Airbag deployment control method and apparatus, and vehicle

Abstract

An airbag deployment control method. The method comprises: acquiring driving record data captured by a vehicle in real time during driving; on the basis of the driving record data, determining that a vehicle body of the vehicle has a collision deformation, and when the collision deformation meets a first deployment condition of an airbag, further determining whether an acceleration variation of the vehicle meets a second deployment condition of the airbag; and when both the first deployment condition and the second deployment condition are met, which indicates that the vehicle has undergone a collision, outputting a deployment instruction for the airbag, to cause deployment of the airbag. Also disclosed are an airbag deployment control apparatus, a vehicle, an electronic device, and a computer-readable storage medium. According to the control method, vehicle collision detection is performed from two dimensions, i.e., images and acceleration, preventing accidental deployment of the airbag due to bumpy road conditions or emergency braking of the vehicle which is caused by confirmation from a single dimension of acceleration; and the whole determination solution improves the recognition rate of airbag deployment scenarios, and thus can improve the accuracy of airbag deployment control.

Description

Airbag detonation control method, device and vehicle Technical Field

[0001] The present invention relates to the technical field of airbag detonation control, and in particular to an airbag detonation control method, device and vehicle. Background Art

[0002] With the improvement of people's living standards, cars have long been part of thousands of households and have become a common means of transportation. People's requirements for cars are also constantly increasing. When purchasing a car, they not only consider the vehicle's comfort, power, maneuverability and economy, but also vehicle safety is the primary consideration.

[0003] Existing airbag deployment is controlled by the vehicle's airbag controller, which uses an external accelerometer to collect vehicle acceleration data to identify collisions and trigger airbag deployment. This control strategy relies heavily on the accelerometer chip within the airbag controller and accelerometer to determine the deployment threshold. Accelerometer chip failure or unusual operating conditions can lead to inadvertent airbag deployment.

[0004] Therefore, how to improve the accuracy of airbag detonation control is a technical problem that needs to be solved urgently. Summary of the Invention

[0005] The present invention provides a safety airbag detonation control method, device and vehicle, which can improve the accuracy of safety airbag detonation control.

[0006] The embodiment of the present invention provides the following solutions:

[0007] In a first aspect, an embodiment of the present invention provides a method for controlling the detonation of an airbag, the method comprising:

[0008] Acquire driving record data captured in real time while the vehicle is driving, wherein the driving record data is continuously recorded image data or video stream data of the vehicle and its surroundings;

[0009] Determine whether the vehicle body has collision deformation based on driving record data;

[0010] When the vehicle body is deformed by a collision and the deformation satisfies a first detonation condition of the airbag, determining whether a change in acceleration of the vehicle satisfies a second detonation condition of the airbag;

[0011] When both the first detonation condition and the second detonation condition are satisfied, an airbag detonation instruction is outputted to detonate and pop out the airbag.

[0012] In an optional embodiment, obtaining driving record data captured in real time while the vehicle is traveling includes:

[0013] Receive the vehicle's power-on command;

[0014] Starting a panoramic camera system of the vehicle according to a power-on instruction, and determining output data of the panoramic camera system as driving record data;

[0015] When the vehicle's speed is lower than the speed threshold, the driving record data is output to the vehicle's multimedia system for display and storage;

[0016] When the driving speed is equal to or higher than the speed threshold, the multimedia system is controlled to continue storing and stop displaying.

[0017] In an optional embodiment, the driving record data is video stream data; and determining whether the vehicle body has collision deformation based on the driving record data includes:

[0018] extracting at least two continuously recorded image frames from the video stream data;

[0019] Outputting the two image frames to a preset image processing model to compare the image frames;

[0020] When deformation features are found in the comparison results of the image frames, it is determined that the vehicle body has collision deformation.

[0021] In an optional embodiment, determining whether the collision deformation satisfies the first detonation condition of the airbag includes:

[0022] determining whether the deformation areas of the plurality of continuously recorded deformation images continue to increase with recording time;

[0023] If so, it is determined that the collision deformation meets the first explosion condition.

