Intelligent detection and alarm method, device and equipment for living body in vehicle and storage medium

Abstract

The invention discloses an in-vehicle living body intelligent detection alarm method, device and equipment and a storage medium, and relates to the technical field of vehicle intelligent monitoring, and the method comprises the steps: obtaining in-vehicle living body sound source information and target position area information; using a sound source positioning algorithm to identify coordinates of each sound source in the in-vehicle living body sound source information, and determining in-vehicle sound source position information; detecting the number of sound sources in the target position area information based on the in-vehicle sound source position information, and determining sound source detection number information; and controlling the vehicle to give an alarm based on the sound source detection quantity information, and completing intelligent detection and alarm of living bodies in the vehicle. According to the method, the sound source information is collected, the space coordinates of the sound source in the vehicle are accurately recognized by using the sound source positioning algorithm, and the number of effective sound sources in the calibrated dangerous area is detected, so that an alarm is automatically triggered to inform a user, the sound sources inside and outside the vehicle are effectively distinguished to reduce false alarms, and efficient and accurate in-vehicle living body intelligent detection and safety early warning are realized.

Description

Technical Field

[0001] This application relates to the field of vehicle intelligent monitoring technology, and in particular to in-vehicle intelligent detection alarm methods, devices, equipment and storage media for liveness detection. Background Technology

[0002] With the rapid development of the automotive industry and the widespread application of intelligent sensing technology, users' demand for vehicle safety is increasing. If a living being is left inside the vehicle after it has been locked and the vehicle is left unattended, it could lead to safety accidents such as suffocation or high-temperature poisoning. Therefore, it is necessary to detect living beings inside the vehicle in real time after leaving the vehicle and to issue an alarm in a timely manner in order to improve vehicle safety and accident prevention capabilities.

[0003] Currently, the existing approach uses millimeter-wave radar technology to detect moving objects inside the vehicle by transmitting and receiving millimeter-wave signals, thereby determining the presence of a living being. However, the existing approach is costly, has complex hardware configurations, and is susceptible to environmental interference, leading to false alarms or missed alarms. Therefore, how to perform intelligent detection and alarm for living beings inside the vehicle more efficiently and accurately has become an urgent problem to be solved.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this application is to provide a method, device, equipment, and storage medium for intelligent detection and alarm of living beings inside a vehicle, aiming to solve the technical problem of how to perform intelligent detection and alarm of living beings inside a vehicle more efficiently and accurately.

[0006] To achieve the above objectives, this application proposes an in-vehicle intelligent liveness detection alarm method, the method comprising: Acquire information on live sound sources inside the vehicle and the target location area; The coordinates of each sound source in the in-vehicle live sound source information are identified using a sound source localization algorithm to determine the location information of the sound sources in the vehicle. Based on the in-vehicle sound source location information, the number of sound sources located in the target location area information is detected, and the sound source detection quantity information is determined. Based on the number of sound sources detected, the vehicle alarm is controlled to complete the intelligent detection alarm for living persons inside the vehicle.

[0007] In one embodiment, the step of acquiring in-vehicle live sound source information and target location area information includes: Get vehicle model information; Based on the vehicle model information, in-vehicle live sound sources are collected in the corresponding target area to obtain in-vehicle live sound source information. The target area includes the driver's seat, passenger seat, left rear seat, and right rear seat areas. Based on the vehicle model information, determine the vehicle demand information, and construct an in-vehicle sound source boundary coordinate library based on the boundary values ​​corresponding to the vehicle demand information. Based on the in-vehicle sound source boundary coordinate library, the in-vehicle detection alarm area is calibrated to obtain the target location area information.

[0008] In one embodiment, the step of using a sound source localization algorithm to identify the coordinates of each sound source in the in-vehicle live sound source information and determine the location information of the sound sources in the vehicle includes: A spatial coordinate system is established based on the vehicle interior space corresponding to the in-vehicle live sound source information, and a sound source coordinate set is determined according to the coordinates of each sound source in the spatial coordinate system. By using a sound source localization algorithm to identify the sound source position deviation corresponding to the sound source coordinate set, the sound source position information inside the vehicle is obtained.

[0009] In one embodiment, the step of using a sound source localization algorithm to identify the sound source position deviation corresponding to the sound source coordinate set and obtaining the sound source position information inside the vehicle includes: Obtain the sound source time difference and sound source propagation speed; The distance from the sound source to the reference sound source position is calculated based on the sound source time difference and the sound source propagation speed, and the reference distance difference is determined. By using a sound source localization algorithm to identify the sound source position deviation corresponding to the sound source coordinate set and the reference distance difference, the in-vehicle sound source position information is obtained.

[0010] In one embodiment, the step of detecting the number of sound sources in the target location area based on the in-vehicle sound source location information and determining the sound source detection quantity information includes: Get the duration of the vehicle being locked and powered off; Based on the duration of the vehicle being locked and powered off, the number of sound sources corresponding to the in-vehicle sound source location information that are located within the target location area is detected, thus obtaining sound source detection quantity information.

