Detection method and device for abnormal sound in vehicle, vehicle and storage medium

Abstract

The invention provides an in-vehicle abnormal sound detection method and device, a vehicle and a storage medium, the method is applied to the field of vehicles, and the method comprises the steps that under the condition that the vehicle is in a power-on state, whether target abnormal sound is generated in a compartment of the vehicle or not is detected; when it is detected that the target abnormal sound is generated in the compartment, the generation position of the target abnormal sound is determined, and an abnormal sound generation process video at the generation position of the target abnormal sound is recorded; and playing the abnormal sound generation process video. According to the method, the abnormal sound generation process video can be recorded and played under the condition that the target abnormal sound is detected to be generated in the compartment, so that a driver can quickly identify an abnormal sound source in the vehicle, the distraction of the driver caused by unknown abnormal sound is reduced, and the driving safety and the driving concentration are remarkably improved.

Description

Technical Field

[0001] The present application relates to the field of vehicles, and more specifically, to a method, a device, a vehicle and a storage medium for detecting abnormal noise in a vehicle. Background Art

[0002] As modern cars become more complex and their interior space utilization rate increases, drivers are faced with more and more distractions during driving. Especially in long-distance driving or complex road conditions, unusual noises in the car (such as items moving in the trunk, items falling from the seat, etc.) can easily arouse the driver's curiosity and anxiety, which in turn distracts attention and affects driving safety.

[0003] The existing solution is often to stop and check, but this not only wastes time, but may also cause traffic safety hazards in some cases. Summary of the invention

[0004] The present application provides a method, device, vehicle and storage medium for detecting abnormal noise in a vehicle. The method can record and play a video of the abnormal noise generation process when a target abnormal noise is detected inside the vehicle compartment, so as to facilitate the driver to quickly identify the source of the abnormal noise in the vehicle, reduce the driver's distraction caused by unknown abnormal noise, and significantly improve driving safety and driving concentration.

[0005] In a first aspect, a method for detecting abnormal noise in a vehicle is provided, the method comprising: when the vehicle is in a powered-on state, detecting whether a target abnormal noise is generated inside a cabin of the vehicle; when the target abnormal noise is detected inside the cabin, determining a generation location of the target abnormal noise, and recording a video of the abnormal noise generation process at the generation location of the target abnormal noise; and playing the video of the abnormal noise generation process.

[0006] The above technical solution detects in real time whether there is a target abnormal sound inside the vehicle's cabin when the vehicle is powered on, and determines the location of the target abnormal sound when the target abnormal sound is detected inside the cabin, and promptly discovers potential safety hazards inside the cabin through real-time monitoring and precise positioning of the abnormal sound. In addition, when a target abnormal sound is detected inside the cabin, a video of the abnormal sound generation process is recorded, and then the video of the abnormal sound generation process is played, so that the driver can quickly identify the source of the abnormal sound in the car, reduce the driver's distraction caused by unknown abnormal sounds, significantly improve driving safety and driving concentration, and enable the driver to focus on road conditions more at ease, thereby effectively reducing the risk of potential accidents.

[0007] In combination with the first aspect, in certain implementations of the first aspect, playing the video of the abnormal sound generation process includes: determining a target playback mode of the video of the abnormal sound generation process; and playing the video of the abnormal sound generation process according to the target playback mode.

[0008] In combination with the first aspect and the above-mentioned implementation methods, in certain implementation methods of the first aspect, determining the target playback mode of the abnormal sound generation process video includes: when the target abnormal sound is generated once, determining the target playback mode as: playing the abnormal sound generation process video in the target display area of ​​the vehicle screen according to the first preset playback duration, and playing the abnormal sound generation process video with magnified details in a sub-window in the target display area; when the target abnormal sound is generated more than or equal to two times, determining the target playback mode according to the generation position of each target abnormal sound in multiple target abnormal sounds and the generation time point of each target abnormal sound in the multiple target abnormal sounds.

[0009] In the above technical solution, when the target abnormal sound occurs once, the video is played in the target display area of ​​the vehicle screen according to the first preset playback time, which allows the user to focus on the specific area, and the abnormal sound generation process video with magnified details is played in the sub-window of the target display area, which helps the user to observe the details of the abnormal sound generation moment more clearly. When the target abnormal sound occurs multiple times, the playback mode is determined according to the generation position of each target abnormal sound and the generation time point of each target abnormal sound, so as to facilitate the subsequent more reasonable playback of the abnormal sound generation process video corresponding to multiple target abnormal sounds, so as to facilitate the user to understand the generation process of the abnormal sound more clearly.

[0010] In combination with the first aspect and the above-mentioned implementation manner, in some implementation manners of the first aspect, the target playback mode is determined according to the generation position of each target abnormal sound among multiple target abnormal sounds and the generation time point of each target abnormal sound among the multiple target abnormal sounds, including: if the interval distance between the generation positions of any two target abnormal sounds among the multiple target abnormal sounds is greater than a preset distance threshold and the generation time points of any two target abnormal sounds among the multiple target abnormal sounds are the same time point, then the target playback mode is determined as: according to a preset order and a second preset playback time, the abnormal sound generation process video is played in the target display area of ​​the vehicle screen in sequence, and the abnormal sound generation process video with magnified details is played in the sub-window in the target display area; if the interval distance between the generation positions of any two target abnormal sounds among the multiple target abnormal sounds is less than or equal to the preset distance threshold and the time difference between the generation time points of any two target abnormal sounds among the multiple target abnormal sounds is less than or equal to the preset time threshold, then the target playback mode is determined as: according to a third preset playback time, the abnormal sound generation process video is played in the target display area of ​​the vehicle screen.

[0011] In the above technical solution, when the distance between any two abnormal sound generation locations among multiple target abnormal sounds is greater than the preset distance threshold and the generation time points are the same, the abnormal sound generation process video is played in a preset order, so that the abnormal sounds generated at multiple different locations at the same time can be presented in an orderly manner. The second preset playback time is set to ensure that the abnormal sound video at each location has enough time to be displayed, so that the user can fully observe the abnormal sound process. At the same time, playing the video with enlarged details in the subwindow of the target display area helps the user to clearly capture the details of the moment when the abnormal sound is generated at each location. When the distance between any two abnormal sound generation locations among multiple target abnormal sounds is less than or equal to the preset distance threshold and the time difference between the generation time points is less than or equal to the preset time threshold, it means that these abnormal sounds are relatively concentrated in space and time. According to the third preset playback time, the abnormal sound generation process video is played in the target display area of ​​the vehicle screen, and these concentrated target abnormal sounds can be presented to the user as a whole. Users do not need to switch between multiple video clips to view, and can more efficiently understand multiple closely related target abnormal sounds, avoiding interference to users caused by playing multiple videos.

[0012] In combination with the first aspect and the above-mentioned implementation methods, in some implementation methods of the first aspect, detecting whether a target abnormal sound is generated inside the vehicle cabin includes: collecting sound data inside the cabin in real time; determining whether there is sound data matching the characteristics of the target abnormal sound in the collected sound data; and determining that the target abnormal sound is generated inside the cabin if there is sound data matching the characteristics of the target abnormal sound.

