Traffic sign identification method and device based on digital twinning

Abstract

The invention provides a traffic sign recognition method and device based on digital twinning, and relates to the technical field of traffic sign recognition, and the method comprises the steps: firstly collecting traffic sign data and environment data in a vehicle driving process in real time, and then inputting the data into a pre-established digital twinning model for precise analysis. Through analysis, information such as the type and the position of the traffic sign can be obtained. And finally, pushing the traffic sign information in the analysis result to the user to assist the user in making a correct driving decision. According to the method, the advantages of the digital twinning technology are combined, the accuracy and reliability of traffic sign recognition are improved, and a new idea is provided for the development of the intelligent traffic field.

Description

Technical Field

[0001] This application relates to the technical field of traffic sign recognition, and particularly to a traffic sign recognition method and device based on digital twin. Background Art

[0002] In recent years, with the development of autonomous driving technology, the research on detecting and recognizing targets such as road defects, pedestrians, and traffic signs in autonomous driving scenarios has increased. However, in the field of autonomous driving, the recognition of traffic signs also plays an important role. Its detection effect is directly related to the driving decision of intelligent connected vehicles. Accurately recognizing and positioning it can provide rich information for intelligent vehicles and ensure the safe driving of vehicles. Therefore, the research on the detection and recognition of traffic signs is of great significance.

[0003] Existing traffic sign recognition methods are generally divided into two categories: one is based on traditional methods, such as extreme learning machines, support vector machines, etc. These methods usually rely on manually extracted features, which may lead to the loss of important information. In addition, when traffic signs are blocked, the recognition effect of traditional methods is poor. The other is based on deep learning methods, such as convolutional neural networks, etc., which achieve traffic sign recognition through the training of a large amount of data. Although this method performs well in experiments, it still faces time and space limitations in actual applications. As the scale and depth of the network increase, the required resources increase exponentially, while the computing power and storage space of in-vehicle devices or wearable devices often cannot meet the needs of these complex networks. Therefore, how to improve the accuracy of traffic sign recognition, provide timely warnings and guidance for drivers, and at the same time reduce the complexity of the algorithm has become an urgent problem to be solved. Summary of the Invention

[0004] In view of the above problems, this application provides a traffic sign recognition method based on digital twin, including the following:

[0005] In a first aspect, this application provides a traffic sign recognition method based on digital twin, which includes:

[0006] Collect traffic sign data and environmental data in the environmental data during the vehicle driving process in real time;

[0007] Input the collected traffic sign data and environmental data into a pre-established digital twin model, and analyze the traffic sign data according to the characteristics of the traffic sign data and the environmental data;

[0008] Push the traffic sign information in the analysis result to the user.

[0009] Optionally, the establishment process of the digital twin model includes:

[0010] Collect data related to traffic signs from the real world, where the data related to traffic signs includes image data, location data, environmental data, and traffic flow data related to traffic signs;

[0011] Clean and standardize the collected data;

[0012] Based on the processed data, construct a digital twin model of traffic signs and the dynamic environment corresponding to the traffic signs.

[0013] Optionally, the analysis of the traffic sign data according to the characteristics of the traffic sign data and the environmental data includes:

[0014] Analyze the traffic sign data at the current moment according to the characteristics of the traffic sign data and the environmental data to obtain the traffic sign data at the current moment;

[0015] And / or predict the traffic data signs at a future moment based on the characteristics of the traffic sign data and the environmental data.

[0016] Optionally, the real-time collection of traffic sign data and environmental data in the environmental data during vehicle driving includes:

[0017] Through data collection devices such as cameras and sensors installed on the vehicle, real-time capture the traffic sign images and relevant environmental data encountered during vehicle driving.

[0018] Optionally, when inputting the collected traffic sign data and environmental data into a pre-established digital twin model and analyzing the traffic sign data according to the characteristics of the traffic sign data and the environmental data, different recognition algorithms are used for analysis and processing according to different characteristics of the traffic sign data and the environmental data.

[0019] Optionally, before pushing the traffic sign information in the analysis result to the user, the method further includes:

[0020] Evaluate the analysis result based on preset evaluation performance indicators.

