58 results about "Traffic sign" patented technology

The application discloses a kind of intelligent unmanned vehicle environment perception systems based on multi-sensor information fusion, it is related to unmanned vehicle technical field.The system includes: sensor module, for collecting multi-source heterogeneous data, including GPS / IMU, laser radar, camera and millimeter wave radar;Data acquisition and fusion module, through the Kalman filter to multi-source data space-time synchronous fusion;Environment perception module, based on deep learning identification road boundary, obstacle and traffic sign, constructs dynamic perception model;High-precision map construction module, using SLAM technology and semantic information constructs and updates semantic three-dimensional map;Positioning algorithm module, fusion visual odometry, fusion data and high-precision map, calculates vehicle real-time pose;And control module, according to positioning and perception result carries out path planning and navigation control, the application provides a kind of intelligent unmanned vehicle environment perception systems based on multi-sensor information fusion, can be autonomously navigated and stably driven under complex and severe environment.

The application discloses a real-time traffic sign positioning and recognition method and system based on kernel adaptive attention, wherein the method comprises the following steps: acquiring an image to be recognized; inputting the image to be recognized into a trained traffic sign positioning and recognition model to obtain a traffic sign positioning and recognition result; wherein the trained traffic sign positioning and recognition model is realized by using an improved YOLOv12 architecture, the improved YOLOv12 architecture comprises a backbone network, a neck network and a detection network connected in sequence, the backbone network performs feature extraction on the image to be recognized, the neck network performs feature fusion on the extracted features, the detection network performs detection on the fused features to obtain the traffic sign positioning and recognition result, and a kernel adaptive attention mechanism module KA-CBAM is added in the backbone network.

The application discloses a kind of sign detection method, device, nonvolatile storage medium and computer equipment.Therein, the method includes: obtaining historical frame, target frame and the motion information of vehicle, wherein historical frame and target frame are the image obtained by the camera of vehicle shooting;According to motion information and historical frame in historical detection frame, determine target area, wherein historical detection frame is used to mark traffic sign in historical frame;According to target area and target frame, generate target detection frame, wherein target detection frame is used to mark target traffic sign in target area in target frame.The application solves the technical problem that a large amount of computing power is required to identify traffic sign from video images in real time while driving.

The disclosed systems and techniques facilitate efficient detection and classification of traffic signs in driving environments. The disclosed techniques include, obtaining, using a sensing system of a vehicle a first set of perspective camera images of an environment and a second set of radar images of the environment. The techniques further include generating, using a first neural network, one or more camera features characterizing the first set of images, generating, using a second neural network, one or more radar features characterizing the second set of images, and processing the one or more camera features and the one or more radar features to obtain an identification of one or more traffic signs in the environment.

In various examples, multilabel hierarchical classification of objects for autonomous systems and applications is described herein. Systems and methods are disclosed that use one or more neural networks to classify objects, such as traffic signs, using multilabel classification and / or hierarchical classification. For instance, a multilabel subnetwork of the neural network(s) may classify an object based at least on one or more attributes associated with the object. As such, the output from the multilabel subnetwork may include at least a classification associated with the object and an attribute classification(s) associated with the object. A hierarchical subnetwork of the neural network(s) may also classify the object using one or more class labels, where a class label indicates another classification and / or a class group associated with the object. The systems and methods may then use the classification, the attribute classification(s), and / or the class label(s) to determine a final classification associated with the object.

The application relates to a vehicle testing method, device, computer equipment, computer readable storage medium and computer program product. The method comprises the following steps: acquiring current weather information, current road information, a current category number of traffic signs and current dynamic information of all traffic participants in a current frame of an automatic driving scene; acquiring a first evaluation index, a second evaluation index, a third evaluation index and a fourth evaluation index of the automatic driving scene based on the current weather information, the current road information, the current category number and the current dynamic information respectively; acquiring a target evaluation index of the automatic driving scene based on the above evaluation indexes and corresponding weight values of each evaluation index; and testing a target vehicle in the automatic driving scene based on the target evaluation index. The method provided by the application can test the vehicle more accurately.