[0013] The above technical solution collects the sound data inside the car in real time, ensuring that the sound changes at any time can be captured in time. The collected sound data is compared with the pre-set target abnormal sound characteristics to determine whether the target abnormal sound exists. The target abnormal sound can be accurately identified, and the interference of other irrelevant sounds is eliminated, thereby improving the accuracy of the judgment.

[0014] In combination with the first aspect and the above-mentioned implementation methods, in certain implementation methods of the first aspect, recording the video of the abnormal sound generation process at the target abnormal sound generation location includes: calculating the interval distance between each camera of the multiple cameras inside the vehicle and the target abnormal sound generation location, and determining the camera among the multiple cameras with the shortest interval distance to the target abnormal sound generation location as the target recording camera; controlling the target recording camera to record the video of the abnormal sound generation process at the target abnormal sound generation location.

[0015] The above technical solution selects the camera with the shortest interval as the target recording camera, which can minimize the problems of blurred images and loss of details caused by distance. The closer the distance, the clearer the image captured by the camera, and the more accurately the specific situation of the location where the abnormal sound is generated can be presented.

[0016] In combination with the first aspect and the above-mentioned implementation methods, in some implementation methods of the first aspect, playing the video of the abnormal sound generation process includes: determining whether there is a preset privacy screen in the video of the abnormal sound generation process; when it is determined that there is the preset privacy screen, blurring the preset privacy screen in the video of the abnormal sound generation process to obtain the blurred video of the abnormal sound generation process; and playing the blurred video of the abnormal sound generation process.

[0017] The above technical solution, by judging and blurring the preset privacy screen, can prevent the improper acquisition and abuse of these private contents from the source, effectively protect the personal privacy security of users, and avoid potential risks brought to users by privacy leakage, such as identity theft, harassment and other issues. The blurred video removes the private content that may cause users to be sensitive or uncomfortable, and will not distract the user's attention during playback, allowing users to focus more on information related to abnormal sounds, thereby optimizing the experience of watching and analyzing videos and improving the user's experience.

[0018] In a second aspect, a device for detecting abnormal noise in a vehicle is provided, the device comprising: a detection module, for detecting whether a target abnormal noise is generated inside a vehicle compartment when the vehicle is in a powered-on state; a recording module, for determining a generating position of the target abnormal noise when a target abnormal noise is detected inside the vehicle compartment, and recording a video of the abnormal noise generating process at the generating position of the target abnormal noise; and a playback module, for playing the video of the abnormal noise generating process.

[0019] In combination with the second aspect, in certain implementations of the second aspect, the playback module is specifically used to: determine a target playback mode for the video of the abnormal sound generation process; and play the video of the abnormal sound generation process according to the target playback mode.

[0020] In combination with the second aspect and the above-mentioned implementation methods, in some implementation methods of the second aspect, the playback module includes a determination unit, which is specifically used to: when the target abnormal sound is generated once, determine the target playback mode as: according to the first preset playback time, play the abnormal sound generation process video in the target display area of ​​the vehicle screen, and play the abnormal sound generation process video with enlarged details in the sub-window in the target display area; when the target abnormal sound is generated more than or equal to two times, determine the target playback mode according to the generation position of each target abnormal sound in multiple target abnormal sounds and the generation time point of each target abnormal sound in the multiple target abnormal sounds.

[0021] In combination with the second aspect and the above-mentioned implementation manner, in some implementation manners of the second aspect, the determination unit is further specifically used to: if the interval distance between the generation positions of any two target abnormal sounds among the multiple target abnormal sounds is greater than a preset distance threshold and the generation time points of any two target abnormal sounds among the multiple target abnormal sounds are the same time point, then determine the target playback mode as: play the abnormal sound generation process video in the target display area of ​​the vehicle screen in sequence according to a preset order and a second preset playback duration, and play the abnormal sound generation process video with magnified details in a sub-window in the target display area; if the interval distance between the generation positions of any two target abnormal sounds among the multiple target abnormal sounds is less than or equal to the preset distance threshold and the time difference between the generation time points of any two target abnormal sounds among the multiple target abnormal sounds is less than or equal to the preset time threshold, then determine the target playback mode as: play the abnormal sound generation process video in the target display area of ​​the vehicle screen according to a third preset playback duration.

[0022] In combination with the second aspect and the above-mentioned implementation methods, in some implementation methods of the second aspect, the detection module is specifically used to: collect sound data inside the car in real time; determine whether there is sound data matching the characteristics of the target abnormal sound in the collected sound data; and determine that the target abnormal sound is generated inside the car if there is sound data matching the characteristics of the target abnormal sound.

[0023] In combination with the second aspect and the above-mentioned implementation methods, in certain implementation methods of the second aspect, the recording module is specifically used to: calculate the interval distance between each camera of the multiple cameras inside the vehicle and the location where the target abnormal sound is generated, and determine the camera among the multiple cameras with the shortest interval distance to the location where the target abnormal sound is generated as the target recording camera; control the target recording camera to record the video of the abnormal sound generation process at the location where the target abnormal sound is generated.

[0024] In combination with the second aspect and the above-mentioned implementation methods, in some implementation methods of the second aspect, the playback module is also specifically used to: determine whether there is a preset privacy screen in the video of the abnormal sound generation process; when it is determined that the preset privacy screen exists, blur the preset privacy screen in the video of the abnormal sound generation process to obtain the blurred video of the abnormal sound generation process; and play the blurred video of the abnormal sound generation process.

[0025] In a third aspect, a vehicle is provided, comprising a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the vehicle executes the method for detecting abnormal noise in the vehicle in the first aspect and any possible implementation of the first aspect.

[0026] In a fourth aspect, a computer program product is provided, which includes: a computer program code, which, when executed on a computer, enables the computer to execute the method for detecting abnormal noise in a vehicle in the first aspect and any possible implementation of the first aspect.

[0027] In a fifth aspect, a computer-readable storage medium is provided, which stores a computer program code. When the computer program code runs on a computer, the computer executes the method for detecting abnormal noise in a vehicle in the above-mentioned first aspect and any possible implementation of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 is a schematic flow chart of a method for detecting abnormal noise in a vehicle provided in an embodiment of the present application;

[0029] Figure 2 It is a structural schematic diagram of an abnormal noise detection system in a vehicle provided in an embodiment of the present application;

[0030] Figure 3 This is a schematic diagram of a playback interface of a video of an abnormal sound generation process provided in an embodiment of the present application;

[0031] Figure 4 This is a schematic diagram of another playback interface of a video of an abnormal sound generation process provided in an embodiment of the present application;

[0032] Figure 5 It is a structural schematic diagram of a device for detecting abnormal noise in a vehicle provided in an embodiment of the present application;

[0033] Figure 6 It is a structural schematic diagram of a vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0034] The technical solution in the present application will be described clearly and in detail below in conjunction with the accompanying drawings. In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B: "and / or" in the text is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0035] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.

[0036] As modern cars become more complex and their interior space utilization rate increases, drivers are faced with more and more distractions during driving. Especially in long-distance driving or complex road conditions, unusual noises in the car (such as items moving in the trunk, items falling from the seat, etc.) can easily arouse the driver's curiosity and anxiety, which in turn distracts attention and affects driving safety.

