Speed limit information fusion method and device

Abstract

The invention provides a speed limit information fusion method and device, and the method comprises the steps: obtaining map speed limit information and map speed limit confidence based on a map navigation system; acquiring image data in front of a road, and recognizing speed limit information in the image data through a speed limit recognition model to obtain camera speed limit information and camera speed limit confidence; taking the map speed limit confidence coefficient and the camera speed limit confidence coefficient as prior probabilities, and obtaining a posterior probability through a Bayesian algorithm based on the prior probabilities and the conditional probabilities; and the final speed limit information is determined based on the posterior probability, the map speed limit information and the camera speed limit information, so that the accuracy and reliability of the speed limit information are improved.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular to a method and apparatus for speed limit information fusion. Background Technology

[0002] In intelligent driving systems, accurate acquisition of road speed limit information is crucial for ensuring driving safety and improving driving efficiency. Currently, road speed limit information mainly comes from map navigation systems and traffic speed limit signs recognized by cameras. However, map speed limit information may contain errors due to inaccurate positioning and untimely map updates; while camera-recognized speed limit information may be affected by factors such as inclement weather, lighting conditions, and high-speed scenarios, leading to inaccurate recognition. Summary of the Invention

[0003] This application provides a method and apparatus for fusing speed limit information to improve the accuracy and reliability of speed limit information. The technical solution disclosed herein is as follows:

[0004] In a first aspect, embodiments of this application propose a speed limit information fusion method, including:

[0005] Based on the map navigation system, obtain map speed limit information and map speed limit confidence level;

[0006] Acquire image data of the road ahead, and use a speed limit recognition model to identify the speed limit information in the image data to obtain camera speed limit information and camera speed limit confidence.

[0007] The map speed limit confidence and the camera speed limit confidence are used as prior probabilities. Based on the prior probabilities and conditional probabilities, the posterior probabilities are obtained through a Bayesian algorithm.

[0008] The final speed limit information is determined based on the posterior probability, the map speed limit information, and the camera speed limit information.

[0009] Secondly, embodiments of this application propose a speed limit information fusion device, comprising:

[0010] The data processing module is used to obtain map speed limit information and map speed limit confidence based on the map navigation system;

[0011] The image processing module is used to acquire image data of the road ahead, and to identify the speed limit information in the image data through a speed limit recognition model to obtain camera speed limit information and camera speed limit confidence.

[0012] The data calculation module is used to take the map speed limit confidence and the camera speed limit confidence as prior probabilities, and obtain the posterior probability based on the prior probabilities and conditional probabilities using a Bayesian algorithm.

[0013] The speed limit determination module is used to determine the final speed limit information based on the posterior probability, the map speed limit information, and the camera speed limit information.

[0014] Thirdly, embodiments of this application provide an electronic device, including: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method described in the first aspect.

[0015] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method described in the first aspect.

[0016] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the method described in the first aspect.

[0017] The speed limit information fusion method and apparatus provided in this application acquire map speed limit information and map speed limit confidence scores based on a map navigation system; acquire camera speed limit information and camera speed limit confidence scores from speed limit sign images captured by a camera through a recognition model; and fuse map speed limit information and camera speed limit confidence scores using a Bayesian algorithm based on map speed limit confidence scores and camera speed limit confidence scores. This effectively reduces errors from a single information source and improves the accuracy and reliability of speed limit information. Even under complex environmental conditions (such as severe weather, insufficient lighting, etc.), it can still provide reliable speed limit information, reducing false alarms and missed alarms. Accurate speed limit information helps drivers better comply with traffic rules, reduce speeding, and thus lower the risk of traffic accidents. By providing real-time speed limit reminders and warnings, it promptly reminds drivers to adjust their speed, further enhancing driving safety. This application can automatically adapt to different driving scenarios without requiring manual adjustments by the driver, improving driving convenience and comfort, and can be applied to various types of intelligent driving vehicles, including autonomous vehicles and driver assistance systems.

[0018] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0019] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0020] Figure 1 A flowchart illustrating a speed limit information fusion method provided in an embodiment of this application;

[0021] Figure 2 Example image showing lane information obtained from a map navigation system;

[0022] Figure 3 A block diagram of a speed limit information fusion device provided in an embodiment of this application;

[0023] Figure 4 This is a block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0024] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0025] The following description, with reference to the accompanying drawings, describes a speed limit information fusion method, apparatus, and device according to embodiments of this application.