The application relates to the underground mine unmanned vehicle positioning technical field, in particular to an underground mine environment-based unmanned vehicle repositioning device and system based on road sign recognition, which comprises a bottom plate, the upper surface of the bottom plate is symmetrically provided with transport tracks, the upper surfaces of the two transport tracks are provided with sign position acquisition assemblies in a rolling mode, the sign position acquisition assembly comprises a plurality of roller wheels rolling installed on the upper surfaces of the transport tracks and L-shaped mounting plates fixedly sleeved on the outer surfaces of the roller wheels, the upper ends of the plurality of L-shaped mounting plates are fixedly connected with a machine seat, the upper surface of the machine seat is provided with an image processing module, and the surface of one end of the image processing module is provided with a controller, which is beneficial to the underground mine environment-based unmanned vehicle repositioning based on road sign recognition, can efficiently and accurately identify various traffic signs on the road, including text type traffic signs and other graphic signs, and can identify the approximate position of the vehicle in the mine.

This invention discloses a method and system for adjusting variable traffic signs in icy and snowy weather. The method includes: First, collecting various environmental parameters affecting driver behavior at the location of the variable traffic sign using monitoring equipment, and generating a corresponding environmental state vector based on the collected parameters. Then, inputting the generated environmental state vector into a pre-trained deep reinforcement learning model, which determines the dynamic adjustment amount of the variable traffic sign. The dynamic adjustment amount can include positional adjustments between adjacent signs, or angular adjustments of the variable traffic sign in various directions in three-dimensional space. Finally, determining the deployment location and spacing of the variable traffic sign based on the dynamic adjustment amount output by the deep reinforcement learning model ensures that drivers can quickly and accurately identify traffic signs and operate their vehicles safely, thus guaranteeing traffic safety in the diversion zone.

This invention discloses a class-level parameter aggregation method and system based on homomorphic encryption. The method includes the following steps: generating public and private keys for categories required for homomorphic encryption; distributing the private keys to clients with the right to use category data, where the categories are traffic signs or road condition events; training a classification model, calculating the parameter vectors for the corresponding categories on the client side, and calculating the visibility counts for the corresponding categories; concatenating the parameter vectors and visibility counts for each category into a slot vector to be encrypted, encoding the slot vector into homomorphically encrypted plaintext, and encrypting it with the public key to obtain ciphertext; performing homomorphic addition on the ciphertext category by category and slot by slot to obtain the sum of ciphertext parameters and the sum of ciphertext visibility counts; decrypting the authorized categories holding the private keys, calculating the global class-level parameters based on unbiased averaging, and merging and updating them with the local historical classification heads; updating the classification model, and outputting the traffic sign or road condition event recognition results. This invention enables fine-grained decryption authorization, reduces the risk of category distribution leakage, and saves bandwidth.

This application discloses a method and system for evaluating the night visibility of traffic safety facilities, relating to the field of image processing technology. The method includes: acquiring an image of a traffic safety facility to be evaluated; if the image is a traffic sign image, determining the retroreflection coefficient of each color region of the traffic sign; evaluating the night visibility of the traffic sign based on the retroreflection coefficient and the uniformity of gray values ​​in the specific distribution area of ​​the traffic sign; if the image is a traffic marking image, determining the retroreflection brightness coefficient of the traffic marking and the uniformity of gray values ​​in the specific image region where the traffic marking is located; and evaluating the night visibility of the traffic marking based on the retroreflection brightness coefficient and the uniformity of gray values ​​in the specific distribution area of ​​the traffic marking. The night visibility detection method for traffic safety facilities in this application has high detection accuracy and strong reliability.

A method for detecting grouped traffic sign objects comprises receiving image data from a multitude of vehicles, wherein the image data captures a multitude of traffic signs, refining the image data by filtering it to remove unsuitable image frames, and assigning each traffic sign captured in the image data to one or more sign groups. For each corresponding sign group within the one or more sign groups, the method also comprises processing the corresponding sign group to extract metadata associated with each of the traffic signs assigned to the corresponding sign group, deriving a target for the corresponding sign group based on the metadata, deriving a context for each of the traffic signs assigned to the corresponding sign group based on the metadata, and storing the corresponding sign group in a data store.

