Vehicle safety air bag control method and system, vehicle and readable storage medium

Abstract

The invention relates to a vehicle safety air bag control method and system, a vehicle and a readable storage medium. The method comprises the following steps: acquiring an in-vehicle monitoring image including a passenger; identifying the in-vehicle monitoring image, and determining the state information of a driving and taking position and the body shape information of a passenger; under the condition that the vehicle is collided, if the state information of the driving and taking position meets the safety air bag explosion condition, determining a safety air bag to be exploded in the vehicle and the explosion time of the safety air bag to be exploded according to the body type information; and controlling the to-be-exploded safety airbag to perform safety explosion according to the explosion time. By adopting the method, the problem of insufficient adaptability of a control method of the vehicle safety airbag can be solved, and the riding safety is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a control method, system, vehicle and readable storage medium for a vehicle airbag. Background Art

[0002] With the development and widespread application of computer technology, vehicle airbag control technology has emerged. This technology can monitor vehicle collision conditions in real time and respond quickly, providing effective protection for passengers at the moment of impact. However, traditional vehicle collision protection relies on seatbelts to restrain passengers and deploy airbags to prevent them from being thrown out of the vehicle or leaning forward excessively in a collision.

[0003] However, the control of airbags in related technologies is based on sensor signal acquisition and logical judgment by the control unit. This control method cannot meet complex situations, has insufficient adaptability, and is difficult to achieve personalized safety protection. Summary of the Invention

[0004] Based on this, it is necessary to provide a vehicle airbag control method, system, vehicle, computer-readable storage medium and computer program product that can solve the above technical problems and improve the safety of passengers.

[0005] In a first aspect, the present application provides a method for controlling a vehicle airbag, comprising:

[0006] Acquiring in-vehicle surveillance images including occupants;

[0007] Identify the in-vehicle monitoring image to determine the status information of the driver's seat and the body shape information of the occupant;

[0008] In the event of a collision of the vehicle, if the state information of the driver's seat meets an airbag deployment condition, determining an airbag to be deployed in the vehicle and a deployment time of the airbag to be deployed based on the body shape information;

[0009] The airbag to be detonated is controlled to be detonated safely according to the detonation time.

[0010] In one embodiment, the identifying the in-vehicle monitoring image and determining the status information of the driver's seat includes:

[0011] Performing body part recognition on the occupant in the driver's seat in the in-vehicle monitoring image to determine target body parts of the occupant; determining angle data between the target body parts; and / or

[0012] Performing target object recognition on an object in the driver's seat in the in-vehicle monitoring image, and if a target object exists and is installed on a target seat in the vehicle, determining installation information of the target object;

[0013] State information of the driving position is determined according to the angle data and / or the installation information.

[0014] In one embodiment, identifying the in-vehicle monitoring image to determine the occupant's body shape information includes:

[0015] Performing contour recognition on the occupant in the driver's seat in the in-vehicle monitoring image to determine the contour coordinate data of the occupant;

[0016] The body shape information of the occupant is determined based on the outline coordinate data.

[0017] In one embodiment, determining the body shape information of the occupant based on the contour coordinate data includes:

[0018] Projecting each contour point of the contour coordinate data into a preset coordinate system to obtain the projection coordinates of each contour point in the preset coordinate system;

[0019] According to the projection coordinates, all vertical coordinate differences of the same horizontal coordinate are calculated;

[0020] According to the projection coordinates, all horizontal coordinate differences of the same vertical coordinate are calculated;

[0021] Calculating the orthographic projection area according to the projection coordinates;

[0022] The body shape information of the occupant is determined according to all the vertical coordinate differences, all the horizontal coordinate differences, and the orthographic projection area.

[0023] In one embodiment, determining the occupant's body shape information based on all the ordinate differences, all the abscissa differences, and the orthographic projection area includes:

[0024] Performing mean processing on all the vertical coordinate differences and / or all the horizontal coordinate differences to determine a target mean;

[0025] Determining thickness values corresponding to all the projection coordinates according to the target mean and a preset human body width-to-thickness ratio;

[0026] determining reference weight information according to the orthographic projection area and the thickness value;

[0027] Reference height information is determined based on all of the vertical coordinate differences and / or all of the horizontal coordinate differences.

[0028] In one embodiment, if the state information of the driver's seat meets the airbag deployment condition, it includes:

[0029] If the angle data is within a preset safety angle range, and / or if the installation information is preset installation information, then the driver's seat status information satisfies the airbag deployment condition;

[0030] If the state information of the driver's seat does not meet the airbag deployment condition, the airbag of the vehicle is not deployed.

[0031] In one embodiment, determining an airbag to be deployed in a vehicle and a deployment time of the airbag to be deployed based on the body shape information includes:

[0032] Determining a target height range corresponding to the height in the body shape information, and determining an airbag to be deployed in the vehicle from a first mapping table based on the target height range; the first mapping table includes a correspondence between height ranges and airbags in the vehicle; the vehicle includes at least two airbags;

[0033] A target weight range corresponding to the weight is determined based on the weight in the body shape information, and a detonation time of the airbag to be detonated is determined from a second mapping table based on the target weight range; the second mapping table includes a correspondence between weight ranges and the detonation time of each airbag.

