A road sign recognition method, device, vehicle and storage medium

Abstract

Embodiments of the present application provide a road sign recognition method and device, a vehicle and a storage medium. The method comprises: acquiring a road environment image captured by an image acquisition device in real time and vehicle position information collected by a positioning sensor in real time; extracting a to-be-recognized road sign contained in the road environment image and determining whether the to-be-recognized road sign meets a preset determination condition; if the to-be-recognized road sign meets the preset determination condition, taking the meaning and type of a known road sign matched with the to-be-recognized road sign as a target recognition result of the to-be-recognized road sign; and if the to-be-recognized road sign does not meet the preset determination condition, determining the target recognition result of the to-be-recognized road sign according to the to-be-recognized road sign and the vehicle position information and combining a pre-trained visual language model. With the method, the visual language model is used to process the road signs that are not common, and the recognition of the road signs that are not common is realized, thereby providing a guarantee for the safe driving of the autonomous vehicle.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a road sign recognition method, device, vehicle, and storage medium. Background Technology

[0002] Different countries have different road signs, and uncommon road signs and their meanings can be confusing and easily confused, making driving in other countries potentially challenging. Autonomous and semi-autonomous vehicles may struggle to recognize unfamiliar road signs because they haven't been pre-trained with machine language algorithms. When these uncommon road signs appear, semi-autonomous vehicles should transfer control to the driver. However, drivers may also need to rely on tools like Google Maps for recognition, and this reliance on external resources can introduce interference and increase the risk of accidents. In the case of fully autonomous vehicles without a driver, they must stop when encountering such unfamiliar road signs, potentially causing traffic disruptions and inconvenience to other road users. Therefore, a method is needed to solve the problem of recognizing uncommon road signs. Summary of the Invention

[0003] This invention provides a road sign recognition method, device, vehicle, and storage medium, enabling the recognition of uncommon road signs.

[0004] Firstly, this embodiment provides a road sign recognition method, which includes:

[0005] The system acquires real-time images of the road environment captured by the image acquisition device and real-time vehicle location information collected by the positioning sensor.

[0006] Extract the road signs to be identified contained in the road environment image, and determine whether the road signs to be identified meet the preset judgment conditions. The preset judgment conditions are that the road signs to be identified match the known road signs and the confidence level is greater than or equal to the set confidence level threshold.

[0007] If the preset judgment condition is met, the meaning and type of the known road sign that matches the road sign to be identified will be used as the target identification result of the road sign to be identified.

[0008] If the preset judgment conditions are not met, the target recognition result of the road sign to be recognized is determined based on the road sign to be recognized and the vehicle location information, combined with the pre-trained visual language model.

[0009] Secondly, this embodiment provides a road sign recognition device, which includes:

[0010] The image acquisition module is used to acquire real-time road environment images captured by the image acquisition device and real-time vehicle position information collected by the positioning sensor.

[0011] The judgment module is used to extract the road signs to be identified contained in the road environment image and determine whether the road signs to be identified meet the preset judgment conditions. The preset judgment conditions are that the road signs to be identified match the known road signs and the confidence level is greater than or equal to the set confidence level threshold.

[0012] The first determining module is used to, if the preset judgment condition is met, take the meaning and type of a known road sign that matches the road sign to be identified as the target identification result of the road sign to be identified;

[0013] The second determining module is used to determine the target recognition result of the road sign to be recognized based on the road sign to be recognized and the vehicle location information, combined with a pre-trained visual language model, if the preset judgment conditions are not met.

[0014] Thirdly, this embodiment provides a vehicle, including:

[0015] Vehicle body;

[0016] An image acquisition device and a positioning sensor are respectively installed on the vehicle body;

[0017] The controller is communicatively connected to the image acquisition device and the positioning sensor, and the controller includes:

[0018] At least one processor; and

[0019] A memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the road sign recognition method according to any embodiment of the present invention.

[0021] Fourthly, this embodiment provides a computer-readable storage medium, wherein the computer program is executed by the at least one processor to enable the at least one processor to perform the road sign recognition method according to any embodiment of the present invention.

[0022] This invention provides a road sign recognition method, device, vehicle, and storage medium. The method includes: first, acquiring a road environment image captured in real time by an image acquisition device and vehicle location information collected in real time by a positioning sensor; then, extracting the road signs to be recognized contained in the road environment image and determining whether the road signs to be recognized meet a preset judgment condition, wherein the preset judgment condition is that the road signs to be recognized match known road signs and the confidence level is greater than or equal to a set confidence level threshold; if the preset judgment condition is met, the meaning and type of the known road signs that match the road signs to be recognized are used as the target recognition result of the road signs to be recognized; if the preset judgment condition is not met, the target recognition result of the road signs to be recognized is determined based on the road signs to be recognized and the vehicle location information, combined with a pre-trained visual language model. The above technical solution captures road environment images in real time during vehicle operation to detect road signs. If the detected road sign is a known road sign, its meaning and type can be directly obtained. If the detected road sign is an uncommon road sign, it can be processed using the natural language processing function of a visual language model. Based on the processing results of the visual language model, the road sign is classified to obtain its meaning and type. This provides a control basis for autonomous or semi-autonomous vehicles, improves driving safety, and has significant practical value.

[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1a This is a flowchart illustrating a road sign recognition method provided in Embodiment 1 of the present invention;

[0026] Figure 1b Here are some example images of uncommon road signs;

[0027] Figure 2a This is a flowchart illustrating another road sign recognition method provided in Embodiment 2 of the present invention;

[0028] Figure 2b This is an example diagram of an uncommon road sign in a road sign recognition method provided in Embodiment 2 of the present invention;

[0029] Figure 2c This is a flowchart illustrating the execution of a road sign recognition method in a specific application scenario according to Embodiment 2 of the present invention.

