27 results about "Road edge" patented technology

The invention relates to a method for recognizing road categories and determining a speed zone for a motor vehicle (10) based thereon, comprising the steps of: acquiring data from an exterior area (50) of the motor vehicle (10) by means of a sensor device (40); analyzing a surface (60) of a roadway traveled on by the motor vehicle (10) and an adjacent roadway environment including the roadway boundary, based on the acquired data from the exterior area (50) by means of a control device (30), for a feature that is characteristic of the surface (60) and for the presence of road edge design elements (70) in the area of ​​the roadway environment;Rule-based determination of the speed zone by the control unit (30) based on the characteristic feature of the surface (60) and / or on the basis of existing roadside design elements (70), wherein the characteristic feature of the surface (60) includes at least the surface structure. The invention further relates to a device (20) comprising a control unit (30) and a sensor device (40) designed to carry out the method according to the invention or possible embodiments of the method according to the invention, as well as a motor vehicle (10) with such a device (20).

The application provides a vehicle control method and device, electronic equipment and vehicle. The method comprises the following steps: deploying a front-view integrated machine in the vehicle to identify the road edge and / or oncoming vehicle; deploying a millimeter wave radar in the vehicle to obtain a first lateral distance and a first estimated collision time between the vehicle and the road edge, and / or a second lateral distance and a second estimated collision time between the vehicle and the oncoming vehicle; obtaining a vehicle risk assessment level according to the first lateral distance and the first estimated collision time, and / or the second lateral distance and the second estimated collision time; obtaining an operation state of an emergency lane keeping system in the vehicle according to the risk assessment level; if the operation state is an active state, sending a warning prompt according to the risk assessment level, or controlling the vehicle to move in a direction opposite to the lateral direction of the road edge and / or the oncoming vehicle through an electronic power steering system. The application reduces the cost and improves the deployability by deploying a light-weight device.

The application discloses a road edge closing assembly and belongs to the technical field of robots. The road edge closing assembly comprises a rotating assembly, an up-down push rod assembly and a scraper assembly. The rotating assembly is used for connecting a moving assembly of a robot. The up-down push rod assembly is connected with the rotating assembly. The scraper assembly is connected with the up-down push rod assembly. The scraper assembly comprises a working scraper used for closing the road edge.

The application discloses an image-based road edge recognition method and system, the method comprising: acquiring a road scene image of a current frame, inputting the road scene image into a road semantic segmentation model, outputting a road semantic label map, obtaining an initial road edge observation point sequence and a corresponding observation confidence evaluation value of the current frame and a lane line geometric parameter set by using a road observation mechanism; determining a reference lane line from the lane line geometric parameter set and identifying a spatial constraint mode between the initial road edge observation point sequence and the reference lane line; constructing a time sequence feature vector based on a spatial constraint mode of continuous multiple frames within a preset window, evaluating a comprehensive confidence of a spatial constraint relationship of the current frame; and generating a discrete coordinate point set of a final road edge curve according to a comparison result of the observation confidence and the comprehensive confidence by using a preset routing strategy. Thus, high-reliability and high-precision road edge recognition is achieved.

Embodiments of the present disclosure disclose a true value acquisition method and device, electronic equipment and storage medium. The method comprises: obtaining existing linear elements based on historical point cloud data and current point cloud data; determining a target point cloud center line matched with the existing linear elements from the current point cloud data; and performing position optimization on the existing linear elements by using the target point cloud center line to obtain a true value linear element. The technical solution can combine the position information in the current point cloud data and the other attribute information of the existing linear elements based on the fact that the position coordinates of the target point cloud center line in the current point cloud data coincide with the linear elements such as lane lines and road edge lines on the real road, and the other attribute information of the existing linear elements is accurate, to obtain the true value linear element, thereby reducing the manual operation time, improving the true value acquisition efficiency, and improving the quality evaluation accuracy and evaluation efficiency of the linear elements identified by the algorithm.

The application relates to a municipal road disease patrol detection method and related device, which comprises the following steps: acquiring a road surface collection image of a patrol vehicle and a real-time lateral offset relative to a lane center line; determining a specific semantic area to which the image belongs according to the offset, and retrieving an associated disease distribution prior probability; generating a dynamic attention mask and a prior confidence gain coefficient according to the semantic area; inputting the above data into a deep neural network, using the mask to perform spatial weighted modulation on image features, using the gain coefficient to adjust a determination threshold, and outputting a detection result. The application uses spatial prior knowledge contained in the vehicle motion trajectory to adaptively detect the disease distribution law of different road surface areas, improves the detection rate of small diseases in the wheel track, effectively suppresses the false alarm in the road edge area, and improves the accuracy and anti-interference ability of automatic patrol.

