External horn sound processing method and related equipment

Abstract

This invention discloses a method and related equipment for processing external vehicle horn sounds. These methods relate to the field of vehicle control and primarily address the current lack of corresponding methods for processing noisy external vehicle horn sounds. The method includes: obtaining an optimized audio signal from the exterior of a target vehicle, wherein the optimized audio signal is determined by preprocessing an initial audio signal; classifying the optimized audio signal using a support vector machine to obtain an audio classification result; and combining the audio classification result with the external environment and the vehicle's own state to determine an audio filtering operation for the exterior of the target vehicle. This invention is applicable to the process of processing external vehicle horn sounds.

Description

Technical Field

[0001] The present invention relates to the field of vehicle control, and in particular to a method for processing an external horn sound of a vehicle and related equipment. Background Art

[0002] As urban traffic density increases, the driving environment becomes increasingly complex. In busy traffic, horn sounds have become an important means of communication and reminder. However, frequent and unreasonable horn sounds often disrupt drivers, affecting their mood and driving concentration, and sometimes even leading to unsafe driving behavior. Although existing vehicle noise control technologies can reduce the impact of external noise to a certain extent, these technologies are often unable to specifically identify and filter potentially disruptive horn sounds, especially those that are unreasonably sounded when there is no safety risk. Therefore, there is currently a lack of corresponding methods to deal with noisy horn sounds outside the vehicle. Summary of the Invention

[0003] In view of the above problems, the present invention provides a method for processing external vehicle horn sounds and related equipment, the main purpose of which is to solve the problem that there is currently a lack of corresponding processing methods for noisy external vehicle horn sounds.

[0004] To solve at least one of the above technical problems, in a first aspect, the present invention provides a method for processing an external horn sound of a vehicle, the method comprising:

[0005] Acquiring an optimized audio signal outside the target vehicle, wherein the optimized audio signal is determined by preprocessing the initial audio signal;

[0006] classifying the optimized audio signal based on a support vector machine to obtain an audio classification result;

[0007] The audio classification result is combined with the environment outside the target vehicle and the target vehicle's own state to determine an audio filtering operation outside the target vehicle.

[0008] Optionally, the above method further includes:

[0009] Acquire an initial audio signal outside the target vehicle;

[0010] The initial audio signal is preprocessed to obtain the optimized audio signal, wherein the preprocessing includes pre-emphasis processing, framing and windowing processing, fast Fourier transform processing, Mel filter bank processing and discrete cosine transform processing.

[0011] Optionally, preprocessing the initial audio signal to obtain the optimized audio signal includes:

[0012] The pre-emphasis processing is performed on the initial audio signal based on the following formula to obtain a second audio signal:

[0013] s′[n]=s[n]-αs[n-1]

[0014] Wherein, s′[n] is the second audio signal, s[n] is the initial audio signal, and the value range of α is 0.9-0.97;

[0015] The second audio signal is subjected to the framing and windowing processing based on the following formula to obtain a third audio signal:

[0016] xi[n]=s′[n+iH]w[n]

[0017] Wherein, xi[n] is the third audio signal, indicating the audio signal of the i-th frame, H is the frame shift, and w[n] is the window function.

[0018] Optionally, the preprocessing the initial audio signal to obtain the optimized audio signal includes:

[0019] performing the fast Fourier transform process on the third audio signal to obtain a fourth audio signal;

[0020] The Mel filter bank processing is performed on the fourth audio signal based on the following formula to obtain a fifth audio signal:

[0021] E i [m]=∑ k |X i [k]M m [k]| 2

[0022] Among them, E i [m] is the fifth audio signal, representing the Mel spectrum energy of the i-th frame, X i [k] is the fourth audio signal, representing the spectrum, and m is the index of the Mel filter bank;

[0023] The fifth audio signal is subjected to the discrete cosine transform process based on the following formula to obtain the optimized audio signal:

[0024]

[0025] Among them, c i [n] is the optimized audio signal, representing the nth Mel frequency cepstral coefficient of the i-th frame, and M is the number of Mel filters.