[0037] The existing solution is often to stop and check, but this not only wastes time, but may also cause traffic safety hazards in some cases.

[0038] In order to solve the above technical problems, the embodiment of the present application provides a method for detecting abnormal noise in a vehicle, and the execution subject of the method is a vehicle, specifically a controller in the vehicle. The method can detect abnormal noise generated in the vehicle in real time, and when a target abnormal noise is detected, provide the driver with a video of the abnormal noise generation process, which can help the driver quickly identify the source of the abnormal noise in the vehicle, thereby improving driving safety and concentration.

[0039] Figure 1 It is a schematic flow chart of a method for detecting abnormal noise in a vehicle provided in an embodiment of the present application.

[0040] For example, Figure 1 As shown, the method 100 includes:

[0041] S101, when the vehicle is powered on, detecting whether a target abnormal sound is generated inside the vehicle compartment;

[0042] S102, when a target abnormal sound is detected inside the vehicle compartment, determining a generating position of the target abnormal sound, and recording a video of the abnormal sound generating process at the generating position of the target abnormal sound;

[0043] S103, playing the video of the abnormal sound generation process.

[0044] In the embodiment of the present application, when the vehicle is powered on, it is detected in real time whether there is a target abnormal sound inside the vehicle compartment, and when the target abnormal sound is detected inside the compartment, the location of the target abnormal sound is determined, and the potential safety hazards inside the compartment are discovered in time through real-time monitoring and precise positioning of the abnormal sound. And when the target abnormal sound is detected inside the compartment, a video of the abnormal sound generation process is recorded, and then the video of the abnormal sound generation process is played, so that the driver can quickly identify the source of the abnormal sound in the car, reduce the driver's distraction caused by unknown abnormal sound, significantly improve driving safety and driving concentration, and enable the driver to focus on the road conditions more at ease, thereby effectively reducing the risk of potential accidents.

[0045] based on Figure 1 The method shown in the figure, the embodiment of the present application can also provide a vehicle abnormal sound detection system, such as Figure 2 As shown, the system 200 may include a sound sensor 201, a camera 202, a central control screen 203, and a central processing unit (CPU) 204. The CPU 204 may be connected to the sound sensor 201, the camera 202, and the central control screen 203, respectively.

[0046] The sound sensor 201 may be installed at different locations inside the vehicle compartment, such as between the front and rear seats of the vehicle, inside the trunk of the vehicle, etc. The sound sensor 201 may be used to capture sound data inside the vehicle compartment.

[0047] The camera 202 can be integrated into the ceiling screen of the vehicle, or installed in the trunk of the vehicle. The camera 202 can provide a wide-angle field of view that can cover the entire interior of the vehicle, and is used to record the video of the abnormal sound generation process. The camera 202 supports high-definition video streaming, and can quickly adjust the focus according to instructions to zoom in on a specific area of ​​the picture.

[0048] The central control screen 203 may be used to display the video images recorded by the camera 202 , and may also be used to display prompt information.

[0049] The CPU 204 is used to receive the sound data inside the vehicle cabin captured by the sound sensor 201, classify the sound data, and determine whether there is a target abnormal sound.

[0050] The CPU 204 is also used to receive the video of the abnormal sound generation process recorded by the camera 202, and perform image recognition on the video of the abnormal sound generation process.

[0051] The CPU 204 is also used to transmit the video of the abnormal sound generation process to the central control screen 203.

[0052] It can be understood that the above-mentioned CPU 204 can be understood as a processing unit in the controller of the vehicle.

[0053] The above-mentioned embodiment, through the in-vehicle abnormal sound detection system integrating sound sensors and cameras, can realize real-time monitoring and precise positioning of abnormal noises in the vehicle, and when the target abnormal noise is detected, immediately capture the image of the relevant area and play it on the central control screen, which can reduce the driver's distraction caused by unknown abnormal noises and enable the driver to focus on road conditions more at ease, thereby effectively reducing the risk of potential accidents and providing a smarter, more convenient and safer driving assistance experience.

[0054] Combine the following Figure 2 The system shown is Figure 1 The implementation method of each step in the illustrated embodiment is specifically described.

[0055] For the above S101, it can be understood that the above vehicle being powered on means that the vehicle's electrical system has been started and is working normally. When it is determined that the vehicle is powered on, the above vehicle abnormal sound detection system can be activated to detect whether there is a target abnormal sound inside the vehicle.

[0056] Exemplarily, when the vehicle's power management system detects that the vehicle is in a powered-on state, a signal indicating that the vehicle is in a powered-on state may be sent to the vehicle's controller, so that the vehicle's controller activates the in-vehicle abnormal sound detection system after receiving the signal.

[0057] In some embodiments, the above-mentioned abnormal noise detection system in the vehicle can also be activated when the vehicle is in driving state.

[0058] Exemplarily, a speed threshold may be set, and when the current speed of the vehicle is greater than or equal to the speed threshold, the vehicle controller may activate the in-vehicle abnormal sound detection system.

[0059] The target abnormal sound mentioned above refers to abnormal sound that is not a human voice or other normal operation sound, such as the abnormal sound caused by the movement of objects in the trunk, or the abnormal sound caused by objects falling from the seat.

[0060] For example, as described above, the sound data inside the car can be collected in real time by a sound sensor installed inside the car, and the sound data collected by the sound sensor can be transmitted to the CPU in real time for analysis, the sound data can be classified, and the target abnormal sound can be identified.

[0061] In one possible implementation, detecting whether a target abnormal sound is generated inside a vehicle cabin includes: collecting sound data from inside the cabin in real time; determining whether sound data matching the characteristics of the target abnormal sound exists in the collected sound data; and determining that the target abnormal sound is generated inside the cabin if sound data matching the characteristics of the target abnormal sound exists.

[0062] It is understandable that the sound data inside the car can be collected in real time by installing sound sensors at different locations inside the car.

[0063] Exemplarily, the collected sound data may include, but are not limited to, wind noise, engine noise, sound of electronic equipment running, human voice, and possible target abnormal noise during vehicle driving.

[0064] Furthermore, after the sound data inside the vehicle compartment is collected, the collected sound data can be transmitted to the CPU, which analyzes and determines the sound data to determine whether a target abnormal sound is generated inside the vehicle compartment.

[0065] In some embodiments, a large number of known target abnormal sound samples and other non-abnormal sound samples can be collected in advance, and these samples can be labeled and divided into two categories: "abnormal sound" and "non-abnormal sound". A classification model is constructed, and based on these samples, the classification model is trained using a machine learning algorithm, so that the trained classification model can determine whether there is sound data that matches the characteristics of the target abnormal sound based on the input sound data. The trained classification model is integrated into the CPU, and the sound data can be analyzed by the CPU, and it can be determined whether there is sound data that matches the characteristics of the target abnormal sound in the collected sound data.

[0066] In some other embodiments, a large amount of sound data can be input into a clustering algorithm model, and the clustering algorithm model can automatically classify the sound data into different categories according to the similarity of the data. By analyzing these categories, the category corresponding to the target abnormal sound can be determined, and then the common features of the category corresponding to the target abnormal sound can be extracted as the features of the target abnormal sound.