[0030] Figure 3 This is a schematic diagram of the structure of a road sign recognition device provided in Embodiment 3 of the present invention;

[0031] Figure 4 This is a structural schematic diagram of a vehicle provided in Embodiment 4 of the present invention. Detailed Implementation

[0032] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "original," "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0034] Example 1

[0035] Figure 1a This is a flowchart illustrating a road sign recognition method provided in Embodiment 1 of the present invention. This method is applicable to the automatic recognition of uncommon road signs. The method can be executed by a road sign recognition device, which can be implemented in hardware and / or software and is generally integrated into a vehicle.

[0036] Different countries have different road signs, and some signs are not commonly seen. For example, Figure 1b Here are some example images of uncommon road signs, such as Figure 1bAs shown, these road signs represent camel crossing, no-transportation, no-overtaking, steep cliff, and blind mountain signs, respectively. These road signs are uncommon in different regions because they haven't been pre-trained to be recognized. Therefore, when autonomous or semi-autonomous vehicles encounter these signs, their machine language algorithms may not be able to recognize them. When these uncommon signs appear, semi-autonomous vehicles should transfer control to the driver. However, even the driver may not be familiar with the meaning of the road signs and need to rely on tools such as search engines for identification. This reliance on external resources can be distracting and increase the risk of accidents. For fully autonomous vehicles without a driver, they must stop when encountering such unfamiliar road signs, which may cause traffic disruptions and inconvenience other road users.

[0037] Based on this, this embodiment provides a road sign recognition method, offering a solution based on a Visual Language Model (VLM) that can recognize unexpected and uncommon road signs on the road. This capability is valuable for autonomous and semi-autonomous vehicles, enabling them to react appropriately to unexpected road conditions.

[0038] like Figure 1a As shown, the road sign recognition method provided in this embodiment may specifically include the following steps:

[0039] S101. Acquire real-time road environment images captured by the image acquisition device and real-time vehicle position information collected by the positioning sensor.

[0040] The application scenario of this embodiment can be described as follows: During vehicle operation, images of the current road environment are acquired in real time, and road signs within the environment are identified. Based on the identified road signs, appropriate vehicle control is implemented. The vehicle is equipped with image acquisition devices, such as cameras and video recording equipment, as well as positioning sensors, such as those using the Global Positioning System (GPS). During vehicle operation, the image acquisition devices capture images of the road environment in real time, and these captured images are recorded as road environment images. Simultaneously, the positioning sensors can locate the vehicle in real time, and the obtained positioning information is recorded as vehicle position information. The road environment images and vehicle position information serve as the foundational data for subsequent road sign recognition.

[0041] S102. Extract the road signs to be identified contained in the road environment image and determine whether the road signs to be identified meet the preset judgment conditions.

[0042] The preset judgment condition is that the road sign to be identified matches a known road sign and the confidence level is greater than or equal to the set confidence level threshold.

[0043] In this embodiment, after acquiring a road environment image, a pre-trained object detection model can be used to detect potential objects within the image and determine whether any of these potential objects contain road signs. If the road environment image does not contain road signs, the road sign recognition method is not required. If the road environment image contains road signs, these signs are used as the road signs to be identified, and further identification is performed on them.

[0044] Following the above description, when it is determined that a road sign is present in the road environment image, the road sign to be identified is extracted from the image, and it is further determined whether the road sign to be identified is a pre-stored known road sign. Specifically, the features of the road sign to be identified are matched with the features of pre-stored known road signs. If a match is found, the confidence level of the road sign to be identified is further determined. That is, based on the matching between the extracted features of the road sign to be identified and the features of known road signs, the confidence level of the road sign to be identified is calculated. It can be considered that the better the match between the road sign to be identified and the known road signs, the higher the confidence level; the lower the match between the road sign to be identified and the known road signs, the lower the confidence level. When the road sign to be identified matches a known road sign, and the confidence level is greater than or equal to a set confidence threshold, the road sign to be identified is considered to meet the preset judgment conditions. If the features of the road sign to be identified do not match the features of the pre-stored known road signs, or if the features of the road sign to be identified match the features of the pre-stored known road signs but the set channel is less than the preset confidence threshold, then the road sign to be identified is considered not to meet the preset judgment conditions and further identification of the road sign to be identified is required.

[0045] S103. If the preset judgment conditions are met, the meaning and type of the known road sign that matches the road sign to be identified will be used as the target recognition result of the road sign to be identified.

[0046] Specifically, if the road sign to be identified meets the preset judgment conditions, the meaning and type of the known road sign that matches the road sign to be identified will be used as the target meaning and target type of the road sign to be identified, and the target meaning and target type will be used as the target identification result of the road sign to be identified.

[0047] S104. If the preset judgment conditions are not met, the target recognition result of the road sign to be recognized is determined based on the road sign to be recognized and the vehicle position information, combined with the pre-trained visual language model.

[0048] In this embodiment, when it is determined that the road sign to be identified does not meet the preset judgment conditions, further identification of the road sign is required. This embodiment uses a visual language model to identify the road sign, obtaining its meaning and type, which serves as the target identification result. For example, the type of road sign can be a stop sign, a speed limit sign, etc., and its meaning can be "No parking" or "No exceeding 50 km / h," etc. There are no specific limitations on the type and meaning of the road sign here. The visual language model refers to an artificial intelligence model that integrates text understanding and visual perception. These models aim to process and generate content involving text and images, realizing tasks such as image captioning, visual question answering, and generating descriptions from visual input. In this embodiment, a visual language model can be used to process and understand textual information related to road signs. For example, processing the textual description of a sign or combining it with contextual information from natural language can enhance the overall understanding of the driving environment. Furthermore, understanding the road layout, weather conditions, or specific driving situations described in natural language helps in better identifying signs.

