide a driver to park reasonably, and meanwhile, analyzes real-time information data formed by gathering dispersed information of stalls and volume of the park by means ofdynamic information markers so as to assist a management department for management decision. By collecting stall information of the park and the temporary stalls of a pavement, the stall informationis updated in real time. The updated data is sent to the information processing center by means of a self-assembled network, an information processing terminal carries out treatment, statistics, analysis and the like on the collected parking information, a GIS technology is introduced to an urban level park system; data edition and inquiry of blocks, parks and other geographic information are achieved by means of an electronic map, so that the layered management of patterned traffic data is achieved.