Vehicle roof protection device control method and device, electronic equipment and medium

By analyzing the vehicle's external environment image, identifying the type of moving objects and predicting impact force, the problem of misjudging and activating protective devices in the prior art is solved, and more accurate protective measures are achieved, resource waste is reduced and user experience is improved.

CN119078730APending Publication Date: 2024-12-06CHONGQING SELIS PHOENIX INTELLIGENT INNOVATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411289628.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-14
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The existing vehicle protection system frequently and unnecessary activation of protective devices due to misjudgment, increasing equipment wear and energy consumption, and reducing service life and trust.

Method used

Multi-frame environmental images are obtained through the vehicle's external camera, the type of moving objects and the position of the landing point are identified and analyzed, and the impact force is predicted to determine whether the protective device is activated to avoid unnecessary activation.

Benefits of technology

Accurately analyze and predict contact situations of moving objects, reduce false alarm rates, reduce resource waste, and ensure timely protection when really needed.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119078730A_ABST
    Figure CN119078730A_ABST
Patent Text Reader

Abstract

The invention provides a vehicle roof protection device control method and device, electronic equipment and a medium. The method comprises the steps that multiple frames of environment images outside a vehicle are acquired; performing identification processing on each frame of environment image to determine whether each frame of environment image contains a moving object; when each frame of environment image contains a moving object, determining the motion type of the moving object; calling a processing interface corresponding to the motion type according to the motion type of the motion object; determining whether the falling point position of the moving object is on the vehicle or not through a processing interface corresponding to the motion type; when the falling point position of the moving object is on the vehicle, the impact force generated when the moving object makes contact with the vehicle is determined through a processing interface corresponding to the motion type; according to the impact force generated when the moving object makes contact with the vehicle, a protection device of the vehicle roof is controlled. According to the application, the drop point and the impact force of the moving object are accurately predicted by using the processing interfaces of different motion types, and the activation accuracy of the protection device can be greatly improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of controlling a protective device for a vehicle roof, and in particular to a method, device, electronic equipment and medium for controlling a protective device for a vehicle roof. Background Art

[0002] With the development of automobile safety technology, the design of vehicle protection systems has become increasingly important, especially protective measures when the vehicle is parked. At present, in order to prevent stationary vehicles from being damaged or stolen, vehicle manufacturers usually install protective devices on the roof of the vehicle and install cameras at multiple locations outside the vehicle. These cameras are responsible for capturing images of the vehicle's surrounding environment and transmitting the images to the on-board computing system (i.e., the vehicle computer system) in real time. The existing vehicle protection system analyzes the captured images through the vehicle computer system to identify whether there are moving objects in the image. Once a moving object is identified, the system automatically activates the protective device to prevent the vehicle from potential damage. However, this method has obvious shortcomings. Since the system activates the protective device only based on whether there is a moving object in the image, it cannot distinguish the specific movement type of the moving object and the real threat of the movement. Therefore, the protection system in the prior art may frequently and unnecessarily activate the protective device due to misjudgment, which not only increases the wear of the equipment and reduces the service life of the protective device, but also may lead to unnecessary energy consumption and maintenance costs. In addition, frequent misoperation will also affect the user's experience and trust in the vehicle protection system. Summary of the invention

[0003] In view of this, the embodiments of the present application provide a method, device, electronic device and readable storage medium for controlling a protective device of a vehicle roof to solve the technical problem that the protective system in the prior art may frequently and unnecessarily activate the protective device due to misjudgment, which not only increases the wear of the equipment and reduces the service life of the protective device, but also may cause unnecessary energy consumption and maintenance costs.

[0004] According to a first aspect of an embodiment of the present application, a method for controlling a protective device on a vehicle roof is provided, comprising: acquiring multiple frames of environmental images outside a vehicle through a camera outside the vehicle according to a preset time interval; identifying and processing each frame of the environmental image to determine whether each frame of the environmental image contains a moving object; when each frame of the environmental image contains a moving object, determining the motion type of the moving object; according to the motion type of the moving object, calling a processing interface corresponding to the motion type; determining whether a landing point of the moving object is on the vehicle through the processing interface corresponding to the motion type; when the landing point of the moving object is on the vehicle, determining the impact force when the moving object contacts the vehicle through the processing interface corresponding to the motion type; and controlling the protective device on the vehicle roof according to the impact force when the moving object contacts the vehicle.

[0005] According to a second aspect of an embodiment of the present application, a protective device control device for a vehicle roof is provided, the device comprising: an acquisition module, for acquiring multiple frames of environmental images outside the vehicle through a camera outside the vehicle according to a preset time interval; an identification module, for identifying and processing each frame of the environmental image to determine whether each frame of the environmental image contains a moving object; a motion type determination module, for determining the motion type of the moving object when each frame of the environmental image contains a moving object; an interface calling module, for calling a processing interface corresponding to the motion type according to the motion type of the moving object; a landing point determination module, for determining whether the landing point of the moving object is on the vehicle through the processing interface corresponding to the motion type; an impact force determination module, for determining the impact force when the moving object contacts the vehicle through the processing interface corresponding to the motion type when the landing point of the moving object is on the vehicle; and a control module, for controlling the protective device for the vehicle roof according to the impact force when the moving object contacts the vehicle.

[0006] According to a third aspect of an embodiment of the present application, a vehicle device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method provided in the first aspect are implemented.

[0007] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps of the method provided in the first aspect are implemented.