[0049] The process of determining the target recognition result of the road sign to be recognized based on the pre-trained visual language model can be described as follows: extract the text information, symbol information and road sign color of the road sign to be recognized; interpret the road sign information based on the visual language model to obtain the interpretation text of the road sign to be recognized; perform post-processing on the interpretation text of the road sign to be recognized to obtain the post-processed interpretation text; and determine the target recognition result of the road sign to be recognized based on the post-processed interpretation text and vehicle position information.

[0050] For example, continue to refer to Figure 1a For Figure 1a The first road sign in the image was processed using a visual language model, resulting in the following text explanation: This image shows a road sign with a silhouette of a camel, indicating that a camel may be crossing the road in this area. When you see this sign, you should be careful, slow down, and pay attention to any camels that may be crossing the road to avoid accidents. The presence of a real camel in the background reinforces the warning in this area. Further, the road sign can be categorized based on the explanatory text to determine its meaning and type.

[0051] Understandably, adopting this technology can enhance safety: Accurate identification of uncommon road signs helps autonomous or semi-autonomous vehicles respond appropriately to unique traffic situations. It also helps avoid traffic violations: Identifying and understanding uncommon road signs enables vehicles to comply with traffic rules and regulations, reducing the risk of traffic violations and related legal consequences. Furthermore, it facilitates efficient traffic flow: Correctly identifying uncommon road signs allows vehicles to make informed decisions, contributing to smoother traffic flow, reducing congestion, and improving the overall transportation system. Accident prevention: Uncommon road signs may indicate potential hazards or changes in road conditions; timely identification of these signs allows vehicles to take preventative measures, reducing the likelihood of accidents. Adapting to different environments: Different regions may have unique road signs that are unfamiliar to vehicles not accustomed to these areas; identifying uncommon signs allows vehicles to seamlessly adapt to different environments. Improved navigation: Autonomous vehicles capable of identifying uncommon road signs can enhance navigation capabilities. This ensures accurate route planning and minimizes the risk of getting lost or taking the wrong route. Reliable identification of various road signs helps build public trust in autonomous and semi-autonomous vehicle technologies, which is crucial for their widespread acceptance and adoption. Reduced reliance on human intervention: Because they can recognize less common road signs, autonomous vehicles can operate more independently, reducing the frequency of human driver intervention. This contributes to a smoother, more seamless autonomous driving experience. Global compatibility: Visual language models can be trained on diverse datasets, making them more adaptable to different regions and their unique road sign variations. This global compatibility benefits autonomous vehicles operating in different geographical locations. Reduced reliance on pre-programming: Visual language models reduce the need for extensive pre-programming of specific road sign features. Their ability to understand natural language allows for a more flexible and adaptive approach to recognizing a wide variety of signs. Improved generalization: Visual language models have the potential to generalize their understanding of road signs, making them more powerful in recognizing variations or unexpected elements in different driving scenarios.

[0052] This invention provides a road sign recognition method. During vehicle operation, road environment images are captured in real time for road sign detection. If the detected road sign is a known road sign, its meaning and type can be directly obtained. If the detected road sign is an uncommon road sign, it can be processed using natural language processing based on a visual language model. The processing results from the visual language model are then used to classify the road sign, thereby obtaining its meaning and type. This provides control information for autonomous or semi-autonomous vehicles, improving driving safety and demonstrating significant practical value.

[0053] As an optional embodiment of the present invention, based on the above embodiments, this optional embodiment can be optimized to further include, after determining the target recognition result of the road sign to be recognized, sending the target recognition result of the road sign to be recognized to the vehicle's control system so that the vehicle performs the corresponding operation.

[0054] In this embodiment, the vehicle is also equipped with processing units such as an electronic control unit that supports remote information processing of visual language models. Communication interfaces between different processing units can employ controller area networks (MANs), Ethernet, or similar methods. The vehicle is also equipped with processing units for operations such as parking, steering, and acceleration to control the vehicle.

[0055] Specifically, after obtaining the target recognition results of the road sign to be identified—that is, the target meaning and target type of the road sign—the target meaning and target type can be sent to the vehicle's control system to control the vehicle based on the meaning and type of the road sign, so that the vehicle performs the corresponding operation. For example, decisions made based on road sign recognition are integrated with other vehicle systems or electronic control units to perform appropriate operations. This integration ensures coordination with other aspects of vehicle operation, making decisions about taking appropriate actions based on the identified road signs, such as navigation, braking, steering, adjusting speed, changing lanes, or issuing warning signals to the driver.

[0056] The aforementioned technical solutions add steps to control vehicles based on road sign recognition results, enhancing safety. Accurately identifying uncommon signs helps autonomous or semi-autonomous vehicles react appropriately to unique traffic situations. Avoiding traffic violations: Recognizing and understanding uncommon road signs enables vehicles to comply with traffic rules and regulations. This reduces the risk of traffic violations and related legal consequences. Efficient traffic flow: Correctly recognizing unusual road signs allows vehicles to make informed decisions, contributing to smoother traffic flow. This efficiency helps reduce congestion and improve the overall transportation system. Accident prevention: Uncommon road signs may indicate potential hazards or changes in road conditions. Timely recognition of these signs allows vehicles to take preventative measures, thereby reducing the likelihood of accidents.

