36 results about "Intelligent vehicle technologies" patented technology

The invention discloses an intelligent vehicle laser radar maneuvering multi-target tracking method based on an IMM-MHT algorithm, and the intelligent vehicle laser radar maneuvering multi-target tracking method belongs to the technical field of intelligent vehicles. The intelligent vehicle laser radar maneuvering multi-target tracking method is implemented by generating a tracking gate firstly, receiving a measurement value and performing detection and identification on the measurement value, making a joint hypothesis of a flight path and measurement, simplifying and managing the hypothesis, performing detection and identification on the flight path, and finally filtering and predicting the flight path. The intelligent vehicle laser radar maneuvering multi-target tracking method comprises the steps of: step (1), forming a flight path tracking gate; step (2), receiving a t-moment measurement value and identifying the t-moment measurement value by adopting an image processing method; step (3), generating an association hypothesis of measurement and a flight path in the tracking gate; step (4), managing the hypothesis; step (5), calculating information such as speed and angular speed of the flight path, and identifying the flight path; step (6), and filtering and predicting the flight path by adopting an interactive multi-model algorithm. Through integrating the interactive multi-model algorithm and a multi-hypothesis tracking algorithm, the intelligent vehicle laser radar maneuvering multi-target tracking method can better deal with the intelligent vehicle maneuvering multi-target tracking problem in a complex environment.

The invention provides an expressway dangerous road section and construction region early-warning control system and an expressway dangerous road section and construction region early-warning controlmethod, which belong to the technical field of intelligent vehicles. The an expressway dangerous road section and construction region early-warning control system comprises a data collection module, anetwork communication module, a data calculation processing module, a scene processing module, and an early-warning publishing and feedback module. The an expressway dangerous road section and construction region early-warning control method comprises the steps of: a data acquisition step, which is implemented by loading data by means of a local roadside intelligent control station; a network communication step used for V2I (Vehicle to Infrastructure) communication of the Internet of Vehicles; a data calculating and processing step used for calculating and processing received data and transmitting a data processing result to the scene processing module; a scene processing step, which is implemented by judging a specific type of a road section, and judging a distance reminder between a vehicle and the dangerous road section as well as a construction region; and an early-warning step, which is implemented by performing auxiliary operation prompt or early warning according to the type ofthe road section and the distance between the vehicle and the dangerous road section as well as the construction region. The expressway dangerous road section and construction region early-warning control method plays a positive role in reducing the accident rate of dangerous road sections and construction regions of an expressway, and improves the driving safety.

The invention discloses a destination identification method for a plug-in type hybrid vehicle, comprising the steps of obtaining vehicle running state data; and identifying a destination based on a variable-order Markov model. When a destination is not set, the method effectively abstracts the driving habits and rules of a driver according to GPS historic traveling track data, forecasts a destination greater than a confidence coefficient threshold and a path node sequence to the destination, and further estimates the whole vehicle energy consumption of each path node; the method lays the foundation for energy management strategy global optimization, is conductive to increasing automobile dynamic property and economical efficiency, and accords with the energy saving and environmental protection themes of current automobile development. The method uses a PMM algorithm to reduce the space complexity and calculated quantity of a prediction model and a zero frequency problem, utilizes the variable-order Markov model to match automobile historic and current multi-source data, can more flexibly and more accurately predict a destination node and journey sequence, and is of great significance for the intelligent vehicle technology.

The embodiment of the invention relates to the technical field of intelligent vehicles, and discloses an account switching method of a vehicle-mounted system, a vehicle-mounted system and a vehicle. The method comprises the following steps: when the vehicle-mounted system is in a non-networking state and a pressure sensing signal of a main driving position is detected, triggering a vehicle-mountedimage sensing device to obtain a face image of a user; when the human face feature information in the human face image is matched with at least one piece of locally stored historical human face feature information, locally querying a user code matched with the historical face feature information; obtaining a historical login state corresponding to the user code, if the historical login state is valid, switching the current login account number of the vehicle-mounted system to the account number corresponding to the user code, so that when the vehicle-mounted system is in the non-networking state, the vehicle-mounted system can be quickly switched to the personalized setting information corresponding to the account numbers of different users to cater to the driving habits of different users, and the user experience is improved.

The invention discloses a pedestrian detection method based on wavelet fractal characteristic, which relates to the technology of intelligent vehicles in an intelligent traffic system. The pedestrian detection method comprises the following steps: (1) reading a training sample set and standardizing all sample images to the pixel size of 48*96; (2) carrying three times of two-dimensional wavelet transformation on the sample images, and getting six wavelet sub-graphs in the second layer and the third layer; (3) getting absolute values of the wavelet sub-graphs obtained in the step (2), and carrying out stretching and scaling so that the numeric area is uniformly mapped to 0 to 255; (4) respectively getting fractal dimension vectors of the wavelet sub-graphs treated in the step (3); (5) standardizing the fractal vectors corresponding to each sub-graph obtained in the step (4); (6) combining the fractal vectors standardized in the step (5), and obtaining the wavelet fractal characteristic vector of 6*(n-1) dimension; and (7) using the wavelet fractal characteristic obtained in the step (6) for training a soft-supporter vector machine, and using the obtained discriminant function for realizing pedestrian detection. The invention has the characteristics of concise characteristic expression form, strong characteristic distinguishing capability and higher pedestrian detection efficiency.