[0008] Compared with the prior art, the beneficial effects of the embodiments of the present application include at least: the embodiments of the present application can accurately predict whether the moving object will contact the vehicle and the specific location of the contact by analyzing the motion trajectory of the moving object. This accurate landing point prediction method avoids the situation where the protective device is triggered because the moving object is only close to the vehicle but not actually in contact with the vehicle. Different moving objects (such as flying spheres or large objects moving quickly) pose different potential threats to the vehicle. By predicting the impact force, it is possible to judge the degree of damage that the moving object may cause to the vehicle, thereby determining whether the protective device needs to be activated and the degree of activation (such as partial activation or full activation). Existing methods may not be able to distinguish the specific motion type and impact potential of the moving object, resulting in frequent and unnecessary activation. The method of the present application uses precise analysis to activate the protective device only when it is really needed, greatly reducing the false alarm rate and reducing resource waste. While ensuring that false activation is not frequent, timely and appropriate protection can also be provided when it is really needed, thereby effectively protecting the vehicle from damage caused by actual threats. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0010] Figure 1 is a flow chart of a method for controlling a protective device of a vehicle roof according to an embodiment of the present application;

[0011] Figure 2 is a flow chart of another method for controlling a protective device of a vehicle roof according to an embodiment of the present application;

[0012] Figure 3 is a flow chart of another method for controlling a protective device of a vehicle roof according to an embodiment of the present application;

[0013] Figure 4 It is a block diagram of a protective device control device for a vehicle roof according to an embodiment of the present application.

[0014] Figure 5 It is a structural schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0015] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0016] Figure 1 It is a flow chart of a method for controlling a protective device of a vehicle roof according to an embodiment of the present application. The method provided by the embodiment of the present application can be executed by any electronic device with computer processing capabilities, for example, the electronic device can be a vehicle device installed in a vehicle.

[0017] like Figure 1 As shown, the method for controlling the protective device of the vehicle roof includes steps S110 to S170.

[0018] In step S110, a plurality of frames of environment images outside the vehicle are acquired through a camera outside the vehicle at preset time intervals.

[0019] In step S120, recognition processing is performed on each frame of the environment image to determine whether each frame of the environment image contains a moving object.

[0020] In step S130, when each frame of the environmental image contains a moving object, the movement type of the moving object is determined.

[0021] In step S140, according to the motion type of the motion object, a processing interface corresponding to the motion type is called.

[0022] In step S150, it is determined whether the landing point of the moving object is on the vehicle through the processing interface corresponding to the movement type.

[0023] In step S160, when the landing point of the moving object is on the vehicle, the impact force when the moving object contacts the vehicle is determined through a processing interface corresponding to the motion type.

[0024] In step S170, the protective device of the vehicle roof is controlled according to the impact force when the moving object contacts the vehicle.

[0025] The method can accurately predict whether the moving object will contact the vehicle and the specific location of the contact by analyzing the motion trajectory of the moving object. This accurate drop point prediction method avoids the situation where the protective device is triggered because the moving object is only close to the vehicle but not actually in contact with the vehicle. Different moving objects (such as flying spheres or large objects moving quickly) pose different potential threats to the vehicle. By predicting the impact force, it is possible to judge the degree of damage that the moving object may cause to the vehicle, thereby deciding whether the protective device needs to be activated and the degree of activation (such as partial activation or full activation). Existing methods may not be able to distinguish the specific motion type and impact potential of the moving object, resulting in frequent and unnecessary activation. The method of the present application activates the protective device only when it is really needed through precise analysis, greatly reducing the false alarm rate and reducing resource waste. While ensuring that false activation is not frequent, timely and appropriate protection can also be provided when it is really needed, thereby effectively protecting the vehicle from damage caused by actual threats.

[0026] In some embodiments, multiple frames of environmental images outside the vehicle are acquired through a camera outside the vehicle at preset time intervals. For example, multiple high-resolution cameras are installed outside the vehicle, and these cameras are usually arranged at key positions such as the front, rear, and side of the vehicle to capture the environment around the vehicle in all directions. This layout ensures that relevant visual information can be captured regardless of the direction from which the moving object approaches. The preset time interval refers to the time interval for the camera to take continuous images, and this parameter can be set according to actual needs. The camera automatically captures images of the external environment of the vehicle within a preset time interval. These images need to have sufficient resolution and clarity so that the moving objects in the image can be accurately identified and analyzed. The acquired image data needs to be transmitted to the vehicle system in real time, usually through a high-speed data interface, such as a CAN bus or Ethernet. The vehicle system will analyze these images, including motion detection, object recognition, trajectory prediction, etc., to achieve subsequent intelligent decision-making.

[0027] In some embodiments, a pre-trained image recognition model is used to identify and analyze each frame of the environment image outside the vehicle. The image recognition model can be trained by deep learning or machine learning algorithms. During the training phase, a large number of images of the vehicle's external environment are input to the image recognition model, which are annotated with the position, type and other relevant attributes of the moving object. In this way, the image recognition model learns to recognize different types of moving objects (such as free-falling objects, thrown objects, moving pendulums, objects subject to wind resistance, etc.) and their movement trajectories. After the training is completed, the image recognition model can be deployed to the vehicle's on-board system. The on-board system usually has a certain computing power and can process image data from the vehicle's camera in real time. In actual operation, the on-board system continuously collects multiple frames of environmental images from the vehicle's external camera. These images are sent to the image recognition model for analysis at preset time intervals. The image recognition model first identifies each object in the image, and then compares the position changes of the same object between consecutive frames. If the position of the object changes in consecutive image frames, the image recognition model determines that these objects are moving objects.