[0021] In a second aspect, the present application provides a traffic sign recognition device based on digital twins, and the device includes:

[0022] A data collection unit for real-time collecting traffic sign data and environmental data in the environmental data during vehicle driving;

[0023] A data processing unit for inputting the collected traffic sign data and environmental data into a pre-established digital twin model and analyzing the traffic sign data according to the characteristics of the traffic sign data and the environmental data;

[0024] An information push unit for pushing the traffic sign information in the analysis result to the user.

[0025] Optionally, the device further includes a model establishment unit for establishing the digital twin model;

[0026] The model establishment unit specifically includes:

[0027] A data acquisition subunit for acquiring data related to traffic signs from the real world, where the data related to traffic signs includes image data, position data, environmental data, and traffic flow data related to traffic signs of traffic signs;

[0028] A data processing subunit for cleaning and standardizing the collected data;

[0029] A construction subunit for constructing a digital twin model of traffic signs and the dynamic environment corresponding to traffic signs based on the processed data.

[0030] Optionally, the data processing unit analyzes the traffic sign data according to the characteristics of the traffic sign data and the environmental data, including:

[0031] Analyzing the traffic sign data at the current moment according to the characteristics of the traffic sign data and the environmental data to obtain the traffic sign data at the current moment;

[0032] And / or predicting the traffic data signs at a future moment based on the characteristics of the traffic sign data and the environmental data.

[0033] Optionally, the data acquisition unit real-time acquires traffic sign data and environmental data in the environmental data during vehicle driving, including:

[0034] By data acquisition devices such as cameras and sensors installed on the vehicle, real-time capturing traffic sign images and related environmental data encountered during vehicle driving.

[0035] Optionally, the data processing unit specifically uses different recognition algorithms for analysis and processing according to the characteristics of different traffic sign data and the environmental data.

[0036] Optionally, the device further includes an evaluation unit for evaluating the analysis result based on preset evaluation performance indicators before pushing the traffic sign information in the analysis result to the user.

[0037] In a third aspect, the present application provides a device, which includes a memory and a processor. The memory is used to store instructions or codes, and the processor is used to execute the instructions or codes so that the device performs the digital-twin-based traffic sign recognition method introduced in any implementation manner of the foregoing first aspect.

[0038] In a fourth aspect, the present application provides a computer-readable storage medium, in which codes are stored. When the codes are run, the device running the codes implements the digital-twin-based traffic sign recognition method introduced in any implementation manner of the foregoing first aspect.

[0039] The present application provides a digital-twin-based traffic sign recognition method. This method collects traffic sign data and environmental data during vehicle driving in real time and inputs them into a pre-established digital twin model for analysis. By leveraging the characteristics of the digital twin model, accurate recognition of traffic signs is achieved. This method not only improves the accuracy and reliability of traffic sign recognition but also can dynamically adjust the recognition results of traffic signs according to changes in environmental data, thus better adapting to complex traffic environments. In addition, pushing the traffic sign information in the analysis results to users in a timely manner helps users make correct driving decisions and improves driving safety. In short, this method provides a new and effective means of traffic sign recognition for the field of intelligent transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] To more clearly illustrate the technical solutions in the embodiments or the prior art, the following briefly introduces the drawings required for the description of the embodiments or the prior art. Obviously, the following-described drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0041] Figure 1 It is a flowchart of a digital-twin-based traffic sign recognition method provided by an embodiment of the present application;

[0042] Figure 2 It is a schematic structural diagram of a digital-twin-based traffic sign recognition device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the following will clearly and completely describe the technical solutions in the embodiments of this application with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts shall fall within the scope of protection of this application.

[0044] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data that have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions.

[0045] Figure 1 This is a flowchart of a traffic sign recognition method based on digital twin provided by an embodiment of this application. In combination with Figure 1 As shown, the traffic sign recognition method based on digital twin provided by an embodiment of this application may include:

[0046] S101. Real-time collect traffic sign data and environmental data in the environmental data during vehicle driving.

[0047] Traffic sign data refers to the images or recognition results of signs on the road that convey traffic information, such as mandatory, prohibited, and dangerous information. These signs usually use characters, symbols, and colors to convey information, such as speed limit signs, no left turn signs, etc.