Embodiments of the present invention provide a method for locating a vehicle, a server, and a vehicle, which belong to the technical field of intelligent vehicles, and solve the problem of locating the vehicle when the vehicle cannot communicate with the server in the prior art. The method is applied to a server, and the method includes: receiving a notification message from a vehicle, the notification message including identification information of other vehicles and a signal strength value, the signal strength value being received by the vehicle and sent by the other vehicle The strength value of the broadcast signal; according to the signal strength value, determine the position of the vehicle that sends out the broadcast signal. The embodiment of the present invention is applicable to the positioning process of the vehicle.

The invention belongs to the technical field of intelligent vehicles. The invention provides a positioning correction method, device and system, and the method comprises the steps: correcting the boundary line data, converted into a vehicle body coordinate system, in a high-precision map through employing the point cloud data corresponding to an obstacle in front of a vehicle, obtaining the precise boundary line data of the high-precision map, and meeting the precise navigation demands of an intelligent vehicle.

The invention discloses a BiLSTM-based weekly vehicle lane change intention prediction method, and relates to the technical field of intelligent vehicles. The method comprises the following steps: 1) an offline training process of a lane change intention prediction model: constructing a training database through collection and processing of a large-scale real driving scene; and training a lane changing intention prediction model; and 2) online real-time prediction of the lane change intention prediction model: after real-time data acquisition and data preprocessing of the own vehicle, performing online real-time prediction by using the trained lane change intention prediction model to predict the current lane change intention of the surrounding vehicles. Factors influencing lane changing of surrounding vehicles are comprehensively considered, the Inception-ResNet-v2 network is utilized to extract frame level features of vehicle videos, the vehicle state and the frame level features are fused, the BiLSTM network prediction capability is improved, the detection precision and efficiency are further improved, the lane changing intention of the surrounding vehicles is effectively predicted, and a great role is played in improving the safety performance of the unmanned vehicle.

The invention relates to the technical field of intelligent vehicles, and provides a vehicle function service recommendation method and device. The method comprises the following steps: detecting vehicle state data; and according to the vehicle state data, carrying out vehicle function service recommendation based on a vehicle recommendation database, wherein the vehicle recommendation database comprises a corresponding relationship between the vehicle state data and vehicle function services of personal habits of a user. According to the vehicle function service recommendation method and device, the time cost of thinking and using of the user can be reduced, and meanwhile the driving safety is greatly improved.

The invention relates to the technical field of intelligent vehicles, in particular to a method and device for processing data in a vehicle, the method is applied to an automobile data recorder, and the method comprises the steps of detecting an abnormal driving event used for representing that the driving state of the vehicle is abnormal; when detecting that the abnormal driving event exists, acquiring event information corresponding to the abnormal driving event and a driving record image corresponding to the abnormal driving event; establishing a corresponding relationship between the eventinformation and the driving record image, and generating and storing a video index file; and receiving a search operation performed by the user based on the event information and/or the name of the driving record image, obtaining a target driving record image corresponding to the search operation based on the video index file, and feeding back the target driving record image to the user. According to the invention, a user can quickly and conveniently search the driving record image corresponding to the abnormal driving event.

The invention provides a highway meteorological environment forecasting and early warning control system and method based on the Internet of Vehicles, and belongs to the technical field of intelligentvehicles. The method comprises the following steps: performing communication with a local roadside intelligent control base station through a network communication module, obtaining multi-source traffic data and meteorological data, and performing encoding processing on the multi-source traffic data and the meteorological data to obtain an Internet of Vehicles BSM data set; detecting highway vehicle risk event probability caused by a meteorological environment in the Internet of Vehicles BSM data set in real time on the basis of a discrimination algorithm of traffic meteorological informationand a road surface safety level, performing collision prediction on the Internet of Vehicles BSM data set on the basis of a rough set and an information entropy measurement method, and outputting risk prediction information; and performing risk avoiding warning or auxiliary operation processing according to the risk prediction information, and updating a database in real time. The system meets the functional requirements of real-time early warning, and can be widely applied to anti-collision early warning and safe driving auxiliary systems of various road meteorological environments.

The embodiment of the invention relates to an intelligent vehicle technology, and particularly provides a control method of a vehicle-mounted display device. The control method comprises the following steps: acquiring first sensing information, such as in-vehicle image information acquired through a camera in a cabin; acquiring second sensing information, such as pressure sensor information of a co-driver seat, wherein the first sensing information and the second sensing information are respectively used for determining first co-driver riding information and second co-driver riding information; and when the first co-driver riding information indicates that the passenger exists in the co-driver seat and the second co-driver riding information indicates that the passenger exists in the co-driver seat, sending a split-screen display instruction to enable the vehicle-mounted display device to carry out split-screen display. Compared with the scheme of determining whether the co-driver has a passenger or not through single sensing information to decide whether to split the screen or not, the control method and control device can perform screen splitting more appropriately.