[0011] In one embodiment, the step of controlling the vehicle alarm based on the sound source detection quantity information to complete the in-vehicle intelligent liveness detection alarm includes: Obtain information on the number of target sound sources detected; Based on the sound source detection quantity information and the target sound source detection quantity information, the vehicle alarm is controlled to complete the intelligent detection alarm for living persons inside the vehicle.

[0012] In one embodiment, the step of controlling the vehicle alarm based on the sound source detection quantity information and the target sound source detection quantity information to complete the in-vehicle intelligent liveness detection alarm further includes: Based on the sound source detection quantity information and the target sound source detection quantity information, a corresponding alarm notification is generated; The alarm notification is pushed out to complete the intelligent detection alarm for liveness detection inside the vehicle.

[0013] Furthermore, to achieve the above objectives, this application also proposes an in-vehicle intelligent liveness detection alarm device, which includes: The acquisition module is used to acquire information on live sound sources inside the vehicle and information on the target location area. The processing module is used to identify the coordinates of each sound source in the in-vehicle live sound source information using a sound source localization algorithm, and to determine the location information of the sound sources in the vehicle. The processing module is also used to detect the number of sound sources in the target location area based on the in-vehicle sound source location information, and determine the sound source detection quantity information; The execution module is used to control the vehicle alarm based on the sound source detection quantity information to complete the intelligent detection alarm for living persons inside the vehicle.

[0014] In addition, to achieve the above objectives, this application also proposes an in-vehicle intelligent detection alarm device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the in-vehicle intelligent detection alarm method described above.

[0015] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the in-vehicle intelligent detection alarm method described above.

[0016] One or more technical solutions proposed in this application have at least the following technical effects: This embodiment proposes an in-vehicle intelligent detection alarm method, which acquires in-vehicle sound source information and target location area information; uses a sound source localization algorithm to identify the coordinates of each sound source in the in-vehicle sound source information, and determines the location information of the sound sources in the vehicle; detects the number of sound sources in the target location area based on the in-vehicle sound source location information, and determines the sound source detection quantity information; and controls the vehicle alarm based on the sound source detection quantity information, thus completing the in-vehicle intelligent detection alarm. This application collects sound source information and uses a sound source localization algorithm to accurately identify the spatial coordinates of the sound sources in the vehicle, and detects the number of valid sound sources located within a calibrated danger zone, thereby automatically triggering an alarm to notify the user. It effectively distinguishes between in-vehicle and out-of-vehicle sound sources to reduce false alarms, achieving efficient and accurate in-vehicle intelligent detection and safety warning. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the system logic for the in-vehicle intelligent liveness detection alarm method of this application; Figure 2 This is a flowchart illustrating an embodiment of the in-vehicle intelligent detection alarm method of this application. Figure 3 This is a flowchart illustrating Embodiment 2 of the in-vehicle intelligent detection alarm method of this application; Figure 4 This is a schematic diagram of the module structure of the in-vehicle intelligent liveness detection alarm device according to an embodiment of this application; Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the in-vehicle intelligent liveness detection alarm method in this application embodiment.

[0020] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0022] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0023] The main solution of this application embodiment is: to acquire in-vehicle live sound source information and target location area information; to use a sound source localization algorithm to identify the coordinates of each sound source in the in-vehicle live sound source information and determine the in-vehicle sound source location information; to detect the number of sound sources in the target location area information based on the in-vehicle sound source location information and determine the sound source detection quantity information; and to control the vehicle alarm based on the sound source detection quantity information to complete the in-vehicle live intelligent detection alarm.

[0024] In this embodiment, for ease of description, the following description will focus on the intelligent detection alarm device for identifying living beings inside the vehicle.

[0025] Due to the high cost and complex hardware configuration of existing technologies, they are susceptible to environmental interference, leading to false alarms or missed alarms.

[0026] This application provides a solution, such as Figure 1 As shown, Figure 1 This is a schematic diagram of the in-vehicle intelligent liveness detection alarm system of this application. Microphones 1, 2, 3, and 4 are respectively located at the driver's seat, passenger seat, left rear seat, and right rear seat. They can also be arranged differently according to the vehicle model definition. They are used to collect sound sources. After the control unit collects the microphone sound source information, it processes it and calculates the sound source location. When the vehicle is locked, if an in-vehicle sound source is detected, an alarm information is sent to the information uploading device. After receiving the alarm information, the information uploading device uploads the information to the TSP server via the network. After receiving the alarm information, the TSP server sends the information to the registered mobile device under this vehicle via SMS or other means.

[0027] As can be seen from the above embodiments, this application collects sound source information and uses a sound source localization algorithm to accurately identify the spatial coordinates of the sound source inside the vehicle, and detects the number of effective sound sources located in the calibrated danger zone, thereby automatically triggering an alarm to notify the user, effectively distinguishing between sound sources inside and outside the vehicle to reduce false alarms, and achieving efficient and accurate intelligent detection and safety warning of living beings inside the vehicle.

[0028] Based on this, this application provides an in-vehicle intelligent liveness detection alarm method, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the in-vehicle intelligent detection alarm method of this application.