[0034] In a second aspect, the present application also provides a vehicle airbag control system, including an image acquisition device, a vehicle host, a body domain controller, and an airbag controller, wherein:

[0035] The image acquisition device is used to acquire in-vehicle monitoring images including the occupants;

[0036] The vehicle host is configured to recognize the in-vehicle monitoring image, determine the status information of the driver's seat and the body shape information of the occupant, and send the status information and the body shape information to the airbag controller via the body domain controller;

[0037] The airbag controller is configured to determine, in the event of a collision of the vehicle, the airbags to be deployed and the deployment time of the airbags to be deployed based on the body shape information if the status information satisfies the airbag deployment conditions, and control the airbags to be deployed to deploy safely according to the deployment time.

[0038] In a third aspect, the present application further provides a vehicle, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0039] Acquiring in-vehicle surveillance images including occupants;

[0040] Identify the in-vehicle monitoring image to determine the status information of the driver's seat and the body shape information of the occupant;

[0041] In the event of a collision of the vehicle, if the state information of the driver's seat meets an airbag deployment condition, determining an airbag to be deployed in the vehicle and a deployment time of the airbag to be deployed based on the body shape information;

[0042] The airbag to be detonated is controlled to be detonated safely according to the detonation time.

[0043] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0044] Acquiring in-vehicle surveillance images including occupants;

[0045] Identify the in-vehicle monitoring image to determine the status information of the driver's seat and the body shape information of the occupant;

[0046] In the event of a collision of the vehicle, if the state information of the driver's seat meets an airbag deployment condition, determining an airbag to be deployed in the vehicle and a deployment time of the airbag to be deployed based on the body shape information;

[0047] The airbag to be detonated is controlled to be detonated safely according to the detonation time.

[0048] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0049] Acquiring in-vehicle surveillance images including occupants;

[0050] Identify the in-vehicle monitoring image to determine the status information of the driver's seat and the body shape information of the occupant;

[0051] In the event of a collision of the vehicle, if the state information of the driver's seat meets an airbag deployment condition, determining an airbag to be deployed in the vehicle and a deployment time of the airbag to be deployed based on the body shape information;

[0052] The airbag to be detonated is controlled to be detonated safely according to the detonation time.

[0053] The aforementioned vehicle airbag control method, system, vehicle, computer-readable storage medium, and computer program product, for vehicle airbag control, first identify the status of the driver's seat and the occupant's body shape by recognizing in-vehicle surveillance images. In the event of a collision, the system first confirms that the driver's seat status information meets the airbag deployment conditions, thereby avoiding further damage caused by deploying the airbag in an unsafe situation. Furthermore, if the airbag deployment conditions are met, the system determines the airbags to be deployed in the vehicle and the deployment time based on the body shape information. This allows targeted deployment of airbags in corresponding locations based on the body shape information, adapting to the protection needs of different body shapes and further improving safety compared to related technologies. Furthermore, this embodiment only requires image recognition to identify the driver's seat status information and the occupant's body shape information, eliminating the need for additional sensors and reducing vehicle airbag control costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0055] Figure 1 A diagram showing an application environment of a method for controlling a vehicle airbag according to an embodiment;

[0056] Figure 2 1 is a flow chart of a method for controlling a vehicle airbag in one embodiment;

[0057] Figure 3 A schematic diagram of contour recognition and facial information recognition in one embodiment;

[0058] Figure 4 is a schematic diagram of an unsafe sitting posture in one embodiment;

[0059] Figure 5 A schematic diagram of the recognition result of contour coordinate data in one embodiment;

[0060] Figure 6 This is a flow chart of an application scenario of a method for controlling a vehicle airbag in one embodiment;

[0061] Figure 7 is a structural block diagram of a vehicle airbag control system according to one embodiment;

[0062] Figure 8is a structural block diagram of a vehicle airbag control system in another embodiment;

[0063] Figure 9 FIG. 1 is a diagram of the internal structure of a vehicle in one embodiment. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0065] Airbag control is an integral component of automotive safety systems. Traditionally, seatbelts provide some protection by restraining passengers and preventing them from being thrown from the vehicle during a collision. However, relying solely on seatbelts has limitations in certain situations. This is why airbag technology emerged.

[0066] Related airbag technologies have limited sensor sensitivity and control accuracy, which can lead to false triggering or inaccurate deployment in certain collision situations. Furthermore, they lack adaptability when handling complex situations such as varying passenger sizes, seating positions, and collision angles, making it difficult to achieve personalized safety protection. Therefore, a vehicle airbag control method is proposed.

[0067] The vehicle airbag control method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, vehicle 102 and server 104 communicate via a network. Vehicle 102 is equipped with an image capture device, airbags (not shown), and an intelligent vehicle terminal. Vehicle 102 captures in-vehicle surveillance images, including those of the occupants, from the image capture device. It then identifies the in-vehicle status information and the occupant's body shape. In the event of a collision, if the in-vehicle status information meets the airbag deployment conditions, the vehicle determines the airbag to be deployed and the deployment time of the airbag to be deployed based on the body shape information. The airbag to be deployed is then safely deployed according to the deployment time. The intelligent vehicle terminal transmits the acquired in-vehicle airbag and deployment time information to the cloud via a TSP (Telematics Service Provider). Users can then access the relevant information from the cloud via a mobile app.