[0067] For the newly collected sound data, the same method as that used to extract the target abnormal sound features is used to convert the sound data into a feature vector. For example, if the target abnormal sound features include frequency, amplitude, duration, etc., then the corresponding frequency, amplitude, duration, etc. information is extracted from the newly collected sound data to form a feature vector.

[0068] Then, a suitable similarity measurement method is used, such as Euclidean distance, cosine similarity, etc., to calculate the similarity between the feature vector of the newly collected sound data and the feature vector corresponding to the feature of the target abnormal sound. If the calculated similarity exceeds a preset threshold, it can be considered that there is sound data in the collected sound data that matches the target abnormal sound feature.

[0069] Furthermore, when there is sound data matching the characteristics of the target abnormal sound in the collected sound data, it is determined that the target abnormal sound is generated inside the vehicle compartment.

[0070] The above method collects the sound data inside the car in real time, ensuring that the sound changes at any time can be captured in time. The collected sound data is compared with the pre-set target abnormal sound characteristics to determine whether the target abnormal sound exists, which can accurately identify the target abnormal sound and eliminate the interference of other irrelevant sounds, thereby improving the accuracy of the judgment.

[0071] As for the above S102, it can be understood that when a target abnormal sound is detected to be generated inside the vehicle compartment, the location where the target abnormal sound is generated can be determined first.

[0072] The target abnormal sound generation location may be the area in the vehicle compartment where the source of the target abnormal sound belongs. For example, if the vehicle compartment is divided into three areas: front, middle, and rear, the area in the vehicle compartment where the source of the target abnormal sound belongs may be the front area, the middle area, or the rear area.

[0073] Furthermore, after determining the area inside the vehicle to which the target abnormal noise belongs, based on the area inside the vehicle to which the source of the target abnormal noise belongs, the camera in the corresponding area can be controlled to record a video of the abnormal noise generation process at the location where the target abnormal noise is generated.

[0074] Specifically, a sound sensor and a camera are respectively arranged in each area inside the vehicle compartment, and the area inside the vehicle compartment to which the source of the target abnormal sound belongs is determined based on the time sequence in which the target abnormal sound reaches the sound sensors in different areas inside the vehicle compartment.

[0075] For example, assume that the vehicle compartment is divided into three areas: front, middle, and rear, and sound sensors and cameras are respectively arranged in the front, middle, and rear areas. If the sound sensor located in the front area of ​​the vehicle compartment detects the target abnormal sound first, it can be determined that the source of the target abnormal sound belongs to the front area of ​​the vehicle compartment, that is, the location where the target abnormal sound is generated is in the front area of ​​the vehicle compartment.

[0076] Further, after determining that the target abnormal sound generation position is in the front area of ​​the vehicle compartment, the camera located in the front area of ​​the vehicle compartment may be controlled to record a video of the abnormal sound generation process at the target abnormal sound generation position.

[0077] The target abnormal noise generation position may also be the position coordinates of the source of the target abnormal noise inside the vehicle compartment.

[0078] For example, a three-dimensional coordinate system is established with the center of the car (i.e., the geometric center of the car in three-dimensional space) as the origin, the length direction of the car as the x-axis, the width direction as the y-axis, and the height direction as the z-axis. The front direction is defined as the positive direction of the x-axis, the right side direction of the car as the positive direction of the y-axis, and the top direction of the car as the positive direction of the z-axis. Based on the coordinate system established above, three-dimensional coordinates can be used to represent the position of each point in the car.

[0079] In some embodiments, multiple sound sensors disposed at different locations in the vehicle cabin may be used to detect the target abnormal sound, and based on the time when the target abnormal sound reaches the multiple sound sensors at different locations, the position coordinates of the source of the target abnormal sound inside the vehicle cabin may be determined.

[0080] For example, assuming that three sound sensors are set at different positions inside the car, and the position coordinates of the three sound sensors inside the car are known, when a target abnormal sound is detected inside the car, the time when the target abnormal sound reaches the three sound sensors can be obtained, and the distance from the position where the target abnormal sound is generated to each sound sensor can be calculated in combination with the propagation speed of sound in the air. Then, a circle is drawn with each sound sensor as the center and the calculated distance from the position where the target abnormal sound is generated to the sound sensor as the radius, to obtain three circles, and the intersection of the three circles is the position coordinates of the source of the target abnormal sound inside the car.

[0081] The location of the target abnormal sound can also be calculated using the time difference between the target abnormal sound reaching the three sound sensors and the speed of sound propagation in the air using a hyperbola positioning algorithm. For example, based on the coordinates of the three sound sensors A, B, and C, the time difference between the target abnormal sound reaching the A and B sensors and the time difference between the target abnormal sound reaching the A and C sensors, a hyperbola with A and B as the focus and a hyperbola with A and C as the focus are constructed. The intersection of the two hyperbolas is the location coordinate of the source of the target abnormal sound inside the car.

[0082] Furthermore, after determining the position coordinates of the source of the target abnormal sound inside the vehicle compartment, a camera near the location where the target abnormal sound is generated may be controlled to record a picture of the location where the target abnormal sound is generated.

[0083] In one possible implementation, recording a video of a target abnormal noise generation process at a location where the abnormal noise is generated includes: calculating the interval distance between each camera among a plurality of cameras inside the vehicle and the location where the target abnormal noise is generated, and determining a camera among the plurality of cameras with the shortest interval distance to the location where the target abnormal noise is generated as a target recording camera; and controlling the target recording camera to record a video of the abnormal noise generation process at the location where the target abnormal noise is generated.

[0084] It can be understood that by determining the spatial relationship between each camera inside the vehicle and the target abnormal sound generating location, the camera closest to the target abnormal sound generating location can be found. Since the closer the distance, the better the recording effect, the camera with the shortest interval distance to the target abnormal sound generating location can be determined as the target recording camera.

[0085] For example, the interior of the vehicle may be spatially modeled or known vehicle structure information, camera installation location data, etc. may be used to calculate the straight-line distance or actual spatial distance between each camera and the location where the target abnormal sound is generated through a certain algorithm.

[0086] Specifically, a three-dimensional coordinate system is established with the center of the car (i.e., the geometric center of the car in three-dimensional space) as the origin, the length direction of the car as the x-axis, the width direction as the y-axis, and the height direction as the z-axis. The front direction of the car is defined as the positive direction of the x-axis, the right side direction of the car is defined as the positive direction of the y-axis, and the top direction of the car is defined as the positive direction of the z-axis.

[0087] Based on the coordinate system established above, the position of each point in the car can be represented by three-dimensional coordinates. The position of the camera and the position where the target abnormal sound is generated have corresponding coordinates. If the coordinates of the camera are (x1, y1, z1) and the coordinates of the position where the target abnormal sound is generated are (x2, y2, z2), the distance between the camera and the position where the target abnormal sound is generated can be calculated according to the distance formula between the two points, that is,

[0088]

[0089] Furthermore, after calculating the distances between the multiple cameras and the location where the target abnormal sound is generated, the distances can be compared. By comparing all the distance values, the camera corresponding to the smallest distance is found and determined as the target recording camera.