[0026] Figure 1 This is a flowchart illustrating a speed limit information fusion method provided in an embodiment of this application.

[0027] It should be noted that the execution subject of the speed limit information fusion method in this application embodiment is the speed limit information fusion device of this application embodiment. This speed limit information fusion device can be configured in an electronic device so that the electronic device can perform the speed limit information fusion function. For example... Figure 1 As shown, the speed limit information fusion method includes the following steps:

[0028] Step S101: Based on the map navigation system, obtain map speed limit information and map speed limit confidence.

[0029] In some embodiments, lane speed limit information and lane width information are obtained based on a map navigation system; map speed limit information and map speed limit confidence are obtained based on the lane speed limit information, lane width information and positioning information.

[0030] In some embodiments, the method for obtaining map speed limit information and map speed limit confidence based on lane speed limit information, lane width information, and positioning information includes: determining map speed limit information based on lane speed limit information and positioning information; obtaining the width of the lane where the positioning point is located based on lane speed limit information, lane width information, and positioning information; obtaining the positioning error range based on positioning error and positioning information; obtaining information on the same speed limit for multiple lanes involved in the positioning error range based on lane speed limit information; and determining map speed limit confidence based on the same speed limit information, positioning error range, lane width information, and the width of the lane where the positioning point is located.

[0031] In some embodiments, a method for determining map speed limit confidence based on information about identical speed limits, positioning error range, lane width information, and the width of the lane where the positioning point is located includes: determining map speed limit confidence based on information about identical speed limits, positioning error range, lane width information, and the width of the lane where the positioning point is located; determining the total lane width within the positioning error range that has the same speed limit as the lane where the positioning point is located; and determining map speed limit confidence based on the ratio between the total lane width and the lane width corresponding to the positioning error range.

[0032] In one example, such as Figure 2 As shown, assume there are n lanes (in actual road conditions, there are a maximum of 12 lanes in both directions, defined as n≤12), with speed limits for each lane as S1, S2, ..., Sn, and lane widths as L1, L2, ..., Ln. The lane speed limit and lane width information are derived from the map module and provided by the map provider. The vehicle's positioning system uses the rear axle center point as its origin. Figure 2 In this context, O is the origin, and the positioning error is assumed to be d. Therefore, the positioning error range includes AO and OE, where AO = OE = d. Generally, road width is around 3.5m, and GPS positioning error is around 5m. Therefore, the positioning error range typically spans multiple lanes. Figure 2 The probability of being located in lane 1 is AB / AE, so the probability of the vehicle having a speed limit of S1 is AB / AE; similarly, the probability of a speed limit of S2 is BC / AE, the probability of a speed limit of S3 is CD / AE, and the probability of a speed limit of S4 is DE / AE. Because the speed limits of multiple lanes are similar, that is, S1, S2, S3, and S4 are mostly the same, unless there is a scenario where some lanes are on the main road and some are on the auxiliary road, the speed limit probabilities can be superimposed for lanes with the same speed limit. For example, if S1 = S2, then the probability of the vehicle having a current speed limit of S1 is AC / AE; if S1 = S2 = S3, then the probability of a speed limit of S1 is AD / AE, and the probability of being located in lane 2 is AD / AE.

[0033] In one example, speed limit information for the current road is obtained from a map navigation system, including both regular speed limits and speed limits for special road sections. Variables are defined: Lmap represents the map speed limit value, and Pmap represents the map speed limit confidence level.

[0034] In some embodiments, the confidence level of the map speed limit is determined based on location information and preset confidence rules. The confidence level of the map speed limit is typically set to a high value, such as 0.9, because the confidence level will vary depending on the level of intelligent transportation development in different locations and the operating status of the vehicle positioning system. For example, in first- and second-tier cities, road information is abundant and location information is accurate, resulting in a higher confidence level for the map speed limit; in remote areas, road information is scarce and location is inaccurate, leading to a lower confidence level for the road speed limit.

[0035] In some embodiments, the map speed limit confidence level is determined based on the positioning accuracy of the map navigation system.

[0036] Step S102: Acquire image data of the road ahead, identify the speed limit information in the image data through a speed limit recognition model, and obtain the camera speed limit information and camera speed limit confidence.