[0068] The terminal 102 may be, but is not limited to, various types of vehicles. The server 104 may be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The intelligent vehicle-mounted terminal may be of different types, and the image acquisition device may be of different types of devices having image acquisition capabilities.

[0069] In an exemplary embodiment, Figure 2 As shown, a method for controlling a vehicle airbag is provided, and the method is applied to Figure 1 Taking the vehicle in FIG. 1 as an example, the method includes the following steps 202 to 208. Among them:

[0070] Step 202: Acquire an in-vehicle monitoring image including the occupants.

[0071] The in-vehicle surveillance images may be captured by an image capture device located at a preset location in the vehicle. The number of preset locations may be one or more, and is not limited herein. The images captured by the image capture device may or may not contain occupants. If occupants are present, the steps of determining the driver's seat status information and the occupant's body shape information are not required.

[0072] For example, in response to a driving safety function activation instruction triggered on the vehicle's onboard display screen, image information or video information transmitted by the in-vehicle camera is acquired in real time to obtain a corresponding in-vehicle monitoring image.

[0073] Step 204 : Identify the in-vehicle monitoring image to determine the status information of the driving position and the body shape information of the occupants.

[0074] State information may include angle data between target body parts of the occupant in the driver's seat and the vehicle's seat, as well as information about the installation of target objects in the driver's seat. This angle data can be used to determine the occupant's sitting posture, and based on this angle data, whether the sitting posture is safe can be determined. For example, if the angle data between the target body parts is within a preset safe angle range, it indicates a safe sitting posture; otherwise, it indicates an unsafe sitting posture. Body shape information may include height and weight.

[0075] Understandably, when recognizing in-car surveillance images, the system first checks whether a passenger is in the driver's seat. Only after a passenger is identified does it proceed to determine their physical size. This approach helps avoid misjudgments. For example, if a box or other heavy object is placed on the passenger seat, a misjudgment may occur if the human body is not first determined. This can lead to pop-up reminders to fasten seatbelts, for example, which could damage the airbag.

[0076] Optionally, before determining the status information of the driver's seat and the occupant's body shape information, the acquired in-vehicle surveillance image is grayscale processed to obtain a grayscale image after grayscale processing. The grayscale image is then subjected to edge detection to identify the outline of objects. If the outline of the object is identified, the occupant's facial information is identified to determine the presence of an occupant in the driver's seat. Furthermore, seatbelt information in the grayscale-processed in-vehicle surveillance image is identified to determine whether the seatbelt's position in the grayscale-processed in-vehicle surveillance image is within a preset position range. If not, it indicates that the occupant is not fastening their seatbelt as required. If the occupant is not fastening their seatbelt as required and the vehicle speed exceeds a preset speed, a safety reminder is generated, which is displayed as a pop-up window on the vehicle's host computer to remind the passenger to fasten their seatbelt.

[0077] When the occupant is wearing their seatbelt as required, the driver's seat status information and the occupant's body shape information are determined by recognizing the in-vehicle surveillance image. The occupant's body shape information can be determined by image recognition, determining the occupant's outline data, projecting the outline data, determining the projection coordinates, and then determining the projected area and width of the frontal projection of the human body based on the projection coordinates. Furthermore, based on the same vertical coordinate value or horizontal coordinate value in the projected coordinates, the corresponding vertical coordinate difference or horizontal coordinate difference is determined. The height and height used for volume calculation are determined based on the vertical coordinate difference or horizontal coordinate difference, thereby determining the occupant's body shape information.

[0078] In grayscale image processing, the grayscale value reflects the intensity of reflected light from the surface of the object corresponding to that point in the image—the degree of brightness or darkness. Grayscale values are typically represented by a numerical value, generally ranging from 0 to 255. 0 represents black, meaning no brightness; 255 represents white, the brightest state; and values in between represent varying degrees of gray. Larger values indicate higher brightness, closer to white, while smaller values indicate lower brightness, closer to black. Images are composed of three colors: red, green, and blue (RGB), and each color also ranges from 0 to 255. When converting a color image to grayscale, a weighted average of the RGB values of each pixel is typically calculated using a specific algorithm to produce a single numerical value, which serves as the grayscale value for that pixel. For example, the common weighted average formula is: grayscale value = 0.299×R +0.587×G + 0.114×B. Through this formula, each pixel in the color image can be converted into a corresponding grayscale value to form a grayscale image. For example, the RGB of a certain point = (100, 80, 75), converted to grayscale value = 100×0.299+0.587×80+0.114×75=85.41.

[0079] To identify the outline of an object through edge detection, the grayscale processed image can be subjected to edge detection. For example, points with grayscale values less than a first preset value (e.g., 100) are directly discarded, and points with grayscale values greater than a second preset value (e.g., 200) are retained and regarded as edges by default. In this way, the outline of the object in the photo can be extracted. Figure 3 The figure shows a schematic diagram of contour recognition and facial information recognition in one embodiment. Facial information recognition can be determined based on the proportional relationship between the distances between target key points of the face. For example, a face can be recognized using the following parameters: the horizontal distance between the two eyes is generally about 1.5 to 2 times the width of one eye, and the distance between the inner corners of the two eyes is basically equal to the width of one eye; the vertical distance from the midpoint of the eye (center of the pupil) to the bottom of the nose is about 1 / 3 of the vertical height of the face; the horizontal distance from the outer corners of the eyes to the sides of the nose is roughly equal, generally 1 to 1.5 times the width of the nose; the width of the mouth is generally smaller than the width of the bottom of the nose, and the horizontal distance from the corners of the mouth to the sides of the nose is approximately 1 / 2 to 2 / 3 of the width of the nose; the vertical distance from the eyebrows to the mouth is about 2 / 3 to 3 / 4 of the vertical height of the face. It should be noted that grayscale processing, edge detection to recognize the contours of objects, and facial information recognition can be achieved using existing methods and will not be elaborated here.