[0028] In some embodiments, different logic processing interfaces are configured according to the motion type of the moving object (such as free fall motion, parabolic motion, pendulum motion, discrete motion), and different logic processing interfaces can be used to predict the landing point of the moving object and the impact force it may have on the vehicle. This method not only improves the flexibility and scalability of the vehicle system, but also responds accurately according to specific circumstances. Specifically, first, it is necessary to define the logic processing interface for each type of motion. Each interface contains the calculation method required to process this type of motion. For example: the free fall interface is used to calculate the landing point and expected impact force based on gravity acceleration and initial height. The parabolic motion interface is used to predict the landing point by analyzing the parabola equation and to calculate the speed of the object to estimate the impact force. The pendulum motion interface is used to analyze periodic motion to predict the point closest to the vehicle and the kinetic energy at that point to estimate the impact force. The discrete motion interface is used to use random or probabilistic models to predict possible landing points and impact forces, which may require complex statistical methods due to its uncertainty. Each interface is encapsulated as a module or class and implemented as an independent component in the vehicle system. These interfaces can be called through API (application programming interface), ensuring that they can be accessed when needed. By integrating these interfaces into the vehicle system, the appropriate interface can be selected based on the data analyzed in real time. For example, when an object is determined to be in parabolic motion through image recognition and motion analysis, the parabolic motion interface will be called to handle the subsequent calculations. When the vehicle's external camera captures a moving object, the motion type is first identified, and then the corresponding processing interface is dynamically called based on the identification result. In this way, the predicted landing point position and impact force can be calculated in real time, providing the driver with sufficient reaction time to take evasive measures. In this embodiment, based on actual operating data and feedback, these interfaces can be continuously optimized and updated to improve the accuracy of the prediction and the reliability of the system. The above method can effectively handle various complex motion situations, reduce the risk of vehicle damage, and improve the safety of the vehicle in various environments. This modular and interfaced processing method also provides convenience for future upgrades and maintenance of the system.

[0029] Figure 2 It is a flowchart of the steps of determining whether the environment image of each frame contains a moving object in an embodiment of the present application.

[0030] like Figure 2 As shown, step S120 may specifically include step S210 and step S220.

[0031] In step S210, recognition processing is performed on each frame of the environment image to obtain position data of the moving object in each frame of the environment image.

[0032] In step S220, if the position data of the moving object in each frame of the environmental image meets the preset displacement condition, it is determined that each frame of the environmental image contains a moving object; if the position data of the moving object in each frame of the environmental image does not meet the preset displacement condition, it is determined that each frame of the environmental image does not contain a moving object.

[0033] The method can perform recognition processing on each frame of environmental image and obtain the position data of the moving object in each frame of environmental image. If the position data of the moving object in each frame of environmental image meets the preset displacement condition, it is determined that each frame of environmental image contains the moving object; if the position data of the moving object in each frame of environmental image does not meet the preset displacement condition, it is determined that each frame of environmental image does not contain the moving object. In this way, it is possible to quickly and effectively identify whether the environmental image contains a moving object.

[0034] In some embodiments, each frame of the environmental image is processed for recognition, and the position data of the moving object in each frame of the environmental image is obtained. For example, the vehicle's on-board system uses the deployed image recognition model to process multiple frames of environmental images from the vehicle's external camera in real time. First, all visible objects in the image are identified and a unique identifier is assigned to each object. The position data of each object in each frame is recorded, usually including the coordinate position of the object. The preset displacement condition refers to the position change threshold used to determine whether the object has moved. This condition can be preset based on factors such as the type of object, environmental background, and vehicle speed. For example, for pedestrians and bicycles, a small position change may be regarded as a valid movement; while for distant objects, a more obvious position change may be required to confirm that it is a moving object. The on-board system can continuously compare the position data of the same object in consecutive frames. By calculating the change in the object position (for example, by Euclidean distance or other appropriate distance measurement), check whether this change reaches the threshold of the preset displacement condition. If the position change meets the preset displacement condition, it indicates that the object has obvious movement in the consecutive image frames, and it is determined that these frames contain moving objects. If the position change does not meet the preset displacement condition, it indicates that the object is almost stationary during the observation period, and it is determined that these frames do not contain moving objects. This application can effectively identify and respond to dynamic changes in the vehicle's external environment, improve the vehicle's active safety performance, and thus protect the safety of the vehicle and its passengers. This method not only improves the accuracy of the protection system, but also optimizes the system's response time and reduces the possibility of misoperation.

[0035] Based on the above embodiments, in order to more accurately identify and analyze moving objects in the external environment of the vehicle, the image recognition model uses a three-dimensional coordinate system to process and represent the position data of objects in each frame of the environmental image. In the image recognition model, a three-dimensional coordinate system with the vehicle as a reference is constructed. The origin of this coordinate system is usually set at a fixed point of the vehicle, such as the front or rear of the vehicle. The coordinate system is set as follows: X-axis: along the length of the vehicle, usually from the front to the rear or vice versa. Y-axis: along the width of the vehicle, from one side to the other. Z-axis: perpendicular to the horizontal plane of the vehicle, pointing upward to the sky. Whenever the vehicle's camera captures an environmental image, the image recognition model will analyze the objects in the image and convert their positions into coordinate points in the above three-dimensional coordinate system. For example, all objects in the environmental image are identified, such as pedestrians, other vehicles, thrown objects, pendulums, free-falling objects, etc. Then the pixel position of each object in the image is calculated, and these pixel positions are converted to actual positions in the three-dimensional coordinate system according to the calibration parameters of the camera (such as focal length, angle, camera position, etc.). Using the position data in the continuous frame images, the movement trajectory of each object can be tracked: by comparing the 3D coordinates of the same object in the continuous frames, it is possible to determine whether the object is moving. By pre-building a 3D coordinate system in the image recognition model and using the vehicle as a reference point to accurately calculate the position of the object, the accuracy of environmental perception and the overall effectiveness of the system are effectively improved. This method not only helps to improve the safety of the vehicle, but also optimizes the vehicle's adaptability to the environment and its response strategy.