[0024] In an optional embodiment, after the vehicle body undergoes collision deformation, the method further includes:

[0025] Determine the actual location of the collision deformation on the vehicle;

[0026] The actual position is output to the vehicle's multimedia system for collision warning.

[0027] In an optional embodiment, outputting an airbag detonation instruction includes:

[0028] Determine the target seating position of the vehicle's occupant monitoring system based on the output of the vehicle's occupant monitoring system;

[0029] Output a detonation command to detonate the airbag corresponding to the target seating position.

[0030] In a second aspect, an embodiment of the present invention further provides a vehicle, wherein the airbag of the vehicle is detonated and controlled by any control method in the first aspect.

[0031] In a third aspect, an embodiment of the present invention further provides an airbag detonation control device, the device comprising:

[0032] An acquisition module is configured to acquire driving record data captured in real time by the vehicle while it is traveling, wherein the driving record data is continuously recorded image data or video stream data of the vehicle and its surroundings;

[0033] A first determining module is configured to determine whether the vehicle body has collision deformation based on the driving record data;

[0034] a second determining module configured to determine whether a change in acceleration of the vehicle satisfies a second triggering condition of the airbag when the vehicle body is deformed by a collision and the collision deformation satisfies a first triggering condition of the airbag;

[0035] The output module is configured to output an airbag detonation instruction when both the first detonation condition and the second detonation condition are satisfied, so that the airbag is detonated and popped out.

[0036] In a fourth aspect, an embodiment of the present invention further provides an electronic device comprising a processor and a memory, wherein the memory is coupled to the processor and stores instructions, and when the instructions are executed by the processor, the steps of any one of the methods in the first aspect are implemented.

[0037] In a fifth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any one of the methods in the first aspect when executed by a processor.

[0038] Compared with the prior art, the airbag detonation control method, device and vehicle of the present invention have the following advantages:

[0039] The control method of the present invention acquires real-time driving data captured by a vehicle during driving. The driving data is continuously recorded image data or video stream data of the vehicle and its surroundings. Based on the driving data, it is determined that the vehicle body has undergone collision deformation. If the collision deformation meets the first airbag deployment condition, the vehicle determines based on the driving data that the airbag deployment is necessary. The method further determines whether the change in the vehicle's acceleration meets the second airbag deployment condition. If both the first and second conditions are met, indicating that the vehicle has collided and that the airbag deployment is necessary to protect the driver and passengers, the method outputs an airbag deployment command, causing the airbag to deploy. This control method performs vehicle collision detection from both image and acceleration dimensions, preventing false airbag deployment caused by sudden braking or bumpy road conditions due to a single acceleration dimension. This overall judgment scheme improves the recognition rate of airbag deployment scenarios, thereby enhancing the accuracy of airbag deployment control. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0041] FIG1 is a flow chart of an airbag deployment control method provided by an embodiment of the present invention;

[0042] FIG2 is a schematic structural diagram of an airbag detonation control device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field fall within the scope of protection of the embodiments of the present invention.

[0044] Please refer to Figure 1, which is a flow chart of an airbag deployment control method provided by an embodiment of the present invention. The control method can be implemented based on a vehicle controller (ECU) or an airbag controller. It is sufficient that the control method can be executed to deploy the airbag, and no specific limitation is imposed herein. The control method includes:

[0045] S11. Acquire driving record data captured in real time while the vehicle is traveling, wherein the driving record data is continuously recorded image data or video stream data of the vehicle and its surroundings.

[0046] Specifically, driving record data can be captured by a driving recorder, for example, using the front camera to capture first data of the front of the vehicle and its surroundings, and using the rear camera to capture second data of the rear of the vehicle and its surroundings. Real-time recording of driving record data can also be achieved through a mobile terminal, for example, using the vehicle user's mobile phone to capture image data at a preset interval, so as to continuously record the actual situation of the vehicle and its surroundings.