[0080] Step 206 : In the event of a vehicle collision, if the status information of the driver's seat meets the airbag deployment condition, determine the airbag to be deployed in the vehicle and the deployment time of the airbag to be deployed based on the body shape information.

[0081] The airbag deployment conditions are predetermined and may include the driver's seat occupant's safe sitting posture and / or the target object's installation information on the driver's seat being preset installation information. For example, if the target object is a child seat, if there is a child seat on the passenger seat and the child seat is installed upside down, it does not represent preset installation information. Preset installation information may be installation information in a specified direction and at a specified location in accordance with safety requirements. The vehicle may have at least two or three airbags. In the case of two airbags, the airbags may be located at the front and outer ends of the instrument panel, respectively. In the case of three airbags, the airbags may be located at the front and outer ends of the instrument panel, respectively, and at the driver's seat and the armrest between the driver's seat and the armrest.

[0082] The airbag's deployment time is positively correlated with its size; the earlier it deploys, the larger the airbag will deploy. To minimize damage to passengers of varying weights, different airbag deployment times are assigned to different weights. To accommodate and protect passengers of varying heights, airbags are positioned in different locations depending on their height.

[0083] For example, in the event of a vehicle collision, if the status information of the driver's seat meets the airbag deployment conditions, the airbag to be deployed in the vehicle is determined based on the height in the body information, and the airbag deployment time is determined based on the weight in the body information, and the deployment time is used as the deployment time of the airbag to be deployed.

[0084] Step 208 : Control the airbag to be detonated to detonate safely according to the detonation time.

[0085] For example, in the event of a vehicle collision, that is, upon receiving a collision signal, the airbag controller controls the airbag to be deployed to be safely deployed at the designated deployment time based on the determined airbag to be deployed and the deployment time of the airbag to be deployed.

[0086] In the above-mentioned vehicle airbag control method, vehicle airbag control is performed by first identifying in-vehicle surveillance images to determine driver and passenger seat status information and occupant size information. In the event of a collision, the method first confirms that the driver and passenger seat status information meets airbag deployment conditions, thereby avoiding airbag deployment in unsafe situations that could cause greater harm. Furthermore, if the airbag deployment conditions are met, the method determines the airbags to be deployed and the deployment time of the airbags based on the size information. This allows targeted deployment of airbags in corresponding locations based on the size information, adapting to the protection needs of different body types and further improving safety compared to related technologies. Furthermore, this embodiment only requires image recognition to identify driver and passenger seat status information and occupant size information, eliminating the need for additional sensors and reducing vehicle airbag control costs.

[0087] In order to detect whether the airbag deployment conditions are met in the vehicle, in an exemplary embodiment, the vehicle interior monitoring image is recognized to determine the status information of the driver's seat, including:

[0088] Perform body part recognition on the occupant in the driver's seat in the in-vehicle monitoring image to determine target body parts of the occupant; determine angle data between the target body parts; and / or

[0089] Performing target object recognition on objects in the driver's seat of the vehicle's surveillance image. If a target object exists and is installed on a target seat in the vehicle, determining the installation information of the target object;

[0090] Status information of the driving position is determined based on the angle data and / or the installation information.

[0091] It is understandable that in some scenarios, due to the user's improper sitting posture, the airbag will cause greater harm to the user after the collision, such as Figure 4The unsafe sitting posture shown, Figure 4 The angles between the target body parts in the two sitting postures shown exceed the preset safety angle range, indicating an unsafe sitting posture. Optionally, after grayscale processing of the in-vehicle surveillance image, the correct sitting posture is confirmed by identifying the angles between the target body parts, namely the head, torso, and legs. For example, if the angle between the legs and the upper and lower parts of the seat cushion (or consel) exceeds a certain angle, i.e., is outside the preset safety angle range (e.g., greater than 30°), the passenger's sitting posture is determined to be incorrect. In the event of a vehicle collision, the airbag controller will control the relevant airbags not to deploy for safety reasons.

[0092] Furthermore, if a child seat is detected on the passenger seat and the child seat is installed upside down, the airbag should not deploy; if it does, it could cause greater harm to the user. Determining whether the occupant's sitting posture is correct can be done by detecting the angle between target body parts. If the angle is not within a preset safe angle range, the posture is determined to be unsafe, and the airbag deployment conditions are not met. It is understood that determining the status information of the driver's seat can be achieved through existing image recognition processing methods, which are not specifically limited here.

[0093] Accordingly, if the status information of the driver's seat meets the airbag deployment conditions, including: if the angle data is within the preset safety angle range and / or if the installation information is the preset installation information, then the status information of the driver's seat meets the airbag deployment conditions; if the status information of the driver's seat does not meet the airbag deployment conditions, the vehicle's airbag will not be deployed, that is, the angle data is not within the preset safety angle range and / or if the installation information is not the preset installation information, then the airbag deployment conditions are not met, and the airbag will not be deployed even if a collision occurs.