[0057] As an optional embodiment of the present invention, based on the above embodiments, this optional embodiment can optimize the process of extracting the road signs to be identified contained in the road environment image by further including:

[0058] a1) Preprocess the road environment image to obtain the processed road environment image.

[0059] In this embodiment, after real-time acquisition of road environment images, the images are first processed to determine whether they contain road signs, thus determining whether road sign recognition is necessary. It should be noted that the image acquisition device continuously acquires road environment images; the acquisition process is ongoing. While processing the current road environment image, the next moment's image can be acquired simultaneously.

[0060] This step is used to preprocess the road environment image so that it is suitable for subsequent road sign recognition, thus obtaining a preprocessed road environment image.

[0061] As a specific implementation method, the road environment image can be preprocessed to obtain a preprocessed road environment image, including: feature enhancement, color normalization and resizing of the road environment image to obtain a preprocessed road environment image.

[0062] Specifically, the raw image data is preprocessed, including but not limited to feature enhancement, color normalization, and resizing, to enhance image quality, remove noise, extract relevant features, and enable efficient subsequent processing.

[0063] b1) Based on a preset target detection algorithm, target detection is performed on the processed road environment image to obtain the potential objects contained in the processed road environment image.

[0064] In this context, the object detection algorithm can be understood as a pre-trained detection algorithm. The input of the algorithm is an image, and the output is the objects contained in the image. In this embodiment, the objects contained in the road environment image are denoted as potential objects. Specifically, the object detection algorithm is applied to identify potential objects in the road environment image, including road signs.

[0065] c1) If the potential objects contain road signs, then identify the road signs as road signs to be identified.

[0066] Specifically, if the potential objects contained in the road environment image include road signs, these road signs are treated as road signs to be identified, and information about the detected road signs, such as their location and size, is extracted. Further identification of these road signs is then required.

[0067] d1) If the potential objects do not contain road signs, then it is determined that there is no need to perform road sign recognition on the road environment image.

[0068] Specifically, if the potential objects contained in the road environment image do not include road signs, then there is no need to perform further road sign recognition on the road environment image.

[0069] The above technical solution adds a step to determine whether there are road signs in the road environment image, providing a basis for whether to perform road sign recognition in the future.

[0070] Example 2

[0071] Figure 2a This is a flowchart illustrating another road sign recognition method provided in Embodiment 2 of the present invention. This embodiment is a further optimization of the above embodiment. In this embodiment, the definition of "determining the target recognition result of the road sign to be recognized based on the road sign to be recognized and the vehicle location information, combined with a pre-trained visual language model" is further optimized, and the definition of "judging whether the road sign to be recognized meets the preset judgment conditions" is further optimized.

[0072] like Figure 2a As shown in the figure, this embodiment 2 provides a road sign recognition method, which specifically includes the following steps:

[0073] S201. Acquire real-time road environment images captured by the image acquisition device and real-time vehicle position information collected by the positioning sensor.

[0074] In this embodiment, the image acquisition device serves as an input device, capturing real-time images of the road environment, including road signs, and providing continuous updates of the road scene. Vehicle position information acquired by the positioning sensor supplements the image data.

[0075] S202. Extract the road signs to be identified from the road environment image.

[0076] Specifically, road signs contained in the road environment image are extracted and denoted as road signs to be identified.

[0077] S203. Extract the feature information of the road signs to be identified.

[0078] Specifically, extract the feature information of the road signs to be identified.

[0079] S204. Compare the feature information of the road sign to be identified with the feature information of known road signs to obtain the comparison result and the confidence level of the comparison result.

[0080] In this embodiment, known road signs are pre-stored. The feature information of the road sign to be identified is compared with the feature information of the known road signs to obtain a comparison result. The confidence level of the comparison result is calculated based on the matching situation between the feature information of the road sign to be identified and the feature information of the known road signs.

[0081] S205. If the comparison result shows that the feature information of the road sign to be identified matches the feature information of a known road sign, and the confidence level is greater than or equal to the set confidence threshold, then the road sign to be identified is determined to meet the preset judgment condition. Continue to execute step S207.

[0082] Specifically, the feature information of the road sign to be identified is compared with the feature information of known road signs. If the feature information of the road sign to be identified matches the feature information of known road signs and the confidence level is greater than or equal to the set confidence level threshold, then the road sign to be identified is determined to meet the preset judgment conditions.

[0083] S206. Otherwise, determine that the road sign to be identified does not meet the preset judgment conditions. Continue to step S208.

[0084] Specifically, the feature information of the road sign to be identified is compared with the feature information of known road signs. If the feature information of the road sign to be identified does not match the feature information of known road signs, or if the feature information of the road sign to be identified matches the feature information of known road signs but the confidence level is less than the set confidence level threshold, then it is determined that the road sign to be identified does not meet the preset judgment conditions.

[0085] S207. If the preset judgment conditions are met, the meaning and type of the known road sign that matches the road sign to be identified shall be used as the target identification result of the road sign to be identified.

[0086] Specifically, if the comparison result meets the preset judgment conditions, the meaning and type of the known road sign that matches the road sign to be identified will be used as the target meaning and target type of the road sign to be identified, and the target meaning and target type will be used as the target identification result.

[0087] S208. If the preset judgment conditions are not met, extract the road sign information of the road sign to be identified.

[0088] The road sign information includes at least text information, symbol information, and road sign colors.

[0089] Specifically, if the comparison result does not meet the preset judgment conditions, further identification of the road sign to be identified based on a visual language model is required. This step is used to extract the road sign information of the road sign to be identified, which includes at least text information, symbol information, and road sign color.

[0090] S209. Based on the visual language model, interpret the road sign information to obtain the explanatory text of the road sign to be identified.

