Vehicle door opening early warning method and device, computer equipment and storage medium

Abstract

The invention discloses a vehicle door opening early warning method and device, computer equipment and a storage medium. The method comprises the following steps: when a vehicle is in a parking state, acquiring back-row audios and videos in the vehicle; detecting whether back-row passengers have door opening intentions or not; if yes, determining the body type of the rear-row passenger by adopting an image technology; obtaining a door opening side video and performing in-vehicle projection; obtaining rear angle radar data; calculating the transverse distance and the longitudinal distance of each object on the door opening side, and determining a collision object and the corresponding transverse distance and longitudinal distance; the speed of a collision object is determined, and collision time is determined; and controlling the door opening angle according to the collision time, the transverse distance, the door size and the back-row passenger body type. By means of the method, passengers in the back row can be prompted efficiently and directly, accidents are prevented, the situation that no door opening early warning exists in the vehicle when the angle radar breaks down can be avoided, the opening angle of the vehicle door can be controlled, the requirements for getting off of the passengers and collision prevention are met, and practicability is enhanced.

Description

Technical Field

[0001] The present invention relates to the field of intelligent automobile technology, and more specifically to a vehicle door opening warning method, device, computer equipment and storage medium. Background Art

[0002] With the continuous development of the Internet, automobile technology is also constantly improving. Today's cars are very different from the cars of the past. Today's cars are becoming more and more intelligent, and people's demand for automobile technology is getting higher and higher. Moreover, with the improvement of people's living standards, every household has a private car. With the continuous popularization of vehicles, parking safety is also receiving more and more attention from people.

[0003] As for the door opening after parking, today's smart cars are equipped with a door opening warning function. The existing door opening warning mainly relies on sound alarms and optical door opening warnings emitted by instruments. However, these alarms are poorly perceived by rear passengers, resulting in frequent traffic accidents caused by failure to observe the rear door opening. The current door opening warning function mainly collects signals through the rear corner radar, but the radar has a low recognition rate for low-speed pedestrians, so it cannot issue a warning in time when pedestrians pass by. In addition, when the corner radar fails, the door opening warning function will also fail. Moreover, the existing door opening warning function can only control the door to be fully opened or closed, which is not very practical.

[0004] Therefore, it is necessary to design a new method to efficiently and directly warn rear passengers to prevent accidents. At the same time, it can also avoid the lack of any door opening warning in the car when the corner radar fails, and can control the door opening angle to meet the needs of passengers getting off the car and preventing collisions, thereby enhancing practicality. Summary of the invention

[0005] The purpose of the present invention is to overcome the defects of the prior art and provide a vehicle door opening warning method, device, computer equipment and storage medium.

[0006] To achieve the above object, the present invention adopts the following technical solution: a vehicle door opening warning method, comprising:

[0007] When the vehicle is parked, obtain the rear audio and video in the vehicle;

[0008] Detecting whether a rear passenger intends to open the door based on the rear audio and video in the vehicle;

[0009] If the rear passenger intends to open the door, image technology is used to determine the rear passenger's body shape;

[0010] Get the door opening side video and project it inside the car;

[0011] Get rear corner radar data;

[0012] Calculate the lateral distance and longitudinal distance of each object on the door opening side according to the door opening side video and the rear corner radar data, and determine the collision object and the corresponding lateral distance and longitudinal distance;

[0013] determining a velocity of a collision object based on the rear angle radar data, determining an acceleration in combination with the collision object and a corresponding longitudinal distance, and determining a collision time based on the acceleration, velocity, and longitudinal distance;

[0014] The door opening angle is controlled according to the collision time, the lateral distance, the door size and the body size of the rear passengers.

[0015] A further technical solution is: the method of detecting whether a rear passenger intends to open the door based on the rear audio and video in the vehicle includes:

[0016] Optical flow analysis is used to analyze the movements of rear passengers based on the rear audio and video in the vehicle, and / or sound is used to detect keywords in the rear audio and video in the vehicle to determine whether there is an intention to open the door.

[0017] A further technical solution is: the method of using image technology to determine the body shape of rear passengers includes:

[0018] Acquire facial images and sitting posture images of rear passengers;

[0019] Analyzing the sitting posture image using image processing technology to preliminarily determine the body shape;

[0020] The facial image of the rear passenger is analyzed to determine facial features, and combined with the initially determined body shape to determine the body shape of the rear passenger.

[0021] A further technical solution is: the lateral distance and longitudinal distance of each object on the door opening side are calculated according to the door opening side video and the rear corner radar data, and the collision object and the corresponding lateral distance and longitudinal distance are determined, including:

[0022] Calculating the lateral distance, angle and longitudinal distance between the door and each object on the door opening side according to the rear corner radar data to obtain first data;

[0023] Calculating the lateral distance and longitudinal distance between the vehicle door and each object on the door opening side according to the door opening side video to obtain second data;

[0024] Determine the final horizontal distance and vertical distance of each object on the door opening side according to the first data and the second data;

[0025] The object with the smallest lateral distance among the objects on the final door opening side is determined to be the collision object, and the corresponding lateral distance and longitudinal distance are obtained.

[0026] A further technical solution is: determining the final horizontal distance and vertical distance of each object on the door opening side according to the first data and the second data includes:

[0027] The minimum value of the lateral distance and the longitudinal distance of each object on the door opening side in the first data and the second data is taken to obtain the final lateral distance and longitudinal distance of each object on the door opening side.

[0028] A further technical solution is: controlling the door opening angle according to the collision time, the lateral distance, the door size and the size of the rear passenger includes:

[0029] Determine whether the collision time is less than a set time;

[0030] If the collision time is less than the set time, the door is opened normally;

[0031] If the collision time is not less than the set time, the door opening angle is controlled according to the lateral distance, door size and rear passenger body size.

