726 results about "Carriageway" patented technology

A vehicular driving assist system includes at least one sensor disposed at a vehicle and having a field of sensing exterior of the vehicle. An ECU includes circuitry and associated software, with the circuitry including a data processor for processing sensor data captured by the sensor to detect presence of objects in the field of sensing of the sensor. The ECU, responsive to processing by the data processor at the ECU of sensor data captured by the sensor, determines traffic attributes for a plurality of traffic lanes of a road the vehicle is travelling along. The ECU, responsive to determining the traffic attributes determines a predicted traffic value based on the traffic attributes and an output from a trained prediction model. The ECU, responsive to determining the predicted value, determines a traffic jam probability for at least one traffic lane based on the predicted value and the respective traffic attributes.

The invention discloses a traffic scene risk identification method and device considering dynamic and static information fusion, and a storage medium. The method comprises the steps of 1, obtaining a traffic scene high-precision map and a time sequence track of each vehicle; track points in the time sequence tracks are converted into a high-precision map coordinate system, lane matching is carried out, and a time sequence track high-precision map of each vehicle is obtained; 2, predicting vehicle positions, and extracting dynamic and static characteristics of each vehicle time sequence track; 3, fusing the dynamic and static features of each vehicle to obtain a fused feature; inputting the fusion features of all vehicles into a risk factor prediction model to predict and obtain dynamic and static risk factor prediction results; on the basis of prediction errors between dynamic and static risk factor prediction results and corresponding real results, combined with vehicle position prediction errors, calculating a comprehensive risk value of the traffic scene; the equipment and the storage medium are used for implementing the method. The method provides a new thought for traffic risk identification.

The invention relates to the technical field of intelligent driving, and discloses a lane line detection method based on an attention mechanism, and the method comprises the steps: obtaining a lane line data set for data enhancement processing; constructing a backbone network EMAResNet, and fusing the EMA with a backbone network ResNet 18; inserting a self-attention layer SA between the backbone network and the neck network; the neck network adopts a feature pyramid network FPN to be fused with an improved PSA module; inputting the feature map generated by the neck network into a decoder, respectively generating a confidence map and an offset map by using the key nodding head and the offset head in the decoder, and constructing a lane line according to the confidence map and the offset map; and based on the lane line data set, performing model training by using four loss functions of auxiliary loss, key point head loss, offset head loss and focus loss, and performing lane line detection by using the optimized model. Compared with the prior art, the method has the advantages that the perception capability of the model for different scale features is enhanced, the complex scene can be better processed, and the lane line detection precision and robustness are improved.

The embodiment of the invention provides a traffic flow simulation parameter calibration method and device, equipment and a storage medium, and relates to the technical field of data processing. According to the method, track data and current speed data of corresponding vehicles are obtained, lane data obtained by lane area division at an intersection are obtained, multiple groups of car-following vehicle pairs are selected from the vehicles according to passing timestamps of the vehicles passing through lane stop lines, and the car-following vehicle pairs are selected according to the passing timestamps of the vehicles passing through the lane stop lines. And inputting the current radar data into the car-following model for data processing to obtain predicted speed data of a rear car, performing error statistics according to the current speed data and the predicted speed data corresponding to the rear car by using an orthogonal analysis method to obtain an error result, and calibrating simulation parameters in the car-following model based on the error result to obtain target simulation parameters. A high-precision map does not need to be introduced, multiple groups of following vehicle pairs are selected by using timestamps, adverse effects of heterogeneous data on result accuracy are effectively avoided, and the accuracy of a calibration result is improved by using an orthogonal analysis method.

A vehicle includes a windshield configured to transmit a front view of the vehicle to an interior of the vehicle, and a display device configured to display information set to overlap the front view on the windshield, and to divide the windshield into a first display area including a driving lane, both sides of the driving lane, and an upper settings area, and at least one peripheral display area located in a periphery of the first display area, display at least one of driving energy information, speed information, driving lane information, augmented reality (AR) turn by turn (TBT) information, traffic signal information, a distance to a vehicle ahead, warnings, and surrounding vehicles information on the first display area, and display at least one of destination arrival information, media content information, surrounding real image, audio video navigation (AVN) menu, speed limit information, and local geographic information on the peripheral display area.