[0091] In this embodiment, the visual language model infers from the input data, using its learned knowledge to identify and interpret the textual content of road signs. The visual language model is the core component responsible for understanding and interpreting the textual information present in road signs. It processes the road sign information extracted from the image to derive its meaning and context. The visual language model uses machine learning frameworks such as TensorFlow, PyTorch, or Hugging Face Transformer to interpret the textual information from the road signs. Specifically, based on the interpretation of the road sign information by the visual language model, the explanatory text of the road sign to be identified is obtained.

[0092] S210. Post-process the explanatory text of the road sign to be identified to obtain the post-processed explanatory text.

[0093] Specifically, the explanatory text of the road signs to be identified undergoes additional processing, which is recorded as post-processing, to optimize the results, eliminate noise, and improve accuracy.

[0094] As a specific implementation method, the explanatory text of the road sign to be identified is post-processed to obtain the post-processed explanatory text, including filtering, error correction, consistency check, time correlation check, map cross-reference check, proximity check and priority check of the explanatory text of the road sign to be identified.

[0095] Specifically, post-processing includes: Error filtering: removing any false or irrelevant information that the visual language model might misunderstand. Error classification correction: adjusting the results to correct any errors in text recognition or interpretation. Consistency check: ensuring the recognized text conforms to the expected context based on the location and type of common road signs in the area. Temporal relevance: adjusting the interpretation according to the time of day, which may affect the relevance of certain signs (e.g., school districts). Cross-referencing with maps: validating detected signs against a digital map to confirm their presence and relevance at a given location. Proximity check: ensuring the detected signs are relevant to the vehicle's current location and route. Prioritization check: ranking the importance of detected signs to determine which signs require immediate action.

[0096] S211. Based on the post-processing interpretation text and vehicle location information, determine the target recognition result of the road sign to be recognized.

[0097] In this embodiment, the post-processed interpretation text is categorized to determine the type of road sign and its associated meaning. Vehicle location data and digital maps can also be referenced. Based on the post-processed interpretation text of the road sign to be identified, combined with vehicle location information—that is, by incorporating contextual information from natural language—a comprehensive understanding of the driving environment can be enhanced. For example, understanding the road layout, weather conditions, or specific driving situations described in natural language helps in better sign recognition.

[0098] For example, Figure 2b This is an example diagram of an uncommon road sign in a road sign recognition method provided in Embodiment 2 of the present invention. Figure 2b As shown, this is used as the road sign to be identified, and its text is extracted: "50"; shape: circular; color: white background, black text, and red border; and GPS data indicating the highway location is obtained. Then, based on a pre-trained visual language model, inference is made: the model associates "50" with a regulatory speed symbol. It is confirmed that the circular "50" with a white background, black text, and red border is a standard regulatory sign. Final classification: Type: Regulatory sign; meaning: maximum permitted speed is 50 km / h. After feeding back the meaning and type of this road sign to the vehicle control unit, the vehicle control unit decides to limit the vehicle speed to 50 km / h.

[0099] As a specific implementation method, based on the post-processed interpretation text and vehicle location information, the target recognition result of the road sign to be recognized is determined, including:

[0100] a2) Based on the post-processed interpretation text and vehicle location information, determine the initial meaning and initial type of the road sign to be identified as the initial identification result and determine the confidence level of the initial identification result.

[0101] Specifically, the post-processed interpretation text is categorized to determine the type of road sign and its associated meaning. Vehicle location data and digital maps can also be referenced. Based on the post-processed interpretation text of the road sign to be identified, combined with vehicle location information—that is, by incorporating contextual information from natural language—the overall understanding of the driving environment can be enhanced. For example, understanding the road layout, weather conditions, or specific driving situations described in natural language helps in better sign recognition. The initial meaning and type of the road sign to be identified are used as the initial recognition result, and the confidence level of the initial recognition result is calculated.

[0102] Further, the confidence level of the initial identification results is determined, including:

[0103] a21) Obtain the confidence level of each processing stage in the road environment image processing process and the pre-assigned weight of each processing stage.

[0104] In this embodiment, the confidence score is calculated during the visual language model analysis stage. It evaluates the accuracy and reliability of detected and interpreted road signs from aspects such as object detection algorithms, bounding box accuracy, text analysis, context verification, noise reduction, and consistency checks. By assigning weights to each stage according to its importance and then calculating a weighted average, the final confidence score is obtained, accurately reflecting the reliability of the detected and interpreted road signs. This step is used to obtain the confidence scores of each processing stage in the road environment image processing process and the pre-assigned weights of each processing node.

[0105] a22) Multiply the confidence scores of each processing stage by their corresponding pre-assigned weights and sum them to obtain the confidence scores of the initial identification results.

[0106] This step is used to calculate the weighted average to obtain the final confidence score. For example, assume the confidence scores for different stages are as follows: 0.85 for the object detection algorithm stage, 0.90 for the text extraction stage, 0.80 for the text analysis stage (visual language model analysis), and 0.75 for the contextual validation stage (GPS). Weights can be assigned to each stage based on its importance, for example: object detection: 30%, text extraction: 30%, text analysis: 20%, contextual validation: 20%. Then, the weighted average final confidence score is calculated as (0.85 × 0.30) + (0.90 × 0.30) + (0.80 × 0.20) + (0.75 × 0.20) = 0.835.

[0107] The above technical solution specifies the steps for determining the confidence level of the initial recognition results during the visual language model detection stage.

[0108] b2) If the confidence level of the initial recognition result is less than the set confidence level threshold, then it is determined that the road sign to be recognized cannot be identified.