[0026] Optionally, classifying the optimized audio signal based on a support vector machine to obtain an audio classification result includes:

[0027] Inputting the optimized audio signal as a feature vector into the support vector machine;

[0028] Training the support vector machine to determine a classification hyperplane to minimize the classification error of the optimized audio signal;

[0029] The optimized audio signal is classified based on the support vector machine to obtain a classification result, wherein the classification result includes urgent audio and irrational audio.

[0030] Optionally, combining the audio classification result with the environment outside the target vehicle and the target vehicle's own state to determine an audio filtering operation outside the target vehicle includes:

[0031] Construct a multimodal data fusion model based on Kalman filtering and deep learning;

[0032] The audio classification result is combined with the environment outside the target vehicle and the target vehicle's own state through the multimodal data fusion model to determine the audio filtering operation outside the target vehicle.

[0033] Optionally, combining the audio classification result with the environment outside the target vehicle and the target vehicle's own state through the multimodal data fusion model to determine an audio filtering operation outside the target vehicle includes:

[0034] Determine the external environment and the state of the target vehicle based on Kalman filtering technology; and

[0035] Visual information and time series data of the target vehicle are determined based on deep learning.

[0036] In a second aspect, an embodiment of the present invention further provides an external vehicle horn sound processing device, comprising:

[0037] an acquiring unit, configured to acquire an optimized audio signal outside the target vehicle, wherein the optimized audio signal is determined by preprocessing the initial audio signal;

[0038] A classification unit, configured to classify the optimized audio signal using a support vector machine to obtain an audio classification result;

[0039] A determination unit is configured to combine the audio classification result with the environment outside the target vehicle and the target vehicle's own state to determine an audio filtering operation outside the target vehicle.

[0040] To achieve the above object, according to a third aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed by a processor, the steps of the above-mentioned method for processing external vehicle horn sound are implemented.

[0041] In order to achieve the above-mentioned purpose, according to the fourth aspect of the present invention, an electronic device is provided, comprising at least one processor and at least one memory connected to the processor; wherein the above-mentioned processor is used to call the program instructions in the above-mentioned memory to execute the steps of the above-mentioned method for processing the external vehicle horn sound.

[0042] By means of the above technical solution, the present invention provides a method for processing the horn sound outside the vehicle and related equipment. This solves the problem that there is currently a lack of corresponding processing methods for noisy horn sounds outside the vehicle. The present invention obtains an optimized audio signal outside the target vehicle, wherein the optimized audio signal is determined by pre-processing the initial audio signal; the optimized audio signal is classified based on a support vector machine to obtain an audio classification result; and the audio classification result is combined with the environment outside the target vehicle and its own state to determine the audio filtering operation outside the target vehicle. In the above solution, the horn sound outside the vehicle is identified and its characteristics (such as frequency, intensity, duration, etc.) are analyzed. Combined with the road condition and vehicle condition information collected by sensors such as on-board cameras, an intelligent algorithm is used to determine whether these horn sounds represent actual safety risks. When the system determines that the horn sound is an unreasonable interference, it can automatically adjust the audio system in the car to reduce or filter out these horn sounds, thereby protecting the driver from interference and ensuring the safety of the driving process.

[0043] Correspondingly, the external vehicle horn sound processing device, equipment, and computer-readable storage medium provided by the embodiments of the present invention also have the above-mentioned technical effects.