A vehicle includes at least one imaging sensor. A controller is in communication with the at least one imaging sensor and includes a processor and a memory. The memory stores a sign reasoner module configured to receive a lane level map graph and an image generated by the at least one imaging sensor. The sign reasoner module is configured to identify a traffic flow message of a sign in the image and to update the lane level map graph based on the traffic flow message. The sign reasoner is a generative artificial intelligence (AI) and includes a connection to at least one external information source. The sign reasoner is configured to identify the traffic flow message based at least in part on a retrieval augmented generation analysis of the external information source.

The utility model discloses a fine soft branch class middle and big shrub supporting device of multi -functional integration, is equipped with telescopic support rod, spiral support coil and fixing device, and the spiral support coil is based on telescopic support rod, can provide stable support to the branch and leaf of fine soft branch class middle and big shrub, prevent shrub lodging, and can utilize spiral support coil as elastic buffer to realize wind -resisting and shock -resisting, to stabilize the root system of shrub and prevent wind erosion, and, shrub can correspondingly dynamic adjustment growth form under the restraint of spiral support coil, and, with the height growth change of fine soft branch class middle and big shrub, can gradually stretch out upwards through the telescopic end of telescopic support rod, to make the spherical space surrounded by spiral support coil expand upwards the growth space of shrub, and can guide fine soft branch class middle and big shrub to grow upwards through the spherical space, avoid the branch of shrub in city road isolation band to droop and shield traffic sign.

The utility model relates to the technical field of signboard fixing, particularly a highway traffic signboard fixing structure of quick installation, including support column and signboard, two trusses are fixedly connected at the top of support column, the utility model has the advantages of: when installing the signboard, only need to push the clamping baffle into the lead square hole, then slide the connecting support plate to one side, make the connecting vertical board push into the bayonet, make the clamping baffle when to the bottom of bayonet, make the upward freedom degree of connecting vertical board be locked, simultaneously, the end of truss is hooked by the falling of the clamping hook, make the freedom degree of connecting vertical board sliding to the lead square hole direction be fixed, realize complete fixing, the operation of this fixing mode is simple, need not long time alignment hole position, also need not tighten bolt, only need to push to one side after inserting, improve the installation efficiency, through the connection of connecting vertical board and clamping baffle and bayonet, compared with the connection of bolt, its strength is higher, and the problem of bolt corrosion and difficult disassembly does not occur.

This invention discloses an intelligent generation algorithm and system for intersection traffic organization and traffic signs and markings, belonging to the field of intelligent transportation technology. The intelligent generation algorithm for intersection traffic organization and traffic signs and markings includes parameter input, logical algorithm, result output, iterative calculation, and scheme verification. It can assist users in realizing the intelligent generation of intersection traffic organization and traffic signs and marking schemes, getting rid of the dependence on the designer's personal experience in traditional traffic design schemes, greatly eliminating personal subjectivity, and ensuring the compliance of traffic design schemes. Furthermore, based on the intelligent generation algorithm for intersection traffic organization and traffic signs and markings, an intelligent generation system for intersection traffic organization and traffic signs and markings is proposed, which to a certain extent solves the problems of current traffic scheme design being cumbersome and complex, having high entry barriers, and being unable to guarantee scheme compliance. It has broad application prospects in optimizing the design of existing intersection traffic schemes and verifying and reviewing traffic design scheme drawings.

This utility model provides an intelligent variable information sign device for traffic engineering, relating to the field of traffic sign technology. It includes: a suspension frame, a main frame, information panels, turnbuckles, an electric cylinder, and a transmission link. The top of the suspension frame is fixedly connected to a traffic support rod, and the bottom of the suspension frame is connected to the main frame. A turnbuckle is connected inside the top of the suspension frame and is connected to the main frame. Three information panels are installed inside the suspension frame. An electric cylinder is installed at the bottom of the main frame, and a transmission link is connected to the bottom of each information panel. This utility model ensures the synchronicity of the rotation adjustment of the three information panels through gear meshing. It allows for rotation adjustment of the three information panels according to traffic control needs, enabling switching between two traffic signs to meet traffic control requirements. Furthermore, according to traffic control, rotating the turnbuckles causes the main frame to rise and fall, changing the height of the traffic sign and better meeting practical application needs.