The invention discloses an intelligent traffic signal control method and system based on Agent-ARIMA, and a program product. The intelligent traffic signal control method comprises the steps of calculating the shortest green light time of each intersection direction, distributing the green light time of each direction, distributing the green light time of left-turn and straight lanes, adjusting the traffic cycle, calculating the time weight offset of multiple intersections, and predicting the traffic flow in the future by using an ARIMA model. And inputting the prediction time of the ARIMA algorithm into the LLM-Agent agent for time prediction, and the like. The method is suitable for different city scales, time distribution of the traffic lights is dynamically adjusted through accurate prediction and analysis of the traffic flow, the traffic jam condition of a large city can be optimized, and the traffic efficiency of a small city can also be improved.

A driving assistance method uses a controller to perform automated lane change to control the own vehicle in such a way that the own vehicle makes a lane change under a condition that the passenger is at least in contact with the steering wheel, the driving assistance method causing the controller to perform processing including: selecting a target lane; and when automated lane change from a current lane to the target lane includes a first automated lane change from a first lane to a second lane and a second automated lane change from the second lane to a third lane, performing lane-keeping assistance under a condition that the passenger is at least in contact with the steering wheel from an end of control of the first automated lane change until a start of control of the second automated lane change.

A vehicle system recognizes a situation of surroundings of a host vehicle, automatically controls at least steering of the host vehicle on the basis of the recognized situation of the surroundings to cause the host vehicle to perform lane change, acquires information on a route from a navigation device guiding the route along which the host vehicle travels, and suppresses control for assisting the steering on the basis of an event regarding the route when the event occurs in the navigation device.

The invention discloses a lane construction method and device, equipment, a storage medium and a product, and relates to the technical field of intelligent driving, and the method comprises the steps: carrying out the coordinate point splicing and coordinate point fitting based on a pre-obtained inter-frame lane map, and obtaining a lane fitting curve; according to the lane fitting curve, lane coordinate sequence construction is carried out to obtain a scene level lane sequence, specifically, after interframe lane maps are spliced, fitting is carried out on a spliced coordinate point sequence, then operations such as equidistant truncation and coordinate point interpolation are carried out on the fitting curve to construct the scene level lane coordinate sequence, and the scene level lane sequence is obtained. Therefore, the lane construction precision is improved, and the accuracy of vehicle lane binding and vehicle lane change and cut-in recognition is improved.

An image recognition apparatus comprises an image information acquirer that acquires image information in a given cycle by capturing an image of a traveling path along which an own vehicle travels, a road sign recognizer that recognizes a road sign based on the image information and a traffic lane recognizer that recognizes traffic lanes located in the traveling path based on the image information. A memory is provided in the image recognition apparatus to store traffic lane information about a traffic lane recognized by the traffic lane recognizer in a time series. A determiner is also provided to determine if the road sign recognized by the road sign recognizer is for an own traffic lane by choosing a most suitable traffic lane among the traffic lanes recognized for a given period based on the traffic lane information stored in the time series.

Techniques for segmenting and classifying a representation of aggregated sensor data from a scene are discussed herein. Sensor data may be collected during multiple traversals of a same scene, and the sensor data may be filtered to remove portions of the sensor data not relevant to road network maps. In some examples, the filtered data may be aggregated and represented in voxels of a three-dimensional voxel space, from which an image representing a top-down view of the scene may be generated, though other views are also contemplated. Operations may include segmenting and / or classifying the image e.g., by a trained machine-learned model, to associate class labels indicative of map elements (e.g., driving lane, stop line, turn lane, and the like) with segments identified in the image. Additionally, techniques may create or update road network maps based on segmented and semantically labeled image(s) of various portions of an environment.

The invention provides a mobile illumination detection device and system, and the device comprises the steps: setting a plurality of illumination detection points through a control module, controlling a mobile carrier to sequentially move to each illumination detection point, controlling an illumination detection module to carry out the illumination detection of each illumination detection point, and generating illumination detection data; generating illumination adjustment data through a dimming module according to the illumination detection data when the illumination conditions of the target detection area are inconsistent, so as to carry out dimming operation on each target roadside illumination device; therefore, the illumination conditions of the plurality of roadside illumination devices in the target detection area on the lane pavement can be automatically detected and adjusted, and the technical problems of high resource cost, low working efficiency, poor detection precision and obvious traffic potential safety hazards caused by an existing manual or semi-manual illumination detection method are effectively avoided. And the illumination conditions of the target detection area can be consistent, so that the illumination of road illumination is ensured, and the safety of night travel is further ensured.