[0048] Environmental data refers to various information about the surrounding environment during vehicle driving, which may include but not be limited to weather conditions, light conditions, road surface conditions, the positions and speeds of other vehicles, pedestrian dynamics, etc.

[0049] In this application, through real-time collection, the collection of data is realized. The specific data collection methods include collection through cameras: The cameras installed on the vehicle can capture the traffic sign images on the road, and these images can then be recognized and analyzed to extract the specific information of the traffic signs. Collection through sensors: In addition to cameras, the vehicle may also be equipped with various sensors, such as radar, lidar (LiDAR), ultrasonic sensors, etc. These sensors can collect data about the surrounding environment of the vehicle, such as distance, speed, direction, etc.

[0050] In one implementation of the embodiment of the present application, real-time collection is completed by data collection devices such as cameras and sensors installed on the vehicle. These devices can capture traffic sign images and relevant environmental data encountered during the vehicle's driving in real time, providing a basis for subsequent data processing and analysis. After the data is collected, the collected real-time data is transmitted to the cloud or edge computing device through a wireless network for storage and processing. During the data transmission process, it is necessary to ensure the integrity and security of the data to avoid data loss or being tampered with. In addition, these data collection devices need to have high-precision and high-frequency data collection capabilities to ensure that the detailed information of traffic signs can be accurately captured.

[0051] S102. Input the collected traffic sign data and environmental data into a pre-established digital twin model, and analyze the traffic sign data according to the characteristics of the traffic sign data and the environmental data.

[0052] The digital twin model is a model established using digital twin technology. Digital twin technology is a technical means that creates a virtual representation of a physical entity in a digital way and uses historical data, real-time data, and algorithm models, etc., to simulate, verify, predict, and control the behavior and performance of the physical entity during its entire life cycle. In this application, the digital twin model can simultaneously process and analyze the changes and characteristics of traffic signs in time and space. Specifically, the time characteristics mean that the system can use historical data and real-time data to track the state changes of traffic signs at different time periods. For example, some traffic signs may change or be temporarily invalid during a specific time period, and the system needs to be able to identify these temporal changes to ensure that drivers can obtain accurate traffic rule guidance at different times. Spatial characteristics: It can identify the position and distribution of traffic signs in space, which helps to accurately identify and understand the indication intention of traffic signs in complex traffic scenarios, such as multi-lane intersections or construction sections.

[0053] Before inputting the collected traffic sign data and environmental data into the pre-established digital twin model, it is also necessary to perform analysis and processing on the traffic sign data. This process involves preprocessing the collected data and feature extraction and analysis. The quality and usability of the data are improved through preprocessing operations such as removing noise, correcting image distortion, and adjusting the image size. This step is one of the key steps to improve the recognition accuracy. Feature information of traffic signs, such as color, shape, pattern, etc., is extracted from the preprocessed data. Traditional image processing algorithms or deep learning algorithms can be used for feature extraction and analyze this feature information to determine the type and meaning of traffic signs, providing a basis for subsequent recognition.

[0054] In an implementation of the embodiment of the present application, analyzing the traffic sign data according to the characteristics of the traffic sign data and the environmental data includes:

[0055] Analyze the traffic sign data at the current moment according to the characteristics of the traffic sign data and the environmental data to obtain the traffic sign data at the current moment; and / or predict the traffic sign data at a certain moment in the future based on the characteristics of the traffic sign data and the environmental data.

[0056] In order to analyze the traffic sign data at the current moment according to the characteristics of the traffic sign data and the environmental data to obtain the traffic sign data at the current moment, it is necessary to analyze the traffic sign at the current moment based on the real-time collected traffic sign data such as the type, location, color, etc. of the sign, and environmental data such as weather, light, surrounding vehicle conditions, etc. By identifying the specific meaning of the traffic sign, such as the speed limit, whether turning is prohibited, etc., and considering the impact of environmental factors on the interpretation of the sign, such as rainy days may cause the sign to be blurred, and at night it may be necessary to adjust the exposure of the camera to clearly capture the sign. The analysis results will directly reflect the traffic sign data at the current moment, which is crucial for the immediate response of vehicle navigation and driving assistance systems.