[0029] In this embodiment, the in-vehicle intelligent liveness detection alarm method includes steps S10~S40: Step S10: Obtain information on the live sound source inside the vehicle and the target location area; It should be noted that the in-vehicle live sound source information is the sound signal emitted by a left-behind live body collected by multiple microphones arranged inside the vehicle. The inside of the vehicle can be the driver's seat, passenger seat, left rear seat, and right rear seat. The live body can be a child or a pet. The target location area information is the spatial coordinate range of the dangerous area inside the vehicle that needs to be monitored for live bodies, which is established by pre-calibration.

[0030] It is understood that the in-vehicle live sound source information includes the original waveform data, frequency characteristics, intensity, and time sequence of the sound received by each microphone, which is used for sound source localization and analysis. The target location area information is defined by constructing an in-vehicle sound source boundary coordinate library based on the specific internal structure of the vehicle model. The purpose is to accurately define the effective spatial range of alarm detection, thereby focusing the system monitoring on the key area where the live sound is most likely to appear, and effectively eliminating interference from external sound sources or non-interested areas inside the vehicle. The non-interested areas inside the vehicle can be the dashboard or door panels.

[0031] In a specific embodiment, the in-vehicle live sound source information is obtained by collecting raw audio data from multiple in-vehicle microphones located in the driver's seat, passenger seat, left rear seat, and right rear seat after the vehicle is locked and powered off. The target location area information is determined based on the vehicle's internal structure by establishing a spatial coordinate system and calibrating an in-vehicle sound source boundary coordinate library. Specifically, the alarm area is defined using the spatial boundary coordinate points of key areas such as the seats. To avoid incorrect alarms triggered by external sound sources, the maximum boundary value of possible sound sources within the vehicle needs to be determined during vehicle development; that is, the in-vehicle sound source boundary coordinate library needs to be obtained. , , (m=1, 2, 3, ...), where the maximum value of m depends on the vehicle's interior space and environmental requirements, and is determined based on the actual vehicle model. The more points taken, the higher the accuracy will be.

[0032] In one feasible implementation, step S10 may include steps A11 to A14: Step A11: Obtain vehicle model information; It should be noted that the vehicle model information is a set of parameters used to uniquely identify the specific model, configuration, and interior space structure of a vehicle.

[0033] Understandably, due to differences in interior design and seat layout among different vehicle models, the installation positions of microphones also vary accordingly. Therefore, it is necessary to select the corresponding positions to arrange multiple microphones based on the vehicle model information. This means that multiple microphones can be arranged in the corresponding positions based on the vehicle model information, such as microphones on the driver's side, passenger side, left rear seat, and right rear seat. This allows for the acquisition of the precise spatial coordinates of multiple microphones in the vehicle body coordinate system of that specific vehicle model. Based on the spatial boundaries of the vehicle's interior space corresponding to the vehicle model information, an in-vehicle sound source boundary coordinate library is established through calibration, thereby accurately defining the target location area to be monitored, i.e., the alarm area, to avoid false alarms for external sound sources or non-living, permanently occupied areas such as doors and the trunk.

[0034] Step A12: Collect in-vehicle live sound sources in the corresponding target area according to the vehicle model information to obtain in-vehicle live sound source information. The target area includes the driver's seat, passenger seat, left rear seat, and right rear seat areas. It should be noted that after the vehicle is locked and powered off, the control unit can activate the microphone layout scheme determined according to the vehicle model information, dynamically activate and call the in-vehicle microphones located in the four core seating areas of the driver's seat, passenger seat, left rear seat, and right rear seat, forming a distributed acquisition array to synchronously or quasi-synchronously record the ambient sound inside the vehicle, thereby obtaining multi-channel raw audio data containing time difference information.

[0035] It is understandable that different car models have different interior spaces, seat layouts, and microphone pre-installation locations. The collection area is limited to the driver's seat, passenger seat, left rear seat, and right rear seat because these are the seat areas where a live person is most likely to remain. This arrangement ensures that the monitoring range can effectively cover all key locations inside the car, while also helping to initially eliminate interference from non-key areas such as car doors and the trunk.

[0036] Step A13: Determine vehicle demand information based on the vehicle model information, and construct an in-vehicle sound source boundary coordinate library based on the boundary values ​​corresponding to the vehicle demand information; It should be noted that the vehicle requirement information is engineering parameters determined based on the vehicle's internal physical space structure and the safety monitoring requirements for liveness detection. The in-vehicle sound source boundary coordinate library is a database set containing a large number of spatial coordinate points that is pre-stored in the system and is used to delineate the monitoring range.

[0037] Understandably, vehicle requirement information includes the range of safe areas that need to be monitored inside the vehicle model. For each seat area, the center point of the seat cushion surface and the space within a certain range around it are taken as the key monitoring area. For example, the monitoring range for the driver's seat is 5cm forward from the seat back and 5cm upward from the seat cushion. The in-vehicle sound source boundary coordinate library can be the range defined according to the vehicle requirement information. The in-vehicle sound source boundary coordinate library is created by collecting a large number of dense coordinate points on the boundary of each area that needs to be monitored in the spatial coordinate system. The more points collected, the higher the accuracy will be.

[0038] Step A14: Based on the in-vehicle sound source boundary coordinate library, calibrate the in-vehicle detection alarm area to obtain the target location area information.

