846 results about "Traffic sign" patented technology

The invention discloses a logistics park vehicle path planning method and system, and the method comprises the steps: obtaining the real-time position and task state information of a vehicle in a park, dynamically constructing a vehicle path planning network model, dividing a road into nodes and edges, and forming a directed weighted graph; according to the directed weighted graph, an improved multi-lane algorithm is adopted, the path length, the congestion degree and the vehicle characteristic factors are comprehensively considered, and the optimal path of each vehicle is calculated; for the optimal path, introducing a virtual lane and a time dimension, pre-judging occupation conditions of multiple vehicles on the virtual lane for each time slice, and constructing a conflict constraint matrix; obtaining park high-precision map data, extracting road network topology, lane lines and traffic sign marking elements, performing lane-level refinement on the optimal path, and generating a driving track; and through a multi-sensor fusion positioning technology, obtaining high-precision position and attitude information of the vehicle, matching the high-precision position and attitude information with the driving track, and calculating a track tracking error.

The invention provides a vehicle collision risk early warning method, system and device and a medium, and belongs to the technical field of vehicle safety control. The method comprises the steps that surrounding environment information of a vehicle is collected in real time through a vehicle built-in sensor and a GPS module; a multi-sensor fusion device technology is used to carry out comprehensive processing on surrounding environment information of a vehicle, and an environment perception model is generated after data integration; based on the environment perception model, target identification is carried out by using a computer vision technology based on a convolutional neural network so as to identify travelers, vehicles, traffic signs and obstacles; performing behavior prediction based on a deep learning model to predict a behavior track of a front vehicle or pedestrian; evaluating a potential collision risk in the current scene in combination with the target recognition result and the behavior prediction result; when a potential collision risk is detected, an early warning signal is sent to a driver, and when the driver does not take corresponding measures, active safety measures are automatically triggered to avoid collision or reduce accident damage.

Various embodiments of the present disclosure relate to operator assistance based on extracting natural language characters from one or more sensed objects. For instance, particular embodiments may generate a natural language utterance based on extracting natural language text in a nearby traffic sign. In an illustrative example, particular embodiments may detect, via object detection and within image data, one or more regions of the image data depicting the traffic sign. Particular embodiments can then extract one or more first natural language characters represented in the traffic sign based at least on performing optical character recognition within the one or more regions of the image data in response to detecting the one or more regions of the image data depicting the traffic sign.

An object detection system for autonomous vehicles, comprising the following: Several vehicle-mounted sensors, including at least one camera, at least one LiDAR sensor, at least one radar sensor, and at least one ultrasonic sensor, each sensor configured to capture data representing the environment surrounding the vehicle; a sensor fusion module functionally connected to the multiple sensors, the sensor fusion module being configured to receive and integrate data from the multiple sensors to produce a comprehensive representation of the vehicle's environment; a data processing unit operationally connected to the sensor fusion module, wherein the data processing unit is configured to preprocess the integrated data by filtering noise, highlighting relevant features, and normalizing sensor outputs to a common frame of reference; a feature extraction module operationally connected to the data processing unit, wherein the feature extraction module is configured to identify and extract characteristic features from the preprocessed data that correspond to objects within the vehicle environment; an object detection unit operationally connected to the feature extraction module, wherein the object detection unit comprises a deep neural network model configured to classify the extracted features in real time into predefined object categories such as vehicles, pedestrians, cyclists, traffic signs, and obstacles; and a decision controller that is operationally connected to the object recognition unit, wherein the decision controller is configured to analyze the classified objects, determine potential collision risks and generate appropriate control commands to adjust the navigation path, speed and other driving parameters of the vehicle to ensure safe and efficient autonomous operation.

The invention discloses a road traffic sign target detection method based on YOLOv8, and relates to the field of road target detection, in the method, a CDFF-YOLO model is constructed, and an MPA module is embedded in a feature fusion network of the model to enhance the feature fusion capability of C2f; an MSF module is constructed, GSConv and CARAFE up-sampling operators are embedded to realize a multi-dimensional sequence information fusion effect, and the detection precision of the model is improved while the parameter quantity and the calculation quantity of the model are reduced as much as possible. A DFF module is constructed, two-dimensional Fourier transform and inverse transform methods are adopted to enable feature information to be enhanced in a frequency domain and a space domain at the same time, and the detection performance of a network model for shielded small targets and small targets under uneven illumination is effectively improved. The three modules not only enhance the detection effect of the small target model, but also enable the network to stably cope with the detection scene of the small target. According to the method, the detection performance of the small road traffic sign target is excellent, the processing speed is high, and deployment of mobile terminal equipment is facilitated.