[0047] In practical applications, since driving recorders are mostly used to record vehicle driving data, and mobile terminals are mostly used by vehicle users to implement driving route navigation, and due to the limitations of shooting angles, it is impossible to obtain the overall collision situation of the vehicle body. Based on this, in a specific embodiment, obtaining driving record data captured in real time during driving of the vehicle includes:

[0048] The first step is to receive a vehicle power-on command. This command can be issued by the driver turning the vehicle key to the ON position. Upon receiving the power-on command, the vehicle controller and each control terminal are initialized and begin operating according to the pre-set program.

[0049] The second step is to activate the vehicle's panoramic camera system (also known as a 360° panoramic imaging system) based on a power-on command, and the output data from the panoramic camera system is determined as the driving record data. The panoramic camera system uses multiple cameras to capture the vehicle and its surroundings. Specifically, it includes a first camera mounted at the front of the vehicle, a second camera mounted at the rear of the vehicle, a third camera mounted below the left rearview mirror, and a fourth camera mounted below the right rearview mirror. The panoramic camera system fuses the data captured by these four cameras to generate a panoramic image surrounding the vehicle, and the output data representing this panoramic image is determined as the driving record data.

[0050] The third step is to output the recorded driving data to the vehicle's multimedia system for display and storage when the vehicle's speed is below the speed threshold. When the speed is at or above the speed threshold, the multimedia system is controlled to continue storing the data but stop displaying it. The panoramic camera system's output data is often used for display purposes under unusual road conditions. For example, when the vehicle's speed is below the speed threshold and it needs to navigate a narrow passage, the driver's control commands are used to output the recorded driving data to the multimedia system for display. The driver then uses the information displayed on the multimedia system to improve vehicle control accuracy and prevent accidents such as collisions. When the vehicle's speed is at or above the speed threshold, the current control strategy is to disable the panoramic camera system. To maintain continuous data acquisition, the panoramic camera system is controlled to run in the background of the vehicle's computer system to continue acquiring recorded driving data. Because the panoramic camera system's output data provides a comprehensive representation of the vehicle's surroundings and does not require additional camera accessories, it is ideally suited for acquiring recorded driving data for airbag control, preventing airbag deployment caused by misuse of road test conditions. After obtaining the driving record data captured in real time during the driving process of the vehicle, the process proceeds to step S12.

[0051] S12. Determine whether the vehicle body has collision deformation based on the driving record data.

[0052] Specifically, the collision deformation can be a concave deformation of the vehicle body or a convex deformation, and no specific restrictions are imposed here. Since the driving record data is image data or video stream data, it is possible to determine whether the vehicle body has undergone collision deformation based on image recognition. For example, a convolutional neural network model is constructed as an image recognition model. First, images containing collision deformation and normal vehicle bodies are used as a training set to train the image recognition model. Then, a preset verification set is used to verify the accuracy of the trained image recognition model. When the verification results indicate that the collision deformation can be accurately identified, the driving record data is input into the image recognition model, and the output of the image recognition model is used to determine whether the vehicle body has undergone deformation.

[0053] Because convolutional neural network models require high computing power to implement image recognition, they place high demands on the vehicle's hardware configuration, which may lead to limitations in their application. Based on this, in one specific embodiment, the driving record data is video stream data; determining whether the vehicle body has collision deformation based on the driving record data includes:

[0054] The first step is to extract at least two consecutively recorded image frames from the video stream data. Video stream data typically contains 30 or 60 image frames per second. Two adjacent image frames in the video stream data are used as the extracted image frames. To improve image frame processing efficiency, two image frames can also be extracted at a preset interval to reduce the number of image frames processed. For example, the frame headers and frame tails of 3-5 consecutive image frames can be extracted and used as two consecutively recorded image frames.