[0039] It is understandable that by accurately calibrating the in-vehicle detection alarm area in advance, the calculated sound source location can be quickly compared with the in-vehicle detection alarm area, avoiding false alarms caused by sound sources such as pedestrians talking outside the vehicle or roadside noise being misjudged as living beings inside the vehicle, thus significantly improving the accuracy and reliability of the system.

[0040] Step S20: Use a sound source localization algorithm to identify the coordinates of each sound source in the in-vehicle live sound source information and determine the location information of the sound sources in the vehicle. It should be noted that the in-vehicle sound source location information is calculated by processing the raw sound signals collected by multiple microphones and using a sound source localization algorithm to determine the precise source coordinates of each detected sound in the three-dimensional space of the vehicle.

[0041] It is understandable that the in-vehicle sound source location information refers to the specific location of each sound signal source in the vehicle's internal coordinate system. For example, a crying sound is located 30 centimeters above the left rear seat cushion, and a scratching sound is located in the footwell under the passenger seat. The specific spatial location can be directly determined. While determining the coordinates, the system has actually completed the initial screening, that is, it can clearly distinguish whether the sound comes from the interior space of the vehicle or the external environment, such as the conversation of passersby or the honking of a vehicle next to it. Only the coordinates of the sound sources that are initially determined to originate from inside the vehicle will be retained and transmitted for further analysis.

[0042] In a specific embodiment, a sound source localization algorithm can be used for estimation. Specifically, the coordinates of the four microphones inside the vehicle are defined as follows: , , (k=1,2,3,4), defining the coordinates of the sound source as x, y, z, then the distance from the sound source to the microphone can be expressed as: =

[0043] Squaring both sides of the above equation, we can express it as follows:

[0044] Subtracting the initial distance S from the sound source to the microphone from both sides, the converted expression is:

[0045] make = , Substituting the distance from the microphone to the origin into the above formula, we can obtain:

[0046] The distance between the sound source and the k-th microphone Distance between the sound source and the first microphone Distance difference After squaring, it can be represented as: +

[0047] Therefore, a merge operation can be performed, which can be represented as:

[0048] At this point, after matrix transformation, we can obtain the formula for calculating the sound source location, expressed as:

[0049] In the formula:

[0050]

[0051]

[0052] Where V is the speed of sound in the air, and tk is the time difference between the k-th microphone and the first microphone receiving the same sound source. , , , The distances from the four microphones to the origin of the coordinate system. , , The coordinates X, Y, and Z of the four microphones represent the sound source locations. This represents the position from the sound source to microphone 1.

[0053] This allows us to calculate x, y, and z, obtaining the coordinates of each sound source in the in-vehicle live sound source information, thus obtaining the in-vehicle sound source location information.

[0054] Step S30: Detect the number of sound sources in the target location area based on the in-vehicle sound source location information, and determine the sound source detection quantity information; It should be noted that the sound source detection quantity information is the total number of all valid sound sources located within the preset danger zone inside the vehicle, calculated by comparing the coordinates of each located sound source with the pre-calibrated in-vehicle sound source boundary coordinate library.

[0055] In a specific embodiment, the duration of vehicle locking and power-off is obtained; based on the duration of vehicle locking and power-off, the number of sound sources corresponding to each sound source location information inside the vehicle that falls within the target location area information is detected to obtain sound source detection quantity information, i.e., the duration of vehicle locking and power-off after the vehicle is externally locked and the entire vehicle is powered off. The number of sound sources was then detected, among which, You can manually calibrate the location based on the actual situation and enable audio source localization to detect the location of audio sources inside the vehicle. For example, the location of the audio source inside the vehicle is ( , , (n=1, 2, 3, ...), while If the number of sound sources n obtained within a certain time is greater than the calibrated quantity Num, an alarm will be triggered. At this time, the control unit will transmit the alarm information to the information uploading device.

[0056] In one feasible implementation, step S30 may include steps B11-B12: Step B11: Obtain the duration of the vehicle being locked and powered off; It should be noted that the duration of vehicle locking and power-off is a delay time that begins after the vehicle is confirmed to be locked and the entire vehicle power system is completely powered down.

[0057] It is understandable that in the initial period after a vehicle is locked and powered off, there may be a series of transient, non-living noise sources causing interference in its internal environment. By setting a reasonable delay period, these transient noise sources can be allowed to dissipate naturally, thereby ensuring that detection is started in a stable in-vehicle acoustic environment and significantly reducing the possibility of misjudging non-living noise as the presence of living beings.

[0058] Step B12: Based on the duration of the vehicle being locked and powered off, the number of sound sources corresponding to each sound source location information inside the vehicle that are located in the target location area is detected to obtain sound source detection quantity information.

[0059] It is understood that the number of sound sources detected is not the total number of sound sources, but rather a count of valid events that may indicate the presence of living beings inside the vehicle, filtered by spatial location. This excludes interference from external sound sources or non-interested areas inside the vehicle, and is used to trigger vehicle alarms. For example, if three sound sources are detected within five minutes in the driver's seat, passenger seat, or rear seat area, and the number of detected sound sources exceeds one, an alarm will be triggered. In this case, the number of sound sources detected is three, which meets the alarm conditions.

[0060] Step S40: Control the vehicle alarm based on the sound source detection quantity information to complete the intelligent detection alarm for living persons inside the vehicle.