[0057] For predicting traffic signs at a certain moment in the future based on the characteristics of traffic sign data and environmental data, this step uses historical data and real-time data to predict future traffic conditions. Specifically, by analyzing the characteristics of traffic sign data such as the periodic changes of signs, such as the speed limit difference between weekdays and weekends, and the trend of environmental data such as the weather forecast showing that it is about to rain, which may affect the road conditions, the traffic sign data at a certain moment in the future can be predicted. This kind of prediction is of great significance for planning routes in advance, adjusting driving strategies, etc., especially in autonomous driving systems, where the prediction ability can significantly improve safety and efficiency.

[0058] In order to more effectively respond to the challenges of traffic sign recognition when vehicles are driving in different environments, the embodiments of the present application propose a method for flexibly selecting different recognition algorithms for data analysis based on the specific characteristics of the traffic signs and the application scenarios in which they are located.

[0059] In one implementation of the embodiment of the present application, the collected traffic sign data and environmental data are input into a pre-established digital twin model. When analyzing the traffic sign data according to the characteristics of the traffic sign data and the environmental data, different recognition algorithms are used for analysis and processing according to the characteristics of different traffic sign data and the environmental data. Specifically, according to the characteristics and application scenarios of the traffic sign, a suitable recognition algorithm is selected, and algorithms such as convolutional neural networks and graph reinforcement learning can be used. The following are several examples of corresponding algorithms used in different driving environments:

[0060] 1. Highway scenario: A simple Convolutional Neural Network (CNN) can be adopted because the data volume is large and the labels are clear, making it easy to train an accurate model.

[0061] 2. Night and adverse weather scenarios: Since the visibility of traffic signs is low and the image quality is poor in this scenario. A method combining traditional image processing techniques and deep learning can be used. For example, first use image enhancement techniques (such as histogram equalization) to improve the image quality, and then use a deep learning model for recognition.

[0062] 3. Construction area scenario: Since the traffic signs in the construction area often change and there may be temporary signs, Graph Reinforcement Learning or other dynamic learning methods can be adopted. These methods can make adaptive adjustments according to real-time changing data and improve the robustness of recognition.

[0063] S103. Push the traffic sign information in the analysis result to the user.

[0064] After completing the recognition and analysis of traffic signs, push the recognized traffic sign information such as type, location, meaning, etc. to the user so that the user can timely understand the road conditions and make correct driving decisions. This step is usually achieved through channels such as in-vehicle terminals and mobile APPs. In addition, in order to quantify and subsequently improve the performance of the traffic sign recognition algorithm, a series of evaluation metrics need to be defined, including but not limited to accuracy, recall rate, F1 score, etc. Evaluating the analysis result according to these evaluation metrics can find out the problems and deficiencies in the recognition process and provide a basis for subsequent algorithm optimization. That is, before pushing the traffic sign information in the analysis result to the user, evaluate the analysis result based on the preset evaluation performance metrics. This can ensure that the information pushed to the user has been strictly verified and evaluated, improving the accuracy and reliability of the information. Further, the evaluation result and analysis content can be sorted into a detailed analysis report. The report content includes but not limited to information such as the performance metrics of the traffic sign recognition scheme, recognition accuracy, and reasons for misrecognition.

[0065] The above embodiments introduce the traffic sign recognition method based on digital twin. Next, the construction process of the digital twin model in the above process will be introduced:

[0066] Collect data related to traffic signs from the real world. The data related to traffic signs includes image data, location data, environmental data, and traffic flow data related to traffic signs; clean and standardize the collected data; based on the processed data, construct a digital twin model of traffic signs and the dynamic environment corresponding to traffic signs.

[0067] Collecting real-world data refers to collecting various data related to traffic signs from the real world using high-precision map data and other means, including but not limited to image data, location data, environmental data (such as weather, lighting, etc.) of traffic signs, and traffic flow data related to traffic signs. These data can be obtained through various channels such as in-vehicle cameras, sensors, and traffic monitoring cameras. The digital twin model is an accurate mapping of traffic signs in the virtual world, which needs to cover the physical attributes, spatio-temporal states, and environmental correlation data of traffic signs, and be deeply integrated with the road scene where they are located. All relevant information such as the appearance features, location information, and environmental factors of traffic signs is included in this model. The digital twin model can simulate the performance of traffic signs in different environments, providing a basis for subsequent recognition and analysis. In addition, the digital twin model can simulate and predict the state of traffic signs. By using historical data and combining with real-time traffic flow related to traffic signs, it can predict the state of traffic signs in certain environments for a period of time in the future, providing more accurate data support for traffic sign recognition.