The invention discloses a guideboard surface deformation detection method and system based on a dynamic video sequence. The method comprises the following steps: acquiring road video data with a timestamp and position information; a traffic sign is automatically identified from the road video data, and geometric anomaly detection is carried out; a time sequence tracking sequence is established for the guideboard, and whether continuous abnormity exists in the guideboard is determined through multi-frame analysis; if yes, performing local texture consistency and local contour geometric analysis on the guideboard to obtain a fusion analysis result; performing state evaluation on supporting equipment corresponding to the guideboard to obtain a state evaluation result of the guideboard supporting equipment; and determining the final surface deformation state and the corresponding grade of the guideboard based on the fusion analysis result and the state evaluation result of the guideboard supporting equipment. By implementing the method provided by the invention, automatic detection and quantitative analysis of the bending or deformation condition of the road sign can be realized without manual intervention, and early warning information can be output in time.

The invention discloses a vehicle-mounted driving assistance method, which relates to the technical field of driving assistance and comprises the following steps: acquiring road image data acquired by a vehicle-mounted camera and vehicle state data acquired by a vehicle-mounted sensor; performing image recognition on the road image data, extracting traffic signs, lane lines and surrounding vehicle position information, and generating road environment data; and judging a current driving risk level according to the road environment data and the vehicle state data, and feeding back early warning information to a driver according to the driving risk level. According to the invention, a comprehensive utilization and real-time feedback mechanism of multi-source data is provided, and the perception and reaction capability of a driver to potential risks is enhanced. Therefore, the system not only can deal with conventional driving situations, but also can deal with complex and dynamically changing traffic situations, so that the driving safety is greatly improved, and the possibility of accidents is reduced.

In various examples, three-dimensional (3D) object or feature detection and localization for autonomous and semi-autonomous systems and applications is described herein. Systems and methods are disclosed that use different types of sensors, such as an image sensor and a LIDAR sensor, to determine information associated with objects, such as traffic objects (e.g., traffic signs, traffic signals, traffic markings, etc.). To determine the information for an object, image data is processed to determine a bounding shape associated with the object. The bounding shape is then used to determine a 3D shape, such as a frustum, corresponding to the object. Additionally, points data generated using the LIDAR sensor, such as an occupancy map and / or a point cloud, is processed to identify a portion of the points associated with (e.g., located within) the 3D shape. This portion of the points may then be used to determine the information associated with the object.

A method includes receiving image data captured by a traffic feature detection system. The image data is representative of a traffic feature within an environment. The method includes identifying a type of the traffic feature. The method includes isolating a portion of the image data containing the traffic feature. Based on the portion of the image data containing the traffic feature, the method includes determining a pixel color value for the traffic feature. Based on the type of the traffic feature, the method includes determining an expected pixel color value for the traffic feature. Based on a comparison of the expected pixel color value and the determined pixel color value for the traffic feature, the method includes determining a health status for the traffic feature.

The invention provides a YOLOv8 traffic sign real-time detection method based on edge calculation optimization, and the method comprises the steps: collecting traffic scene image data in real time, carrying out the preprocessing of the collected image data, inputting an optimized YOLOv8 network model, carrying out the feature extraction, carrying out the processing of feature maps of different scales through an SE module and a bidirectional feature fusion strategy, and carrying out the detection of a traffic sign. Entering a detection head for target detection to obtain a detection result; an obtained detection result is transmitted to a central server or an automatic driving system in a structured data format through a low-delay communication protocol; in a central server or an automatic driving system, real-time statistics and trend analysis are carried out on detection results, and through deep optimization and deployment strategy improvement on a YOLOv8 model, many limitations in an edge calculation scene in the prior art are overcome. Specifically, a lightweight optimization strategy combining model pruning, quantitative processing and an efficient inference engine is provided, and the detection precision and robustness are improved in combination with an environment adaptive image preprocessing method.

In various examples, systems and methods are described that may be used to generate a mask of a geographic area and corresponding vector representations of one or more environmental features included in the area. In some embodiments, the method and system may generate or obtain a first tile image representing a portion of a path surface corresponding to a geographic area. One or more features may be extracted from the data where the extracted features may indicate environmental characteristics associated with the path surface—e.g., lane boundaries, medians, traffic signs, signals, etc. Additionally, the method or system may generate a mask corresponding to the tile image and vector representations of the portion of the geographic area. In some embodiments, the locations of the environmental features associated with the mask may be reconciled with one or more previously generated masks that include some of the same environmental features.