[0036] In some embodiments, if the position data of the moving object in each frame of the environmental image meets the preset displacement condition, it is determined that each frame of the environmental image contains a moving object; if the position data of the moving object in each frame of the environmental image does not meet the preset displacement condition, it is determined that each frame of the environmental image does not contain a moving object. For example, the preset displacement condition is set according to the operating environment and safety requirements of the vehicle. These conditions define the minimum movement distance or change amount that an object reaches between consecutive frames to be identified as a "moving object". The displacement condition can be set based on a variety of factors, such as the type of object, ambient light, vehicle speed, etc. The environmental image is continuously acquired by a camera outside the vehicle, and an image processing algorithm is used to identify and track each object in the image. The position of each object in each frame is recorded, usually in the form of coordinates. The position coordinate changes of the same object in consecutive frames will be analyzed. By calculating the displacement distance of the object between different frames (for example, using the Euclidean distance formula), it is evaluated whether this displacement meets the preset displacement condition. If the displacement meets the preset condition: it indicates that the object has obvious movement during the observation period, and it is determined that the frame image contains a moving object. If the displacement does not meet the preset condition, it indicates that the object remains stationary during the observation period or its movement is too small to trigger a system response. In this case, it is determined that the frame image does not contain a moving object, thereby avoiding unnecessary activation of protective measures. Based on the above analysis results, it can be intelligently decided whether to activate the protective device. If a moving object is detected and it is predicted that it may cause a potential collision, appropriate safety measures will be taken, that is, the protective device on the vehicle roof will be opened.

[0037] Figure 3 FIG. 1 is a flow chart of the steps of determining the motion type of the motion object in an embodiment of the present application. Figure 3 As shown, step S130 may specifically include steps S310 to S330.

[0038] In step S310, the moving direction of the moving object is determined according to the position data of the moving object in each frame of the environmental image.

[0039] In step S320, when the moving direction of the moving object is vertical ground movement, it is determined that the moving type of the moving object is free fall movement.

[0040] In step S330, when the moving direction of the moving object is non-vertical ground movement, it is determined that the movement type of the moving object is parabolic movement, pendulum movement, or discrete movement.

[0041] This method can determine the direction of motion of the moving object based on the position data of the moving object in each frame of the environmental image. When the direction of motion of the moving object is vertical to the ground, the motion type of the moving object is determined to be free fall motion. When the direction of motion of the moving object is non-vertical to the ground, the motion type of the moving object is determined to be parabolic motion, pendulum motion, or discrete motion. In this way, not only can the type and direction of the moving object be accurately determined, but also the most appropriate time to start protective measures can be taken according to the specific situation, which greatly improves driving safety and the ability to adapt to the environment.

[0042] In some embodiments, the direction of movement of the moving object is determined based on the position data of the moving object in each frame of the environmental image. For example, the external camera of the vehicle continuously captures environmental images, which are then used by the vehicle system to identify the objects in each frame by using an image recognition algorithm. When the object is identified, an object tracking technique (such as optical flow method, Kalman filter, etc.) is used to track the position change of the object in consecutive frames. For each tracked object, the system calculates its displacement between consecutive frames. This is usually achieved by simply changing the position from the previous frame to the current frame. For example, if an object moves from the position (x1, y1) of the first frame to the position (x2, y2) of the second frame, the displacement vector Δx, Δy can be expressed as Δx = x2-x1, Δy = y2-y1. According to the displacement vector, not only the distance moved by the object can be determined, but also the direction of movement is indicated. The direction of movement can be determined by the angle of the displacement vector. The inverse tangent function (atan2) is usually used to calculate the angle from the X axis to the displacement vector. The angle describes the direction of movement of the object relative to the horizontal axis and can be used to determine whether the object moves forward, backward, left or right. Through the above steps, the vehicle protection system can accurately determine the movement direction of objects in the environment.

[0043] In some embodiments, when the moving direction of the moving object is vertical ground motion, the moving object's motion type is determined to be free fall motion. For example, the moving direction is determined by the displacement vector of the object in the continuous image frames. If the displacement vector is mainly in the vertical direction (i.e., the Z-axis direction, assuming that the Z-axis is perpendicular to the ground), it is determined that the object may be moving vertically. In order to further confirm whether it is free fall motion, it is necessary to analyze the acceleration of the moving object. If the acceleration of the moving object is the acceleration of gravity, it indicates that the moving object's motion type is free fall motion.

[0044] In some embodiments, when the direction of motion of the moving object is non-vertical ground motion, the motion type of the moving object is determined to be parabolic motion, pendulum motion, or discrete motion. For example, the environment image is continuously captured by the external camera of the vehicle, and the position change of the moving object is tracked by the image processing algorithm. These position data need to be converted into actual physical coordinates for accurate motion analysis. When the direction of motion of the moving object is determined to be mainly non-vertical ground motion by analyzing the environment image, the position data of the moving object in the continuous frames are fitted to try to match different motion models, such as parabolic motion, pendulum motion, or discrete motion. Specifically, the velocity and acceleration vector of the object are calculated by the position data, and the change pattern of these vectors is further analyzed: for parabolic motion, the acceleration should be relatively constant and point to the center of the earth. For pendulum motion, the acceleration vector changes direction as the position of the object changes, and always points to the center point of the motion. For discrete motion, the acceleration may show irregular or sudden changes.

[0045] In some embodiments, determining whether the landing point of the moving object is on the vehicle through the processing interface corresponding to the motion type includes: determining the landing height of the moving object based on the motion information of the moving object and the air resistance coefficient and the wind resistance coefficient through the trajectory formula of free fall motion; comparing the landing height of the moving object with the coordinates of the point on the surface of the vehicle in the three-dimensional coordinate system to determine whether the landing point of the moving object is on the vehicle. For example, the processing interface corresponding to the free fall motion encapsulates the motion trajectory formula of the moving object. There are two types of motion trajectories of the moving object: one trajectory formula of free fall motion is as follows:

[0046]

[0047] Among them, y represents the vertical height of the moving object, t represents time, g is the gravitational acceleration of the moving object (about 9.8 meters per second squared on the surface of the earth), V0 represents the initial speed of the moving object, x represents the horizontal displacement of the moving object, k represents the drag coefficient, and b represents the air resistance coefficient. The vertical height of the moving object can be calculated in real time through this formula, and then it is determined whether the moving object falls on the vehicle based on the coordinates of the point on the surface of the vehicle in the three-dimensional coordinate system and y. In this example, the motion information of the above-mentioned moving object includes t, g, V0, and x.