[0055] In the second step, the two image frames are output to a preset image processing model for comparison. The image processing model can compare the two image frames for differences. If the two image frames are identical, it indicates that no collision has occurred. The two newly extracted image frames are then compared to determine if there are any differences. If the comparison results indicate a difference, further identification is performed to determine if it is a deformation feature. Deformation features can be derived based on training of the image processing model. For example, if the body contour of a vehicle is extracted from an image frame and the grayscale value of the deformed area differs significantly from the surrounding area, deformation of the vehicle body can be determined.

[0056] In the third step, when deformation features are found in the comparison results of the image frames, it indicates that the vehicle has collided with an object in the surrounding environment, and then it is determined that the vehicle body has collision deformation. When it is determined that the vehicle body has collision deformation, the process proceeds to step S13.

[0057] S13: When the vehicle body is deformed by a collision and the deformation satisfies a first airbag deployment condition, determining whether a change in acceleration of the vehicle satisfies a second airbag deployment condition.

[0058] Specifically, it is possible to determine whether the first detonation condition is met based on the deformation area of ​​the collision deformation. For example, an area threshold is set as the first detonation condition. When the collision deformation of the vehicle body is identified, it is further determined whether the deformation area is greater than the area threshold. If it is less than or equal to the area threshold, it is determined that the collision deformation does not meet the first detonation condition. On the contrary, if it is greater than the area threshold, it is determined that the first detonation threshold is met, and it is judged that the acceleration change of the vehicle meets the second detonation condition. The second detonation condition can be set based on actual needs. For example, the lateral acceleration or longitudinal acceleration of the vehicle is greater than the acceleration threshold within a preset time period. The preset time period can be set to 5ms, and the acceleration threshold can be set to 15m / s. 2 .

[0059] In practical applications, since airbag deployment directly affects the safety of drivers and passengers, strict requirements are placed on the time response and area calculation accuracy of the deformation area in the image, which may also lead to insufficient applicability of the control method. Based on this, in a specific embodiment, determining whether the collision deformation meets the first airbag deployment condition includes:

[0060] Determine whether the deformation area of ​​multiple continuously recorded deformation images continues to increase with the recording time. When a deformation area is identified on the vehicle body, the deformation areas of at least two deformation images are compared. If the deformation area gradually increases with the acquisition and recording time of the image frames, it means that the collision deformation of the vehicle body gradually intensifies, and it is determined that the collision deformation meets the first detonation condition. The number of deformation images to be compared can be freely set, for example, three. It can be understood that this comparison method compares whether the area of ​​the two image frames shows an increasing trend to determine whether the first detonation condition is met, eliminates the calculation redundancy of the deformation area, improves the processing efficiency of the image frames, and reduces the configuration requirements for the vehicle computing hardware.

[0061] Since the specific location of the collision on the vehicle body can be determined by processing the image frames, in order to improve the driving safety of the vehicle, in a specific embodiment, after the vehicle body is deformed by the collision, the method further includes:

[0062] The actual location of the collision deformation in the vehicle is determined. The actual location of the collision deformation can be determined based on driving record data. For example, if a collision defect is determined in the vehicle body, the panoramic camera system can retroactively capture the camera corresponding to the collision area. Based on the camera's captured area, the actual location of the collision deformation in the vehicle is determined. The actual location is output to the vehicle's multimedia system as a collision warning. This collision warning can be visual, such as displaying the corresponding side collision information on the vehicle's multimedia screen to provide a warning to the driver and passengers. Alternatively, both visual and audio warnings can be used. During the warning process, the vehicle's acceleration change is simultaneously determined to determine whether it meets the second airbag triggering condition. If either the first or second triggering condition is not met, monitoring continues. If both conditions are met, the system proceeds to step S14.

[0063] S14: Outputting an airbag detonation instruction when both the first detonation condition and the second detonation condition are satisfied, so that the airbag is detonated and popped out.