[0109] The confidence threshold can be set based on practical experience to ensure that the classification confidence is high enough. For example, the confidence threshold can be set to 80%. Specifically, if the confidence of the initial recognition result is less than the set confidence threshold, it is determined that the method provided in this embodiment cannot accurately identify the road sign to be identified, that is, it is determined that the road sign cannot be identified.

[0110] For example, if the confidence level falls below a threshold (40%), the system may warn the driver and transfer control of the vehicle to the driver, in the case of a semi-autonomous vehicle. In the case of an autonomous vehicle, the vehicle is pulled to an emergency stop. A confidence level above 80% is considered high, and the classification of road signs and decisions can continue.

[0111] c2) If the confidence level of the initial recognition result is greater than or equal to the set confidence level threshold, then the initial recognition result is taken as the target recognition result.

[0112] Specifically, if the confidence level of the initial identification result is greater than or equal to the set confidence level threshold, the identification result is considered to be relatively accurate, and the initial identification result can be used as the target identification result.

[0113] The above technical solution specifies the steps for determining the confidence level of the initial identification results, further improves the accuracy of the initial identification results, and ensures the accuracy of the road signs to be identified.

[0114] As an optional embodiment of the present invention, based on the above embodiments, the method can be optimized to further include: controlling the vehicle to stop urgently and issuing an alarm prompt after determining that the road sign to be identified cannot be identified.

[0115] Specifically, if it is determined that the road sign cannot be identified, the vehicle needs to be brought to an emergency stop, and an alarm should be issued. The above technical solution adds an emergency stopping control step, ensuring vehicle safety when road signs are unclear.

[0116] To more clearly illustrate the execution process of the road sign recognition method provided in this embodiment of the invention, an example of road sign recognition in a practical application scenario will be used for explanation. For example, Figure 2c This is a flowchart illustrating the execution of a road sign recognition method in a specific application scenario according to Embodiment 2 of the present invention. Figure 2c As shown, the specific steps of the road sign recognition method include:

[0117] S1. Acquire real-time road environment images captured by the image acquisition device and real-time vehicle location information collected by the positioning sensor.

[0118] S2. Perform feature enhancement, color normalization, and resizing on the road environment image to obtain a preprocessed road environment image.

[0119] S3. Based on the preset target detection algorithm, target detection is performed on the processed road environment image to obtain the potential objects contained in the processed road environment image.

[0120] S4. If the potential objects contain road signs, then identify the road signs as the road signs to be identified. Proceed to step S6.

[0121] S5. If the potential objects do not contain road signs, then it is determined that there is no need to perform road sign recognition on the road environment image.

[0122] S6. Extract the road signs to be identified from the road environment image.

[0123] S7. Extract the feature information of the road signs to be identified.

[0124] S8. Compare the feature information of the road sign to be identified with the feature information of known road signs to obtain the comparison result and the confidence level of the comparison result.

[0125] S9. If the comparison result shows that the feature information of the road sign to be identified matches the feature information of a known road sign, and the confidence level is greater than or equal to the set confidence level threshold, then the road sign to be identified is determined to meet the preset judgment conditions. Proceed to step S11.

[0126] S10. Otherwise, determine that the road sign to be identified does not meet the preset judgment conditions. Jump to step S12.

[0127] S11. If the preset judgment conditions are met, the meaning and type of the known road sign that matches the road sign to be identified will be used as the target identification result of the road sign to be identified. Jump to S18.

[0128] S12. If the preset judgment conditions are not met, extract the road sign information of the road sign to be identified.

[0129] S13. Based on the visual language model, interpret the road sign information to obtain the explanatory text of the road sign to be identified.

[0130] S14. Filter, correct, check consistency, check time correlation, check map cross-reference, check proximity, and check priority of the explanatory text of the road signs to be identified to obtain the post-processed explanatory text.

[0131] S15. Based on the post-processing interpretation text and vehicle location information, determine the initial meaning and initial type of the road sign to be identified as the initial identification result and determine the confidence level of the initial identification result.

[0132] S16. If the confidence level of the initial recognition result is less than the set confidence level threshold, then it is determined that the road sign to be recognized cannot be identified. Skip to S19.

[0133] S17. If the confidence level of the initial identification result is greater than or equal to the set confidence level threshold, then the initial identification result is taken as the target identification result. Jump to S18.

[0134] S18. Send the target recognition result of the road sign to be recognized to the vehicle's control system so that the vehicle can perform the corresponding operation.

[0135] S19. Control the vehicle to stop urgently and issue an alarm.

[0136] Example 3

[0137] Figure 3 This is a schematic diagram of a road sign recognition device provided in Embodiment 3 of the present invention. This device is suitable for automatically recognizing uncommon road signs. The road sign recognition device can be implemented in hardware and / or software and is generally integrated into a vehicle. Figure 3 As shown, the system includes: an image acquisition module 31, a judgment module 32, a first determination module 33, and a second determination module 34; wherein,

[0138] The image acquisition module 31 is used to acquire real-time road environment images captured by the image acquisition device and real-time vehicle position information collected by the positioning sensor.

[0139] The judgment module 32 is used to extract the road signs to be identified contained in the road environment image and to determine whether the road signs to be identified meet the preset judgment conditions. The preset judgment conditions are that the road signs to be identified match the known road signs and the confidence level is greater than or equal to the set confidence level threshold.

[0140] The first determining module 33 is used to take the meaning and type of a known road sign that matches the road sign to be identified as the target identification result of the road sign to be identified if the preset judgment conditions are met.

[0141] The second determining module 34 is used to determine the target recognition result of the road sign to be recognized based on the road sign to be recognized and the vehicle position information, combined with a pre-trained visual language model, if the preset judgment conditions are not met.