[0037] As one implementation method, the method for obtaining camera speed limit information and camera speed limit confidence includes: preprocessing image data to obtain preprocessed image data; extracting image features of the speed limit sign from the preprocessed image data using an image processing algorithm; and recognizing the image features using a speed limit recognition model to obtain camera speed limit information and camera speed limit confidence.

[0038] In one example, a speed limit recognition model is obtained by training a machine learning model (such as a convolutional neural network CNN); image data of the road ahead is collected in real time by an onboard camera; the collected image data is preprocessed with noise reduction and contrast enhancement to improve recognition accuracy; features of the speed limit sign, such as shape, color, and numbers, are extracted using image processing algorithms; the extracted features are classified using machine learning algorithms (such as convolutional neural networks CNN) to identify the specific speed limit value of the speed limit sign and obtain the camera speed limit confidence score, thus realizing speed limit sign recognition based on machine learning and computer vision.

[0039] As another implementation method, target detection algorithms are used to identify targets in image data to obtain target recognition results. If the target recognition result indicates that a speed limit sign has been detected, photovoltaic character recognition technology or a deep learning module is used to identify the digital information on the speed limit sign and output the camera speed limit information and camera speed limit confidence level.

[0040] In one example, the object detection algorithm can choose the visual object detection algorithm YOLO, construct a speed limit sign dataset containing various scenes and lighting conditions, and perform annotation and data augmentation; select a YOLOv11 model suitable for speed limit sign detection, and train it on the constructed dataset to obtain a speed limit sign recognition model, which is used to identify speed limit signs; after recognizing the speed limit sign, further identify the digital information on the speed limit sign, usually using OCR technology or a deep learning model (such as CRNN), and obtain confidence information.

[0041] In this embodiment, a camera captures traffic speed limit signs, and a machine learning algorithm is used to identify the speed limit information. The identification results include camera speed limit information and its confidence level, camera speed limit information Lcam and camera speed limit confidence level Pcam.

[0042] Step S103: Using the map speed limit confidence and the camera speed limit confidence as prior probabilities, and based on the prior probabilities and conditional probabilities, the posterior probabilities are obtained through a Bayesian algorithm.

[0043] In some embodiments, the posterior probability P(Lcam|Lmap) of the speed limit information is obtained according to Bayes' theorem using the following formula:

[0044] P(Lcam∣Lmap)=P(Lmap∣Lcam)×P(Lcam) / P(Lmap)

[0045] Where P(Lcam) and P(Lmap) are prior probabilities, P(Lmap) = Pmap, where Pmap is the confidence level of the map speed limit, and P(Lcam) = Pcam, where Pcam is the confidence level of the camera speed limit; P(Lmap|Lcam) is the conditional probability, which can be estimated using experimental or historical data; P(Lcam|Lmap) represents the probability that the camera speed limit Lcam is true when the map speed limit Lmap is true.

[0046] In some embodiments, the method for obtaining conditional probability includes: obtaining multiple sets of speed limit data, each set of speed limit data including map speed limit values, camera speed limit values, and actual speed limit values, wherein the road types and actual scenarios corresponding to the multiple sets of speed limit data are different; based on the multiple sets of speed limit data, obtaining a first number of map speed limit values ​​and camera speed limit values ​​that are consistent with actual speed limit values, and a second number of camera speed limit values ​​that are consistent with actual speed limit values; and obtaining the conditional probability based on the ratio of the first number to the second number.

[0047] In one example, data collection is performed for different scenarios. Data collection includes obtaining road speed limit information (Lmap) from a high-precision map, capturing speed limit signs (Lcam) using a camera and recognizing the speed limit information, and obtaining the actual speed limit information (Ltrue) through manual annotation or high-precision sensors. Different scenarios can include: multiple different urban road scenarios, highway scenarios, and rural road scenarios. Urban road scenarios include different weather conditions (sunny, rainy, foggy) and lighting conditions (daytime, nighttime); multiple highway scenarios can be selected, including different speed limits and traffic flows; multiple rural road scenarios can be selected, including different road conditions and speed limit sign settings. After data collection, the data can be annotated to check the accuracy of the map speed limit information (whether Lmap matches the actual speed limit Ltrue) and the accuracy of the camera speed limit information (whether Lcam matches the actual speed limit Ltrue). Based on the annotated information, N sets of statistical data (N≥1000) are obtained, and the conditional probability is calculated using the following formula:

[0048] P(Lmap|Lcam) = (Number of times when both map speed limit and camera speed limit are true) / (Number of times when camera speed limit is true).