[0044] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0046] Figure 1 A schematic flow chart of a method for processing an external vehicle horn sound provided by an embodiment of the present invention is shown;

[0047] Figure 2 A schematic block diagram showing the composition of an external vehicle horn sound processing device provided by an embodiment of the present invention is shown;

[0048] Figure 3A schematic block diagram of the composition of an electronic device for processing off-vehicle horn sound provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0049] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0050] In order to solve the problem of the lack of corresponding processing methods for the noisy horn sound outside the car, the embodiment of the present invention provides a method for processing the horn sound outside the car, such as Figure 1 As shown, the method includes:

[0051] S101, obtaining an optimized audio signal outside a target vehicle, wherein the optimized audio signal is determined by preprocessing an initial audio signal;

[0052] The above step S101 further includes S1011, S1012 and S1013:

[0053] S1011, obtaining an initial audio signal outside the target vehicle;

[0054] The initial audio signal is preprocessed to obtain the optimized audio signal, wherein the preprocessing includes pre-emphasis processing, framing and windowing processing, fast Fourier transform processing, Mel filter bank processing and discrete cosine transform processing.

[0055] For example, this application uses a microphone array outside the vehicle to collect ambient sound signals. High dynamic range audio processing technology is used to ensure accurate sound capture, including low-frequency to high-frequency horn sounds. A sound recognition algorithm is applied to analyze the collected audio signals, identifying the characteristics of the horn sound (including frequency, intensity, duration, etc.). Using machine learning techniques, a model is trained to distinguish between emergency horn sounds and unreasonable horn sounds, while also considering factors such as the direction of the sound source and relative speed.

[0056] S1012: Perform the pre-emphasis processing on the initial audio signal based on the following formula to obtain a second audio signal:

[0057] s′[n]=s[n]-αs[n-1]

[0058] Wherein, s′[n] is the second audio signal, s[n] is the initial audio signal, and the value range of α is 0.9-0.97;

[0059] The second audio signal is subjected to the framing and windowing processing based on the following formula to obtain a third audio signal:

[0060] xi[n]=s′[n+iH]w[n]

[0061] Wherein, xi[n] is the third audio signal, indicating the audio signal of the i-th frame, H is the frame shift, and w[n] is the window function.

[0062] S1013. Perform the fast Fourier transform process on the third audio signal to obtain a fourth audio signal;

[0063] The Mel filter bank processing is performed on the fourth audio signal based on the following formula to obtain a fifth audio signal:

[0064] E i [m]=∑ k |X i [k]M m [k]| 2

[0065] Among them, E i [m] is the fifth audio signal, representing the Mel spectrum energy of the i-th frame, X i [k] is the fourth audio signal, representing the spectrum, and m is the index of the Mel filter bank;

[0066] The fifth audio signal is subjected to the discrete cosine transform process based on the following formula to obtain the optimized audio signal:

[0067]

[0068] Among them, c i [n] is the optimized audio signal, representing the nth Mel frequency cepstral coefficient of the i-th frame, and M is the number of Mel filters.

[0069] Specifically, this application first preprocesses the collected initial audio signal, including denoising, normalization, and feature extraction. In the feature extraction stage, Mel-Frequency Cepstral Coefficients (MFCC) can be used as the feature representation of the sound. MFCC can effectively capture the basic properties of the sound. Its feature extraction process can be simplified into the following steps:

[0070] Pre-emphasis processing: pre-emphasize the initial audio signal s[n] to enhance the high-frequency components;

[0071] Framing and windowing: divide s′[n] into overlapping frames and add a window to each frame;

[0072] The purpose of the above-mentioned pre-emphasis and frame windowing is to enhance the features in the signal that are important for horn sound recognition, while reducing the influence of background noise.

[0073] Fast Fourier transform (FFT): Perform FFT on each frame signal xi[n] to obtain the spectrum X i [k];

[0074] Mel filter bank processing: Apply a set of Mel filters M[k] to X i [k], calculate the Mel spectrum energy of each frame;

[0075] Discrete cosine transform (DCT): Mel spectrum energy E for each frame i [m] Perform DCT and obtain MFCC.

[0076] S102, classifying the optimized audio signal based on a support vector machine to obtain an audio classification result;

[0077] The above step S102 further includes S1021:

[0078] S1021. Input the optimized audio signal as a feature vector into the support vector machine; train the support vector machine to determine a classification hyperplane to minimize the classification error of the optimized audio signal; classify the optimized audio signal based on the support vector machine to obtain a classification result, wherein the classification result includes urgent audio and irrational audio.