The application discloses a detection device mounted on a vehicle side and an unstructured road edge detection method, and relates to the technical field of video recognition. Step one: an original image enters a ResNet50 backbone network, layer-by-layer convolution and down-sampling are performed, and features of different levels are respectively output; step two: deep layer features output by the backbone network are input into a Deformable.ASPP module, and multi-scale enhanced features of a fixed channel number are output; step three: high layer features of the ASPP are sent into an edge enhancement module, edge features are extracted, the edge features are spliced and fused with ASPP output in a channel dimension, and multi-level features are extracted by the ResNet50 backbone network, wherein shallow layer features contain rich edge and texture information, and deep layer features contain global semantic information. Then, multi-scale feature extraction is performed through the Deformable ASPP module, deformable convolution is used to adaptively capture target regions of different scales and deformations, and the weight of each branch is dynamically adjusted through a controller.

The application discloses a coloring method and device of a three-dimensional road surface, a storage medium, an electronic device and a vehicle, and can solve the problems of time-consuming and inaccuracy in generating a road edge line. The method comprises: performing a reduction operation on the three-dimensional road surface according to a preset interval and a curved surface parameter of the three-dimensional road surface to generate a first three-dimensional road surface point cloud; determining a second three-dimensional road surface point cloud corresponding to a road image according to the pose of each frame of road image in the first three-dimensional road surface point cloud, the second three-dimensional road surface point cloud comprising three-dimensional road surface points in the first three-dimensional road surface point cloud, which are at a distance less than or equal to a preset distance from the pose of the road image; projecting the second three-dimensional road surface point cloud to the corresponding road image to obtain a projection point cloud in the road image; and coloring a target three-dimensional road surface point in the first three-dimensional road surface point cloud corresponding to a target projection point into a target color to highlight the road edge of the three-dimensional road surface, the target projection point comprising a projection point in the projection point cloud of each frame of road image located in a target area.

The application discloses a kind of unstructured curved road safety warning system and method based on binocular camera, safety warning system includes binocular camera module, road edge detection module, central processing module, comparison module, communication module, vehicle-mounted signal receiving module, LED screen and voice module, wherein binocular camera module and road edge detection module are connected between and both are connected with central processing module, central processing module is sequentially connected with comparison module, communication module and vehicle-mounted signal receiving module, vehicle-mounted signal receiving module is connected with LED screen and voice module respectively, its method is: first step, arrangement binocular camera and sensing device;Second step, arrangement central processing module and other modules;Third step, running curvature identification algorithm;Fourth step, obtain safety speed;Fifth step, curved road warning system algorithm operation;Beneficial effect: the application can reduce the possibility of accident of unstructured large-curvature curved road, and the practicality is stronger.

The application discloses a kind of grid and road coordination trajectory generation method and system, method includes: all trajectory points in each grid unit that grid trajectory passes are weighted fusion and obtain aggregation coordinates, cross-unit boundary feature extraction is carried out using last grid unit and current grid unit;Construct time sequence grid image sequence, stack multilayer 3D convolution on time sequence grid image sequence, obtain grid trajectory vector;Linear mapping is carried out to the original attribute of road edge in the road network of road trajectory, as the original output feature of three kinds of adjacency graph, inject time coding and position coding of minute level and week level on the fusion feature of multiple adjacency graph, the sequence obtained carries out the multi-head attention calculation of three kinds of attributes of road type, azimuth and length, obtains road trajectory vector;With road trajectory vector as query vector, grid trajectory vector as key vector and value vector, obtain fusion feature;The application has the advantages that: high accuracy and strong robustness.

This invention relates to a road network extraction method based on a deep learning network with multi-source structural priors. The method includes: acquiring satellite imagery, road maps, and road edge maps of the same target area; inputting the road edge maps into a road edge information branch network to obtain first, second, and third road edge features; inputting the satellite imagery into a satellite imagery branch network to perform layer-by-layer feature encoding on the satellite imagery, and obtaining fusion features of satellite and road edges based on the road edge features, road edge features, and satellite-encoded features; inputting the road maps into a road map branch network for feature modeling to obtain a set of layered road encoding features; and obtaining the road network extraction result based on the set of layered road encoding features, road edge features, and the fusion features of satellite and road edges. This invention achieves high-precision and continuous road network extraction through collaborative modeling and complementary enhancement of multi-source information.