[0048] Another free-fall trajectory formula is as follows:

[0049]

[0050] Among them, y is the height of the falling point of the moving object, g is the gravitational acceleration of the moving object (about 9.8 meters per second squared on the surface of the earth), t is the time of the moving object, Cd is the air resistance coefficient, A is the cross-sectional area of ​​the moving object, v is the falling speed of the moving object, and θ is the speed direction of the moving object. This formula can be used to calculate the height of the falling point of the moving object in real time, and then determine whether the moving object falls on the vehicle based on the coordinates of the point on the vehicle surface in the three-dimensional coordinate system and y.

[0051] In some embodiments, when the landing point of the moving object is on the vehicle, determining the impact force when the moving object contacts the vehicle through the processing interface corresponding to the motion type includes: when the landing point of the moving object is on the vehicle, using the impact force formula of free fall motion, based on the motion information of the moving object, the mass of the moving object, the air resistance and the drag coefficient. For example, the processing interface corresponding to free fall motion also encapsulates the impact force formula when the moving object contacts the vehicle, which is as follows:

[0052]

[0053] Wherein, m represents the mass of the moving object, g represents the gravitational acceleration of the moving object, k represents the drag coefficient, x represents the displacement of the moving object, Fd represents the air resistance, and a represents the acceleration of the moving object. In this embodiment, the motion information of the moving object includes g, x, and a. Fd can be calculated according to the following formula:

[0054]

[0055] Among them, Fd represents air resistance, Cd represents air resistance coefficient, A represents cross-sectional area of ​​moving object, ρ represents density in air, and v represents speed of moving object.

[0056] Based on the above embodiments, the impact force generated when a moving object falls can be calculated according to Newton's second law F=ma and the above formula. When the roof, door or other body structure is subjected to external force, if its structure is reasonably designed and the material used is strong enough, the body structure can resist the external force and keep its shape unchanged. The following formula is used to describe the deformation resistance of the roof structure: Among them, F is the magnitude of the force on the roof, E is the Young's modulus of the roof material, ΔL is the plastic deformation of the roof, and L is the length of the roof. Or in order to more accurately describe the deformation resistance of the car roof, we can consider factors such as the geometry of the roof structure, the connection method between the roof and other body parts, and the thickness and strength of the roof material, and describe it with a formula: Among them, F is the magnitude of the force on the roof, Ei is the Young's modulus of the i-th material, ti is the thickness of the i-th material, L is the length of the roof, and fi is the contribution rate of the i-th material to the roof's anti-deformation. Compare the impact force generated when the moving object falls and the anti-deformation capacity of the roof. If the impact force generated when the moving object falls is less than the anti-deformation capacity, it means that the moving object will not affect the roof structure, and there is no need to avoid or defend against falling objects.

[0057] Based on the above embodiments, the type, size, speed and other information of the moving object can be obtained, the magnitude of external forces such as gravity and air resistance can be calculated, the magnitude of acceleration can be calculated based on the displacement of the moving object in each direction of the two frames of images before and after, and the above impact force formula and motion trajectory formula can be substituted to construct the motion curve of the moving object in the three-dimensional coordinate system. According to the shape of the motion curve, it can be judged whether there is a contact collision with the vehicle at a certain moment. If so, the specific landing point of the moving object on the vehicle can be obtained based on the contact collision point, and the corresponding contact collision time can be obtained to predict the opening of the protective device.

[0058] In some embodiments, determining whether the landing point of the moving object is on the vehicle through the processing interface corresponding to the motion type includes: determining the height of the moving object in the direction perpendicular to the ground based on the motion information of the moving object, the resistance of the lateral wind, the angle in the horizontal direction, and the curvature coefficient of the parabola through the trajectory formula of parabolic motion; comparing the height of the moving object in the direction perpendicular to the ground with the coordinates of a point on the surface of the vehicle in a three-dimensional coordinate system to determine whether the landing point of the moving object is on the vehicle. For example, the processing interface corresponding to parabolic motion encapsulates the motion trajectory formula of the moving object. There are two types of motion trajectories of moving objects: one trajectory formula of parabolic motion is as follows:

[0059]

[0060] Where y represents the height of the moving object perpendicular to the ground, g is the gravitational acceleration of the moving object (about 9.8 meters per second squared on the surface of the earth), k represents the curvature coefficient of the parabola, x represents the horizontal position of the moving object, v represents the speed of the moving object, cos(θ) represents the cosine value of the angle between the horizontal direction and the resistance of the lateral wind, and sin(θ) represents the sine value of the angle between the horizontal direction and the resistance of the lateral wind; the curvature coefficient of the parabola is obtained by substituting the coordinates of the object thrown at the vertex into the centerline equation Where a and b are the slopes of two points on the center line, and y and x are the vertical and horizontal coordinates of the vertex and another point on the center line, respectively. This formula can be used to calculate the height of the moving object in the direction perpendicular to the ground in real time, and then determine whether the moving object falls on the vehicle based on the coordinates of the point on the vehicle surface in the three-dimensional coordinate system and y. In this embodiment, the motion information of the moving object includes g, x, v, and θ.

[0061] Another trajectory formula for parabolic motion is as follows:

[0062]

[0063] Among them, y represents the vertical displacement of the moving object; t represents time; a represents the gravitational acceleration of the moving object; b, c, d are constants, representing the influence of air resistance, lateral wind resistance and other factors respectively; f represents frequency; t represents time; φ represents the phase angle. This formula can be used to calculate the height of the moving object perpendicular to the ground in real time, and then determine whether the moving object falls on the vehicle based on the coordinates of the point on the vehicle surface in the three-dimensional coordinate system and y.