[0079] For example, after the initial audio signal is pre-processed as described above, a support vector machine (SVM) is used to classify the horn sound. The goal of the SVM is to find a hyperplane that maximizes the margin between data points of different categories.

[0080] Specifically, first extract the MFCC c i [n] is input into the SVM as a feature vector. Then, the SVM model is trained to find the classification hyperplane that minimizes the classification error:

[0081]

[0082] Requirements:

[0083]

[0084] in, and b define the hyperplane, C is the penalty parameter, ξi is the slack variable, φ(xi) is the function that maps the data to a higher dimensional space, y i is the category label.

[0085] Then, the horn sound classification is performed. For the new horn sound feature vector, the trained SVM model is used to classify it to determine whether it is an emergency horn sound or an unreasonable horn sound, that is, the emergency audio and unreasonable audio mentioned above.

[0086] The audio classification results outputted above will directly affect the input of the following step of "combining the audio classification results with the environment outside the target vehicle and its own state to determine the audio filtering operation outside the target vehicle", wherein the audio classification results will be combined with the vehicle's environment and state information for a more in-depth analysis. Through this integration, the present application is able to evaluate the urgency and relevance of the horn sound in a broader context, thereby improving the accuracy of the final decision. In addition, the classification results of the horn sound will also guide the audio filtering operation outside the target vehicle and the in-vehicle audio control operation, determining whether and how to adjust the in-vehicle audio system to ensure that the driver is only alerted by important warning sounds.

[0087] S103: Combining the audio classification result with the environment outside the target vehicle and the target vehicle's own state to determine an audio filtering operation outside the target vehicle.

[0088] The above step S103 further includes S1031 and S1032:

[0089] S1031. Constructing a multimodal data fusion model based on Kalman filtering and deep learning;

[0090] The audio classification result is combined with the environment outside the target vehicle and the target vehicle's own state through the multimodal data fusion model to determine the audio filtering operation outside the target vehicle.

[0091] Exemplarily, the present application collects real-time road and vehicle condition information through on-board cameras, radars and other sensors. The horn sound data and environmental data are comprehensively analyzed, and a deep learning algorithm is used to evaluate the relevance and urgency of the horn sound. Advanced data fusion technology is used to comprehensively process and analyze data collected from different sources, including the above-mentioned horn data and environmental and vehicle condition data collected by on-board sensors (such as cameras and radars). The core of this step is to use a data fusion algorithm to perform synthetic analysis on the information, thereby accurately evaluating the urgency and relevance of the horn sound.

[0092] Furthermore, to achieve effective data fusion, multimodal data fusion technology is employed, specifically a fusion model based on Kalman filtering and deep learning techniques. Kalman filtering technology has significant advantages in processing noisy dynamic system state estimation and is suitable for real-time updating and prediction of vehicle states. Deep learning techniques, particularly convolutional neural networks (CNNs) and long short-term memory networks (LSTMs), can effectively process and analyze visual information and time series data.

[0093] Based on the above solution, advanced audio processing technology, environmental perception capabilities and deep learning algorithms are used to intelligently identify and filter out irrelevant horn sounds outside the car, while ensuring that emergency and relevant warning sounds can be noticed by the driver in a timely manner.

[0094] The above step S1031 further includes S10311:

[0095] S10311. Determine the external environment and the state of the target vehicle based on Kalman filtering technology; and determine the visual information and time series data of the target vehicle based on deep learning.

[0096] The specific steps are as follows:

[0097] Preprocessing: First, the various collected data (horn sound data, video streams, radar signals, etc.) are preprocessed, including denoising, standardization and feature extraction to ensure data quality and consistency.

[0098] Feature fusion: Preprocessed data features are integrated through deep learning models. For example, CNN is used to extract environmental features from image data captured by the vehicle camera, while LSTM is used to process the horn sound features and time series features of the vehicle's motion state captured by the microphone.