Techniques for vehicle positioning to optimize or improve sensor utility are described herein. A vehicle may receive sensor data of an environment. The vehicle can use the sensor data to detect relevant objects (e.g., traffic signs, traffic lights, construction signs, construction workers, buildings, etc.) proximate the vehicle. Further, the vehicle can use the sensor data to detect blocking objects or objects that block the sensor field of view (e.g., busses, semi-trucks, trailers, etc.) proximate the vehicle. The vehicle may generate candidate actions and evaluate such candidate actions (e.g., determine cost values) based on whether the blocking object(s) occlude the relevant object(s) from the one or more sensor devices of the vehicle. The vehicle can be controlled based on such evaluations (e.g., follow the candidate actions, generate modified actions to increase view of the relevant object(s), etc.).

The utility model belongs to the traffic sign technical field of channel, especially the anti -impact type top mark. Bracket top mark pole and the connecting disc of top mark pole top setting, the fixed disc is arranged below the connecting disc, the buffer spring is arranged between connecting disc and fixed disc, the buffer disc is further arranged between connecting disc and fixed disc, the buffer spring is arranged between connecting disc and buffer disc, the auxiliary spring is further arranged between buffer disc and fixed disc, the utility model discloses through the increase of auxiliary spring, the first deformation is the characteristic of buffer spring when blowing, ensure that it can also guarantee basic reset after the disability of buffer spring, at the same time, through the setting of strengthening assembly, it will not produce the disability caused by exceeding the elastic limit due to the deformation and the excessive bending of too big under certain wind force, thereby under the condition of guaranteeing deformable buffer, improve the service life.

This invention provides a method and apparatus for generating adversarial examples of traffic signs for adversarial training. The method employs a vehicle-road model and camera imaging model based on actual roads and imaging equipment to obtain adaptive traffic sign samples, making the final generated adversarial attack samples more realistic and improving their quality. Secondly, it obtains adversarial attack samples through the combined effects of style loss, content loss, adversarial loss, and smoothing loss, avoiding the problem of existing physical world adversarial attack methods adding excessive perturbations to enhance robustness, resulting in poor concealment of the adversarial attack samples. Finally, based on the improved quality and concealment of the adversarial attack samples, adversarial training of a second target detection model is performed, thereby improving the adversarial detection performance of the second target detection model.

The application discloses a navigation method, device, equipment, storage medium and product, relates to the technical field of vehicle navigation, and the navigation method comprises the steps of acquiring multi-source data corresponding to a vehicle and driving scene information, wherein the multi-source sensing data at least comprises navigation data and traffic sign data; based on the driving scene information, adjusting the weight proportion of each data source in the multi-source data in navigation; performing semantic understanding on the traffic sign data to obtain structured data; and adjusting the navigation decision of the vehicle based on the adjusted weight proportion and the structured data. Through the adjusted weight proportion and the structured data after semantic understanding, the navigation decision is timely adjusted, so that the actual road position of the vehicle can be accurately determined.

The present invention relates to a method (60) for filtering relevant traffic signs (21) for a vehicle (10) in an exit area (35), comprising at least the method steps of: detecting (52a) an exit area (35); detecting (52b) the intended route (50) of the vehicle (10); and determining (54) the relevance (59) of detected traffic signs (23) with regard to the intended route (50). The invention also relates to its use, a driver assistance system (20), and a vehicle (10) for carrying out the method according to the invention.

1. Name of the product in this design: Urban Rail Transit Information Sign. 2. Purpose of this design: Primarily for displaying traffic signs. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: a 3D model.