[0061] Understandably, the system can compare the number of valid sound sources with the preset alarm threshold. When the alarm conditions are met, the system will automatically trigger the alarm mechanism and send the alarm information to the car owner through the vehicle's built-in communication device, thus completing the entire process of intelligent detection and alarm of living beings in the vehicle.

[0062] In a specific embodiment, the number of target sound sources detected is obtained; based on the number of sound sources detected and the number of target sound sources detected, the vehicle alarm is controlled to complete the intelligent detection alarm for living beings inside the vehicle. A corresponding alarm notification is generated based on the number of sound sources detected and the number of target sound sources detected; the alarm notification is pushed to complete the intelligent detection alarm for living beings inside the vehicle. Specifically, when the control unit determines that the number of sound sources detected exceeds a preset threshold, it automatically generates an alarm command containing the location and quantity of the sound sources and sends it to the vehicle information upload device via the CAN bus. The vehicle information upload device uploads the alarm information to the TSP server in real time through its built-in 4G / 5G communication module. The TSP server performs protocol parsing and format encapsulation on the received events and uses the corresponding push channel to immediately send the structured alarm message to the mobile device bound to the vehicle owner, thus realizing intelligent alarm functionality.

[0063] In one feasible implementation, step S40 may include steps C11-C12: Step C11: Obtain the target sound source detection quantity information; It should be noted that the target sound source detection quantity information is a pre-calibrated alarm trigger threshold, that is, the minimum number of effective sound sources for the system to determine whether an alarm is needed.

[0064] It is understood that the target sound source detection quantity information can be set according to actual needs. For example, setting it to 1 or 2 means that an alarm is triggered when at least 1 or 2 valid sound sources are detected. The target sound source detection quantity information is usually stored in the control unit and loaded during system initialization.

[0065] Step C12: Based on the sound source detection quantity information and the target sound source detection quantity information, control the vehicle alarm to complete the in-vehicle intelligent liveness detection alarm.

[0066] It is understood that the number of sound sources detected is compared with the number of target sound sources detected. If the number of sound sources detected is greater than or equal to the number of target sound sources detected, an alarm operation is triggered.

[0067] In one feasible implementation, step C12 may include steps D11-D12: Step D11: Generate a corresponding alarm notification based on the sound source detection quantity information and the target sound source detection quantity information; It should be noted that the alarm notification is an electronic message containing alarm information, such as a text message, push notification, or voice prompt.

[0068] It is understood that the alarm notification may include information such as alarm type, time of occurrence, and vehicle location, to inform the vehicle owner that there may be a risk of a living being left inside the vehicle. After the control unit determines that an alarm has been triggered, it will generate a corresponding alarm notification and send it to the information uploading device.

[0069] Step D12: Push the alarm notification to complete the in-vehicle intelligent detection alarm.

[0070] Understandably, alarm notifications can be uploaded to a remote server, such as a TSP server, via a vehicle information uploading device, such as an in-vehicle T-Box. The TSP server then sends the alarm information to the vehicle owner's pre-bound mobile device, such as a mobile phone. In this way, even if the vehicle owner is far away from the vehicle, they can receive the alarm information in a timely manner and take appropriate measures to avoid safety accidents.

[0071] This embodiment proposes an in-vehicle intelligent detection alarm method, which acquires in-vehicle sound source information and target location area information; uses a sound source localization algorithm to identify the coordinates of each sound source in the in-vehicle sound source information, determining the in-vehicle sound source location information; detects the number of sound sources in the target location area based on the in-vehicle sound source location information, determining the sound source detection quantity information; and controls the vehicle alarm based on the sound source detection quantity information, completing the in-vehicle intelligent detection alarm. This solves the technical problem of how to perform in-vehicle intelligent detection alarm more efficiently and accurately. Compared with existing technologies, this application, by collecting sound source information and using a sound source localization algorithm to accurately identify the spatial coordinates of sound sources inside the vehicle, and detecting the number of effective sound sources located within a calibrated danger zone, automatically triggers an alarm to notify the user, ensuring the timeliness and reliability of in-vehicle liveness detection, significantly reducing the safety risks caused by forgetting that a live person is inside the vehicle, effectively distinguishing between in-vehicle and external sound sources to reduce false alarms, and achieving efficient and accurate in-vehicle intelligent detection and safety warning.

[0072] Based on the first embodiment of this application, in the second embodiment of this application, the same or similar content as the first embodiment can be referred to the above description, and will not be repeated hereafter.

[0073] In this embodiment, refer to Figure 3 , Figure 3 This is a flowchart illustrating Embodiment 2 of the in-vehicle intelligent detection alarm method of this application. Step S20 specifically includes steps S21 to S22: Step S21: Establish a spatial coordinate system based on the vehicle interior space corresponding to the in-vehicle live sound source information, and determine the sound source coordinate set according to the coordinates of each sound source in the spatial coordinate system. It should be noted that the sound source coordinate set is the set of spatial location coordinates of valid sound sources identified by the system through the sound source localization algorithm.

