115 results about "Vehicle category" patented technology

Systems and methods are disclosed for computing various determinations at one or more mobile devices and / or central machines. In part, such determinations are computed based on analysis of one or more inputs originating at one or more sensors of one or more devices. Such determinations include determining an in-vehicle role, an in-vehicle location, a handheld state, and a vehicle class. Various transformations, modifications, and outputs can result from such determinations. Also disclosed are systems and methods for restricting operation of a mobile device, including restrictions that impede operation by a driver moreso than operation by a passenger. Also disclosed are systems and methods for orienting a coordinate system of a mobile device.

A highly energy efficient automobile that provides payload, safety and performance capacities similar to a comparable vehicle of a given vehicle class. The current invention is ideal for short to medium range urban and suburban driving. The current invention incorporates components in a unique and novel way, in which these components combine to form a system that produces an automobile that reduces overall air pollution while encouraging the commercialization of alternative energy sources. The current invention features an lightweight, low rolling resistance, digitally controlled and direct-drive electric propulsion system. A lightweight spaceframe with a suspension system provides a structure for mounting a low-aerodynamic-drag body system and other components. An intelligent power and thermal management system coupled with a removable auxiliary power module supplies the electrical energy required. While the preferred embodiment is substantially a passenger vehicle, the current invention may be scaled to other land vehicles.

To ensure the toll collection of a vehicle carrying an in-vehicle unit without stopping the vehicle at an entrance toll gate or an exit toll gate, an entrance toll gate lane is equipped sequentially from the entrance with a vehicle class discriminator, an entrance vehicle number reader, a first antenna, a vehicle detector, a ticket issuer, a display unit, a vehicle detector, a second antenna and a start detector. The first antenna communicates with an in-vehicle unit of a coming vehicle to write the entrance toll gate data. The display unit is caused, when the communication succeeds, to permit the passage of the vehicle therethrough. When the communication fails, the display unit is caused to stop the vehicle, and the ticket issuer issues the ticket. The second antenna writes the vehicle class data and the registered number data, as detected by the vehicle class discriminator and the vehicle number reader, in an in-vehicle unit. Thus, the existing facilities can be used as they are.

Exemplary embodiments provide systems, methods, and products that that offer, characterize, price, and / or sell vehicle rental insurance coverage in terms of the type of vehicle, class of vehicle, or exact vehicle that the customer will obtain as a rental, instead of, or in addition to, a dollar limit per day and / or a dollar limit per incident. Various embodiments allow insurers to offer and calculate a premium price for, and / or allow consumers to choose and pay for, coverage specified according to the type of vehicle, class of vehicle, and / or exact vehicle desired as a rental replacement for an insured vehicle. Various embodiments also allow insurers to offer and calculate a premium price for, and allow consumers to choose and pay for, optional add-ons for the rental vehicle, such as a navigation system and / or a child safety seat.

The invention relates to a method and device with which a vehicle traveling through a radar cone is classified by means of length criteria. The length criteria are formed by the difference of the driven distance that the vehicle covers, during which it reflects the radar beam, and the passage distance of the vehicle through the radar cone, which gives a more or less precise measurement for the vehicle length according to the accuracy of the determined passage distance. For determining the passage distance, range values are derived from the radar signals.

The invention provides a vehicle type identification method. The method comprises steps that on the basis of a vehicle brand and a pattern, headstock image sample sets and tailstock image sample sets are classified to acquire multiple categories of multiple vehicle images; on the basis of the multiple categories of multiple vehicle images, a depth convolution neural network is at least trained; at least characteristic codes of multiple vehicle images of various categories are respectively extracted through utilizing the trained depth convolution neural network, and a characteristic code / type / vehicle image relationship database is constructed; the trained depth convolution neural network is utilized to extract a characteristic code of to-be-identified vehicle images, the type information of a vehicle is determined according to the characteristic code / type / vehicle image relationship database, and the vehicle brand and the pattern of the vehicle are identified. The invention further provides a vehicle type identification system. The method and the system can adapt to various environments, accuracy of identifying the vehicle category information is improved, and the method and the system have wide application prospects.