The invention discloses a vehicle-mounted sign retroreflection coefficient detection method and system adaptive to a slope road. When the relative distance between a to-be-detected sign board in a to-be-detected area and a detection vehicle meets a preset shooting distance, the to-be-detected sign board in the to-be-detected area is detected; obtaining road dip angle information, collected by a dip angle sensor in real time, of the detection vehicle at each moment in the driving process in the to-be-detected area; solving a road dip angle in the detection area according to the road dip angle information at each moment; the compensation angle of the detection module is calculated according to the road dip angle, the electric adjusting structure is controlled to adjust the incident angle of the detection module into the target incident angle in real time according to the compensation angle, and the compensated detection module is obtained; using the compensated detection module to photograph a to-be-detected traffic signboard to obtain a to-be-identified signboard image; performing identification processing on the to-be-identified signboard image to obtain a retroreflection brightness coefficient corresponding to the to-be-detected traffic signboard; therefore, the effectiveness and accuracy of detection can still be maintained under complex road conditions.

The invention discloses a traffic sign target detection method, electronic equipment and a medium, and the method comprises the steps: carrying out the feature extraction of a traffic sign image through a backbone network which comprises a full-dimension dynamic convolution module and a space channel collaborative attention module, and obtaining a preliminary feature; a spatial pyramid pooling fast module is used for obtaining features of different receptive fields, channel aggregation is carried out to obtain deep features, feature enhancement is carried out through a spatial channel collaborative attention module, and then the obtained deep features are input into a bidirectional fusion network module for feature fusion. And finally, carrying out target classification and bounding box regression on the feature representations of different scales through a convolution module and a nonlinear activation function. According to the method, the space channel collaborative attention module and the full-dimensional dynamic convolution module are adopted, the model reasoning speed and accuracy are improved while multi-scale feature extraction is achieved, and low-fine-granularity information is fully extracted to help detection of traffic signs in images.

Examples of the presently disclosed technology provide computerized systems and methods that automatically update digital maps in response to detected traffic sign updates in a rapid and efficient manner. Examples achieve these advantages by cascading traffic sign updates through multi-layered digital maps using specific methodologies tailored to different types of traffic sign updates. By providing rapid and accurate digital map updates, examples can improve performance for autonomous driving systems that rely on digital maps for determining vehicle navigation paths—thereby improving traffic safety and efficiency.

A method for traffic sign prediction includes determining a plurality of roadway characteristics. The method also includes determining a plurality of road user information. The method also includes determining a plurality of weather-related information. The method also includes determining a predicted traffic sign based at least in part on the plurality of roadway characteristics, the plurality of road user information, and the plurality of weather-related information. The method also includes performing an action based at least in part on the predicted traffic sign.

A method for countering adversarial attacks on deep neural networks is disclosed. In one embodiment, such a method includes observing, by a first system, actual traffic behavior within a transportation network. The method classifies, by a deep neural network of a second system, a traffic sign for regulating traffic within the transportation network. The method determines whether a conflict exists between the actual traffic behavior and expected traffic behavior based on the traffic sign. If a conflict is deemed to exist, the method adjusts training data of the deep neural network with respect to classifying the traffic sign. In certain embodiments, the first system includes one or more forerunner vehicles and the second system is an autonomous vehicle. The one or more forerunner vehicles may be configured to travel ahead of the autonomous vehicle when navigating the transportation network. A corresponding system and computer program product are also disclosed.

The invention discloses a road traffic potential safety hazard troubleshooting method based on a tunnel road section scene. The method comprises the following steps: S1, constructing a tunnel road section road traffic potential safety hazard troubleshooting knowledge system; s2, establishing a standardized data acquisition process; s3, carrying out cleaning based on the road section data of the map; s4, systematized stake number and troubleshooting road section calibration is carried out; s5, establishing intelligent tunnel road section identification; s6, a tunnel road section road traffic potential safety hazard standardized troubleshooting method and a conclusion are obtained; the AI recognition technology, the laser radar and the intelligent vehicle-mounted equipment are combined, and automatic collection and troubleshooting of traffic signs, marking lines and safety facilities of tunnel road sections are achieved. Through AI automatic kilometer pile identification and manual auxiliary confirmation, the starting and ending points and the up-down direction of the road section are accurately calibrated, the uniqueness of a troubleshooting result is ensured through a data cleaning technology, the troubleshooting efficiency and accuracy of traffic hidden dangers are remarkably improved, and the traffic safety management level of the tunnel road section is effectively improved.