[0099] Kalman filter state estimation: Kalman filter technology is used to estimate and predict the current state of the vehicle and the state of the environment, integrating information from different sensors to obtain a more accurate representation of the vehicle and environment states.

[0100] Urgency and Relevance Assessment: Based on the fused features and state estimates, the SVM model trained in the previous step is used to further assess the urgency and relevance of the horn sound. This model can learn to identify when the horn sound has an urgent impact on safety and when it can be considered insignificant.

[0101] Decision support output: Based on the urgency and relevance assessment results of the horn sound, the system provides decision support information to guide the subsequent horn sound intelligent filtering and in-car audio control modules to take corresponding actions.

[0102] After completing the preliminary horn sound classification based on the SVM, the above-mentioned step of "combining the audio classification results with the environment outside the target vehicle and the vehicle's own state through the multimodal data fusion model to determine the audio filtering operation outside the target vehicle" is specifically as follows:

[0103] Contextual Verification: Utilizes the vehicle’s current environment and state information (such as speed, distance to surrounding vehicles, weather conditions, etc.) to verify the horn classification results. For example, if a horn is detected in dense traffic and the vehicle’s speed suddenly slows down, this may indicate that the detected horn has a high urgency.

[0104] Classification Adjustment: Based on environmental and vehicle condition data, the system may adjust the confidence level of its initial classification results. For example, if the system classifies a horn as "unreasonable" based on sound characteristics, but subsequent environmental analysis reveals a pedestrian suddenly crossing the road ahead, the system may increase the horn's score to "urgent."

[0105] Composite Decision Making: The system can integrate sound classification results with environmental and vehicle condition data, using decision fusion algorithms (such as decision trees, Bayesian networks, or ensemble learning methods) to make a final response decision. This may include determining whether to filter a particular horn sound and how to adjust the in-car audio system to respond to the horn sound.

[0106] It should be noted that this application considers the following scenario: a driver is driving in busy city traffic, and the system captures a strong horn sound through an external microphone array. It is initially identified as non-emergency by the "Horn Sound Recognition and Analysis Module". However, at the same time, the "Environmental and Vehicle Condition Data Integration Analysis Module" analyzes the real-time video stream from the on-board camera and finds that a child suddenly runs towards the road in front. Combined with this environmental information, the system re-evaluates the horn sound as high urgency and chooses not to filter the sound, ensuring that the driver can receive a timely warning and take necessary avoidance measures. This example shows how, by comprehensively analyzing data from different sources, the system can make more accurate judgments in complex actual driving environments.

[0107] It's important to note that this application determines whether to filter or adjust the perceived intensity of specific horn sounds within the vehicle based on horn sound analysis and environmental assessment. Through intelligent adjustments to the vehicle's audio system or other in-vehicle noise control systems, horn sounds deemed unreasonably disruptive can be reduced or completely filtered out, while ensuring that important warning sounds remain unaffected.

[0108] Furthermore, the present application provides a user interface that allows the driver to set the sensitivity and parameters of the horn sound filtering according to personal preferences, and supports the driver to quickly adjust and set it through voice commands or touch screen.

[0109] This solution also takes into account user customization needs, allowing drivers to adjust the sensitivity and range of horn filtering based on their personal preferences. By analyzing real-time road and vehicle conditions, the system ensures a more tranquil and focused driving environment while ensuring safety, effectively improving driver comfort and satisfaction.