[0068] The traffic sign recognition method based on digital twin in the above embodiments of this application has the following advantages:

[0069] (1) Model establishment and optimization: By establishing a high-precision digital twin model, covering detailed information of traffic signs and their surrounding environments. Through multi-modal data fusion, ensure that the model has high robustness and accuracy. In the digital twin environment, conduct model training and optimization to ensure the recognition ability of the model in complex environments.

[0070] (2) Real-time data collection and processing: Use the digital twin model to collect and process real-time traffic sign data, ensuring the real-time and accuracy of the data. Through multi-modal data fusion, supplement and predict the state of traffic signs, especially when traffic signs are blocked.

[0071] (3) Model deployment and inference: Deploy the optimized model to in-vehicle devices or other terminal devices to achieve efficient traffic sign recognition. Through the digital twin model, achieve hierarchical deployment and optimization of the model, reducing the computing and storage burden.

[0072] The above are some specific implementation methods of a traffic sign recognition method based on digital twin provided by the embodiments of this application. Based on this, this application also provides a corresponding device. Next, the device provided by the embodiments of this application will be introduced from the perspective of functional modularization.

[0073] Figure 2 It is a schematic structural diagram of a traffic sign recognition device based on digital twin provided by the embodiments of this application. Combined with Figure 2As shown in the figure, the traffic sign recognition device 200 based on digital twin provided by the embodiment of the present application includes:

[0074] A data acquisition unit 210, configured to acquire traffic sign data and environmental data in the environmental data during vehicle driving in real time;

[0075] A data processing unit 220, configured to input the acquired traffic sign data and environmental data into a pre-established digital twin model, and analyze the traffic sign data according to the characteristics of the traffic sign data and the environmental data;

[0076] An information push unit 230, configured to push the traffic sign information in the analysis result to the user.

[0077] In an implementation manner of the embodiment of the present application, the device further includes a model establishment unit, configured to establish the digital twin model;

[0078] The model establishment unit specifically includes:

[0079] A data acquisition subunit, configured to acquire data related to traffic signs from the real world, where the data related to traffic signs includes image data, position data, environmental data, and traffic flow data related to traffic signs of traffic signs;

[0080] A data processing subunit, configured to clean and standardize the collected data;

[0081] A construction subunit, configured to construct a digital twin model of traffic signs and the dynamic environment corresponding to the traffic signs based on the processed data.

[0082] In an implementation manner of the embodiment of the present application, the data processing unit analyzes the traffic sign data according to the characteristics of the traffic sign data and the environmental data, including:

[0083] Analyzing the traffic sign data at the current moment according to the characteristics of the traffic sign data and the environmental data to obtain the traffic sign data at the current moment;

[0084] And / or predicting the traffic data sign at a future moment based on the characteristics of the traffic sign data and the environmental data.

[0085] In an implementation manner of the embodiment of the present application, the data acquisition unit acquires traffic sign data and environmental data in the environmental data during vehicle driving in real time, including:

[0086] By using data acquisition devices such as cameras and sensors installed on the vehicle, capturing traffic sign images and related environmental data encountered during vehicle driving in real time.

[0087] In an implementation manner of the embodiment of the present application, the data processing unit is specifically configured to perform analysis and processing by using different recognition algorithms according to the characteristics of different traffic sign data and the environmental data.

[0088] In an implementation manner of the embodiment of the present application, the device further includes an evaluation unit, configured to evaluate the analysis result based on a preset evaluation performance index before pushing the traffic sign information in the analysis result to the user.

[0089] The embodiment of the present application further provides a corresponding device and a computer storage medium for implementing the solution provided by the embodiment of the present application.

[0090] Wherein, the device includes a memory and a processor, the memory is used to store instructions or codes, and the processor is used to execute the instructions or codes so that the device executes the method described in any embodiment of the present application.

[0091] The computer storage medium stores codes, and when the codes are run, the device running the codes implements the method described in any embodiment of the present application.