The invention discloses an ETC lane system compatible with weight-calculating charge and a realizing method thereof. The system comprises a non-weight-calculating charge subsystem and a weight-calculating charge subsystem, wherein the non-weight-calculating charge subsystem is used for communicating with an on-vehicle electronic label, identifying vehicle types, judging whether relative vehicle information is valid or not and permitting weight-calculating charge vehicles with valid relative vehicle information to pass or automatically reading, writing, charging and permitting non-weight-calculating charge vehicles with the valid relative vehicle information to pass; the weight-calculating charge subsystem is used for communicating with the on-vehicle electronic label, identifying the vehicle types, weighting the weight-calculating charge vehicles and automatically reading, writing, charging and permitting the weight-calculating charge vehicles to pass or permitting the non-weight-calculating charge vehicles to pass. The invention can respectively carry out the automatic charge transactions of the weight-calculating charge vehicles and the non-weight-calculating charge vehicles on the same ETC lane, controls the passage operation and improves the rapid passage capability of the ETC lane.

The invention discloses an artificial intelligence display screen advertisement dynamic delivery system and method. According to the invention, by acquiring images of crowds and vehicles in each advertisement placing region through a multi-point image, obtaining face and vehicle big data and carrying out AI big data operation so as to identifying the age and gender of the face and the vehicle typeinformation and accurately analyze the classification of the target group of each advertisement putting area; according to the crowd characteristics and vehicle classification of each advertisement placing region, automatically matching advertisement classification corresponding to the target crowd; and displaying the automatically matched advertisement through a display screen in each advertisement placing region, thereby achieving the precise and dynamic putting of the advertisements, greatly improving the advertisement putting effect, and achieving the maximum utilization of the advertisement resources. In addition, the image face data collected by the advertisement dynamic putting system can also share a camera image collection system with an external conforming requirement, full sharing is achieved, and the cost of repeated construction is reduced by using existing camera image recognition data in the society.

The invention provides a vehicle category identification method based on multi-channel video information fusion of license plate information and vehicle profiles. The method comprises the following steps of 1), obtaining video images by adopting a plurality of cameras mounted in different positions, and obtaining a vehicle side image and a vehicle head or tail image; 2), detecting, tracking and separating the vehicle images; 3), generating classification results by adopting corresponding methods for the images acquired by the cameras mounted in the different positions; and 4), comparing detection results of different methods, and adopting a simple voting information fusion mechanism. According to the vehicle category identification method based on the multi-channel video information fusion of the license plate information and the vehicle profiles, provided by the invention, the accuracy is effectively improved.

The invention discloses an automatic auditing system for illegal bus lane occupation based on deep learning, and the method comprises the following steps: employing a bayonet camera to carry out the photographing and evidence collection of a target vehicle illegally occupying a bus lane, the evidence collection information comprising n frames (n>=1) of evidence graphs and the license plate numberinformation of the target vehicle; utilizing a yolo-V2 vehicle detection model to detect all vehicles in n frames of images, adopting a caffe-ssd model to detect a license plate area of the all the detected vehicles, and identifying a license plate number by using an lstm + ctc model; comparing the license plate numbers with the edited distance of a given license plate, and applying GoogLenet Inception-V2 network based vehicle re-identification algorithm to respectively position the position of a target vehicle in the n frames of images; segmenting an image bus lane area by using a deeplab-V2segmentation algorithm, and judging whether a target vehicle occupies a bus lane by calculating the ratio of the intersection of the target vehicle detection frame and the bus lane area to the targetvehicle detection frame; and identifying the type of the target vehicle by applying a vehicle classification network based on ResNet18, and finally judging whether the target vehicle illegally occupies the bus lane according to the type information of the target vehicle and the condition of occupying the bus lane. According to the invention, the police is saved, the illegal auditing efficiency andaccuracy are improved, and the auditing fairness is ensured.

The invention relates to an automatic processing method and device of vehicle violation, computer equipment and a storage medium. By obtaining to-be-checked violation vehicle images and recognizing illegal types of target violation vehicles in the to-be-checked violation vehicle images, a vehicle type recognition model based on deep learning is adopted for recognizing the using types of the targetviolation vehicles, whether or not the using types of the target violation vehicles are matched with using types of vehicles which are not in charge in a traffic safety strategy is judged according to the illegal types, and thus whether or not the target violation vehicles violate laws is determined. In this way, intelligent violation checking of special vehicles is achieved, manual checking is not needed anymore, the checking efficiency is improved, and the problem that during manual checking, the justice and fairness of checking may be influenced due to checking fatigue and subjectivity ofpersonnel is solved.