[0074] It is understood that the sound source coordinate set is the result of multiple sound source locations calculated in batches. Each element is the coordinate value (x, y, z) of a sound source in the vehicle's internal spatial coordinate system. For example, a coordinate (1250, -350, 650) represents the specific location of the sound source inside the vehicle relative to the origin of the coordinate system, indicating the spatial distribution of the sound source.

[0075] In a specific embodiment, a spatial coordinate system can be established based on the vehicle's interior space. For example, the origin (0,0,0) can be set at the center of the vehicle chassis or a fixed point, with the vehicle's forward direction as the X-axis, the left side as the Y-axis, and the top as the Z-axis, forming a vehicle spatial coordinate system. The pre-calibrated installation positions of the microphones located on the driver's side, passenger side, and rear left and right sides can then be determined. , The coordinates of the sound source are mapped to this coordinate system to obtain the coordinate set of the sound source.

[0076] Step S22: Use the sound source localization algorithm to identify the sound source position deviation corresponding to the sound source coordinate set, and obtain the sound source position information inside the vehicle.

[0077] It should be noted that the in-vehicle sound source location information is the accurate location result of valid sound sources after being processed and filtered by a sound source localization algorithm.

[0078] It is understandable that the sound source position deviation is the objective error or difference between the theoretical coordinates of the sound source calculated by the sound source localization algorithm and the actual physical position of the sound source in the vehicle's interior space. For example, there may be a slight error in the measurement of the time difference between the sound signals received by the microphones, and the initial error may be caused by the accuracy of the microphone installation position calibration and the synchronization accuracy of each channel. Therefore, it is necessary to eliminate measurement errors and accurately identify the actual coordinates of the sound source.

[0079] In a specific embodiment, after the sound source signal is acquired, the arrival time difference of the same sound signal received by each microphone is calculated, and the distance difference is obtained by combining the sound propagation speed. The microphone coordinate set and the distance difference are substituted into the sound source localization matrix equation for solution. This can eliminate measurement errors and accurately identify the actual coordinates of the sound source, generating in-vehicle sound source location information containing the effective three-dimensional position of the sound source, thus obtaining the in-vehicle sound source location information.

[0080] In one feasible implementation, step S22 may include steps E11 to E13: Step E11: Obtain the sound source time difference and sound source propagation speed; It should be noted that the sound source time difference is the time difference between the arrival of the same sound signal at different microphones inside the vehicle, and the sound source propagation speed is the speed at which sound travels through the air inside the vehicle.

[0081] Understandably, since multiple microphones inside the vehicle are spatially separated, a sound emitted from a sound source will propagate outward in the form of a spherical wave. It will reach the microphone closer to the sound source earlier and the microphone farther away from the sound source later. This slight difference in time is the sound source time difference. The algorithm analyzes the synchronous audio signals collected by multiple microphones by accurately measuring the sound source time difference, finds the most relevant time offset between the signals of each channel, and then infers the possible location of the sound source.

[0082] Additionally, it should be noted that sound is a mechanical wave, and its speed of propagation in the air is the speed of sound propagation. The speed of sound propagation depends on the temperature, humidity, and composition of the air. For example, under standard atmospheric pressure and 15°C, the speed of sound in dry air is approximately 340 m / s. Since the temperature variation range inside a vehicle is relatively limited, its impact on the speed of sound is within an acceptable error range. Therefore, in automotive applications, in order to balance accuracy and computational complexity, the speed of sound propagation is treated as a known fixed constant, for example, directly taken as 340 m / s.

[0083] Step E12: Calculate the distance from the sound source to the reference sound source position based on the sound source time difference and the sound source propagation speed, and determine the reference distance difference; It should be noted that the reference distance difference is the difference between the distance from the same sound source to the corresponding microphone and the distance to the reference microphone.

[0084] It is understood that the reference distance difference is calculated using the sound source time difference and the sound source propagation speed, that is, the distance difference equals the speed multiplied by the time difference. Since sound propagates at a constant speed, the time it takes for the sound to travel to the additional distance difference is exactly the measured time difference.

[0085] Step E13: Use a sound source localization algorithm to identify the sound source position deviation corresponding to the sound source coordinate set and the reference distance difference, and obtain the sound source position information inside the vehicle.

[0086] It is understood that the in-vehicle sound source location information can be a set of spatial coordinates of one or more sound sources that have been determined to be located in the vehicle. The system first uses a microphone array and positioning algorithm to calculate the original coordinates of all detected sound sources to form a sound source coordinate set. Then, the system compares each coordinate in the sound source coordinate set with the pre-calibrated target location area information, that is, matches it with the in-vehicle sound source boundary coordinate library. Only coordinates that fall within the calibration boundary range will be recognized as in-vehicle sound source location information, filtering out interference from external noise such as pedestrians and vehicles next to the vehicle, effectively distinguishing between in-vehicle and out-of-vehicle sound sources to reduce false alarms.