This utility model relates to the field of traffic sign technology, and more particularly to a traffic sign painting device, comprising a processing platform, a first motor disposed at the bottom of the processing platform, and a first cylinder disposed at the end of the processing platform away from the first motor. Through the arrangement of grinding blades and a compaction rod, when the sign needs to be polished, it is simply placed face down on the grinding blades. Multiple grinding blades, driven by the first motor, improve the aesthetics of the sign surface. Simultaneously, the grinding blades remove the adhesive layer from the sign surface, reducing unevenness. Furthermore, during polishing, the compaction rod increases the contact effect between the sign and the grinding blades, thereby enhancing the polishing effect and improving the adhesion of the subsequent paint spraying, thus increasing the visibility of the painted surface.

A vehicle violation detection method and vehicle violation detection system are provided. The method includes the following steps. A video clip including a plurality of consecutive frames is obtained, wherein the video clip is generated through photographing an intersection by an image capture device. A traffic sign object corresponding to a traffic sign and a license plate object corresponding to a license plate are detected from each of the frames. According to a sign position of the traffic sign object and a plate position of the license plate object in each of the frames, vehicle behavior information of each of the frames is obtained. By conducting regression analysis to the vehicle behavior information of each of the frames, whether a vehicle violation event has occurred is determined.

A flowable luminescent coating composition includes a curable thermoset resin, a filler material, two or more solvents, a plasticizer, a stabilizer, phosphorescent aluminate particles. The phosphorescent aluminate particles are present in the flowable luminescent coating composition at a concentration of 30 to 70 % by weight of the composition. The composition in a cured form has an intensity of glow of 1-50 candelas per square meter for a period of 0.1 to 2 hours upon excitation with ultraviolet light for 5 to 120 seconds. A glow-in-the-dark (GiD) film, a GiD traffic sign, and a GiD system.

The present disclosure relates to a computer-implemented method for processing and storing traffic sign inferences at the cloud server. It involves receiving a traffic sign inference from an edge device, which includes details such as the type, subtype, value, orientation, and location of the traffic sign. The cloud server maps the inference to a way or road ID based on the location, and determines if it meets predefined quality configurations. If met, the cloud server evaluates the number of similar sign detections on the same way ID, considering road coverage thresholds. The decision to store the inference, based on historical data, leads to the creation of a cluster for training a machine learning model.

A street sign authentication arrangement for a motor vehicle includes an RFID tag reader for reading information encrypted on a street sign encountered by the motor vehicle. An electronic processor is communicatively coupled to the RFID tag reader, and verifies, based on the information read from the street sign, that the information was encrypted by an authorized entity. The processor controls movement of the motor vehicle based on the information read from the street sign if the processor is able to verify that the information was encrypted by the authorized entity. The processor refrains from controlling movement of the motor vehicle based on the information read from the street sign if the processor is not able to verify that the information was encrypted by the authorized entity.

A method for providing a driver assistance system, the method is implemented using a driver assistance system (1) comprising a processor (14) and an image acquisition unit (11), the method comprising the following steps a) Control of the image acquisition unit (11) by the processor (14) to continuously acquire images of the vehicle's surroundings; b) Performing an image processing procedure by the processor (14) on at least one of the images captured by the image acquisition unit (11); c) Determine, by the processor (14), whether a traffic sign displaying a message has been detected in at least one of the images; d) if the finding in step c) is positive, determine, by the processor (14), whether additional information relating to the traffic sign is detected that indicates a state associated with the message; e) Determine, by the processor (14), whether an alarm action needs to be performed based on at least the message displayed by the traffic sign and a current state associated with the vehicle, the current state comprising a current time, current weather, movement of the vehicle or any combination thereof, and f) if the determination in step e) is positive, execution of the alarm action by the processor (14), characterized by, that the procedure between steps d) and e) further includes: g) if in at least one of the images in step c) a flat surface comprising a group of traffic signs is detected and additional information associated with one of the traffic signs is detected in relation to one of the traffic signs in step d), selection of one of the traffic signs as a traffic sign to be processed; where step e) is carried out in relation to the traffic sign to be processed, and that step g) further includes: Select one of the traffic signs with the additional information as the primary traffic sign; Determine whether at least part of the current state matches at least part of the future state; If the assessment is positive, carry out step e) with regard to the primary traffic sign that serves as the traffic sign to be processed; and If the finding is negative, carry out step e) with regard to the other traffic sign that serves as the traffic sign to be processed.