The invention relates to the technical field of urban traffic management, in particular to a road section traffic capacity calculation method and system under bus station interference, and the method comprises the steps: determining a research range and a research time period; social vehicle track data and bus track data in a research range and a research time period are acquired; performing curve fitting based on the social vehicle trajectory data and the bus trajectory data to obtain a social vehicle trajectory fitting curve and a bus trajectory fitting curve; on the basis of the social vehicle track fitting curve, lane division is carried out according to a wave crest positioning-interval width fixing lane division method, and a lane sequence is determined; determining a plurality of target lanes influenced by the bus stations according to the lane sequence; and comprehensively evaluating the traffic capacity reduction coefficient of each target lane based on the overlapping area of the fitting curve of the social vehicle and the bus track and the comparative analysis of the lane driving data, and further determining the actual traffic capacity of each target lane in combination with the basic traffic capacity of the lane.

The invention belongs to the technical field of expressway passenger and truck lanes, and particularly relates to an expressway passenger and truck lane dynamic allocation optimization method which comprises the following specific steps: S1, data acquisition and preprocessing: integrating ETC and radar multi-source data, cleaning and fusing original data, and accurately distinguishing small passenger cars and trucks by using an advanced vehicle type recognition technology, so as to obtain a new vehicle type recognition technology; a reliable data basis is provided for subsequent analysis; s2, traffic state perception and prediction: calculating key traffic parameters of traffic flow, speed and density based on the preprocessed data; and a scientific prediction model is called. According to the method, the future short-time passenger and freight predicted flow provided by traffic state perception and prediction is received, and the lane allocation decision is made based on the dynamic data, so that the number of the passenger car special lanes can be increased in time when the flow of the passenger cars is sharply increased in the morning peak, the delay of the passenger cars on the passenger and freight mixed lanes is reduced, and the overall traffic efficiency is effectively improved.

The invention relates to the technical field of image recognition, and discloses a YOLO v9-based lane line recognition method under strong light and weak light backgrounds, and the method comprises the steps: carrying out the scene judgment of first to-be-recognized image data based on the first to-be-recognized image data and illumination intensity data at the same moment in the automatic driving process of a vehicle, and carrying out the recognition of the first to-be-recognized image data; performing strong light suppression processing on the first to-be-recognized image data belonging to the strong light scene, and performing weak light enhancement processing on the first to-be-recognized image data belonging to the weak light scene to obtain second to-be-recognized image data; according to the illumination intensity data, a pre-trained lane line identification model is adopted to carry out lane line identification on the second to-be-identified image data to obtain a lane line identification result, the lane line identification model is constructed by adopting an improved YOLO v9 model, and a neck network of the improved YOLO v9 model is integrated with a channel attention mechanism and a space attention mechanism. According to the method, the accuracy of target detection is effectively improved.

The invention relates to the technical field of lane line detection, in particular to a 3D-BEV lane line sensing method based on polar coordinates, and the method comprises the steps: carrying out the 3D lane line detection through employing the polar coordinates to replace a conventional method based on a rectangular coordinate system, employing a sliding long-strip-shaped window convolution to adapt to a polar coordinate system, and carrying out the 3D lane line detection through employing the sliding long-strip-shaped window convolution. According to the method, the lane line in the picture can be accurately identified in the polar coordinate system, accurate positioning is carried out in the 3D space, the false detection rate is greatly reduced, the radial distribution characteristic of perspective projection can be more naturally matched, and the modeling precision of the geometric structure of the lane line is remarkably improved.