The invention provides a method for identifying a vehicle type identification method, a device, and a computer readable storage medium. The vehicle type identification method comprises steps: obtaining vehicle type identification information of a corresponding vehicle in an image to be identified by constructing a vehicle type identification model and performing vehicle type identification on a zebra crossing area captured by a camera and an image to be identified around the zebra crossing area by using the vehicle type identification model, wherein the vehicle type identification informationincludes vehicle class information, vehicle coordinates, vehicle vertical pixels, and vehicle horizontal pixels; calculating the size and proportion of the corresponding vehicle in the image to be recognized according to the scale of the vehicle vertical pixel, the vehicle horizontal pixel and the zebra crossing in the image to be recognized; searching information of the first vehicle type according to the size and proportion from the website; converting the image to be identified into an HSV image and searching out second vehicle information corresponding to a hue value of the vehicle in theHSV image from the first vehicle type information. The method can effectively reduce the judgment range of the vehicle type and improve the accuracy of the vehicle type recognition.

The invention relates to a bridge vehicle wheel detection method based on a multilayer feature fusion neural network model. The method comprises the following steps of 1) constructing a deep learningneural network model based on multilayer feature fusion; 2) training the model by using the training sample data set; 3) carrying out image enhancement preprocessing operation on the to-be-detected image shot on the bridge; 4) inputting the preprocessed image into the model to obtain an output image with wheel vehicle category coordinate calibration; and 5) matching the detected wheels in the image with the corresponding vehicles by using an overlap rate measurement method. Compared with the prior art, the method has the advantages that the detection precision is improved, the real-time performance is enhanced, the probability of missed detection is reduced and the like, the wheel detection is realized while vehicle target detection is realized, and the vehicles on the same image are automatically matched with the wheels.

The invention provides a method for analog computation and detection of the road test fuel consumption of a vehicle in multiple working conditions. According to the method, the rolling resistance and the air resistance of each speed of the vehicle of a new type are calculated according to the rolling resistance coefficient equation and the air resistance coefficient equation of the type of the vehicle, the consumption torque and the acceleration resistance of an engine accessory are worked out, and then the output power, the torque and the rotating speed of an engine at each speed of the vehicle in the constant speed working condition and in the acceleration working condition can be obtained; the fuel consumption in the multiple working conditions is worked out according to the specific fuel consumption corresponding to the universal characteristic curve of the engine, the dynamic power fuel consumption is compensated for through calculation according to a high drive power within a vehicle speed section, the drive power is higher within a section with a quite low initial speed, so that the output power of the engine is in the stable state, the fuel consumption in the deceleration working condition is determined according to the relation between the engine rotating speed and the idling cut-off rotating speed, and the fuel consumption in the idling condition is worked out according to the idling fuel parameters of the engine; in this way, the fuel consumption or exhaust emission of road tests in the multiple working conditions is automatically worked out.

A central computing system is configured to monitor quotas for multiple different classifications of vehicles that park in a parking facility. License plate reading (LPR) cameras read the license information of each vehicle entering and exiting a parking facility. The vehicle images or identifications are communicated to the central computing system which updates its database and monitors each virtual lot in the parking facility according to quotas, prices and other parameters for each corresponding class of vehicles. Control gates can be provided at entrances and exits to the parking facility. A parking kiosk can be provided to the parking facility that is networked with the central computing system.

The invention relates to a ground moving vehicle target classification and recognition method and system based on a high-resolution distance image, and the method comprises the steps: carrying out the averaging and energy normalization of multiple collected continuous original HRRP echoes of a ground moving vehicle target; calculating the HRRP echo power spectrum features according to the HRRP echoes after averaging and energy normalization; calculating the distances between the HRRP echo power spectrum features and various types of preset power spectrum feature templates, and obtaining a plurality of distances; comparing the distances, and determining the class of the ground moving vehicle target according to a comparison result. The method calculates the distances between the HRRP echo power spectrum features and various types of preset power spectrum feature templates through a nearest neighbor classifier, recognizes the class information of the ground moving vehicle target through comparing the distances between the HRRP echo power spectrum features and various types of preset power spectrum feature templates, achieves the precise classification and recognition of the ground moving vehicles, and provides support for the classification and recognition of military moving vehicles on the ground.