[0094] Compared with the related technologies that identify unsafe sitting postures and the installation of child seats, this method adds a scenario where the airbag is not deployed. It can protect the occupants based on the actual situation of the driving position, improve safety to the greatest extent possible, and ensure the safety of the occupants.

[0095] The following provides a method for determining the body shape information of an occupant based on image recognition. In an exemplary embodiment, recognizing an in-vehicle surveillance image to determine the body shape information of the occupant includes:

[0096] The outline of the occupant in the driver's seat in the in-vehicle monitoring image is recognized to determine the outline coordinate data of the occupant; based on the outline coordinate data, the occupant's body shape information is determined.

[0097] Among them, the contour recognition and determination of the contour coordinate data can be achieved by existing methods, which will not be elaborated here. According to the contour coordinate data, the body shape information of the occupant can be determined by first projecting the contour coordinate data to obtain the projection coordinates, and then determining the height and weight of the occupant based on the projection coordinates. It should be noted that the height and weight here can refer to the height of the upper body and the weight of the upper body, such as Figure 5 FIG. 1 is a schematic diagram of the recognition result of contour coordinate data in an exemplary embodiment.

[0098] Compared with related technologies, this method of determining the body shape information of passengers based on image recognition does not require data from pressure sensors, seat sensors and other related sensors, but only relies on image recognition to determine the body shape information.

[0099] Furthermore, determining the body shape information of the occupant based on the contour coordinate data includes: projecting each contour point of the contour coordinate data into a preset coordinate system to obtain the projection coordinates of each contour point in the preset coordinate system; calculating all vertical coordinate differences of the same horizontal coordinate based on the projection coordinates; calculating all horizontal coordinate differences of the same vertical coordinate based on the projection coordinates; calculating the orthographic projection area based on the projection coordinates; and determining the body shape information of the occupant based on all vertical coordinate differences, all horizontal coordinate differences, and the orthographic projection area.

[0100] The width of the frontal projection of a person's body can be determined based on the contour coordinate data. This width refers to the maximum left-right distance of the person in the image. The ratio of the front to the front (thickness) of the person at the same location is set to approximately 2:1. The orthographic projection area can be understood as the area enclosed by the projection of the contour onto the projection plane, with the projection direction perpendicular to the projection plane.

[0101] For example, the projected area of the front of the human body can be calculated based on the projected coordinates of each contour point in a preset coordinate system. The differences in each horizontal direction for the same vertical coordinate value are calculated, for example, when y=y1, the horizontal coordinate difference is ∆x1, when y=y2, the horizontal coordinate difference is ∆x2, and when y=yn, the horizontal coordinate difference is ∆xn. Furthermore, the differences in each vertical direction for the same horizontal coordinate value are calculated, for example, when x=x1, the vertical coordinate difference is ∆y1, when x=x2, the vertical coordinate difference is ∆y2, and when x=xn, the vertical coordinate difference is ∆yn.

[0102] The calculation method of the projected area can be determined by the following methods:

[0103]

[0104] Furthermore, determining the occupant's body shape information based on all ordinate differences, all abscissa differences, and the orthographic projection area includes:

[0105] Perform mean processing on all ordinate differences and / or all abscissa differences to determine a target mean; determine the thickness values corresponding to all projection coordinates based on the target mean and a preset human body width-to-thickness ratio; determine the reference weight information based on the orthographic projection area and the thickness value; determine the reference height information based on all ordinate differences and / or all abscissa differences.

[0106] Alternatively, since the purpose here is to determine the height of the upper body and the corresponding weight of the upper body, the thickness values corresponding to all projected coordinates can be determined based on all ordinate differences or all abscissa differences. For example, all ordinate differences can be averaged to determine a target mean; the thickness values corresponding to all projected coordinates can be determined based on the product of the target mean and a preset human body width-to-thickness ratio. For example, all abscissa differences can be averaged to determine a target mean; the thickness values corresponding to all projected coordinates can be determined based on the product of the target mean and a preset human body width-to-thickness ratio.

[0107] In this example, we take the mean of all ordinate differences to determine the target mean; and determine the thickness value ∆y corresponding to all projection coordinates based on the target mean and the preset human body width-to-thickness ratio. After determining the thickness value based on the mean of all abscissa differences, we calculate the volume V=S*∆y, and then estimate the weight H=V* based on the volume. (The human body density is about 1.02g / cm 3 ).

[0108] The reference height information is determined based on all ordinate differences or all abscissa differences. The maximum value among all ordinate differences or all abscissa differences can be determined as the height. In this example, the maximum ordinate difference among all ordinate differences is determined as the height.

[0109] In this embodiment, height and weight are determined through image recognition. Although this method is simple, in the control scheme of vehicle airbags, compared with the related art of relying on sensors to determine height and weight, it can reduce costs and ensure data stability and reliability.