[0090] For example, assuming that there are three cameras C1, C2 and C3, the distance between C1 and the target abnormal sound generation location is calculated to be 1 meter, the distance between C2 and the target abnormal sound generation location is calculated to be 1.5 meters, and the distance between C3 and the target abnormal sound generation location is calculated to be 1.3 meters. Then, the camera C1 having the shortest distance to the target abnormal sound generation location can be determined as the target recording camera.

[0091] Once the target recording camera is determined, the vehicle controller (or the CPU in the controller) can send a recording command to the camera to start working and shoot the location where the target abnormal noise is generated. The target recording camera will continuously shoot the scene at the location where the target abnormal noise is generated according to the set frame rate, resolution and other parameters, and record the entire process from the start to the end of the abnormal noise, forming a complete video of the abnormal noise generation process.

[0092] In order to ensure that the target recording camera can record the complete video of the abnormal sound generation process, an early trigger mechanism or pre-recording strategy can be set.

[0093] Exemplarily, specific sound thresholds and sound characteristics can be set as trigger conditions. When the sound sensor detects a sound that matches the characteristics of the target abnormal sound and the sound intensity reaches the set threshold, the target recording camera is immediately triggered to start recording, and a video of the abnormal sound process is obtained.

[0094] Vibration sensors can also be used to monitor vibration conditions near the target location. When the vibration sensor detects abnormal vibration, that is, vibration of a specific frequency and amplitude related to the target abnormal sound, the target recording camera is quickly triggered to start recording, and a video of the abnormal sound process is obtained.

[0095] It is also possible to have multiple cameras inside the vehicle continuously pre-record at a low frame rate and store the video data of the most recent period (such as 30 seconds or 1 minute) in a cache. When the location of the target abnormal sound is determined, not only will the target recording camera be triggered to start recording at a preset frame rate, but the pre-recorded video data in the cache will also be saved and spliced ​​together with the subsequent recorded content to form a complete video record from before to after the abnormal sound occurs, that is, to obtain the video of the abnormal sound process mentioned above.

[0096] The above method selects the camera with the shortest interval as the target recording camera, which can minimize the problems of blurred images and loss of details caused by distance. The closer the distance, the clearer the image captured by the camera, and the more accurate the specific situation at the location where the abnormal sound is generated. And through the early trigger mechanism or pre-recording strategy, a more coherent video record before and after the target abnormal sound occurs can be obtained. This complete record from before to after the abnormal sound occurs can fully present the dynamic process of the abnormal sound generation, avoiding the loss of information caused by only recording the situation after the abnormal sound occurs, and can more completely show the user the process of the target abnormal sound, thereby improving the user experience.

[0097] For the above S103, it can be understood that after obtaining the video of the abnormal sound process, the vehicle's controller (or the CPU in the controller) can transmit the video of the abnormal sound process to the vehicle's central control screen to play the video of the abnormal sound process on the central control screen.

[0098] For example, Figure 3 As shown, the video of the abnormal sound process can be played in the target display area 301 of the central control screen, and a prompt title "abnormal sound video stream is playing" is displayed.

[0099] Furthermore, the user may set the playback mode of the abnormal noise generation process video in advance, and if multiple target abnormal noises are generated inside the car at the same time, the abnormal noise generation process video may also be played according to the preset playback mode.

[0100] In a possible implementation, playing the video of the abnormal sound generation process includes: determining a target playback mode of the video of the abnormal sound generation process; and playing the video of the abnormal sound generation process according to the target playback mode.

[0101] It is understandable that the target playback mode of the above abnormal sound generation process video can be customized by the user according to actual needs, or it can be a playback mode suitable for the current scene determined by the vehicle controller according to actual needs.

[0102] Exemplarily, the target playback mode may include the playback speed of the video of the abnormal sound generation process, the playback duration of the video of the abnormal sound generation process, and the playback order of the video of the abnormal sound generation process.

[0103] Among them, you can choose to play the video of the abnormal sound generation process at normal speed as needed, or you can choose to play the video of the abnormal sound generation process in slow motion or fast motion.

[0104] The playback duration of the abnormal sound generation process video can be selected as needed. For example, if the abnormal sound generation process video is 10 seconds in total, the playback duration can be set to 20 seconds, that is, the abnormal sound generation process video is played twice in a loop.

[0105] If there are multiple target abnormal noises generated inside the car at the same time, and multiple videos of the abnormal noise generation process are recorded, the playback order of the abnormal noise generation process videos can be selected as needed, and the multiple abnormal noise generation process videos can be played in sequence according to the playback order.

[0106] In a possible implementation, determining a target playback mode for a video of an abnormal sound generation process includes: when the target abnormal sound is generated once, determining the target playback mode as: playing the video of the abnormal sound generation process in a target display area of ​​a screen of the vehicle according to a first preset playback duration, and playing the video of the abnormal sound generation process with magnified details in a subwindow in the target display area; and determining the target playback mode according to a generation position of each target abnormal sound among multiple target abnormal sounds and a generation time point of each target abnormal sound among the multiple target abnormal sounds when the target abnormal sound is generated more than or equal to two times.

[0107] Among them, when the target abnormal sound is generated once, the video of the abnormal sound generation process can be played directly according to the first preset playback time.

[0108] Exemplarily, the first preset playback duration may be set according to actual needs, for example, may be set to 10 seconds.

[0109] Furthermore, the above-mentioned video of the abnormal sound generation process can be a video containing a complete picture recorded by the target recording camera; the above-mentioned video of the abnormal sound generation process after enlarging the details can be a video after enlarging a certain part of the video containing a complete picture recorded by the target recording camera.

[0110] For example, Figure 4As shown, the video of the abnormal sound generation process recorded by the camera on the top of the vehicle can be played in the target display area 401 in the central control screen, and the video of the abnormal sound generation process with enlarged details can be displayed in the sub-window 402 in the target display area 401.

[0111] Furthermore, when the target abnormal sound is generated more than or equal to twice, the target playback mode may be determined according to the generation position and generation time point of each target abnormal sound.

[0112] In some embodiments, if the location where the abnormal noise is generated is different each time, the screen of the vehicle can be divided into different areas, and multiple videos of the abnormal noise generation process can be played simultaneously.

[0113] For example, if the first abnormal noise occurs in the rear seat of the vehicle and the second abnormal noise occurs in the trunk of the vehicle, the screen can be divided into two areas, upper and lower, to play the video of the abnormal noise generation process when the abnormal noise occurs in the rear seat of the vehicle and the video of the abnormal noise generation process when the abnormal noise occurs in the trunk of the vehicle respectively.

[0114] In the above method, when the target abnormal sound occurs once, the video is played in the target display area of ​​the vehicle screen according to the first preset playback time, which allows the user to focus on the specific area, and the abnormal sound generation process video with magnified details is played in the sub-window of the target display area, which helps the user to observe the details of the abnormal sound generation moment more clearly. When the target abnormal sound occurs multiple times, the playback mode is determined according to the generation position and generation time of each target abnormal sound, so as to facilitate the subsequent more reasonable playback of the abnormal sound generation process video corresponding to multiple target abnormal sounds, so as to facilitate the user to understand the generation process of the abnormal sound more clearly.