[0064] Specifically, when both the first and second trigger conditions are met, it indicates that collision detection using both image and acceleration dimensions can confirm that the vehicle has collided. To minimize collision damage to the driver and passengers, a trigger command is output to the airbag control terminal to trigger the airbag deployment. Whether the trigger conditions are met can be represented by a binary representation, for example, an output of 0 if the trigger conditions are not met and a 1 if the trigger conditions are met. If both the first and second trigger conditions are 1, the trigger command is output, and the airbag controller triggers the deployment upon receiving the trigger command.

[0065] It can be understood that whether the second detonation condition is met can be implemented based on the vehicle body stability system. After the vehicle body stability system reaches the detonation threshold and simultaneously receives the effective collision signal sent by the panoramic camera system, it means that both the first detonation condition and the second detonation condition are met. Then the airbag circuit is detonated, causing the airbag to pop out and provide timely protection to the driver and passengers.

[0066] It should be noted that since the second detonation condition is subject to the sensing limitations of the acceleration sensor, when it is determined that the first detonation condition is met, if no output signal from the acceleration sensor is received for a continuous preset period of time, it may indicate that the normal detonation function may be affected by a failure of the acceleration chip or a loss of communication. In this case, the second detonation condition is also determined to be met, and the airbag is deployed. This strategy can solve the problem of airbag failure due to sensor failure during a vehicle collision, thereby increasing driving safety.

[0067] In actual applications, existing airbag deployment is a collective deployment, that is, all airbags in the vehicle are deployed based on the deployment command. For seats without passengers, the deployment of airbags will increase the maintenance cost of subsequent airbag replacement. Based on this, in a specific embodiment, outputting the airbag deployment command includes:

[0068] The first step is to determine the target seating position for the vehicle's occupants based on the output of the vehicle's occupancy monitoring system (OMS). The target seating position is the seat position of a passenger. The OMS can identify each seat in the vehicle and mark it as a target seating position if a passenger is present.

[0069] The second step is to issue a detonation command to the airbag corresponding to the target seating position. All airbags in the vehicle are configured to deploy independently. This command only activates the airbags corresponding to seats with passengers. Airbags corresponding to unoccupied seats remain inactive during a collision, minimizing post-sales repair costs.

[0070] Based on the same technical concept as the control method, an embodiment of the present invention further provides a vehicle, wherein the airbag of the vehicle is detonated and controlled by any control method.

[0071] Based on the same technical concept as the control method, an embodiment of the present invention also provides an airbag detonation control device. Please refer to Figure 2, which is a schematic diagram of the structure of the control device. The control device specifically includes:

[0072] The acquisition module 201 is configured to acquire driving record data captured in real time while the vehicle is driving, wherein the driving record data is continuously recorded image data or video stream data of the vehicle and its surroundings;

[0073] The first determining module 202 is configured to determine whether the vehicle body has collision deformation according to the driving record data;

[0074] The second determining module 203 is configured to determine whether the acceleration change of the vehicle meets the second deployment condition of the airbag when the vehicle body has collision deformation and the collision deformation meets the first deployment condition of the airbag;

[0075] The output module 204 is configured to output an airbag detonation instruction when both the first detonation condition and the second detonation condition are satisfied, so that the airbag is detonated and deployed.

[0076] In an optional embodiment, the acquisition module includes:

[0077] a receiving submodule, configured to receive a power-on instruction of a vehicle;

[0078] a first determining submodule configured to start the panoramic camera system of the vehicle according to a power-on instruction and determine output data of the panoramic camera system as driving record data;

[0079] a first output submodule, configured to output the driving record data to the vehicle's multimedia system for display and storage when the vehicle's driving speed is lower than a speed threshold;

[0080] The control submodule is configured to control the multimedia system to continue storing and stop displaying when the vehicle speed is equal to or higher than a vehicle speed threshold.