[0110] In an exemplary embodiment, determining an airbag to be deployed in a vehicle and a deployment time of the airbag to be deployed based on body shape information includes:

[0111] Determining a target height range corresponding to the height in the body shape information, and determining an airbag to be deployed in the vehicle from a first mapping table based on the target height range; the first mapping table includes a correspondence between height ranges and airbags in the vehicle; the vehicle includes at least two airbags;

[0112] A target weight range corresponding to the weight in the body shape information is determined, and the detonation time of the airbag to be detonated is determined from a second mapping table based on the target weight range; the second mapping table includes a correspondence between the weight range and the detonation time of each airbag.

[0113] Among them, the first mapping table includes heights within the first height range and the second height range. When the passenger's height is within the first height range, for example, below 185 cm, the 1# airbag (set at the front end of the dashboard) is detonated after receiving the collision signal; when the passenger's height is within the second height range, for example, above 185 cm, the 2# airbag (at the outer end of the dashboard) is detonated after receiving the collision signal.

[0114] It is understandable that passengers of different heights will collide at different points in the event of a collision, so the airbags at their corresponding positions can be deployed based on the point of collision. For example, if the airbags are set at the front or outer end of the dashboard, the purpose is to protect the target parts of the body of passengers of different heights in the event of a collision. The target part can be, but is not limited to, the head. Taking the head as the target part, the airbag is set at the front of the dashboard, which can be the middle of the dashboard on the passenger side, close to the center console area, to prevent impact on the dashboard. The airbag is set at the outer end of the dashboard, which can be the top edge of the dashboard on the passenger side, close to the windshield, to prevent impact on the windshield. Furthermore, according to different car models, the airbags corresponding to different heights can be adjusted accordingly. The second mapping table shows the corresponding relationship between weight ranges and airbag deployment times: ① Within the first weight range, for example, those under 40kg, deployment occurs 30ms after receiving the collision signal; ② Within the second weight range, for example, those between 40kg and 80kg, deployment occurs 20ms after receiving the collision signal; and ③ Within the third weight range, for example, those over 80kg, deployment occurs 10ms after receiving the collision signal. Weight and deployment time are positively correlated; that is, the greater the weight, the earlier the deployment time, and the corresponding larger airbag deployment.

[0115] In the above method, the detonation time is determined according to different weights, and the method of detonating the airbag is determined according to passengers of different heights. The airbag can be adaptively detonated according to weight and height, thereby achieving personalized safety protection and improving safety.

[0116] In an exemplary embodiment, Figure 6 As shown, a flowchart of an application scenario of a vehicle airbag control method is provided. The vehicle includes an image acquisition device, an onboard host, a body domain controller, an airbag controller, a T-BOX, and a cloud server. The image acquisition device is an onboard camera, specifically including the following:

[0117] S1: The user activates the driving safety function by clicking the soft switch on the large screen.

[0118] S2: After this function is activated, when the vehicle is powered on, the on-board camera collects image information in real time and sends the collected image information to the on-board host.

[0119] S3: The vehicle host receives real-time image information collected by the vehicle camera, converts the image information into digital-analog information, obtains the in-vehicle monitoring image, performs image recognition on the in-vehicle monitoring image, identifies the occupant's sitting posture, whether the seat belt is correctly fastened, and body shape information, and sends the occupant's sitting posture and body shape information to the vehicle body domain controller. If the occupant is not wearing a seat belt or the seat belt is fastened incorrectly, the host will pop up a window to remind the user to fasten the seat belt correctly.

[0120] S4: The body domain controller sends the received sitting posture and body shape information to the airbag controller.

[0121] S5: The airbag controller receives the sitting posture and body shape information. In the event of a vehicle collision, that is, when a collision signal is received, it determines whether to detonate the airbag based on the sitting posture and body shape information, determines the detonation information of the airbag to be detonated and the detonation time of the airbag to be detonated, and performs corresponding actions, and synchronously transmits the detonation information to the body domain controller.

[0122] Optionally, two airbags are positioned on the passenger side of the dashboard, one in front and one in the rear. In the event of a collision, the airbag controller controls whether and where the airbags deploy based on the front passenger's sitting posture and body type. For example, if the driver's seat occupant is in a safe sitting position, the airbag deployment conditions are met, and the airbag controller controls the deployment of the airbags in different locations according to the front passenger's body type (height and weight). If the driver's seat occupant is in an unsafe sitting position, the airbag deployment conditions are not met, and the airbag controller controls the deployment of both airbags at different times.

[0123] S6: The vehicle body domain controller sends the information of whether to deploy the airbag, the airbag to be deployed, and the deployment time of the airbag to be deployed to the T-BOX, and the T-BOX transmits the execution action information to the cloud server.

[0124] It should be noted that the specific implementation of this embodiment can be achieved through the above-mentioned limited methods, which will not be elaborated here.

[0125] In the above embodiment, by recognizing in-vehicle surveillance images, the system determines whether passengers are wearing seatbelts and, if not, reminds passengers to fasten their seatbelts. In the event of a collision, the system first confirms that the driver's seat status information meets the airbag deployment conditions. If the conditions are not met, the airbags are not deployed. If the conditions are met, the system determines which airbags to deploy based on height and the deployment time based on weight. This approach increases the number of scenarios where airbags may not deploy and allows for targeted deployment of airbags based on body shape information, adapting to the protection needs of different body types. Compared to related technologies, this approach further improves safety and the level of intelligent airbag control. Furthermore, this embodiment only requires image recognition to identify the driver's seat status information and occupant body shape information, eliminating the need for additional sensors and reducing vehicle airbag control costs.