[0142] The above technical solution captures road environment images in real time during vehicle operation to detect road signs. If the detected road sign is a known road sign, its meaning and type can be directly obtained. If the detected road sign is an uncommon road sign, it can be processed using the natural language processing function of a visual language model. Based on the processing results of the visual language model, the road sign is classified to obtain its meaning and type. This provides control basis for autonomous or semi-autonomous vehicles, improves driving safety, and has significant practical value.

[0143] Optionally, the second determining module 34 includes:

[0144] The information extraction unit is used to extract road sign information of the road sign to be identified. The road sign information includes at least text information, symbol information, and road sign color.

[0145] The text determination unit is used to interpret road sign information based on a visual language model and obtain the explanatory text of the road sign to be identified.

[0146] The post-processing unit is used to post-process the explanatory text of the road sign to be recognized, and obtain the post-processed explanatory text.

[0147] The result determination unit is used to determine the target recognition result of the road sign to be recognized based on the post-processed interpretation text and vehicle location information.

[0148] Optionally, the post-processing unit is specifically used for:

[0149] The explanatory text of the road signs to be identified is filtered, corrected, checked for consistency, temporal relevance, cross-referenced with maps, proximity, and priority to obtain post-processed explanatory text.

[0150] Optionally, the result determination unit is specifically used for:

[0151] Based on the post-processed interpretation text and vehicle location information, the initial meaning and initial type of the road sign to be identified are determined as the initial identification result, and the confidence level of the initial identification result is determined.

[0152] If the confidence level of the initial recognition result is less than the set confidence level threshold, it is determined that the road sign to be recognized cannot be identified.

[0153] If the confidence level of the initial identification result is greater than or equal to the set confidence level threshold, then the initial identification result will be used as the target identification result.

[0154] Optionally, the confidence level of the initial identification result is determined, including:

[0155] Obtain the confidence level of each processing stage in the road environment image processing process and the pre-assigned weight of each processing stage;

[0156] The confidence level of the initial identification result is obtained by multiplying the confidence level of each processing stage by the corresponding pre-assigned weight and summing the results.

[0157] Optionally, the judgment module 32 is specifically used for:

[0158] Extract feature information of road signs to be identified

[0159] The feature information of the road sign to be identified is compared with the feature information of known road signs to obtain the comparison results and the confidence level of the comparison results;

[0160] If the comparison result shows that the feature information of the road sign to be identified matches the feature information of the known road sign, and the confidence level is greater than or equal to the set confidence level threshold, then the road sign to be identified is determined to meet the preset judgment conditions.

[0161] Otherwise, it is determined that the road sign to be identified does not meet the preset judgment conditions.

[0162] Optionally, the device further includes a target detection module, used to: Before extracting the road signs to be identified contained in the road environment image.

[0163] Preprocess the road environment image to obtain the processed road environment image;

[0164] Based on a preset target detection algorithm, target detection is performed on the processed road environment image to obtain the potential objects contained in the processed road environment image.

[0165] If a potential object contains a road sign, then the road sign is identified as the road sign to be identified.

[0166] If the potential objects do not contain road signs, then it is determined that there is no need to perform road sign recognition on the road environment image.

[0167] Optionally, the road environment image is preprocessed to obtain a preprocessed road environment image, including:

[0168] The road environment image is processed by feature enhancement, color normalization, and resizing to obtain a preprocessed road environment image.

[0169] Optionally, the device further includes a result transmission module, which, after determining the target recognition result of the road sign to be recognized, is used to:

[0170] The target recognition result of the road sign to be recognized is sent to the vehicle's control system so that the vehicle can perform the corresponding operation.

[0171] Optionally, the device also includes an emergency stop control module, which, after determining that the road sign to be identified cannot be recognized, is used to:

[0172] Control the vehicle to stop urgently and issue an alarm.

[0173] The road sign recognition device provided in the embodiments of the present invention can execute the road sign recognition method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0174] Example 4

[0175] Figure 4 This is a schematic diagram of the structure of a vehicle provided in Embodiment 4 of the present invention. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the invention described and / or claimed herein.

[0176] like Figure 4As shown, the vehicle includes a vehicle body (not shown), an image acquisition device 20, a positioning sensor 30, and a controller 40. The image acquisition device 20 and the positioning sensor 30 are mounted on the vehicle body. The controller 40 is communicatively connected to the image acquisition device 20 and the positioning sensor 30; the controller 40 includes at least one processor 41 and a memory, such as a read-only memory (ROM) 42 or a random access memory (RAM) 43, communicatively connected to the at least one processor 41. The memory stores computer programs executable by the at least one processor. The processor 41 can perform various appropriate actions and processes based on the computer program stored in the ROM 42 or loaded from storage unit 48 into the RAM 43. The RAM 43 can also store various programs and data required for the operation of the electronic device 40. The processor 41, ROM 42, and RAM 43 are interconnected via a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0177] Multiple components in electronic device 40 are connected to I / O interface 45, including: input unit 46, such as keyboard, mouse, etc.; output unit 47, such as various types of monitors, speakers, etc.; storage unit 48, such as disk, optical disk, etc.; and communication unit 49, such as network card, modem, wireless transceiver, etc. Communication unit 49 allows electronic device 40 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0178] Processor 41 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 41 performs the various methods and processes described above, such as road sign recognition methods.

[0179] In some embodiments, the road sign recognition method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 48. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 40 via ROM 42 and / or communication unit 49. When the computer program is loaded into RAM 43 and executed by processor 41, one or more steps of the road sign recognition method described above may be performed. Alternatively, in other embodiments, processor 41 may be configured to perform the road sign recognition method by any other suitable means (e.g., by means of firmware).