[0115] Furthermore, in order to facilitate users to learn about abnormal noise conditions at different locations, videos of the abnormal noise generation process can be played in sequence according to a preset order.

[0116] In a possible implementation, a target playback mode is determined according to a generation position of each target abnormal sound among multiple target abnormal sounds and a generation time point of each target abnormal sound among the multiple target abnormal sounds, including: if the interval distance between the generation positions of any two target abnormal sounds among the multiple target abnormal sounds is greater than a preset distance threshold and the generation time points of any two target abnormal sounds among the multiple target abnormal sounds are the same time point, then the target playback mode is determined as: according to a preset order and a second preset playback time, the abnormal sound generation process video is played in the target display area of ​​the vehicle screen in sequence, and the abnormal sound generation process video with enlarged details is played in a sub-window in the target display area.

[0117] The preset distance threshold may be set according to actual needs, for example, 0.1 meter.

[0118] It can be understood that if the interval distance between the generation locations of any two target abnormal sounds among multiple target abnormal sounds is greater than the preset distance threshold and the generation time points of any two target abnormal sounds among multiple target abnormal sounds are the same, it means that multiple target abnormal noises occur at the same time and the generation locations are far apart, and the abnormal noise generation process video may not be recorded by the same camera. In this case, the abnormal noise generation process video can be played in the target display area of ​​the vehicle's screen in sequence according to the preset order and the second preset playback time.

[0119] Exemplarily, the second preset playback duration may be the same as the first preset playback duration, or may be different from the first preset playback duration. This embodiment of the present application is not limited to this. For example, the second preset playback duration may be set to be shorter than the first preset playback duration, such as 5 seconds.

[0120] The above-mentioned preset order can be the order of the distance between the generating position of the target abnormal sound and the main driving position from near to far, or can be the order of the decibel values ​​of the collected target abnormal sound from large to small.

[0121] Among them, users can choose to play the video of the abnormal sound generation process in order from near to far or from high to low decibel values ​​according to actual needs.

[0122] The decibel values ​​of the above-mentioned multiple target abnormal sounds may be collected by the same sound sensor, for example, may be collected by a sound sensor closest to the main driving position.

[0123] For example, assuming that the preset distance threshold is 0.1 meters and the second preset playback duration is 5 seconds, if two target abnormal sounds are detected at the same time point, and the interval between the locations where the two target abnormal sounds are generated is greater than the preset distance threshold, it means that the locations where the two target abnormal sounds are generated are relatively scattered, then the abnormal sound generation process videos corresponding to the two target abnormal sounds can be played in sequence according to the distance between the location where the target abnormal sound is generated and the main driving position.

[0124] If one target abnormal noise occurs in the rear seat of the vehicle and another target abnormal noise occurs in the trunk of the vehicle, and it is determined that the distance between the rear seat of the vehicle is closer to the main driving position, a 5-second video of the target abnormal noise generation process at the rear seat of the vehicle can be played first, and then a 5-second video of the target abnormal noise generation process at the trunk of the vehicle can be played.

[0125] Specifically, you can follow Figure 4 The method shown is that the video of the abnormal sound generation process recorded by the camera is played in the target display area 401 in the central control screen, and the video of the abnormal sound generation process with enlarged details is displayed in the sub-window 402 in the target display area 401.

[0126] In the above method, when the distance between any two abnormal sound generation locations among multiple target abnormal sounds is greater than the preset distance threshold and the generation time points are the same, the abnormal sound generation process video is played in a preset order, which can make the abnormal sounds generated simultaneously in multiple different locations appear in an orderly manner. Set the second preset playback time to ensure that the abnormal sound video at each location has enough time to display, so that the user can fully observe the abnormal sound process. At the same time, playing the video with enlarged details in the sub-window of the target display area helps users clearly capture the details of the moment when the abnormal sound is generated at each location.

[0127] In another possible implementation, a target playback mode is determined based on the generation position of each target abnormal sound among multiple target abnormal sounds and the generation time point of each target abnormal sound among the multiple target abnormal sounds, including: if the interval distance between the generation positions of any two target abnormal sounds among the multiple target abnormal sounds is less than or equal to a preset distance threshold and the time difference between the generation time points of any two target abnormal sounds among the multiple target abnormal sounds is less than or equal to a preset time threshold, then determining the target playback mode as: playing the abnormal sound generation process video in the target display area of ​​the screen of the vehicle according to a third preset playback duration.

[0128] The preset distance threshold can be set according to actual needs, for example, it can be set to 0.1 meters. The preset time threshold can be set according to actual needs, for example, it can be set to 2 seconds.

[0129] It can be understood that if the interval distance between the generation locations of any two target abnormal sounds among multiple target abnormal sounds is less than or equal to the preset distance threshold and the time difference between the generation time points of any two target abnormal sounds among multiple target abnormal sounds is less than or equal to the preset time threshold, it means that the distance between the generation locations of the multiple target abnormal sounds is close and the interval between the occurrence time points is also short, that is, the multiple target abnormal sounds occur continuously at positions with similar distances within a short period of time.

[0130] Since the distances between the locations where multiple target abnormal noises are generated are close, they may be videos of the abnormal noise generation process recorded by the same camera, and since the time intervals between the occurrences of multiple target abnormal noises are also short, it is possible that a video of the abnormal noise generation process recorded by the same camera contains multiple target abnormal noises. Based on this, the abnormal noise generation process video can be directly played once in the target display area of ​​the vehicle screen according to the third preset playback time, and the abnormal noise generation process video with enlarged details will no longer be displayed.

[0131] The third preset playback duration may be the same as the first preset playback duration, or may be different from the first preset playback duration. This embodiment of the present application does not limit this. For example, the third preset playback duration is set to be the same as the first preset playback duration, both of which are set to 10 seconds.

[0132] For example, assuming that the preset distance threshold is 0.1 meters, the preset time threshold is 2 seconds, and the third preset playback time is 10 seconds. If two target abnormal sounds are detected, and the interval between the locations where the two target abnormal sounds are generated is 0.05 meters less than the preset distance threshold, it means that the distance between the locations where the two target abnormal sounds are generated is relatively close, and if the time difference between the time points where the two target abnormal sounds are generated is 1 second less than the preset time threshold, it means that the two target abnormal sounds occur continuously in a short period of time. Then, the abnormal sound generation process video can be played only once, and the abnormal sound generation process video with enlarged details will no longer be displayed.

[0133] Specifically, you can follow Figure 3 The method shown is to play the video of the abnormal sound generation process recorded by the camera once in the target display area in the central control screen according to the third preset playback time.

[0134] In the above method, when the distance between any two abnormal noise generation locations among multiple target abnormal noises is less than or equal to the preset distance threshold and the time difference between the generation time points is less than or equal to the preset time threshold, it means that these abnormal noises are relatively concentrated in space and time. By playing the abnormal noise generation process video in the target display area of ​​the vehicle screen according to the third preset playback time, these concentrated target abnormal noises can be presented to the user as a whole. Users do not need to switch between multiple video clips, and can more efficiently understand multiple closely related target abnormal noises, avoiding interference to users caused by playing multiple videos.