[0110] Through the above-mentioned technical solution, the present invention provides a method for processing external horn sounds, addressing the current lack of corresponding methods for processing noisy external horn sounds. The present invention obtains an optimized audio signal from the target vehicle's exterior, wherein the optimized audio signal is determined by preprocessing the initial audio signal; classifies the optimized audio signal using a support vector machine to obtain an audio classification result; and combines the audio classification result with the target vehicle's external environment and internal state to determine the target vehicle's external audio filtering operation. In this method, the vehicle's built-in audio processing and environmental perception technologies enable intelligent recognition, urgency assessment, and filtering of external horn sounds. Using advanced audio recognition algorithms and data collected by sensors such as onboard cameras, the system comprehensively analyzes the horn sound's source, frequency, duration, and relationship to current road and vehicle conditions to intelligently determine whether the horn sound has actual safety warning significance. For horn sounds identified as unreasonable and abusive and not substantially helpful to the driver, the system automatically adjusts the vehicle's in-vehicle audio system to reduce or completely filter these sounds, reducing unnecessary distractions to the driver and thereby improving driving safety and the driving experience.

[0111] Furthermore, as a response to the above Figure 1 In order to realize the method shown in the figure, the embodiment of the present invention also provides a vehicle horn sound processing device for processing the above-mentioned Figure 1 This device embodiment corresponds to the aforementioned method embodiment. For ease of reading, this device embodiment will not describe the details of the aforementioned method embodiment one by one, but it should be clear that the device in this embodiment can implement all the contents of the aforementioned method embodiment. Figure 2 As shown, the device includes: an acquisition unit 21, a classification unit 22, and a determination unit 23, wherein

[0112] an acquiring unit 21 for acquiring an optimized audio signal outside the target vehicle, wherein the optimized audio signal is determined by preprocessing the initial audio signal;

[0113] A classification unit 22, configured to classify the optimized audio signal using a support vector machine to obtain an audio classification result;

[0114] The determining unit 23 is configured to combine the audio classification result with the environment outside the target vehicle and the target vehicle's own state to determine an audio filtering operation outside the target vehicle.

[0115] The processor includes a core that retrieves corresponding program units from memory. One or more cores can be configured, and by adjusting core parameters, a method for processing external horn sounds can be implemented, addressing the current lack of a corresponding method for processing noisy external horn sounds.

[0116] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program. When the program is executed by a processor, the method for processing the external vehicle horn sound is implemented.

[0117] An embodiment of the present invention provides a processor, which is used to run a program, wherein the method for processing an external vehicle horn sound is executed when the program is run.

[0118] An embodiment of the present invention provides an electronic device, comprising at least one processor and at least one memory connected to the processor; wherein the processor is configured to call program instructions in the memory to execute the above-mentioned method for processing an external vehicle horn sound.

[0119] An embodiment of the present invention provides an electronic device 30, such as Figure 3 As shown, the electronic device includes at least one processor 301, and at least one memory 302 and a bus 303 connected to the processor; wherein the processor 301 and the memory 302 communicate with each other through the bus 303; the processor 301 is used to call the program instructions in the memory to execute the above-mentioned vehicle external horn sound processing method.

[0120] The intelligent electronic devices in this article can be PCs, PADs, mobile phones, etc.

[0121] The present application also provides a computer program product, which, when executed on a process management electronic device, is suitable for executing a program initialized with the steps of the above-mentioned method for processing external vehicle horn sounds.

[0122] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0123] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0124] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0125] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0126] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0127] The present application also provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device is caused to execute the following Figure 1 This corresponds to the flow of memory control in the embodiment.

[0128] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)).

[0129] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0130] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0131] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0132] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0133] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0134] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for processing an external horn sound, characterized in that: include: Acquiring an optimized audio signal outside the target vehicle, wherein the optimized audio signal is determined by preprocessing the initial audio signal; classifying the optimized audio signal based on a support vector machine to obtain an audio classification result; combining the audio classification result with the environment outside the target vehicle and the target vehicle's own state to determine an audio filtering operation outside the target vehicle; The step of combining the audio classification result with the environment outside the target vehicle and the target vehicle's own state to determine an audio filtering operation outside the target vehicle includes: Construct a multimodal data fusion model based on Kalman filtering and deep learning; Combining the audio classification result with the environment outside the target vehicle and the target vehicle's own state through the multimodal data fusion model to determine an audio filtering operation outside the target vehicle; Verify the horn sound classification results using the vehicle's current environment and status information; Based on the environment and vehicle condition data, the system adjusts the confidence level of the initial classification results; The system integrates the sound classification results with the environment and vehicle condition data, and uses a decision fusion algorithm to make the final response decision.