[0064] In some embodiments, when the landing point of the moving object is on the vehicle, determining the impact force when the moving object contacts the vehicle through the processing interface corresponding to the motion type includes: when the landing point of the moving object is on the vehicle, determining the impact force when the moving object contacts the vehicle through the impact force formula of parabolic motion based on the motion information of the moving object, the mass of the moving object, and the local mass of the vehicle. For example, the processing interface corresponding to parabolic motion also encapsulates the impact force formula when the moving object contacts the vehicle, which is as follows:

[0065] m1v 1i +m2v 2i =m1v 1f +m2v 2f

[0066] Where m1 and m2 are the mass of the moving object and the mass of the local part of the vehicle, respectively. The local part is the contact part with the moving object. v i and v f are their speeds before and after the collision, respectively. This formula can be used to calculate the impact force when the moving object contacts a part of the vehicle. In this example, the motion information of the moving object includes v i and v f .

[0067] In some embodiments, determining whether the landing point of the moving object is on the vehicle through the processing interface corresponding to the motion type includes: determining the vertical displacement of the moving object based on the motion information of the moving object, the mass and air resistance of the moving object, and the angle between the wind direction and the horizontal direction through the trajectory formula of the pendulum motion; comparing the vertical displacement of the moving object with the coordinates of the point on the surface of the vehicle in the three-dimensional coordinate system to determine whether the landing point of the moving object is on the vehicle. For example, the vehicle is a crane, a pendulum vehicle, or other vehicle that performs pendulum motion. The processing interface corresponding to the pendulum motion encapsulates the motion trajectory mode of the moving object. The motion trajectory mode of the moving object is as follows:

[0068]

[0069] Among them, y represents the vertical displacement of the moving object; A represents the pendulum length of the moving object; ω represents the angular frequency; V0 represents the initial speed of the moving object; Fd represents the air resistance; m represents the mass of the moving object; φ represents the initial angle; θ represents the angle between the wind direction and the horizontal direction. This formula can be used to calculate the vertical displacement of the moving object in real time, and then determine whether the moving object falls on the vehicle based on the coordinates of the point on the vehicle surface in the three-dimensional coordinate system and y. In this example, the motion information of the moving object includes A, ω, V0, and φ.

[0070] In some embodiments, when the landing point of the moving object is on the vehicle, determining the impact force when the moving object contacts the vehicle through the processing interface corresponding to the motion type includes determining the impact force when the moving object contacts the vehicle through the impact force formula of the pendulum motion based on the mass of the moving object and the angle between the moving object and the part of the vehicle when the landing point of the moving object is on the vehicle. For example, the processing interface corresponding to the pendulum motion also encapsulates the impact force formula when the moving object contacts the vehicle, which is as follows:

[0071] F=mΔp*cosθ

[0072] Among them, F represents the impact force of the moving object, m represents the mass of the moving object, θ represents the impact angle (i.e. the angle between the moving object and the vehicle part), and △p represents the momentum change. This formula can be used to calculate the impact force when the moving object contacts the vehicle part.

[0073] In some embodiments, determining whether the landing point of the moving object is on the vehicle through the processing interface corresponding to the motion type includes: determining the current displacement of the moving object based on the speed of the moving object and the position of the moving object in the previous time step and the time step through the trajectory formula of discrete motion; comparing the current displacement of the moving object with the coordinates of the point on the surface of the vehicle in the three-dimensional coordinate system to determine whether the landing point of the moving object is on the vehicle. For example, the processing interface corresponding to discrete motion encapsulates the motion trajectory mode of the moving object. The motion trajectory mode of the moving object is as follows:

[0074] Xn=Xn-1+v△t

[0075] Among them, Xn represents the position of the nth time step, Xn-1 represents the position of the previous time step, v represents the speed of the moving object, and Δt represents the time step. This formula can be used to calculate the current displacement of the moving object in real time, and then determine whether the moving object falls on the vehicle based on the coordinates of the point on the vehicle surface in the three-dimensional coordinate system and Xn.

[0076] In some embodiments, when the landing point of the moving object is on the vehicle, determining the impact force when the moving object contacts the vehicle through the processing interface corresponding to the motion type includes: when the landing point of the moving object is on the vehicle, determining the impact force when the moving object contacts the vehicle through the impact force formula of discrete motion based on the mass of the moving object, the gravitational acceleration of the moving object, the final velocity of the moving object, and the initial velocity of the moving object. For example, the processing interface corresponding to discrete motion also encapsulates the impact force formula when the moving object contacts the vehicle, which is as follows:

[0077] F = mg (v 2 -u 2 )

[0078] Among them, F represents the impact force, v is the final velocity of the moving object, u is the initial velocity of the moving object, g is the gravitational acceleration of the moving object, and m is the mass of the moving object. This formula can be used to calculate the impact force when the moving object contacts a part of the vehicle.

[0079] Based on the above embodiment, the final velocity of the moving object can be calculated by v=u+(ab)dt, where a is the acceleration (including air resistance and lateral wind resistance), b is the friction coefficient, and dt is the time step. a can be calculated by Calculate. Among them, F represents the impact force, v is the final velocity of the moving object, u is the initial velocity of the moving object, g is the gravitational acceleration of the moving object, and m is the mass of the moving object.

[0080] Through the corresponding formulas encapsulated in the processing interface of the above four types of motion, it is possible to accurately calculate whether the landing point of the moving object is on the vehicle. If so, the impact force when the moving object contacts the vehicle is calculated by the impact force formula, and determine whether to activate the protective device when the moving object contacts the vehicle based on the impact force and the preset threshold. In this way, the defect of the prior art in which the protective device is activated as soon as the environmental image is recognized can be avoided, the false alarm rate is reduced, and the service life of the protective device is increased.