[0135] In some embodiments, if the vehicle's central control screen is currently playing a video of the abnormal sound generation process corresponding to the first target abnormal sound according to a first duration, and the second target abnormal sound happens to occur, the video of the abnormal sound generation process corresponding to the second target abnormal sound can be started when the playback duration of the video of the abnormal sound generation process corresponding to the first target abnormal sound reaches a second duration.

[0136] The first duration is greater than the second duration. The first duration and the second duration can be set according to actual needs, for example, the first duration is set to 10 seconds and the second duration is set to 5 seconds.

[0137] It can be understood that no matter whether the video of the abnormal sound generation process corresponding to the target abnormal sound is played according to the first duration, or the video of the abnormal sound generation process corresponding to the target abnormal sound is played according to the second duration, the playback duration includes the specific picture of the moment the abnormal sound is generated.

[0138] For example, assuming that the first duration is 10 seconds and the second duration is 5 seconds. If the central control screen of the vehicle is currently playing the abnormal noise generation process video corresponding to the first target abnormal noise according to the duration of 10 seconds, and the second target abnormal noise occurs when the abnormal noise generation process video corresponding to the first target abnormal noise is played to the 3rd second, then the abnormal noise generation process video corresponding to the second target abnormal noise can be played when the abnormal noise generation process video corresponding to the first target abnormal noise reaches 5 seconds.

[0139] In some embodiments, while playing the video of the abnormal sound generation process, the user can also be reminded through a preset prompt sound.

[0140] Among them, the above-mentioned preset prompt sound can be set according to actual needs, for example, it can be set to a "ding" sound.

[0141] Furthermore, the above-mentioned prompt sound can be sounded at key time points in the video, such as the moment when the abnormal sound begins to be generated, the moment when the abnormal sound characteristics change significantly, etc. This allows users to be more clearly aware of these key information, which helps users to observe and analyze the abnormal sound situation more accurately.

[0142] In order to fully capture the scene where the abnormal noise is generated, the camera inside the car is very likely to capture the facial information of the user in the car during the recording process. This is personal biometric information, which is unique and sensitive. In addition, other private information may also be recorded, such as the user's special actions in the car, personal belongings, etc. Once this information is leaked, it may cause trouble or even harm to the user. For example, facial information may be used for facial recognition fraud. Based on this, some privacy protection measures can be taken for the private information in the recorded video of the abnormal noise generation process.

[0143] In a possible implementation, playing a video of the abnormal sound generation process includes: determining whether there is a preset privacy screen in the video of the abnormal sound generation process; when it is determined that there is the preset privacy screen, blurring the preset privacy screen in the video of the abnormal sound generation process to obtain a blurred video of the abnormal sound generation process; and playing the blurred video of the abnormal sound generation process.

[0144] It can be understood that the above-mentioned preset privacy screen refers to the image portion that may involve user privacy determined according to preset rules or standards, such as a screen containing private information such as face, identity document information, etc.

[0145] The specific method for determining whether there is a preset privacy screen in the video of the abnormal sound generation process is: Based on image recognition technology, various elements in the video screen are identified through a trained model. For example, a facial recognition algorithm is used to identify whether there is a face in the screen. In addition to faces, some objects can also be identified, such as certain personally identifiable objects and private documents. By analyzing the video screen frame by frame, it is determined whether there is a preset privacy screen in each frame.

[0146] Furthermore, when it is determined that there are preset privacy images in the video of the abnormal sound generation process, these privacy images can be processed to protect user privacy.

[0147] The above-mentioned blurring process refers to changing the pixel value of the privacy screen area through a specific image processing algorithm to blur the screen, making it impossible to clearly distinguish the content therein.

[0148] For example, common blurring methods include Gaussian blurring, which can perform weighted averaging of image pixels according to a Gaussian function to blur the image; and mosaic blurring, which divides the image into small squares (mosaic blocks), and unifies the pixel values ​​in each square to the average value of the square, thereby achieving the purpose of blurring the privacy screen.

[0149] Furthermore, after blurring the video of the abnormal sound generation process including the preset privacy screen, the video of the abnormal sound generation process after blurring is obtained, and then the video of the abnormal sound generation process after blurring can be played.

[0150] Exemplarily, if it is detected that there is a preset privacy screen containing facial information in the video of the abnormal sound generation process, the screen containing facial information in the video of the abnormal sound generation process can be blurred to obtain a blurred video of the abnormal sound generation process, and then the blurred video of the abnormal sound generation process is played.

[0151] The above method, by judging and blurring the preset privacy screen, can prevent the improper acquisition and abuse of these private contents from the source, effectively protect the personal privacy security of users, and avoid potential risks brought to users by privacy leakage, such as identity theft, harassment and other issues. The blurred video removes the private content that may cause users to be sensitive or uncomfortable, and will not distract the user's attention during playback, allowing users to focus more on information related to abnormal sounds, thereby optimizing the experience of watching and analyzing videos and improving the user's experience.

[0152] Figure 5 It is a structural schematic diagram of a device for detecting abnormal noise in a vehicle provided in an embodiment of the present application.

[0153] For example, Figure 5 As shown, the device 500 includes:

[0154] The detection module 501 is used to detect whether a target abnormal sound is generated inside the vehicle compartment when the vehicle is powered on.

[0155] The recording module 502 is used to determine the generation position of the target abnormal sound when detecting that a target abnormal sound is generated inside the vehicle compartment, and to record a video of the abnormal sound generation process at the generation position of the target abnormal sound.

[0156] The playing module 503 is used to play the video of the abnormal sound generation process.

[0157] In a possible implementation, the playback module is specifically used to: determine a target playback mode for the video of the abnormal sound generation process; and play the video of the abnormal sound generation process according to the target playback mode.

[0158] In a possible implementation, the playback module includes a determination unit, which is specifically used to: when the target abnormal sound is generated once, determine the target playback mode as: according to a first preset playback duration, play the abnormal sound generation process video in the target display area of ​​the vehicle screen, and play the abnormal sound generation process video with magnified details in a sub-window in the target display area; when the target abnormal sound is generated more than or equal to two times, determine the target playback mode according to the generation position of each target abnormal sound in multiple target abnormal sounds and the generation time point of each target abnormal sound in the multiple target abnormal sounds.

[0159] In a possible implementation, the determination unit is further specifically used for: if the interval distance between the generation positions of any two target abnormal sounds among the multiple target abnormal sounds is greater than a preset distance threshold and the generation time points of any two target abnormal sounds among the multiple target abnormal sounds are the same time point, then determining the target playback mode is: according to a preset order and a second preset playback time, playing the abnormal sound generation process video in the target display area of ​​the vehicle screen in sequence, and playing the abnormal sound generation process video with magnified details in a subwindow in the target display area; if the interval distance between the generation positions of any two target abnormal sounds among the multiple target abnormal sounds is less than or equal to the preset distance threshold and the time difference between the generation time points of any two target abnormal sounds among the multiple target abnormal sounds is less than or equal to the preset time threshold, then determining the target playback mode is: according to a third preset playback time, playing the abnormal sound generation process video in the target display area of ​​the vehicle screen.

[0160] In one possible implementation, the detection module is specifically used to: collect sound data inside the car in real time; determine whether there is sound data matching the characteristics of the target abnormal sound in the collected sound data; and determine that the target abnormal sound is generated inside the car if there is sound data matching the characteristics of the target abnormal sound.