The present application provides a 3D lane line detection method and device. The method includes: obtaining an image semantic feature matrix and a multidimensional depth feature matrix based on a road scene image and a detection model, converting the multidimensional depth feature matrix into depth probabilities at different depths of the camera's visual cone, and generating lane line BEV features based on the image semantic feature matrix and the depth probabilities at different depths of the camera's visual cone; then, supervising the lane line BEV features based on the road scene image and point cloud ground truth data and performing explicit depth supervision on the multidimensional depth feature matrix to update model parameters until model training is complete; in actual application, performing 3D lane line detection based on the 3D lane line detection model and real-time road scene images to obtain the lane line coordinates in the 3D coordinate system of the vehicle. The method and device can effectively identify 3D lane lines, have low computational complexity, high computational efficiency, and can adapt to complex and changing driving scenarios.

The invention discloses a lane line detection method and device and a storage medium, and the detection method comprises the steps: carrying out the lane line detection of a preprocessed road image, and obtaining each lane line instance; based on each lane line instance, processing the original road image to obtain a connected domain of each lane line; calculating the attribute of the connected domain of each lane line; counting the number of connected domains meeting attribute threshold conditions in each lane line according to the attributes of the connected domains of each lane line; determining the type of the lane line according to the number of connected domains meeting an attribute threshold condition in each lane line; centroids of connected domains meeting attribute threshold conditions in the dotted lane lines are extracted, and all the connected domains are sorted according to the coordinate sizes of the centroids of the connected domains; and screening a plurality of continuous connected domains in the space according to the centroids of two adjacent connected domains to realize positioning of each dotted line block in the dotted line lane line. According to the invention, on the basis of lane line detection, lane line type discrimination and accurate positioning of the dotted line block are realized.

The invention provides an intelligent driving scene reconstruction method and system and a storage medium, and the method comprises the steps: obtaining an OpenStretMap map file based on the real vehicle GPS data, and carrying out the lane-level road network matching based on the OpenStretMap map file; the OpenStreetMap map file obtained after matching of the lane level road network is converted into an OpenDR IVE map file; based on real vehicle GPS data, generating a main vehicle track by using a FastDTW algorithm; based on the environment vehicle information, generating a dynamic interaction object track through a Hungary matching algorithm; and fusing the OpenDRIVE map file, the main vehicle track and the dynamic interaction object track, and reconstructing a scene file in an OpenSCENARIO format in preset simulation software. According to the method, automatic reconstruction is carried out by utilizing the real vehicle data, the real vehicle data can be automatically stored as a universal OpenSCENARIO scene file, simulation testing can be carried out in different types of automatic driving simulation software, a real driving scene can be accurately simulated, and a reliable simulation environment is provided for development, testing and verification of an intelligent driving algorithm.

The invention provides a construction method for a viaduct in a narrow space. The construction method for the viaduct in the narrow space comprises the following steps that 1, a pile foundation platform is constructed; 2, constructing a cast-in-place bent cap; step 3, mounting a portal structure; step 4, component acceptance and transportation; 5, on-site assembling is conducted; step 6, mounting a temporary bracket; step 7, trial hoisting; 8, mounting the box girder; ninthly, the support is detached; the portal structure is slidably mounted on the rail distribution beam arranged on the non-motorized vehicle lane, the temporary support foundation is arranged on the traffic lane, so that the temporary support disperses load through the column bottom distribution beam, and the top is provided with the adjusting steel pipe to finely adjust the elevation of the box beam. The box girders are spliced in sections, the weight of the portal structure hoisted at a time can be reduced through sectional welding forming of the connecting cross beams, the portal structure adapts to small-space operation, and accumulative errors are reduced through sectional welding; a clearance is reserved during disassembly, collision between the box girder and the support is avoided, the disassembly process is controllable, and the integrity of a main body structure is protected.

The invention discloses a vehicle augmented reality navigation method, an augmented reality head-up display device and a vehicle. The method comprises the following steps: acquiring fork road data of a navigation route according to acquired lane-level navigation map data; at least one reverse guiding element is rendered and displayed in an augmented reality head-up display view field range of the vehicle in response to the situation that the fork road data meets a preset triggering condition, the fork road data are obtained based on positioning information of the vehicle and lane-level navigation map data, and different reverse guiding elements are mapped in different forbidden lanes; the forbidden lane is a lane on which the vehicle is forbidden and which is determined based on fork data and perception data of the vehicle. According to the invention, the technical problem of low accuracy and saliency of navigation guidance for a driver in a fork road driving scene in the prior art is solved.