[0081] Figure 4 1 is a block diagram of a vehicle roof protection device control device according to an embodiment of the present application. Figure 4 As shown, the vehicle roof protection device control device 400 includes an acquisition module 410, an identification module 420, a motion type determination module 430, an interface calling module 440, a landing point determination module 450, an impact force determination module 460 and a control module 470.

[0082] Specifically, the acquisition module 410 is used to acquire multiple frames of environmental images outside the vehicle through a camera outside the vehicle according to a preset time interval.

[0083] The recognition module 420 is used to perform recognition processing on each frame of the environment image to determine whether each frame of the environment image contains a moving object.

[0084] The motion type determination module 430 is used to determine the motion type of the moving object when each frame of the environmental image contains a moving object.

[0085] The interface calling module 440 is used to call the processing interface corresponding to the motion type according to the motion type of the motion object.

[0086] The landing point determination module 450 is used to determine whether the landing point of the moving object is on the vehicle through a processing interface corresponding to the motion type.

[0087] The impact force determination module 460 is used to determine the impact force when the moving object contacts the vehicle through a processing interface corresponding to the motion type when the moving object lands on the vehicle.

[0088] The control module 470 is used to control the protective device of the vehicle roof according to the impact force when the moving object contacts the vehicle.

[0089] The protective device control device 400 of the vehicle roof can accurately predict whether the moving object will contact the vehicle and the specific location of the contact by analyzing the motion trajectory of the moving object. This accurate drop point prediction method avoids the situation where the protective device is triggered because the moving object is only close to the vehicle but not actually in contact with the vehicle. Different moving objects (such as flying spheres or large objects moving quickly) have different potential threats to the vehicle. By predicting the impact force, it is possible to judge the degree of damage that the moving object may cause to the vehicle, thereby determining whether the protective device needs to be activated, and the degree of activation (such as partial activation or full activation). Existing methods may not be able to distinguish the specific motion type and impact potential of the moving object, resulting in frequent and unnecessary activation. The method of the present application activates the protective device only when it is really needed through accurate analysis, greatly reducing the false alarm rate and reducing resource waste. While ensuring that false activation is not frequent, timely and appropriate protection can also be provided when it is really needed, thereby effectively protecting the vehicle from damage caused by actual threats.

[0090] In some embodiments, the recognition module 420 is configured to: perform recognition processing on each frame of environmental image to obtain the position data of the moving object in each frame of environmental image; if the position data of the moving object in each frame of environmental image meets the preset displacement condition, determine that each frame of environmental image contains a moving object; if the position data of the moving object in each frame of environmental image does not meet the preset displacement condition, determine that each frame of environmental image does not contain a moving object.

[0091] In some embodiments, the motion type determination module 430 is configured to: determine the motion direction of the moving object based on the position data of the moving object in each frame of the environmental image; when the motion direction of the moving object is vertical ground motion, determine the motion type of the moving object as free fall motion; when the motion direction of the moving object is non-vertical ground motion, determine the motion type of the moving object as parabolic motion, pendulum motion, or discrete motion.

[0092] In some embodiments, the landing point determination module 450 is configured to determine whether the landing point of the moving object is on the vehicle through a processing interface corresponding to the free fall motion; the impact force determination module 460 is configured to determine the impact force when the moving object contacts the vehicle through a processing interface corresponding to the free fall motion when the landing point of the moving object is on the vehicle.

[0093] In some embodiments, the landing point determination module 450 is configured to determine whether the landing point of the moving object is on the vehicle through a processing interface corresponding to the parabolic motion; the impact force determination module 460 is configured to determine the impact force when the moving object contacts the vehicle through a processing interface corresponding to the parabolic motion when the landing point of the moving object is on the vehicle.

[0094] In some embodiments, the landing point determination module 450 is configured to determine whether the landing point of the moving object is on the vehicle through the processing interface corresponding to the pendulum motion; the impact force determination module 460 is configured to determine the impact force when the moving object contacts the vehicle through the processing interface corresponding to the pendulum motion when the landing point of the moving object is on the vehicle.

[0095] In some embodiments, the landing point determination module 450 is configured to determine whether the landing point of the moving object is on the vehicle through a processing interface corresponding to discrete motion; the impact force determination module 460 is configured to determine the impact when the moving object contacts the vehicle through a processing interface corresponding to discrete motion when the landing point of the moving object is on the vehicle.

[0096] Figure 5 is a schematic diagram of the structure of an electronic device according to an embodiment of the present application, such as Figure 5 As shown, the electronic device 500 of this embodiment includes: a processor 510, a memory 520, and a computer program 530 stored in the memory 520 and executable on the processor 510. When the processor 510 executes the computer program 530, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor 510 executes the computer program 530, the functions of the modules in the above-mentioned device embodiments are implemented.

[0097] The electronic device 500 may be a vehicle device installed in a vehicle. The electronic device 500 may include but is not limited to a processor 510 and a memory 520. Those skilled in the art will appreciate that Figure 5 The electronic device 500 is merely an example and does not limit the electronic device 500 . The electronic device 500 may include more or fewer components than those shown in the figure, or different components.

[0098] The processor 510 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0099] The memory 520 may be an internal storage unit of the electronic device 500, for example, a hard disk or memory of the electronic device 500. The memory 520 may also be an external storage device of the electronic device 500, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 500. The memory 520 may also include both an internal storage unit of the electronic device 500 and an external storage device. The memory 520 is used to store computer programs and other programs and data required by the electronic device.

[0100] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units.