[0161] In one possible implementation, the recording module is specifically used to: calculate the interval distance between each camera among the multiple cameras inside the vehicle and the location where the target abnormal sound is generated, and determine the camera among the multiple cameras with the shortest interval distance to the location where the target abnormal sound is generated as the target recording camera; control the target recording camera to record the video of the abnormal sound generation process at the location where the target abnormal sound is generated.

[0162] In a possible implementation, the playback module is further specifically used to: determine whether there is a preset privacy screen in the video of the abnormal sound generation process; when it is determined that the preset privacy screen exists, blur the preset privacy screen in the video of the abnormal sound generation process to obtain the blurred video of the abnormal sound generation process; and play the blurred video of the abnormal sound generation process.

[0163] Figure 6 It is a structural schematic diagram of a vehicle provided in an embodiment of the present application.

[0164] For example, Figure 6 As shown, the vehicle 600 includes: a memory 601 and a processor 602, wherein the memory 601 stores an executable program code 6011, and the processor 602 is used to call and execute the executable program code 6011 to perform a method for detecting abnormal noise in a vehicle.

[0165] In addition, an embodiment of the present application also protects a device, which may include a memory and a processor, wherein the memory stores an executable program code, and the processor is used to call and execute the executable program code to execute a method for detecting abnormal noise in a vehicle provided in an embodiment of the present application.

[0166] In this embodiment, the functional modules of the device can be divided according to the above method example. For example, each functional module can be corresponded, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0167] In the case of dividing each functional module according to each function, the device may also include a detection module, a recording module, a playback module, etc. It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, which will not be repeated here.

[0168] It should be understood that the device provided in this embodiment is used to execute the above-mentioned method for detecting abnormal noise in a vehicle, and thus can achieve the same effect as the above-mentioned implementation method.

[0169] In the case of an integrated unit, the device may include a processing module and a storage module. When the device is applied to a vehicle, the processing module may be used to control and manage the actions of the vehicle. The storage module may be used to support the vehicle in executing relevant program codes and data.

[0170] The processing module may be a processor or a controller, which may implement or execute various exemplary logic blocks, modules and circuits shown in conjunction with the disclosure of the present application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module may be a memory.

[0171] In addition, the device provided in the embodiments of the present application may specifically be a chip, a component or a module, and the chip may include a connected processor and a memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute a method for detecting abnormal noise in a vehicle provided in the above embodiments.

[0172] This embodiment also provides a computer-readable storage medium, in which a computer program code is stored. When the computer program code is executed on a computer, the computer executes the above-mentioned related method steps to implement a method for detecting abnormal noise in a vehicle provided in the above embodiment.

[0173] This embodiment further provides a computer program product. When the computer program product is run on a computer, the computer is caused to execute the above-mentioned related steps to implement a method for detecting abnormal noise in a vehicle provided by the above embodiment.

[0174] Among them, the device, computer-readable storage medium, computer program product or chip provided in this embodiment is used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be repeated here.

[0175] Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0176] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, 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 through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0177] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for detecting abnormal noise in a vehicle, characterized in that: The method comprises: When the vehicle is powered on, detecting whether a target abnormal sound is generated inside the vehicle compartment; When a target abnormal sound is detected inside the vehicle compartment, determining a location where the target abnormal sound is generated, and recording a video of a process of generating the target abnormal sound at the location where the target abnormal sound is generated; Play the video of the abnormal noise generation process.

2. The method according to claim 1, characterized in that The playing of the video of the abnormal sound generation process includes: Determine a target playback mode of the video of the abnormal sound generation process; According to the target playback mode, the video of the abnormal sound generation process is played.

3. The method according to claim 2, characterized in that The determining of a target playback mode of the video of the abnormal sound generation process includes: When the target abnormal sound is generated once, determining the target playback mode is: playing the abnormal sound generation process video in the target display area of ​​the screen of the vehicle according to the first preset playback time, and playing the abnormal sound generation process video with magnified details in the sub-window in the target display area; When the target abnormal sound is generated twice or more, the target playing mode is determined according to the generation position of each target abnormal sound in the multiple target abnormal sounds and the generation time point of each target abnormal sound in the multiple target abnormal sounds.

4. The method according to claim 3, characterized in that: The determining the target playback mode according to the generation position of each target abnormal sound among the multiple target abnormal sounds and the generation time point of each target abnormal sound among the multiple target abnormal sounds includes: If the interval distance between the generation positions of any two target abnormal sounds among the multiple target abnormal sounds is greater than a preset distance threshold and the generation time points of any two target abnormal sounds among the multiple target abnormal sounds are the same time point, the target playback mode is determined as follows: according to a preset sequence and a second preset playback time, the abnormal sound generation process video is played in the target display area of ​​the vehicle screen in sequence, and the abnormal sound generation process video with magnified details is played in a sub-window in the target display area; If the interval distance between the generation locations of any two target abnormal sounds among the multiple target abnormal sounds is less than or equal to the preset distance threshold and the time difference between the generation time points of any two target abnormal sounds among the multiple target abnormal sounds is less than or equal to the preset time threshold, the target playback mode is determined as: playing the abnormal sound generation process video in the target display area of ​​the screen of the vehicle according to a third preset playback duration.

5. The method according to claim 1, characterized in that The detecting whether a target abnormal sound is generated inside the vehicle compartment includes: collecting sound data inside the carriage in real time; Determining whether there is sound data in the collected sound data that matches the characteristics of the target abnormal sound; In the case where there is sound data matching the characteristics of the target abnormal sound, it is determined that the target abnormal sound is generated inside the vehicle compartment.

6. The method according to claim 1, characterized in that The recording of the abnormal sound generation process video at the generation location of the target abnormal sound includes: Calculating the distance between each of the multiple cameras inside the vehicle and the location where the target abnormal sound is generated, and determining the camera with the shortest distance between the multiple cameras and the location where the target abnormal sound is generated as the target recording camera; The target recording camera is controlled to record a video of the abnormal sound generation process at the location where the target abnormal sound is generated.

7. The method according to claim 1, characterized in that The playing of the video of the abnormal sound generation process includes: Determine whether there is a preset privacy screen in the video of the abnormal sound generation process; In the case where it is determined that the preset privacy screen exists, blurring the preset privacy screen in the video of the abnormal sound generation process to obtain the video of the abnormal sound generation process after blurring; Play the video generated by the abnormal sound process after the fuzzy processing.

8. A device for detecting abnormal noise in a vehicle, characterized in that: The device comprises: A detection module, used for detecting whether a target abnormal sound is generated inside the vehicle compartment when the vehicle is powered on; A recording module, configured to determine the location of the target abnormal sound when a target abnormal sound is detected inside the vehicle compartment, and record a video of the abnormal sound generation process at the location of the target abnormal sound; The playing module is used to play the video of the abnormal sound generation process.

9. A vehicle, characterized in that: The vehicle comprises: A memory for storing executable program codes; A processor, configured to call and run the executable program code from the memory, so that the vehicle executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the method according to any one of claims 1 to 7 is implemented.

Images