[0049] Bayesian algorithms can dynamically adjust the confidence level of speed limit information based on different environmental conditions and sensor data, exhibiting strong adaptability. They calculate conditional probabilities using statistical methods to evaluate the confidence level of one speed limit given a known speed limit. Bayesian algorithms can dynamically adjust the confidence level of speed limit information based on real-time data, adapting to different environmental conditions.

[0050] Step S104: Determine the final speed limit information based on the posterior probability, map speed limit information, and camera speed limit information.

[0051] In some embodiments, the method for determining the final speed limit information includes: determining whether the posterior probability is greater than a target threshold; if the posterior probability is greater than the target threshold, determining the final speed limit information as camera speed limit information; if the posterior probability is less than or equal to the target threshold, determining the final speed limit information as map speed limit information.

[0052] In one example, if P(Lcam|Lmap)>1, then the final speed limit Lfinal = Lcam; otherwise, the final speed limit Lfinal = Lmap.

[0053] This can be understood as updating the posterior probability according to Bayes' theorem and selecting the speed limit information with the highest confidence as the final speed limit value.

[0054] In some embodiments, after determining the final speed limit information, the process includes: visualizing the determination of the final speed limit information and playing a voice prompt.

[0055] In one example, the merged speed limit information Lfinal can be displayed to the driver and a reminder can be issued when necessary. The reminder methods include screen display, voice prompts, etc. By using multiple methods such as screen display and voice prompts, the speed limit information can be presented to the driver intuitively, improving the information interaction experience during driving.

[0056] The speed limit information fusion method in this embodiment obtains map speed limit information and map speed limit confidence based on a map navigation system; it obtains camera speed limit information and camera speed limit confidence from speed limit sign images captured by a camera through a recognition model; and it uses a Bayesian algorithm to fuse map speed limit information and camera speed limit confidence based on map speed limit confidence and camera speed limit confidence, which can effectively reduce the error of a single information source and improve the accuracy and reliability of speed limit information. Based on lane speed limit information and positioning information, and combined with positioning error, the map speed limit confidence is determined, improving the accuracy of the map speed limit confidence. Even under complex environmental conditions (such as severe weather, insufficient lighting, etc.), it can still provide reliable speed limit information, reducing false alarms and missed alarms. Accurate speed limit information can help drivers better comply with traffic rules, reduce speeding, and thus reduce the risk of traffic accidents. By providing real-time speed limit reminders and warnings, it promptly reminds drivers to adjust their speed, further enhancing driving safety. This application can automatically adapt to different driving scenarios without requiring manual adjustment by the driver, improving driving convenience and comfort, and can be applied to various types of intelligent driving vehicles, including autonomous vehicles and driver assistance systems.

[0057] To achieve the above embodiments, this application also proposes a speed limit information fusion device. Figure 3 This is a schematic diagram of a speed limit information fusion device provided in an embodiment of this application. Figure 3 As shown, the speed limit information fusion device may include: a data processing module 301, an image processing module 302, a data calculation module 303, and a speed limit determination module 304.

[0058] Among them, the data processing module 301 is used to obtain map speed limit information and map speed limit confidence based on the map navigation system;

[0059] Image processing module 302 is used to acquire image data of the road ahead, identify the speed limit information in the image data through a speed limit recognition model, and obtain camera speed limit information and camera speed limit confidence.

[0060] The data calculation module 303 is used to take the map speed limit confidence and the camera speed limit confidence as prior probabilities, and obtain the posterior probability based on the prior probability and conditional probability through the Bayesian algorithm.

[0061] The speed limit determination module 304 is used to determine the final speed limit information based on the posterior probability, map speed limit information, and camera speed limit information.

[0062] Furthermore, in one possible implementation of this application embodiment, the data processing module 301 is specifically used for:

[0063] Based on the map navigation system, obtain lane speed limit information and lane width information;

[0064] Based on lane speed limit information, lane width information, and location information, map speed limit information and map speed limit confidence are obtained.