The invention belongs to the technical field of automatic driving, and discloses a graph-centered vehicle multi-modal trajectory prediction method, which comprises the following steps of: constructing a local graph of each traffic participating vehicle; after the geometric features and the type features of the lane segments and the dynamic interaction relation between the lane segments and the traffic participating vehicles are spliced, feature extraction is carried out, and node features of a local graph are obtained; projecting all the coded local maps to a global lane map to obtain a global map; after node features of all the local graphs are aggregated, lane convolution operation is carried out, and local feature fusion vectors are obtained; performing feature extraction on the local feature fusion vector to obtain a global interaction feature vector; performing weighted combination on the local feature fusion vector and the global interaction feature vector to obtain node features of a global graph; projecting node features of the global graph back to the local graph to obtain an enhanced local graph; and according to the enhanced local map, obtaining a prediction track of each traffic participating vehicle and the confidence coefficient of each prediction track.

A vehicular driver assistance system includes a front camera module (FCM) disposed at a vehicle. The system, responsive to processing captured image data, generates FCM lane information including information regarding a traffic lane the vehicle is currently traveling along. An e-Horizon module (EHM) generates EHM lane information including information regarding the traffic lane the vehicle is currently traveling along. The vehicular driver assistance system determines an FCM correlation using the FCM lane information and sensor data captured by at least one exterior sensor. The vehicular driver assistance system determines an EHM correlation using the EHM lane information and the sensor data captured by the at least one exterior sensor. Responsive to determining the FCM correlation and the EHM correlation, the system controls lateral movement of the vehicle based on one selected from the group consisting of (i) the FCM lane information and (ii) the EHM lane information.

The invention discloses a passable lane identification method and a vehicle, and belongs to the technical field of automatic driving. According to the technical scheme provided by the embodiment of the invention, under the condition that the target vehicle is in the automatic driving state, the target lane mask is determined by utilizing the environmental perception information, the local map information and the navigation instruction set in the driving direction of the target vehicle, namely, the position identification of the passable lane is realized by utilizing the multi-source and multi-mode data. The passable lane is determined by using the environmental perception information and the target lane mask subsequently, and the accuracy of the obtained passable lane is high.

A driving control method is performed to execute a lane-change control for controlling a host vehicle to autonomously change lanes from a first lane to an adjacent second lane using a processor of a driving control device that controls vehicle speed and steering of the host vehicle traveling in the first lane in an autonomous driving mode. The processor determines that the lane-change control can be executed upon determining that the other vehicle has been detected in a detection zone of the second lane, based on a detection result of a sensor. The processor determines that the lane-change control cannot be executed upon determining that the other has not been detected within the detection zone of the second lane. The processor outputs information regarding whether the lane-change control can be executed.

A driving assistance method uses a controller to perform automated lane change to control the own vehicle in such a way that the own vehicle makes a lane change under a condition that the passenger is at least in contact with the steering wheel, the driving assistance method causing the controller to perform processing including: selecting a target lane; and when automated lane change from a current lane to the target lane includes a first automated lane change from a first lane to a second lane and a second automated lane change from the second lane to a third lane, performing lane-keeping assistance under a condition that the passenger is at least in contact with the steering wheel from an end of control of the first automated lane change until a start of control of the second automated lane change.

The invention discloses a map topological relation reasoning method fused with an SD map, and belongs to the technical field of three-dimensional reconstruction. The method comprises the following steps: acquiring an SD map and carrying out vectorization processing to obtain an SD map broken line sequence; encoding the SD map broken line sequence to obtain SD map features; adjusting the 3D lane coordinates by using the SD map position codes to obtain lane position embedding; and carrying out inter-lane topological relation reasoning by fusing the SD map features and the 3D lane features. According to the method, 3D lane coordinates and SD map position codes are combined to generate lane position embedding, in the process, initialization of a topological relation is assisted by the SD map, and lane geometric information provided by the SD map is effectively fused in a topological reasoning stage; the method not only considers the inherent geometrical characteristics of the lane, but also significantly reduces the influence of the inherent endpoint shift on the topological relation in the lane detection.