The invention relates to the technical field of intelligent vehicles, in particular to a vehicle-mounted equipment interconnection method, system and device. The method comprises the steps of: performing signing in a cloud server to enable the cloud server to update the working state of the vehicle-mounted equipment into an online state, and obtaining authorization information returned by the cloud server and a server address of a transit server; sending the authorization information to the transit server based on the server address, so that the vehicle-mounted equipment is authenticated in the transit server; and after the authentication succeeds, establishing a communication connection with the transit server so as to communicate with other vehicle-mounted equipment through the transit server. According to the invention, interconnection among a plurality of pieces of vehicle-mounted equipment is realized, so that one piece of vehicle-mounted equipment can control another piece of vehicle-mounted equipment.

The invention relates to a rear vehicle reminding device and method used during work of an automatic emergency braking system. The rear vehicle reminding device is characterized by comprising a high side driving circuit, a braking switch and a braking lamp/AEB work warning lamp, wherein the high side driving circuit is a P-channel MOS pipe; a grid electrode of the high side driving circuit is connected with the output end of the automatic emergency braking system; a drain electrode of the high side driving circuit is connected with a positive electrode of a power source, and a negative electrode of the power source is grounded; a source electrode of the high side driving circuit is in parallel connection with one ends of the braking switch and the switching lamp/AEB work warning lamp, theother end of the braking switch is connected with the power source, the other end of the braking lamp/AEB work warning lamp is grounded, and the high side driving circuit is used for controlling the braking lamp/AEB work warning lamp to be turned on or turned off through the braking switch according to primary early-warning signals output by the automatic emergency braking system. The rear vehiclereminding device and method can be widely applied to the technical field of intelligent vehicles.

The invention belongs to the technical field of intelligent vehicles, and in particular relates to an intelligent traffic rollator, which includes a vehicle body, a chassis, a seat and an automatic armrest, a signal receiver installed at the front end of the vehicle body is used to identify traffic light signals, and a control module installed inside the vehicle body To control the operation of the intelligent transportation rollator, the laser tracking probe installed under the front of the chassis performs path identification, the automatic handrail installed in the chute at the front of the car body provides handrails for passengers, and the ultrasonic obstacle avoidance probe installed at the front of the car body identifies obstacles. The loudspeaker installed at the back end plays voice reminders, realizing the function of helping people with disabilities pass the intersection in time during the green light time, alleviating traffic congestion at the intersection, and improving the safety of people with disabilities passing through the intersection.

The invention discloses a scene configuration library generation method and device as well as a safety detection method and device, belongs to the technical field of vehicle safety, and can be appliedto the technical field of Internet of Vehicles or intelligent vehicles. According to a specific embodiment, the method comprises the steps that: a scene configuration preset instruction is obtained,wherein the scene configuration preset instruction comprises information of a plurality of security scenes and at least one detection item used for being triggered in each security scene; a scene configuration library is generated, wherein the scene configuration library comprises a scene configuration set of each safety scene, wherein the scene configuration set of the safety scenes comprises detection items corresponding to the safety scenes. According to the technical scheme provided by the embodiment of the invention, different detection items can be set or triggered for different safety scenes, so that the safety of a vehicle is improved.

The invention relates to the technical field of intelligent vehicles, in particular to a man-machine interaction system for a vehicle, which comprises a data acquisition unit for acquiring crowd type information of passengers in the vehicle and acquiring image data and/or sound data of the passengers and/or other passengers in the vehicle according to the crowd type information; the data processing unit is used for analyzing and processing the image data and/or the sound data acquired by the data acquisition unit according to the crowd category information and converting the image data and/or the sound data into target data; and the data output unit is used for outputting the converted target data to the passengers and/or other passengers in the vehicle according to the crowd category information. The invention also relates to a human-computer interaction method, a computer program product and a corresponding vehicle. According to the embodiment of the invention, specific disabled people, especially hearing impaired people, visual impaired people and speech impaired people can be assisted to realize the necessary information interaction possibility in the vehicle.

The invention provides a log file generation method and device, and relates to the technical field of intelligent vehicles, and the method comprises the steps: receiving a plurality of parameter values outputted by a target module, obtaining the name of the target module and the time when the plurality of parameter values are received, and compressing at least one of the name of the target module, the time when the plurality of parameter values are received and the plurality of parameter values to generate compressed log data, and generating a log file according to the compressed log data. According to the method and the device, the size of the log data is reduced by compressing at least one of the name of the target module in the log data, the time of receiving the multiple parameter values and the multiple parameter values, so that the log file occupying less storage space is generated, the speed of opening return visit of the log file is increased, and the storage amount of the log file is increased.