[0065] Furthermore, in one possible implementation of this application embodiment, the data processing module 301 is specifically used for:

[0066] Based on lane speed limit information and location information, determine the map speed limit information;

[0067] Based on lane speed limit information, lane width information, and location information, the width of the lane where the location point is located is obtained;

[0068] Based on the positioning error and positioning information, the positioning error range is obtained;

[0069] Based on lane speed limit information, information on the situation where multiple lanes within the positioning error range have the same speed limit is obtained;

[0070] Based on information about the same speed limit, the positioning error range, lane width information, and the width of the lane where the positioning point is located, the confidence level of the speed limit on the map is determined.

[0071] Furthermore, in one possible implementation of this application embodiment, the data processing module 301, when determining the map speed limit confidence level based on information about the same speed limit, the positioning error range, lane width information, and the width of the lane where the positioning point is located, is used for:

[0072] Based on information about the same speed limit, the positioning error range, lane width information, and the width of the lane where the positioning point is located, the confidence level of the map speed limit is determined, and the total lane width within the positioning error range that has the same speed limit as the lane where the positioning point is located is determined.

[0073] The confidence level of the speed limit on the map is determined by the ratio between the total lane width and the lane width corresponding to the positioning error range.

[0074] Furthermore, in one possible implementation of this application embodiment, the image processing module 302 is specifically used for:

[0075] The image data is preprocessed to obtain the preprocessed image data;

[0076] Image features of speed limit signs are extracted from preprocessed image data using image processing algorithms.

[0077] By identifying image features using a speed limit recognition model, camera speed limit information and camera speed limit confidence level can be obtained.

[0078] Furthermore, in one possible implementation of this application embodiment, the image processing module 302 is specifically used for:

[0079] The image data is used to identify targets using a target detection algorithm to obtain the target identification results;

[0080] If the target recognition result indicates that a speed limit sign has been detected, the digital information on the speed limit sign is identified through photovoltaic character recognition technology or a deep learning module, and the camera speed limit information and camera speed limit confidence level are output.

[0081] Furthermore, in one possible implementation of this application embodiment, the speed limit determination module 304 is specifically used for:

[0082] Determine whether the posterior probability is greater than the target threshold;

[0083] If the posterior probability is greater than the target threshold, the final speed limit information is determined to be the camera speed limit information;

[0084] If the posterior probability is less than or equal to the target threshold, the final speed limit information is determined to be the map speed limit information.

[0085] Furthermore, in one possible implementation of this application embodiment, the speed limit determination module 304 is also used for:

[0086] Acquire multiple sets of speed limit data, including map speed limit values, camera speed limit values, and actual speed limit values. The road types and actual scenarios corresponding to these multiple sets of speed limit data are different.

[0087] Based on multiple sets of speed limit data, obtain a first number of speed limits where both map speed limits and camera speed limits are consistent with the actual speed limits, and a second number of speed limits where both camera speed limits and actual speed limits are consistent.

[0088] The conditional probability is obtained based on the ratio of the first quantity to the second quantity.

[0089] Furthermore, in one possible implementation of this application embodiment, the device further includes an information reminder module 305, used for:

[0090] Visualize the final speed limit information and play a voice prompt.

[0091] It should be noted that the foregoing explanation of the embodiment of the speed limit information fusion method also applies to the speed limit information fusion device of this embodiment, and will not be repeated here.

[0092] To implement the above embodiments, this application also proposes an electronic device. Please see [link to relevant documentation]. Figure 4 , Figure 4 This is a schematic diagram of the structure of the electronic device provided in an embodiment of this application. For example... Figure 4As shown, the electronic device 400 includes: a processor 401 and a memory 402 communicatively connected to the processor 401; the memory 402 stores computer-executable instructions; the processor 401 executes the computer-executable instructions stored in the memory to implement the method provided in the foregoing embodiments.

[0093] To implement the above embodiments, this application also proposes a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the methods provided in the foregoing embodiments.

[0094] To implement the above embodiments, this application also proposes a computer program product, including a computer program that, when executed by a processor, implements the methods provided in the foregoing embodiments.

[0095] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0096] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0097] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0098] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0099] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0100] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0101] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0102] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for fusing speed limit information, characterized in that, Includes the following steps: Based on the map navigation system, obtain map speed limit information and map speed limit confidence level; Acquire image data of the road ahead, and use a speed limit recognition model to identify the speed limit information in the image data to obtain camera speed limit information and camera speed limit confidence. The map speed limit confidence and the camera speed limit confidence are used as prior probabilities. Based on the prior probabilities and conditional probabilities, the posterior probabilities are obtained through a Bayesian algorithm. The final speed limit information is determined based on the posterior probability, the map speed limit information, and the camera speed limit information.