The application relates to the technical field of environment perception, and discloses a road edge detection method, a road edge detection device, a terminal device and a storage medium. The road edge detection method comprises the following steps: obtaining a target image and point cloud data of a to-be-detected road; inputting the target image into a trained road edge detection model for processing, and outputting a candidate road edge point set; and detecting a road edge detection result of the to-be-detected road according to the candidate road edge point set and the point cloud data. The application improves the existing lane line detection model to make it applicable to road edge detection, and obtains a road edge detection model. When it is necessary to detect the road edge of the to-be-detected road, the image of the to-be-detected road is input into the road edge detection model for processing, and a candidate road edge point set is output. Then, the point cloud data of the to-be-detected road is combined to assist positioning, so that the accuracy of road edge detection is improved.

Driver assistance device (100) comprising: a detection unit (110) designed to detect an edge of a road, and / or a lane of the road and / or an object positioned within a certain range on the road, and also a surface of the road; a calculation unit (120) which is designed to calculate a distance from the edge, a distance from the lane, a distance from the object and a speed of the object and to calculate a time to collision (TTC) for the edge, the lane and the object, respectively, based on the calculated distances and speed; a management unit (130) trained to determine a risk level for at least one of the elements edge, lane and object and to adjust the risk level depending on the time to collision (TTC); and a control unit (140) which is designed to control a headrest and at least one of the elements display, steering system, brake and belt according to the risk level and according to the surface.

The utility model relates to the technical field of scene simulation model, especially traffic road scene simulation model, including model bottom plate, road edge, double yellow line, opposite lane partition fence, solid line, dotted line, car model, pedestrian crossing and human body model, be provided with three road edges on model bottom plate, be provided with three double yellow lines on model bottom plate, be provided with opposite lane partition fence on double yellow line, be provided with three groups of solid lines on model bottom plate, be provided with three groups of dotted lines on model bottom plate, place car model on model bottom plate, place human body model on the road edge similar to car, be provided with pedestrian crossing on model bottom plate. Through model is roundabout structure, roundabout involves multiple direction selection and priority judgment, can help child practice logical thinking and make correct decision quickly, and roundabout structure model can fill the vacancy of child to this knowledge.

The application belongs to the technical field of automatic driving environment perception, and particularly relates to a laser radar point cloud ground segmentation method and system based on adaptive graph signal processing. The method comprises the following steps: preprocessing the point cloud, filtering the region of interest and removing the reflection noise based on the physical lower bound; calculating the local geometric complexity to dynamically adjust the seed point density, constructing a Voronoi topological graph to maintain the connectivity of sparse areas; constructing a graph Laplace matrix and performing spectral decomposition, using an adaptive low-pass filter to separate the ground manifold signal; introducing the sensor height and slope physical constraints, and restoring the smoothed geometric details through the ADMM algorithm; and completing the point cloud labeling based on topological interpolation and context perception lag threshold. The application solves the connectivity collapse problem of the traditional grid method in sparse areas; effectively filters out noise through graph signal processing, and optimizes the retention of key features such as road edges in combination with physical constraints; and has extremely high precision and robustness under different linear beam radars and unstructured terrains.

Systems and methods for defining map data used in controlling a vehicle are provided. In one embodiment, a method includes receiving, by a processor, telemetry data; determining, by the processor, distribution data for a path based on the telemetry data; determining, by the processor, a plurality of sample data based on a trained machine learning model and the distribution data; generating, by the processor, at least one of lane line data and road edge data based on the sample data and a second machine learning model; and storing, by the processor, the map data including the lane line data and road edge data for use in controlling the vehicle.

The present application relates to the field of automatic driving, and particularly relates to a road edge line noise detection method, device, equipment and storage medium. The method comprises the following steps: acquiring a vehicle trajectory line set and a road edge line set collected in advance, wherein the road edge line set comprises a first road edge line and a second road edge line, and the second road edge line is a road edge line in the road edge line set except the first road edge line; generating a detection range corresponding to a road edge point on the first road edge line according to the road edge point and a nearest vehicle trajectory point in the vehicle trajectory line set; detecting whether the second road edge line that meets a preset detection condition exists in the detection range; if yes, it is determined that noise exists in the detection range. The present application determines the range of noise by using the geometric relationship between the vehicle trajectory line and the road edge line, more conveniently optimizes the noise data in the electronic map, and perfects the map optimization process.