[0101] If the integrated module is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium (for example, a computer-readable storage medium). Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. The computer program may include computer program code, which may be in source code form, object code form, executable file or some intermediate form. Computer-readable media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0102] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for controlling a protective device of a vehicle roof, characterized in that: The method comprises: Acquire multiple frames of environment images outside the vehicle through a camera outside the vehicle according to a preset time interval; Performing recognition processing on the environment image of each frame to determine whether the environment image of each frame contains a moving object; When each frame of the environment image contains a moving object, determining the movement type of the moving object; According to the motion type of the motion object, calling a processing interface corresponding to the motion type; Determining, through a processing interface corresponding to the motion type, whether the landing point of the motion object is on the vehicle; When the landing point of the moving object is on the vehicle, determining the impact force when the moving object contacts the vehicle through the processing interface corresponding to the motion type; The protective device of the vehicle roof is controlled according to the impact force when the moving object contacts the vehicle.

2. The method according to claim 1, characterized in that The performing recognition processing on each frame of the environment image to determine whether each frame of the environment image contains a moving object comprises: Performing recognition processing on the environmental image of each frame to obtain position data of the moving object in the environmental image of each frame; If the position data of the moving object in the environmental image of each frame meets the preset displacement condition, it is determined that the environmental image of each frame contains the moving object; If the position data of the moving object in each frame of the environmental image does not satisfy the preset displacement condition, it is determined that the moving object is not included in each frame of the environmental image.

3. The method according to claim 2, characterized in that Determining the motion type of the moving object comprises: Determining the moving direction of the moving object according to the position data of the moving object in each frame of the environmental image; When the moving direction of the moving object is vertical ground movement, determining the moving type of the moving object is free fall movement; When the moving direction of the moving object is non-vertical ground movement, the moving type of the moving object is determined to be parabolic movement, pendulum movement, or discrete movement.

4. The method according to claim 3, characterized in that Determining, through a processing interface corresponding to the motion type, whether the landing point of the motion object is on the vehicle comprises: Determine the vertical height of the moving object based on the free fall trajectory formula, the motion information of the moving object, the air resistance coefficient and the wind resistance coefficient; compare the vertical height of the moving object with the coordinates of a point on the surface of the vehicle in a three-dimensional coordinate system to determine whether the landing point of the moving object is on the vehicle; When the landing point of the moving object is on the vehicle, determining the impact force when the moving object contacts the vehicle through the processing interface corresponding to the motion type includes: When the landing point of the moving object is on the vehicle, the impact force when the moving object contacts the vehicle is determined by the impact force formula of the free fall motion based on the motion information of the moving object, the mass and air resistance of the moving object, and the drag coefficient.

5. The method according to claim 3, characterized in that: Determining, through a processing interface corresponding to the motion type, whether the landing point of the motion object is on the vehicle comprises: Determine the height of the moving object in a direction perpendicular to the ground by using the trajectory formula of the parabolic motion, based on the motion information of the moving object, the angle between the resistance of the lateral wind and the horizontal direction, and the curvature coefficient of the parabola; compare the height of the moving object in a direction perpendicular to the ground with the coordinates of a point on the surface of the vehicle in a three-dimensional coordinate system to determine whether the landing point of the moving object is on the vehicle; When the landing point of the moving object is on the vehicle, determining the impact force when the moving object contacts the vehicle through the processing interface corresponding to the motion type includes: When the landing point of the moving object is on the vehicle, the impact force when the moving object contacts the vehicle is determined by the impact force formula of the parabolic motion based on the motion information of the moving object, the mass of the moving object and the local mass of the vehicle.

6. The method according to claim 3, characterized in that Determining, through a processing interface corresponding to the motion type, whether the landing point of the motion object is on the vehicle comprises: Determine the vertical displacement of the moving object based on the trajectory formula of the pendulum motion, the motion information of the moving object, the mass and air resistance of the moving object, and the angle between the wind direction and the horizontal direction; compare the vertical displacement of the moving object with the coordinates of the point on the surface of the vehicle in the three-dimensional coordinate system to determine whether the landing point of the moving object is on the vehicle; When the landing point of the moving object is on the vehicle, determining the impact force when the moving object contacts the vehicle through the processing interface corresponding to the motion type includes: When the landing point of the moving object is on the vehicle, the impact force when the moving object contacts the vehicle is determined by the impact force formula of the pendulum motion based on the mass of the moving object and the angle between the moving object and the vehicle part.

7. The method according to claim 3, characterized in that The determining, through the processing interface corresponding to the motion type, whether the landing point of the motion object is on the vehicle comprises: Determine the current displacement of the moving object based on the trajectory formula of the discrete motion, the speed of the moving object, the position of the moving object in the previous time step, and the time step; compare the current displacement of the moving object with the coordinates of the point on the surface of the vehicle in the three-dimensional coordinate system to determine whether the landing point of the moving object is on the vehicle; When the landing point of the moving object is on the vehicle, determining the impact force when the moving object contacts the vehicle through the processing interface corresponding to the motion type includes: When the landing point of the moving object is on the vehicle, the impact force when the moving object contacts the vehicle is determined by the impact force formula of the discrete motion based on the mass of the moving object, the gravitational acceleration of the moving object, the final velocity of the moving object, and the initial velocity of the moving object.

8. A vehicle roof protection device control device, characterized in that: The device comprises: An acquisition module, used to acquire multiple frames of environment images outside the vehicle through a camera outside the vehicle according to a preset time interval; An identification module is used to perform identification processing on each frame of the environmental image to determine whether each frame of the environmental image contains a moving object; A motion type determination module, used for determining the motion type of the moving object when the environment image of each frame contains a moving object; An interface calling module, used for calling a processing interface corresponding to the motion type according to the motion type of the motion object; A landing point determination module, used to determine whether the landing point of the moving object is on the vehicle through a processing interface corresponding to the motion type; An impact force determination module, configured to determine the impact force when the moving object contacts the vehicle through a processing interface corresponding to the motion type when the landing point of the moving object is on the vehicle; A control module is used to control the protective device of the vehicle roof according to the impact force when the moving object contacts the vehicle.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, 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 storing 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.