In various examples, three-dimensional (3D) object or feature detection and localization for autonomous and semi-autonomous systems and applications is described herein. Systems and methods are disclosed that use different types of sensors, such as an image sensor and a LIDAR sensor, to determine information associated with objects, such as traffic objects (e.g., traffic signs, traffic signals, traffic markings, etc.). To determine the information for an object, image data is processed to determine a bounding shape associated with the object. The bounding shape is then used to determine a 3D shape, such as a frustum, corresponding to the object. Additionally, points data generated using the LIDAR sensor, such as an occupancy map and / or a point cloud, is processed to identify a portion of the points associated with (e.g., located within) the 3D shape. This portion of the points may then be used to determine the information associated with the object.

Simple traffic management strategies such as static signs, fixed pattern timed traffic lights, etc. fail to address the dynamic nature of traffic flow resulting in traffic backups and inefficiency. Accordingly, there are provided means for dynamically adjusting traffic signs, traffic signals etc. to adjust the flow to remove backups, avoid tailbacks and increase efficiency of travel etc. Further, most control systems are controlled with default control settings or ones based upon limited information. Accordingly, there are provided methods based upon real-time or offline micro-simulations from enhanced information and acquired data accumulated at high frequency, such as from connected vehicles, to allow for improved evolving model(s) of traffic flow within the traffic system to be established for establishing control settings etc. of traffic infrastructure such as traffic signs, traffic signals etc.

The invention provides an automatic driving high-precision map construction method and device based on semantic understanding, and relates to the technical field of high-precision maps, and the method comprises the steps: collecting multi-source perception data and pose data along a target road through a data collection unit, the data acquisition unit at least comprises an image acquisition device, a laser radar acquisition device and a positioning device; based on the pose data and the multi-source sensing data, generating an initial point cloud map of a target road through synchronous positioning; and performing semantic segmentation and element recognition on the initial point cloud map, vectorizing static road elements at least comprising lane lines, traffic signs and a lane topological relation, and constructing a high-precision map with semantic information. The technical problem of insufficient accuracy and reliability of automatic driving high-precision map construction in the prior art is solved. The technical effect of improving the accuracy and reliability of high-precision map construction by accurately analyzing semantic association is achieved.

A radar traffic sign apparatus is provided comprising an electronic or a motorized radar traffic sign. The electronic sign has at least one metasurface to shape complex configurations such as plane and / or corner reflectors. Each metasurface has a top layer of PCB board for controllable elements, a ground layer, and biasing means comprising diodes or switches. The state of the sign can be changed by the elements attached to the top layer. A bias voltage applied at the biasing means causes states of at least one element to change, and an operation mode of the metasurface to switch. The motorized sign may include multiple planes to shape a specific corner reflector with proper RCS. The direction or opening of a motorized sign can be controlled. The radar traffic sign has an ON mode to reflect the radar signal, and an OFF mode where the radar signal is not reflected.

The invention discloses a traffic sign defect detection method and system based on SAM and Transform and a medium, and the method comprises the steps: collecting an image of a traffic sign, carrying out the preprocessing, recognizing the traffic sign in the image through a YOLO target detection model, generating a detection frame of the traffic sign, and framing a region where the traffic sign is located; inputting the detection frame and the corresponding image into an SAM model, and extracting the contour of the traffic sign; and simultaneously inputting the extracted contours of the traffic signs and contours of the traffic signs in a normal state in the database into a neural network classifier based on Transform for comparative analysis, finally outputting a defect detection result, and giving a specific defect type and a confidence score. According to the method, the YOLO target detection, the SAM model and the neural network classifier based on the Transform are combined, and the task of each stage can be optimized on the basis of the result of the previous stage, so that the final detection precision and efficiency are improved.

The invention discloses a traffic sign information extraction method and system based on image recognition, and relates to the technical field of image recognition and processing, and the method comprises the steps: collecting road scene data, generating a panoramic image data set and a point cloud data set, and carrying out the preprocessing of the panoramic image data set and the point cloud data set; constructing a convolutional neural network model, and identifying a panoramic image; performing point cloud data segmentation on the point cloud data set based on a panoramic image recognition result; fusing the point cloud data related to the traffic sign in the point cloud data with the panoramic image recognition result to obtain fused traffic sign data; carrying out encryption output on the fused traffic sign data; according to the method, the panoramic image is recognized by using the convolutional neural network model, point cloud data segmentation is performed on the point cloud data, and the traffic sign data is further extracted, so that the accuracy and efficiency of image recognition are improved, rapid processing of the panoramic image is realized, and the method adapts to a complex road environment and has universality and practicability.