[0087] This embodiment proposes an in-vehicle intelligent detection and alarm method. It establishes a spatial coordinate system based on the vehicle's interior space corresponding to the in-vehicle sound source information, and determines a sound source coordinate set based on the coordinates of each sound source in the spatial coordinate system. A sound source localization algorithm is then used to identify the sound source position deviation corresponding to the sound source coordinate set, obtaining the in-vehicle sound source position information. This solves the technical problem of how to perform in-vehicle intelligent detection and alarm more efficiently and accurately. Compared with existing technologies, this application establishes a spatial coordinate system based on the vehicle's interior space, maps the collected sound source signals to a sound source coordinate set, and uses a sound source localization algorithm to identify and correct the position deviation of the coordinate set, achieving accurate spatial localization of the sound source, significantly reducing the system's false alarm rate, and effectively improving vehicle safety and economy.

[0088] This application also provides an in-vehicle intelligent liveness detection alarm device, please refer to... Figure 4 The in-vehicle intelligent liveness detection alarm device includes: Acquisition module 10 is used to acquire information on live sound sources inside the vehicle and information on the target location area; Processing module 20 is used to identify the coordinates of each sound source in the in-vehicle live sound source information using a sound source localization algorithm, and to determine the in-vehicle sound source location information; The processing module 20 is also used to detect the number of sound sources in the target location area information based on the in-vehicle sound source location information, and determine the sound source detection quantity information; The execution module 30 is used to control the vehicle alarm based on the sound source detection quantity information to complete the intelligent detection alarm for living persons inside the vehicle.

[0089] The acquisition module 10 is also used to acquire vehicle model information; Based on the vehicle model information, in-vehicle live sound sources are collected in the corresponding target area to obtain in-vehicle live sound source information. The target area includes the driver's seat, passenger seat, left rear seat, and right rear seat areas. Based on the vehicle model information, determine the vehicle demand information, and construct an in-vehicle sound source boundary coordinate library based on the boundary values ​​corresponding to the vehicle demand information. Based on the in-vehicle sound source boundary coordinate library, the in-vehicle detection alarm area is calibrated to obtain the target location area information.

[0090] The processing module 20 is also used to establish a spatial coordinate system based on the vehicle interior space corresponding to the in-vehicle live sound source information, and to determine the sound source coordinate set according to the coordinates of each sound source in the spatial coordinate system. By using a sound source localization algorithm to identify the sound source position deviation corresponding to the sound source coordinate set, the sound source position information inside the vehicle is obtained.

[0091] The processing module 20 is also used to obtain the sound source time difference and the sound source propagation speed; The distance from the sound source to the reference sound source position is calculated based on the sound source time difference and the sound source propagation speed, and the reference distance difference is determined. By using a sound source localization algorithm to identify the sound source position deviation corresponding to the sound source coordinate set and the reference distance difference, the in-vehicle sound source position information is obtained.

[0092] The processing module 20 is also used to obtain the duration of the vehicle being locked and powered off; Based on the duration of the vehicle being locked and powered off, the number of sound sources corresponding to the in-vehicle sound source location information that are located within the target location area is detected, thus obtaining sound source detection quantity information.

[0093] The execution module 30 is also used to obtain information on the number of target sound sources detected; Based on the sound source detection quantity information and the target sound source detection quantity information, the vehicle alarm is controlled to complete the intelligent detection alarm for living persons inside the vehicle.

[0094] The execution module 30 is also used to generate a corresponding alarm notification based on the sound source detection quantity information and the target sound source detection quantity information; The alarm notification is pushed out to complete the intelligent detection alarm for liveness detection inside the vehicle.

[0095] The in-vehicle intelligent detection alarm device provided in this application, employing the in-vehicle intelligent detection alarm method described in the above embodiments, can solve the technical problem of how to perform in-vehicle intelligent detection alarms more efficiently and accurately. Compared with the prior art, the beneficial effects of the in-vehicle intelligent detection alarm device provided in this application are the same as those of the in-vehicle intelligent detection alarm method provided in the above embodiments, and other technical features in the in-vehicle intelligent detection alarm device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0096] This application provides an in-vehicle intelligent detection alarm device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the in-vehicle intelligent detection alarm method in the above embodiment 1.

[0097] The following is for reference. Figure 5This document illustrates a structural schematic diagram suitable for implementing the in-vehicle intelligent liveness detection alarm device according to embodiments of this application. The in-vehicle intelligent liveness detection alarm device in embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The in-vehicle intelligent liveness detection alarm device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0098] like Figure 5 As shown, the in-vehicle intelligent liveness detection alarm device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in ROM (Read Only Memory) 1002 or the program loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the in-vehicle intelligent liveness detection alarm device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. Input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the in-vehicle intelligent liveness detection alarm device to exchange data with other devices wirelessly or via wired communication. Although the figures show in-vehicle intelligent liveness detection alarm devices with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems may be implemented alternatively.

[0099] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0100] The in-vehicle intelligent detection alarm device provided in this application, employing the in-vehicle intelligent detection alarm method described in the above embodiments, can solve the technical problem of how to perform in-vehicle intelligent detection alarms more efficiently and accurately. Compared with the prior art, the beneficial effects of the in-vehicle intelligent detection alarm device provided in this application are the same as those of the in-vehicle intelligent detection alarm method provided in the above embodiments, and other technical features of this in-vehicle intelligent detection alarm device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0101] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0102] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0103] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the in-vehicle intelligent detection alarm method in the above embodiments.