The application discloses a vehicle positioning method and device. The method comprises the following steps: acquiring a first position of a vehicle and point cloud data collected by a laser radar installed on the vehicle; extracting road edge point cloud data, road surface point cloud data and rod-shaped object point cloud data from the point cloud data; aligning the road edge point cloud data, the road surface point cloud data and the rod-shaped object point cloud data according to timestamps; then, down-sampling is performed to obtain down-sampled road edge point cloud data, down-sampled road surface point cloud data and down-sampled rod-shaped object point cloud data; searching for point cloud data matched with the down-sampled road edge point cloud data, the down-sampled road surface point cloud data and the down-sampled rod-shaped object point cloud data from a road element point cloud map; determining residuals of the road edge, the rod-shaped object and the road surface according to the mutually matched point cloud data; optimizing the first position according to the residuals to obtain an optimization result; and determining a positioning position of the vehicle according to the optimization result. According to the embodiment of the application, the positioning accuracy and stability can be improved.

A computer-implemented method for estimating a road geometry of a road upon which a vehicle is traveling and related aspects are disclosed. The disclosed embodiments provide a model-based technique for estimating a road model having an arbitrary number of lanes on a road as well as any entrance lanes (i.e. on-ramp or slip roads) and exit lanes (i.e. off ramps or off-slip roads). In more detail, the herein disclosed embodiments utilize a Bayesian approach to multi-lane tracking in various traffic scenarios, such as e.g. highway scenarios. The employed model-based algorithm estimates the lane center curves of multi-lane roads based on vehicle motion data (e.g. speed, angular velocity) and perception data (e.g. camera output, lidar output, radar output, etc.) that includes detected road features (e.g. lane markers, road edges, road barriers, guard rails, road markers, etc.) or other objects (e.g. other road users).

The present application relates to the technical field of side step of vehicle, and particularly relates to a high-performance telescopic electric side step control method and device. In a preset time period after the opening of the vehicle door, ranging data of each measuring point on the side step connecting plate at each monitoring time is obtained, all suspected obstacle influence time periods and obstacle influence parameters of each measuring point are obtained, all obstacle influence time periods are screened out, and then the time interval between adjacent obstacle influence time periods at each measuring point is combined to analyze and obtain the obstacle confidence coefficient at each measuring point, so as to control the telescoping of the electric side step. The present application can monitor the abnormal continuous situation of the ranging data at each measuring point, comprehensively evaluate the possibility of the electric side step being affected by fixed obstacles such as road edges, reduce the influence of other random interference factors, improve the evaluation accuracy of the influence of the telescoping environment obstacles on the electric side step, and further improve the control effect of the electric side step.

The application discloses a road edge positioning detection method and device and a medium. The method comprises the following steps: collecting a road image, and preprocessing the road image; in the preprocessed road information, the road edge position is labeled in each row of pixels in a unit of a row; the labeled road image is used as a training sample for model training, in the model training, an anchor setting region is used as a feature extraction range for feature extraction, and the extracted shallow features are used as inputs of an ASPP module, so that a neural network model is trained; and the trained neural network model is used for road edge detection. Unlike the pixel-by-pixel detection segmentation method based on image segmentation, the collected image is divided and detected according to a region of interest, the input quantity is the road edge position of each row in the image, the deep network Darknet-53 is selected as a feature extraction network, and the gradient problem caused by the excessively deep network is avoided while the super strong expression of the features is ensured according to the characteristics of the ResNet.

The application discloses a non-structured road recognition method on HSV space and belongs to the technical field of intelligent automobile auxiliary driving. The non-structured road color image is firstly calculated to obtain a black-and-white recognition result image by calculating an S component matrix and calculating a threshold value through an OSTU method, then the black-and-white image is divided into multiple squares, the proportion of black-and-white pixels in each square is calculated and converted into a pixel to obtain a smaller binary image, the method of searching left and right contours of the road is adopted on the small binary image to determine a rough road area, and finally the rough road area is corresponded to the S component to accurately recognize the road edge and the road area according to an edge-to-edge method. The application can preferably recognize the non-structured road, has strong anti-interference capacity, is not sensitive to the road shape, has smaller calculation amount and meets the real-time requirement of an unmanned driving system.

A travel controller autonomously controlling a travel of a vehicle, detecting a departure preventer preventing the vehicle from running off a road at an edge of the road under autonomous control from surrounding data representing surroundings of the vehicle, when no departure preventer is detected, determining a possibility of the vehicle reaching the edge of the road based on an expected movement amount of the vehicle in the lateral direction until stopping and a distance from the vehicle to the road edge, and, when there is a possibility of the vehicle reaching the road edge, notifying the driver of a transition demand demanding transition from the autonomous control to manual control of a travel of the vehicle based on driving operations of the driver of the vehicle, and when there is no possibility of the vehicle reaching the road edge, not notifying the driver of the transition demand.