2. The method according to claim 1, characterized in that Also includes: Acquire an initial audio signal outside the target vehicle; The initial audio signal is preprocessed to obtain the optimized audio signal, wherein the preprocessing includes pre-emphasis processing, framing and windowing processing, fast Fourier transform processing, Mel filter bank processing and discrete cosine transform processing.

3. The method according to claim 2, characterized in that The preprocessing of the initial audio signal to obtain the optimized audio signal includes: The pre-emphasis processing is performed on the initial audio signal based on the following formula to obtain a second audio signal: in, is the second audio signal, is the initial audio signal, The value range is 0.9-0.97; The second audio signal is subjected to the framing and windowing processing based on the following formula to obtain a third audio signal: in, is the third audio signal, indicating Frame audio signal, is frame shift, is the window function.

4. The method according to claim 3, characterized in that The preprocessing of the initial audio signal to obtain the optimized audio signal includes: performing the fast Fourier transform process on the third audio signal to obtain a fourth audio signal; The Mel filter bank processing is performed on the fourth audio signal based on the following formula to obtain a fifth audio signal: in, is the fifth audio signal, indicating Mel spectrum energy of the frame, is the fourth audio signal, representing a frequency spectrum, is the index of the Mel filter bank; The fifth audio signal is subjected to the discrete cosine transform process based on the following formula to obtain the optimized audio signal: in, is the optimized audio signal, indicating Frame No. Mel-frequency cepstral coefficients, is the number of Mel filters.

5. The method according to claim 4, characterized in that The classifying the optimized audio signal based on a support vector machine to obtain an audio classification result includes: Inputting the optimized audio signal as a feature vector into the support vector machine; Training the support vector machine to determine a classification hyperplane to minimize the classification error of the optimized audio signal; The optimized audio signal is classified based on the support vector machine to obtain a classification result, wherein the classification result includes urgent audio and irrational audio.

6. The method according to claim 1, characterized in that The step of combining the audio classification result with the environment outside the target vehicle and the target vehicle's own state through the multimodal data fusion model to determine an audio filtering operation outside the target vehicle includes: Determine the external environment and the state of the target vehicle based on Kalman filtering technology; and Visual information and time series data of the target vehicle are determined based on deep learning.

7. A vehicle external horn sound processing device, characterized in that: Also includes: an acquiring unit, configured to acquire an optimized audio signal outside the target vehicle, wherein the optimized audio signal is determined by preprocessing the initial audio signal; A classification unit, configured to classify the optimized audio signal using a support vector machine to obtain an audio classification result; a determination unit for combining the audio classification result with the environment outside the target vehicle and its own state to determine an audio filtering operation outside the target vehicle; The step of combining the audio classification result with the environment outside the target vehicle and the target vehicle's own state to determine an audio filtering operation outside the target vehicle includes: Construct a multimodal data fusion model based on Kalman filtering and deep learning; Combining the audio classification result with the environment outside the target vehicle and the target vehicle's own state through the multimodal data fusion model to determine an audio filtering operation outside the target vehicle; Verify the horn sound classification results using the vehicle's current environment and status information; Based on the environment and vehicle condition data, the system adjusts the confidence level of the initial classification results; The system integrates the sound classification results with the environment and vehicle condition data, and uses a decision fusion algorithm to make the final response decision.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein when the program is executed by a processor, the steps of the method for processing an external horn sound of a vehicle according to any one of claims 1 to 6 are implemented.

9. An electronic device, characterized in that: The electronic device includes at least one processor and at least one memory connected to the processor; wherein the processor is used to call program instructions in the memory to execute the steps of the external vehicle horn sound processing method according to any one of claims 1 to 6.

Images