[0081] In an optional embodiment, the driving record data is video stream data; the first determination module includes:

[0082] an extraction submodule, configured to extract at least two continuously recorded image frames from the video stream data;

[0083] a second output submodule, configured to output the two image frames to a preset image processing model to compare the image frames;

[0084] The second determining submodule is configured to determine that the vehicle body has collision deformation when a deformation feature exists in the comparison result of the image frame.

[0085] In an optional embodiment, the second determining module includes:

[0086] a judgment submodule configured to judge whether the deformation area of ​​the plurality of continuously recorded deformation images continues to increase with recording time;

[0087] The third determining submodule is configured to determine that the collision deformation satisfies the first detonation condition when the deformation areas of the plurality of deformation images continue to increase with recording time.

[0088] In an optional embodiment, the first determining module further includes:

[0089] a fourth determining submodule, configured to determine an actual position of the collision deformation at the vehicle;

[0090] The third output submodule is configured to output the actual position to the vehicle's multimedia system for collision warning.

[0091] In an optional embodiment, the output module includes:

[0092] a fifth determining submodule, configured to determine a target seating position of a driver and passenger in the vehicle based on an output result of an occupant monitoring system of the vehicle;

[0093] The fourth output submodule is configured to output a detonation instruction to detonate the airbag corresponding to the target seating position.

[0094] Based on the same technical concept as the control method, an embodiment of the present invention also provides an electronic device, including a processor and a memory, the memory being coupled to the processor, the memory storing instructions, and implementing the steps of any one of the control methods when the instructions are executed by the processor.

[0095] Based on the same technical concept as the control method, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any one of the control methods when executed by a processor.

[0096] The technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages:

[0097] The control method acquires real-time driving data captured by the vehicle during driving. Driving data consists of continuously recorded images or video streams of the vehicle and its surroundings. Based on the driving data, the control method determines that the vehicle body has undergone collision deformation. If this collision deformation meets the first airbag deployment condition, the control method determines based on the driving data that the airbag deployment is necessary. The control method then determines whether the change in acceleration meets the second airbag deployment condition. If both the first and second conditions are met, indicating a collision, the airbag deployment is necessary to protect the driver and passengers. The control method then outputs an airbag deployment command, causing the airbag to deploy. This control method detects vehicle collisions from both image and acceleration perspectives, preventing false airbag deployment caused by sudden braking or bumpy road conditions based solely on acceleration. This overall judgment scheme improves the recognition rate of airbag deployment scenarios, thereby enhancing the accuracy of airbag deployment control.

[0098] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0099] The present invention is described with reference to flowcharts and / or block diagrams of methods, apparatus (modules, systems), and computer program products according to embodiments of the present invention. It should be understood that each process flow and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, such that execution of the instructions by the processor of the computer or other programmable data processing device produces a device for implementing the functions specified in one or more processes in the flowcharts and / or one or more blocks in the block diagrams.

[0100] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0101] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0102] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0103] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for controlling the detonation of an airbag, characterized in that: The method comprises: Acquire driving record data captured in real time while the vehicle is traveling, wherein the driving record data is continuously recorded image data or video stream data of the vehicle and its surroundings; determining whether the vehicle body has collision deformation according to the driving record data; When the collision deformation occurs on the vehicle body and the collision deformation satisfies a first detonation condition of the airbag, determining whether a change in acceleration of the vehicle satisfies a second detonation condition of the airbag; When both the first detonation condition and the second detonation condition are satisfied, a detonation instruction for the airbag is output, so that the airbag is detonated and popped out.

2. The airbag detonation control method according to claim 1, characterized in that: The acquisition of driving record data captured in real time while the vehicle is traveling includes: receiving a power-on instruction of the vehicle; starting a panoramic camera system of the vehicle according to the power-on instruction, and determining output data of the panoramic camera system as the driving record data; When the driving speed of the vehicle is lower than a speed threshold, outputting the driving record data to a multimedia system of the vehicle for display and storage; When the driving speed is equal to or higher than the speed threshold, the multimedia system is controlled to continue storing and stop displaying.