The invention relates to a navigation path planning method which is characterized by comprising the following steps of: acquiring the class of the current vehicle by a system; acquiring the running path suitable for the vehicle by the system; and planning the running path of the vehicle according to the acquired path by the system. After the scheme of the invention is adopted, a navigation terminal comprises a vehicle class setting module, and a service system is adopted to carry out intelligent identification on the class of the vehicle, and reasonable navigation paths for different classes of vehicles can be planned out at different periods under different traffic limit policies to avoid the problem of penalty on the vehicle, caused by incorrect navigation path, and meanwhile, the working pressure of a traffic management department is also reduced. The invention is suitable for adopting a global position system (GPS) or a Big Dipper satellite navigation system or a GLONASS or GALILEO positioner.

The invention discloses an intelligent management method by using roadside relay for realizing safe vehicle driving. After RFID state parameters of surrounding driving vehicles are read through a roadside relay end, the parameters are transmitted to reading terminals of the surrounding driving vehicles; after the vehicle reading terminals acquire the RFID state parameters of other vehicles, driving state parameters of vehicle types, instant positions, driving directions and instant speeds are marked on a display terminal; and further according to the instant driving state parameters of the surrounding related vehicles, corresponding prompting or early warning is sent. The widely-used RFID technology is adopted, the cost is lower, the application is more convenient, and the method can be forced by the government to be promoted and popularized in a unified model; due to the wireless roadside relay technology mode, the surrounding related vehicle driving state parameters can be effectively acquired, and reliability and safety of the RFID application system can be ensured; sensing data link support is provided for the vehicle networking system, more intelligent driving and unmanned driving can be realized in the future, information acquisition and data processing support can be provided, and an important technical support value is provided.

To provide a vehicle approach notification control apparatus for an electric motorcycle, which can output notification sound for notifying a walker or the like of approach of an electric motorcycle with an appropriate sound volume. The vehicle approach notification control apparatus for an electric motorcycle includes a speaker for generating notification sound equivalent to engine sound of an engine driven motorcycle of a vehicle category that is the same as a vehicle category of the electric motorcycle in response to a motor speed of an electric motor or a vehicle speed. The vehicle approach notification control apparatus includes a pseudo engine sound volume storage device configured to store sound volume data of engine sound with respect to the entire running sound upon running of the engine driven vehicle, and a control unit for controlling the notification sound.

The invention relates to a power battery remaining life prediction method based on data driving. The method comprises the steps of obtaining pure electric vehicle driving data; preprocessing the driving data of the pure electric vehicle; performing feature extraction on the preprocessed data; constructing an algorithm model by using a fusion model of an LSTM model and BP-GM (1, N) according to related feature data obtained by feature extraction; and predicting the residual life of the power battery through the algorithm model. According to driving big data of an electric vehicle, battery health state information and a change rule thereof are fully mined, related characteristics such as historical SOH, SOH characterization parameters, driving characteristics and vehicle category characteristics of the battery are constructed, and the hidden battery health state information and the change rule thereof are fully mined from vehicle data and battery data, therefore, the RUL is predicted on the basis of the SOH of the battery.

The invention discloses a parking lot management system based on big data, thereby solving the problems of unreasonable parking space distribution and low working efficiency in the existing parking lot management system. The system comprises a server, a user recharging module, a parking space information module, an information acquisition module, an illegal parking detection module, a category distinguishing module, a road sign module, a lifting door and a display screen. The category distinguishing module of the parking lot management system automatically and reasonably distributes the parking spaces according to the parking scores of to-be-parked vehicles and grade classification of primarily selected parking spaces, so that customers with high parking scores enjoy relatively good parking spaces, and the customer satisfaction is high; the parking lot management system realizes unmanned management, is high in intelligence, can quickly respond according to vehicle types and different types, automatic quick opening and closing of the overhead door are realized, the working efficiency is improved effectively, and traffic jam at the entrance and exit of the parking lot is avoided.