[0104] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0105] The aforementioned computer-readable storage medium may be included in the in-vehicle intelligent liveness detection alarm device; or it may exist independently and not be installed in the in-vehicle intelligent liveness detection alarm device.

[0106] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the in-vehicle intelligent liveness detection alarm device, the device causes the following actions: acquires in-vehicle liveness sound source information and target location area information; uses a sound source localization algorithm to identify the coordinates of each sound source in the in-vehicle liveness sound source information, and determines the in-vehicle sound source location information; detects the number of sound sources located in the target location area information based on the in-vehicle sound source location information, and determines the sound source detection quantity information; and controls the vehicle alarm based on the sound source detection quantity information, thereby completing the in-vehicle intelligent liveness detection alarm.

[0107] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0108] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0109] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0110] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described in-vehicle intelligent liveness detection alarm method, thereby solving the technical problem of how to perform in-vehicle intelligent liveness detection alarm more efficiently and accurately. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the in-vehicle intelligent liveness detection alarm method provided in the above embodiments, and will not be repeated here.

[0111] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for intelligent detection and alarm of living beings inside a vehicle, characterized in that, The method includes: Acquire information on live sound sources inside the vehicle and the target location area; The coordinates of each sound source in the in-vehicle live sound source information are identified using a sound source localization algorithm to determine the location information of the sound sources in the vehicle. Based on the in-vehicle sound source location information, the number of sound sources located in the target location area information is detected, and the sound source detection quantity information is determined. Based on the number of sound sources detected, the vehicle alarm is controlled to complete the intelligent detection alarm for living persons inside the vehicle.

2. The method as described in claim 1, characterized in that, The steps for acquiring in-vehicle live sound source information and target location area information include: Get vehicle model information; Based on the vehicle model information, in-vehicle live sound sources are collected in the corresponding target area to obtain in-vehicle live sound source information. The target area includes the driver's seat, passenger seat, left rear seat, and right rear seat areas. Based on the vehicle model information, determine the vehicle demand information, and construct an in-vehicle sound source boundary coordinate library based on the boundary values ​​corresponding to the vehicle demand information. Based on the in-vehicle sound source boundary coordinate library, the in-vehicle detection alarm area is calibrated to obtain the target location area information.

3. The method as described in claim 1, characterized in that, The step of using a sound source localization algorithm to identify the coordinates of each sound source in the in-vehicle live sound source information and determine the location information of the sound sources in the vehicle includes: A spatial coordinate system is established based on the vehicle interior space corresponding to the in-vehicle live sound source information, and a sound source coordinate set is determined according to the coordinates of each sound source in the spatial coordinate system. By using a sound source localization algorithm to identify the sound source position deviation corresponding to the sound source coordinate set, the sound source position information inside the vehicle is obtained.

4. The method as described in claim 3, characterized in that, The step of using a sound source localization algorithm to identify the sound source position deviation corresponding to the sound source coordinate set and obtain the sound source position information inside the vehicle includes: Obtain the sound source time difference and sound source propagation speed; The distance from the sound source to the reference sound source position is calculated based on the sound source time difference and the sound source propagation speed, and the reference distance difference is determined. By using a sound source localization algorithm to identify the sound source position deviation corresponding to the sound source coordinate set and the reference distance difference, the in-vehicle sound source position information is obtained.

5. The method as described in claim 1, characterized in that, The step of detecting the number of sound sources in the target location area based on the in-vehicle sound source location information and determining the sound source detection quantity information includes: Get the duration of the vehicle being locked and powered off; Based on the duration of the vehicle being locked and powered off, the number of sound sources corresponding to the in-vehicle sound source location information that are located within the target location area is detected, thus obtaining sound source detection quantity information.

6. The method as described in claim 1, characterized in that, The step of controlling the vehicle alarm based on the sound source detection quantity information to complete the intelligent detection alarm for living persons inside the vehicle includes: Obtain the number of target sound sources detected; Based on the sound source detection quantity information and the target sound source detection quantity information, the vehicle alarm is controlled to complete the intelligent detection alarm for living persons inside the vehicle.

7. The method as described in claim 6, characterized in that, The step of controlling the vehicle alarm based on the sound source detection quantity information and the target sound source detection quantity information to complete the in-vehicle intelligent liveness detection alarm further includes: Based on the sound source detection quantity information and the target sound source detection quantity information, a corresponding alarm notification is generated; The alarm notification is pushed out to complete the intelligent detection alarm for liveness detection inside the vehicle.

8. A vehicle-mounted intelligent liveness detection alarm device, characterized in that, The device includes: The acquisition module is used to acquire information on live sound sources inside the vehicle and information on the target location area. The processing module is used to identify the coordinates of each sound source in the in-vehicle live sound source information using a sound source localization algorithm, and to determine the location information of the sound sources in the vehicle. The processing module is also used to detect the number of sound sources in the target location area based on the in-vehicle sound source location information, and determine the sound source detection quantity information; The execution module is used to control the vehicle alarm based on the sound source detection quantity information to complete the intelligent detection alarm for living persons inside the vehicle.

9. An in-vehicle intelligent liveness detection alarm device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the in-vehicle intelligent detection alarm method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the in-vehicle intelligent detection alarm method as described in any one of claims 1 to 7.

Images