3. The airbag detonation control method according to claim 1, characterized in that: The driving record data is the video stream data; and determining whether the vehicle body has collision deformation based on the driving record data includes: Extracting at least two continuously recorded image frames from the video stream data; Outputting the two image frames to a preset image processing model to compare the image frames; When a deformation feature is present in the comparison result of the image frames, it is determined that the collision deformation exists on the vehicle body.

4. The airbag detonation control method according to claim 1, characterized in that: Determining whether the collision deformation satisfies a first airbag detonation condition includes: determining whether the deformation areas of the plurality of continuously recorded deformation images continue to increase with recording time; If so, it is determined that the collision deformation satisfies the first detonation condition.

5. The airbag detonation control method according to claim 1, characterized in that: After the vehicle body undergoes the collision deformation, the method further includes: determining an actual position of the collision deformation at the vehicle; The actual position is output to the multimedia system of the vehicle for collision warning.

6. The airbag detonation control method according to claim 1, characterized in that: Outputting the detonation instruction of the airbag includes: Determining a target seating position for a driver or passenger in the vehicle based on an output of the vehicle's occupant monitoring system; The detonation instruction is output to detonate the airbag corresponding to the target seating position.

7. A vehicle, characterized in that: The airbag of the vehicle is detonated and controlled by the control method according to any one of claims 1 to 6.

8. An airbag detonation control device, characterized in that: The device comprises: an acquisition module configured to acquire driving record data captured in real time by the vehicle while it is traveling, wherein the driving record data is continuously recorded image data or video stream data of the vehicle and its surroundings; A first determining module is configured to determine whether the vehicle body has collision deformation according to the driving record data; a second determining module configured to determine whether a change in acceleration of the vehicle satisfies a second triggering condition of the airbag when the collision deformation exists on the vehicle body and the collision deformation satisfies a first triggering condition of the airbag; The output module is configured to output a detonation instruction of the airbag when both the first detonation condition and the second detonation condition are satisfied, so that the airbag is detonated and popped out.

9. The airbag detonation control device according to claim 8, characterized in that: The acquisition module includes: a receiving submodule, configured to receive a power-on instruction of the vehicle; a first determining submodule, configured to start the panoramic camera system of the vehicle according to the power-on instruction, and determine output data of the panoramic camera system as the driving record data; a first output submodule, configured to output the driving record data to a multimedia system of the vehicle for display and storage when the driving speed of the vehicle is lower than a speed threshold; The control submodule is configured to control the multimedia system to continue storing and stop displaying when the driving speed is equal to or higher than the speed threshold.

10. The airbag detonation control device according to claim 8, characterized in that: The driving record data is the video stream data; The first determining module includes: An extraction submodule is configured to extract at least two continuously recorded image frames from the video stream data; a second output submodule, configured to output the two image frames to a preset image processing model to compare the image frames; The second determining submodule is configured to determine that the vehicle body has the collision deformation when the comparison result of the image frame has a deformation feature.

11. The airbag detonation control device according to claim 8, characterized in that: The second determining module includes: a judgment submodule configured to judge whether the deformation area of ​​the plurality of continuously recorded deformation images continues to increase with recording time; The third determining submodule is configured to determine that the collision deformation satisfies the first detonation condition when the deformation areas of the plurality of deformation images continue to increase with recording time.

12. The airbag detonation control device according to claim 8, characterized in that: The first determining module further includes: a fourth determining submodule, configured to determine an actual position of the collision deformation at the vehicle; The third output submodule is configured to output the actual position to the multimedia system of the vehicle for collision warning.

13. The airbag detonation control device according to claim 8, characterized in that: The output module includes: a fifth determining submodule, configured to determine a target seating position of a driver and passenger in the vehicle according to an output result of the occupant monitoring system of the vehicle; The fourth output submodule is configured to output the detonation instruction to detonate the airbag corresponding to the target seating position.

14. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory is coupled to the processor and stores instructions. When the instructions are executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images