[0180] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0181] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0182] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0183] To provide interaction with the user, the systems and technologies described herein can be implemented in a vehicle having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the vehicle. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0184] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0185] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0186] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0187] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A road sign recognition method, characterized in that, include: The system acquires real-time images of the road environment captured by the image acquisition device and real-time vehicle location information collected by the positioning sensor. Extract the road signs to be identified contained in the road environment image, and determine whether the road signs to be identified meet the preset judgment conditions. The preset judgment conditions are that the road signs to be identified match the known road signs and the confidence level is greater than or equal to the set confidence level threshold. If the preset judgment condition is met, the meaning and type of the known road sign that matches the road sign to be identified will be used as the target identification result of the road sign to be identified. If the preset judgment conditions are not met, the road sign information of the road sign to be identified is extracted. The road sign information includes at least text information, symbol information, and road sign color. The road sign information is interpreted based on a visual language model to obtain the explanatory text of the road sign to be identified; The explanatory text of the road sign to be identified is post-processed to obtain the post-processed explanatory text; Based on the post-processed interpretation text and the vehicle location information, the target recognition result of the road sign to be recognized is determined.

2. The method according to claim 1, characterized in that, The post-processing of the explanatory text of the road sign to be identified to obtain post-processed explanatory text includes: The explanatory text of the road sign to be identified is filtered, corrected, checked for consistency, temporal relevance, cross-referenced on maps, proxies, and prioritized to obtain the post-processed explanatory text.

3. The method according to claim 1, characterized in that, The step of determining the target recognition result of the road sign to be recognized based on the post-processed interpretation text and the vehicle location information includes: Based on the post-processed interpretation text and the vehicle location information, the initial meaning and initial type of the road sign to be identified are determined as the initial identification result, and the confidence level of the initial identification result is determined. If the confidence level of the initial recognition result is less than the set confidence level threshold, then it is determined that the road sign to be recognized cannot be identified; If the confidence level of the initial identification result is greater than or equal to the set confidence level threshold, then the initial identification result is taken as the target identification result.

4. The method according to claim 3, characterized in that, Determining the confidence level of the initial identification result includes: Obtain the confidence level of each processing stage in the road environment image processing process and the pre-assigned weight of each processing stage; The confidence level of the initial identification result is obtained by multiplying the confidence level of each processing stage by the corresponding pre-assigned weight and summing the results.

5. The method according to claim 1, characterized in that, The step of determining whether the road sign to be identified meets the preset judgment conditions includes: Extract the feature information of the road sign to be identified; The feature information of the road sign to be identified is compared with the feature information of known road signs to obtain the comparison result and the confidence level of the comparison result; If the comparison result shows that the feature information of the road sign to be identified matches the feature information of the known road sign, and the confidence level is greater than or equal to the set confidence level threshold, then the road sign to be identified is determined to meet the preset judgment condition. Otherwise, it is determined that the road sign to be identified does not meet the preset judgment conditions.

6. The method according to claim 1, characterized in that, Before extracting the road signs to be identified contained in the road environment image, the method further includes: The road environment image is preprocessed to obtain a preprocessed road environment image; The processed road environment image is subjected to target detection based on a preset target detection algorithm to obtain potential objects contained in the processed road environment image; If the potential object contains a road sign, then the road sign is identified as the road sign to be identified; If the potential objects do not contain road signs, then it is determined that there is no need to perform road sign recognition on the road environment image.

7. The method according to claim 6, characterized in that, The step of preprocessing the road environment image to obtain a preprocessed road environment image includes: The road environment image is subjected to feature enhancement, color normalization, and resizing to obtain a preprocessed road environment image.

8. The method according to claim 1, characterized in that, After determining the target recognition result of the road sign to be recognized, the method further includes: The target recognition result of the road sign to be recognized is sent to the vehicle's control system so that the vehicle can perform the corresponding operation.

9. The method according to claim 3, characterized in that, After determining that the road sign to be identified cannot be recognized, the method further includes: Control the vehicle to stop urgently and issue an alarm.

10. A road sign recognition device, characterized in that, include: The image acquisition module is used to acquire real-time road environment images captured by the image acquisition device and real-time vehicle position information collected by the positioning sensor. The judgment module is used to extract the road signs to be identified contained in the road environment image and determine whether the road signs to be identified meet the preset judgment conditions. The preset judgment conditions are that the road signs to be identified match the known road signs and the confidence level is greater than or equal to the set confidence level threshold. The first determining module is used to, if the preset judgment condition is met, take the meaning and type of a known road sign that matches the road sign to be identified as the target identification result of the road sign to be identified; The second determination module includes an information extraction unit, a text determination unit, a post-processing unit, and a result determination unit; The information extraction unit is used to extract the road sign information of the road sign to be identified if the preset judgment condition is not met. The road sign information includes at least text information, symbol information, and road sign color. The text determination unit is used to interpret the road sign information based on a visual language model to obtain the explanatory text of the road sign to be identified. The post-processing unit is used to post-process the explanatory text of the road sign to be identified to obtain post-processed explanatory text; The result determination unit is used to determine the target recognition result of the road sign to be recognized based on the post-processed interpretation text and the vehicle location information.

11. A vehicle, characterized in that, include: Vehicle body; An image acquisition device and a positioning sensor are respectively installed on the vehicle body; The controller is communicatively connected to the image acquisition device and the positioning sensor, and the controller includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the road sign recognition method according to any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the road sign recognition method according to any one of claims 1-9.

Images