[0126] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0127] Based on the same inventive concept, embodiments of the present application also provide a vehicle airbag control system for implementing the aforementioned vehicle airbag control method. The solution provided by this system is similar to the solution described in the aforementioned method. Therefore, the specific limitations of the one or more vehicle airbag control system embodiments provided below can be found in the above-described limitations of the vehicle airbag control method and will not be further elaborated here.

[0128] In an exemplary embodiment, Figure 7 As shown, a vehicle airbag control system is provided, which includes an image acquisition device, a vehicle host, a body domain controller and an airbag controller, wherein:

[0129] Image acquisition equipment, used to acquire in-vehicle monitoring images including those of the occupants;

[0130] The vehicle host is used to identify the in-vehicle monitoring image, determine the status information of the driver and passenger seats and the body shape information of the occupants, and send the status information and body shape information to the airbag controller via the body domain controller;

[0131] The airbag controller is used to determine the airbags to be deployed in the vehicle and the deployment time of the airbags to be deployed based on the body shape information in the event of a vehicle collision. If the status information meets the airbag deployment conditions, the airbag controller controls the deployment of the airbags to be deployed safely according to the deployment time.

[0132] The vehicle airbag control system described above controls the vehicle airbags by first identifying in-vehicle surveillance images to determine driver and passenger seat status information and occupant size information. In the event of a collision, the system first confirms that the driver and passenger seat status information meets airbag deployment conditions, thereby preventing airbag deployment in unsafe situations from causing greater harm. Furthermore, when airbag deployment conditions are met, the system determines the airbags to be deployed and their deployment timing based on the size information. This allows targeted deployment of airbags based on the size information, adapting to the protection needs of different body types and further improving safety compared to related technologies. Furthermore, this embodiment only requires image recognition to identify driver and passenger seat status information and occupant size information, eliminating the need for additional sensors and reducing vehicle airbag control costs.

[0133] In an exemplary embodiment, the vehicle host is used to identify the body parts of the occupant in the driver's seat in the vehicle monitoring image, determine the target body parts of the occupant; determine the angle data between the target body parts; and / or

[0134] Performing target object recognition on objects in the driver's seat of the vehicle's surveillance image. If a target object exists and is installed on a target seat in the vehicle, determining the installation information of the target object;

[0135] Status information of the driving position is determined based on the angle data and / or the installation information.

[0136] In an exemplary embodiment, the vehicle-mounted host is used to perform contour recognition on an occupant in the driver's seat in the in-vehicle monitoring image and determine the contour coordinate data of the occupant;

[0137] The body shape information of the occupant is determined based on the outline coordinate data.

[0138] In an exemplary embodiment, the vehicle-mounted host is configured to project each contour point of the contour coordinate data into a preset coordinate system to obtain the projection coordinates of each contour point in the preset coordinate system;

[0139] According to the projection coordinates, calculate the differences of all vertical coordinates with the same horizontal coordinate;

[0140] According to the projection coordinates, calculate the differences of all horizontal coordinates with the same vertical coordinate;

[0141] Calculate the orthographic projection area based on the projection coordinates;

[0142] The body shape information of the occupant is determined based on all ordinate differences, all abscissa differences, and the orthographic projection area.

[0143] In an exemplary embodiment, the vehicle-mounted host is configured to perform mean processing on all the vertical coordinate differences and / or all the horizontal coordinate differences to determine a target mean;

[0144] Determine the thickness values corresponding to all projection coordinates based on the target mean and the preset human body width-to-thickness ratio;

[0145] Determine the reference weight information based on the front projection area and thickness value;

[0146] Reference height information is determined based on all ordinate differences and / or all abscissa differences.

[0147] In an exemplary embodiment, the airbag controller is configured to determine that the driver's seat status information satisfies an airbag deployment condition if the angle data is within a preset safety angle range and / or if the installation information is preset installation information;

[0148] If the status information of the driver's seat does not meet the airbag deployment conditions, the vehicle's airbag will not deploy.

[0149] In an exemplary embodiment, an airbag controller is configured to determine a target height range corresponding to a height in body shape information, and determine an airbag to be deployed in a vehicle from a first mapping table based on the target height range; the first mapping table includes a correspondence between height ranges and airbags in the vehicle; and the vehicle includes at least two airbags.

[0150] A target weight range corresponding to the weight in the body shape information is determined, and the detonation time of the airbag to be detonated is determined from a second mapping table based on the target weight range; the second mapping table includes a correspondence between the weight range and the detonation time of each airbag.

[0151] In an exemplary embodiment, Figure 8As shown, the vehicle airbag control system also includes a cloud server. Each component communicates via a communication link. The vehicle is equipped with an intelligent onboard terminal (T-BOX) and a seatbelt controller. The intelligent onboard terminal (T-BOX) transmits information about the airbags to be deployed and their deployment times from the vehicle's domain controller to the cloud server via the TSP. The seatbelt controller reminds the driver and passengers to use their seatbelts correctly and provides effective protection in a collision through pretensioning and force limiting. The functions of the seatbelt controller include all those described in existing methods and are not specifically limited or elaborated upon here.

[0152] Each module in the aforementioned vehicle airbag control system may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of the vehicle's processor in hardware form, or may be stored in the vehicle's memory in software form, allowing the processor to call and execute the corresponding operations of each module.