A wireless type prepaid IC card system enhances the convenience of users and assures the safe payment of tolls by vehicles including bikes when introduced for toll roads. This toll collecting system is composed of: a card processor that is arranged in a booth for the toll collection process and has an antenna unit for executing the card process through the wireless communication with IC cards, antenna units arranged at the left and right roadsides of the booth for executing the card process through the wireless communication with IC cards, a vehicle class discriminator for discriminating classes of vehicles entering into a traffic lane, and a traffic lane controller that selects an antenna unit to perform the card process according to a discriminated vehicle class and controls the card process.

The invention belongs to the field of Internet of Vehicles, and particularly relates to a multi-parameter fusion adaptive monitoring system under Internet of Vehicles, and a monitoring method thereof.The monitoring method includes the steps: a station terminal obtains information of vehicle attribute and vehicle category and obtains the related information of the outside from a drive test devicethrough the network, and then the vehicle terminal aggregates the obtained information and sends the information to a background management server; the background management server calculates a monitoring state index P of a vehicle according to the data sent by the vehicle terminal, and selects a security level according to the value of the monitoring state index P of the vehicle; and the background management server returns the security level to a user terminal, and the vehicle terminal selects a monitoring strategy according to the received security level of the current vehicle. The monitoring method of the multi-parameter fusion adaptive monitoring system under Internet of Vehicles fully considers the influence of the high dynamics of the Internet of Vehicles, the network time delay anda bandwidth monitoring mechanism, so as to adaptively select the monitoring strategy, thus improving the scalability of the monitoring system, improving the utilization rate of network communicationresources, reducing the resource cost of the user terminal, and improving the monitoring performance of the entire system.

A market for used vehicles is identified for a particular vehicle category. A group of dealers are selected who have a high likelihood of buying units of the products. To identify a market, inventory data is collected from each of a group of dealers within a region on a recurring basis. A dealer profile specifying the business rules for managing the inventory is obtained or produced for each dealer. A supply of products is determined by collecting inventory data from suppliers, such as automobile leasing companies and dealers with surplus inventory. The demand for products is determined by comparison of the dealer profile for each vehicle category to the actual inventory for the corresponding vehicle category and / or to the sales history for the product. The data for each product unit is expanded by reference to third party data bases by use of the vehicle identification number. The data thus collected and produced is aggregated for all of the dealers such that there is a composite representation of the demand for each vehicle category. For each vehicle category having a substantive supply and demand, a market is identified. Participants for this market are those dealers who have a significant demand for the products in the market category. The dealers are invited to a market which is called for the particular vehicle category. Multiple vehicle categories may be combined in one market. As a result, a highly efficient market is organized that is directed to one or more specific vehicle categories that are of high interest to a specified group of dealers and suppliers.

The invention discloses a checkpoint image vehicle retrieval method and system, the method constructs a checkpoint image vehicle retrieval model, and the checkpoint image vehicle retrieval model is composed of a detection network for obtaining a target vehicle image block, a vehicle key point positioning network and a vehicle image block coding network; the method comprises the following steps oftraining the checkpoint image vehicle retrieval model by using the training sample. collecting images of the checkpoint vehicles, inputting the images into the trained checkpoint image vehicle retrieval model, and retrieving from the database to obtain different images belonging to the same vehicle; According to the method, global information including camera postures, vehicle types and the like is used for assisting positioning of vehicle key points, so that accurate vehicle image blocks are obtained; The vehicle image block coding network adopts a quaternary loss function perceived by a sample space structure, negative sample information is fully explored, and the problem of limited performance improvement of the ternary loss function is solved. According to the method, the vehicle picture retrieval accuracy is effectively improved.

Example blind spot detection systems and methods are described. In one implementation, a primary vehicle detects a secondary vehicle ahead of the primary vehicle in an adjacent lane of traffic. A method determines dimensions of the secondary vehicle and estimates a vehicle class associated with the secondary vehicle based on the dimensions of the secondary vehicle. The method also identifies a side-view mirror location on the secondary vehicle and determines a blind spot associated with the secondary vehicle based on the vehicle class and the side-view mirror location.