The present disclosure provides a system and a method for jointly controlling one or multiple connected and automated vehicles (CAVs) and one or multiple human-driven vehicles (HDVs) subject to integer constraints for crossing each of multiple intersections on a road. The method comprises collecting digital representation of states of each of the CAVs, HDVs, and traffic signs, solving an optimization problem jointly optimizing traffic flows based on a macroscopic traffic flow model in a centralized traffic controller (CTC) subject to convex relaxation of the integer constraints, solving a multi-variable mixed-integer programming (MIP) problem in each of multiple intersection traffic controllers (ITCs) optimizing a cost function and minimizing tracking errors in traffic flow values of a microscopic traffic flow model with respect to relaxed traffic flow values from the CTC, and transmitting the optimized values of the control commands to the corresponding CAVs and corresponding traffic signs.

The invention discloses an intersection traffic violation total factor snapshot system based on multi-view collaboration, and relates to the technical field of intelligent traffic, and the system comprises a data collection and transmission module, a data preprocessing and splicing module, a data optimization and analysis module, a traffic violation judgment module, and a data storage and management module. According to the invention, through a panoramic video optimization unit in the data optimization and analysis module, the spliced panoramic video is deeply optimized, and tiny splicing traces or image local distortion generated in the splicing process is further eliminated, so that the panoramic video picture is clearer, smoother and more real, and high-quality image materials are provided for subsequent analysis; and the target in the video is accurately recognized through the image recognition and analysis unit, target feature information of vehicles, pedestrians and traffic signs and marked lines is extracted, traffic illegal behaviors can be more accurately judged based on the information, and the situations of misjudgment and missed judgment are reduced.

The present disclosure provides a system and method for jointly controlling one or more networked automated vehicles (CAVs) and one or more human driven vehicles (HDVs) subject to integer constraints for crossing each of a plurality of intersections on a road. The method includes collecting a digital representation of a state of each of CAV, HDV, and traffic signs, solving an optimization problem of joint optimization of traffic flow based on a macroscopic traffic flow model in a convex relaxation centralized traffic controller (CTC) subject to integer constraints, solving a multivariable mixed integer programming (MIP) problem in each of a plurality of intersection traffic controllers (ITCs) that optimizes a cost function and minimizes tracking errors of traffic flow values of the microscopic traffic flow model with respect to relaxed traffic flow values from the CTCs, and transmitting optimized values of the control commands to corresponding CAVs and corresponding traffic signs.

An aspect of the disclosure provides an apparatus and a method for assisting driving capable of calculating a speed limit of a vehicle using curvature information of a road and accurately recognizing a traffic sign through this. The apparatus for assisting driving of a host vehicle includes a front sensor mounted to the host vehicle and having a field of view in front of the host vehicle, the front sensor configured to obtain front image data; and a controller including a processor configured to process the front image data. The controller may be configured to detect a speed displayed on a sign based on the front image data, to calculate a limit speed of the host vehicle on a driving road based on the front image data, and to display a sign speed smaller than the limit speed on a display of the host vehicle.

The invention relates to the technical field of auxiliary driving, and discloses a deep learning-based road signboard recognition method, which comprises the following steps of: acquiring a road traffic video sequence stream in a vehicle driving process; inputting the road traffic video sequence stream into a deep learning detection framework based on improved YOLOv11 for initial positioning to obtain an initial positioning result of the road signboard; performing cross-frame target tracking on the initial positioning result of the road signboard through an improved Kalman algorithm to obtain a road signboard identification result with a motion track; and displaying the identification result of the road signboard on a vehicle-mounted head-up display of the vehicle. According to the road signboard identification method and system based on deep learning provided by the invention, a scheme based on deep learning and optimized Kalman filtering is adopted, traffic signboards in a complex road traffic environment are identified, and a perfect auxiliary driving system is established, so that key signboard information can be quickly and accurately found in the complex road environment; and a driver is assisted to make correct judgment.

The invention relates to the technical field of accumulated water level measurement, in particular to a sunken road accumulated water monitoring device which comprises a base and a plurality of fixing cones fixed to the bottom of the base and further comprises a plurality of vertical arms fixed to the base, a top plate is fixed to the ends, away from the base, of the vertical arms, and a display panel is fixed to the side of the top plate. A triangular display area is arranged in the display panel; the shielding mechanism is connected with the display panel and can move relative to the display panel; the floating balls are arranged on the side of the base and connected with the follow-up mechanism installed on the base, the follow-up mechanism is connected with the shielding mechanism, and the follow-up mechanism is triggered when the floating balls ascend; when the floating ball is located at different heights, the display areas correspond to different display conditions, display and reflection of the water level condition are comprehensive, in the monitoring process, the height of the floating ball changes, the height of the display panel is fixed, the height of the display panel is equal to that of a traffic sign, and therefore passing personnel can pay attention to and observe the display panel conveniently.