2. The method according to claim 1, characterized in that, The acquisition of map speed limit information and map speed limit confidence based on the map navigation system includes: Based on the map navigation system, obtain lane speed limit information and lane width information; Based on the lane speed limit information, the lane width information, and the positioning information, map speed limit information and map speed limit confidence are obtained.

3. The method according to claim 1, characterized in that, The process of obtaining map speed limit information and map speed limit confidence based on the lane speed limit information, lane width information, and positioning information includes: The map speed limit information is determined based on the lane speed limit information and the location information; Based on the lane speed limit information, the lane width information, and the positioning information, the width of the lane where the positioning point is located is obtained; Based on the positioning error and the positioning information, the positioning error range is obtained; Based on the lane speed limit information, information on the situation where multiple lanes within the positioning error range have the same speed limit is obtained; Based on the information about the same speed limit, the positioning error range, the lane width information, and the width of the lane where the positioning point is located, the confidence level of the map speed limit is determined.

4. The method according to claim 3, characterized in that, The step of determining the map speed limit confidence level based on the same speed limit information, the positioning error range, the lane width information, and the width of the lane where the positioning point is located includes: Based on the information about the same speed limit, the positioning error range, the lane width information, and the width of the lane where the positioning point is located, the confidence level of the map speed limit is determined, and the total lane width within the positioning error range that is the same as the speed limit of the lane where the positioning point is located is determined. The confidence level of the map speed limit is determined based on the ratio between the total lane width and the lane width corresponding to the positioning error range.

5. The method according to claim 1, characterized in that, The step of identifying speed limit information in the image data using a speed limit recognition model to obtain camera speed limit information and camera speed limit confidence includes: The image data is preprocessed to obtain preprocessed image data; Image features of speed limit signs are extracted from the preprocessed image data using image processing algorithms. The image features are identified using a speed limit recognition model to obtain camera speed limit information and camera speed limit confidence.

6. The method according to claim 1, characterized in that, The step of identifying speed limit information in the image data using a speed limit recognition model to obtain camera speed limit information and camera speed limit confidence includes: The image data is used to identify targets using a target detection algorithm to obtain the target identification results; If the target recognition result indicates that a speed limit sign has been detected, the digital information on the speed limit sign is identified through photovoltaic character recognition technology or a deep learning module, and the camera speed limit information and camera speed limit confidence level are output.

7. The method according to claim 1, characterized in that, The process of determining the final speed limit information based on the posterior probability, the map speed limit information, and the camera speed limit information includes: Determine whether the posterior probability is greater than the target threshold; If the posterior probability is greater than the target threshold, the final speed limit information is determined to be the camera speed limit information; If the posterior probability is less than or equal to the target threshold, the final speed limit information is determined to be the map speed limit information.

8. The method according to claim 1, characterized in that, The method for obtaining the conditional probability includes: Multiple sets of speed limit data are acquired. Each set of speed limit data includes map speed limit values, camera speed limit values, and actual speed limit values. The road types and actual scenarios corresponding to the multiple sets of speed limit data are different. Based on the multiple sets of speed limit data, obtain a first number of speed limits where both the map speed limit and the camera speed limit are consistent with the actual speed limit, and a second number of speed limits where the camera speed limit is consistent with the actual speed limit. The conditional probability is obtained based on the ratio of the first quantity to the second quantity.

9. The method according to claim 1, characterized in that, After determining the final speed limit information, the following is included: The final speed limit information is visualized and a voice prompt is played.

10. A speed limit information fusion device, characterized in that, include: The data processing module is used to obtain map speed limit information and map speed limit confidence based on the map navigation system; The image processing module is used to acquire image data of the road ahead, and to identify the speed limit information in the image data through a speed limit recognition model to obtain camera speed limit information and camera speed limit confidence. The data calculation module is used to take the map speed limit confidence and the camera speed limit confidence as prior probabilities, and obtain the posterior probability based on the prior probabilities and conditional probabilities using a Bayesian algorithm. The speed limit determination module is used to determine the final speed limit information based on the posterior probability, the map speed limit information, and the camera speed limit information.

Images