[0092] From the description of the above embodiments, those skilled in the art can clearly understand that all or part of the steps in the above embodiment methods can be implemented by means of software plus a general hardware platform. Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product, and the computer software product can be stored in a storage medium, such as a read-only memory (ROM) / RAM, magnetic disk, optical disk, etc., including several instructions for causing a computer device (which can be a personal computer, a server, or a network communication device such as a router) to execute the methods described in each embodiment or some parts of the embodiments of the present application.

[0093] It can be understood that in the specific implementation manner of the present application, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved need to obtain user permission or consent when the above embodiments of the present application are applied to specific products or technologies, and the collection, use, and processing of relevant data need to comply with relevant laws, regulations, and standards of relevant countries and regions.

[0094] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent in such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the said element.

[0095] It should also be noted that the various embodiments in this specification are described in a progressive manner. For the parts that are the same or similar among the various embodiments, reference can be made to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the device and apparatus, since they are basically similar to the method embodiments, the description is relatively simple, and for the relevant parts, reference can be made to the partial description of the method embodiments. The device and apparatus embodiments described above are only illustrative. The units described as separate components may or may not be physically separated, and the components referred to as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0096] As described above, this is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed in the present application should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A traffic sign recognition method based on digital twin, characterized in that The method includes: Real-time collecting traffic sign data and environmental data in the environmental data during vehicle driving; Inputting the collected traffic sign data and environmental data into a pre-established digital twin model, and analyzing the traffic sign data according to the characteristics of the traffic sign data and the environmental data; Pushing the traffic sign information in the analysis result to the user.

2. The method according to claim 1, wherein The process of establishing the digital twin model includes: Collecting data related to traffic signs from the real world, where the data related to traffic signs includes image data, location data, environmental data of traffic signs, and traffic flow data related to traffic signs; Cleaning and standardizing the collected data; Based on the processed data, constructing a digital twin model of traffic signs and the dynamic environment corresponding to the traffic signs.

3. The method according to claim 1, wherein The analyzing the traffic sign data according to the characteristics of the traffic sign data and the environmental data includes: Analyzing the traffic sign data at the current moment according to the characteristics of the traffic sign data and the environmental data to obtain the traffic sign data at the current moment; And / or predicting the traffic data signs at a future moment based on the characteristics of the traffic sign data and the environmental data.

4. The method according to claim 1, characterized in that The real-time collecting traffic sign data and environmental data in the environmental data during vehicle driving includes: Through data collection devices such as cameras and sensors installed on the vehicle, real-time capturing traffic sign images and related environmental data encountered during vehicle driving.

5. The method according to claim 1, wherein When inputting the collected traffic sign data and environmental data into a pre-established digital twin model and analyzing the traffic sign data according to the characteristics of the traffic sign data and the environmental data, different recognition algorithms are used for analysis and processing according to the characteristics of different traffic sign data and the environmental data.

6. The method according to claim 1, wherein Before pushing the traffic sign information in the analysis result to the user, the method further includes: Evaluating the analysis result based on preset evaluation performance indicators.

7. A traffic sign recognition device based on digital twin, characterized in that, The device includes: A data collection unit for real-time collecting traffic sign data and environmental data in the environmental data during vehicle driving; A data processing unit for inputting the collected traffic sign data and environmental data into a pre-established digital twin model, and analyzing the traffic sign data according to the characteristics of the traffic sign data and the environmental data; An information push unit for pushing the traffic sign information in the analysis result to the user.

8. The device according to claim 7, characterized in that, The device further includes a model establishment unit for establishing the digital twin model; The model establishment unit specifically includes: A data collection sub-unit for collecting data related to traffic signs from the real world, where the data related to traffic signs includes image data, location data, environmental data of traffic signs, and traffic flow data related to traffic signs; A data processing sub-unit for cleaning and standardizing the collected data; A construction sub-unit for constructing a digital twin model of traffic signs and the dynamic environment corresponding to the traffic signs based on the processed data.

9. A computing device, characterized in that, The computing device includes: a memory, a processor; The memory is used for storing computer programs; The processor is configured to implement the method according to any one of claims 1 to 6 when executing the computer program.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and the method according to any one of claims 1 to 6 is implemented when the computer program is executed by a processor.

Images