[0153] In an exemplary embodiment, a vehicle is provided. The vehicle may be a terminal, and its internal structure may be as shown in FIG. Figure 9 As shown. The vehicle includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input system. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input system are connected to the system bus via the input / output interface. The vehicle's processor provides computing and control capabilities. The vehicle's memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operating system and computer programs in the non-volatile storage medium to run. The vehicle's input / output interface is used to exchange information between the processor and external devices. The vehicle's communication interface is used to communicate with external terminals via wired or wireless communication, with wireless communication being achieved via Wi-Fi, a mobile cellular network, near-field communication (NFC), or other technologies. When executed by the processor, the computer program implements a vehicle airbag control method. The vehicle's display unit forms a visually visible image and may be a display screen, a projection system, or a virtual reality imaging system. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the vehicle's input system can be a touch layer covering the display screen, or a button, trackball or touchpad set on the vehicle shell, or an external keyboard, touchpad or mouse.

[0154] Those skilled in the art will understand that Figure 9The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the vehicle to which the solution of the present application is applied. The specific vehicle may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0155] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0156] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0157] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0158] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0159] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0160] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0161] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for controlling a vehicle airbag, characterized in that: The method comprises: Acquiring in-vehicle surveillance images including occupants; Identify the in-vehicle monitoring image to determine the status information of the driver's seat and the body shape information of the occupant; In the event of a collision of the vehicle, if the state information of the driver's seat meets an airbag deployment condition, determining an airbag to be deployed in the vehicle and a deployment time of the airbag to be deployed based on the body shape information; The airbag to be detonated is controlled to be detonated safely according to the detonation time.

2. The method according to claim 1, characterized in that The identifying the in-vehicle monitoring image and determining the state information of the driver's seat includes: Performing body part recognition on the occupant in the driver's seat in the in-vehicle monitoring image to determine target body parts of the occupant; determining angle data between the target body parts; and / or Performing target object recognition on an object in the driver's seat in the in-vehicle monitoring image, and if a target object exists and is installed on a target seat in the vehicle, determining installation information of the target object; State information of the driving position is determined according to the angle data and / or the installation information.

3. The method according to claim 2, characterized in that If the state information of the driver's seat meets the airbag deployment condition, it includes: If the angle data is within a preset safety angle range, and / or if the installation information is preset installation information, then the driver's seat status information satisfies the airbag deployment condition; If the state information of the driver's seat does not meet the airbag deployment condition, the airbag of the vehicle is not deployed.

4. The method according to claim 1, wherein Recognizing the in-vehicle surveillance image to determine the occupant's body shape information includes: Performing contour recognition on the occupant in the driver's seat in the in-vehicle monitoring image to determine the contour coordinate data of the occupant; The body shape information of the occupant is determined based on the outline coordinate data.

5. The method according to claim 4, characterized in that The determining of the body shape information of the occupant based on the outline coordinate data includes: Projecting each contour point of the contour coordinate data into a preset coordinate system to obtain the projection coordinates of each contour point in the preset coordinate system; According to the projection coordinates, all vertical coordinate differences of the same horizontal coordinate are calculated; According to the projection coordinates, all horizontal coordinate differences of the same vertical coordinate are calculated; Calculating the orthographic projection area according to the projection coordinates; The body shape information of the occupant is determined according to all the vertical coordinate differences, all the horizontal coordinate differences, and the orthographic projection area.

6. The method according to claim 5, characterized in that The determining of the occupant's body shape information according to all the ordinate differences, all the abscissa differences, and the orthographic projection area includes: Performing mean processing on all the vertical coordinate differences and / or all the horizontal coordinate differences to determine a target mean; Determining thickness values corresponding to all the projection coordinates according to the target mean and a preset human body width-to-thickness ratio; determining reference weight information according to the orthographic projection area and the thickness value; Reference height information is determined based on all of the vertical coordinate differences and / or all of the horizontal coordinate differences.

7. The method according to any one of claims 1 to 6, characterized in that The step of determining an airbag to be deployed in the vehicle and a deployment time of the airbag to be deployed based on the body shape information includes: Determining a target height range corresponding to the height in the body shape information, and determining an airbag to be deployed in the vehicle from a first mapping table based on the target height range; the first mapping table includes a correspondence between height ranges and airbags in the vehicle; the vehicle includes at least two airbags; A target weight range corresponding to the weight is determined based on the weight in the body shape information, and a detonation time of the airbag to be detonated is determined from a second mapping table based on the target weight range; the second mapping table includes a correspondence between weight ranges and the detonation time of each airbag.

8. A vehicle airbag control system, characterized in that: The system includes an image acquisition device, a vehicle host, a body domain controller and an airbag controller, wherein: The image acquisition device is used to acquire in-vehicle monitoring images including the occupants; The vehicle host is configured to recognize the in-vehicle monitoring image, determine the status information of the driver's seat and the body shape information of the occupant, and send the status information and the body shape information to the airbag controller via the body domain controller; The airbag controller is configured to determine, in the event of a collision of the vehicle, the airbags to be deployed and the deployment time of the airbags to be deployed based on the body shape information if the status information satisfies the airbag deployment conditions, and control the airbags to be deployed to deploy safely according to the deployment time.

9. A vehicle comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

11. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images