[0032] A further technical solution is: controlling the door opening angle according to the lateral distance, door size and rear passenger body size includes:

[0033] Calculating the maximum angle at which the door can be safely opened based on the lateral distance and the door size;

[0034] Determining whether the maximum angle is greater than a door opening angle threshold corresponding to the passenger's body size;

[0035] If the maximum angle is greater than the door opening angle threshold corresponding to the passenger's body size, the door opening angle is controlled to be the maximum angle;

[0036] If the maximum angle is not greater than the door opening angle threshold corresponding to the passenger's body size, the door opening angle is controlled to be zero.

[0037] The present invention also provides a vehicle door opening warning device, comprising:

[0038] An audio and video acquisition unit, used to acquire rear-seat audio and video in the vehicle when the vehicle is in a parked state;

[0039] An intention detection unit, used to detect whether a rear passenger intends to open the door based on the rear audio and video in the vehicle;

[0040] A body size determination unit, used to determine the body size of rear passengers using image technology;

[0041] A projection unit, used to obtain the door opening side video and project it inside the car;

[0042] A radar data acquisition unit, used for acquiring rear angle radar data;

[0043] A distance determination unit, used to calculate the lateral distance and longitudinal distance of each object on the door opening side according to the door opening side video and the rear corner radar data, and determine the collision object and the corresponding lateral distance and longitudinal distance;

[0044] a collision time determination unit, configured to determine a speed of a collision object according to the rear angle radar data, determine an acceleration in combination with the collision object and a corresponding longitudinal distance, and determine a collision time according to the acceleration, speed and longitudinal distance;

[0045] An angle control unit is used to control the door opening angle according to the collision time, the lateral distance, the door size and the body size of the rear passengers.

[0046] The present invention further provides a computer device, which includes a memory and a processor. The memory stores a computer program, and the processor implements the above method when executing the computer program.

[0047] The present invention also provides a storage medium, wherein the storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0048] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention obtains rear-seat audio and video through an in-car camera, detects the passenger's intention to open the door, analyzes the passenger's facial and sitting image to determine his or her body shape, obtains the video of the door opening side and the rear corner radar data, calculates the distance, speed and acceleration of the object, identifies potential collision objects, and evaluates whether the door can be opened safely based on the detection data and calculation results. If there is a risk of collision, the most suitable door opening angle is calculated based on the lateral distance, door size and rear passenger body shape to ensure that the passenger can get off the vehicle safely without causing an accident; efficient and direct prompts to rear-seat passengers are achieved to prevent accidents, while also avoiding any door opening warning in the vehicle when the corner radar fails, and the door opening angle can be controlled to meet the needs of passengers getting off the vehicle and preventing collisions, thereby enhancing practicality.

[0049] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0051] Figure 1A schematic diagram of an application scenario of the vehicle door opening warning method provided by an embodiment of the present invention;

[0052] Figure 2 A schematic diagram of a process flow of a vehicle door opening warning method provided by an embodiment of the present invention;

[0053] Figure 3 A schematic diagram of a sub-process of a vehicle door opening warning method provided by an embodiment of the present invention;

[0054] Figure 4 A schematic diagram of a sub-process of a vehicle door opening warning method provided by an embodiment of the present invention;

[0055] Figure 5 A schematic diagram of a sub-process of a vehicle door opening warning method provided by an embodiment of the present invention;

[0056] Figure 6 A schematic diagram of a sub-process of a vehicle door opening warning method provided by an embodiment of the present invention;

[0057] Figure 7 A schematic block diagram of a vehicle door opening warning device provided by an embodiment of the present invention;

[0058] Figure 8 A schematic block diagram of a body shape determination unit of a vehicle door opening warning device provided in an embodiment of the present invention;

[0059] Fig. 9 A schematic block diagram of a collision time determination unit of a vehicle door opening warning device provided by an embodiment of the present invention;

[0060] Fig.10 A schematic block diagram of an angle control unit of a vehicle door opening warning device provided by an embodiment of the present invention;

[0061] Fig.11 A schematic block diagram of a safety control subunit of a vehicle door opening warning device provided in an embodiment of the present invention;

[0062] Fig.12 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0063] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0065] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0066] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0067] See also Figure 1 and Figure 2 , Figure 1 A schematic diagram of an application scenario of the vehicle door opening warning method provided in an embodiment of the present invention. Figure 2 A schematic flow chart of a vehicle door opening warning method provided by an embodiment of the present invention. The vehicle door opening warning method is applied to a central controller of a car, and the central controller of the car is connected to a smart driving controller, a chassis controller, a cockpit control machine and a body controller through a bus, wherein the smart driving controller is connected to a side view camera and a millimeter wave radar; the chassis controller is connected to a wheel speed sensor, the cockpit controller is connected to a projector, the body controller is connected to a door opening and closing motor, and the millimeter wave radar is a rear corner radar. In addition, the smart driving controller is also connected to a camera in the car. When the vehicle is parked, monitor whether the rear passengers have the intention to open the door, and control the door opening angle according to the passenger's body shape and the video on the door opening side; by obtaining radar data and video, the system calculates the distance, speed and acceleration of the object on the door opening side to judge the collision risk; if a collision risk is detected, adjust the door opening angle to ensure safety, realize efficient and direct prompting of the rear passengers, and prevent accidents. At the same time, it can also avoid no door opening warning in the car when the corner radar fails, and the door opening angle can be controlled to meet the needs of passengers getting off and preventing collisions, and enhance practicality.

[0068] Figure 2 FIG. 1 is a flow chart of a vehicle door opening warning method provided by an embodiment of the present invention. Figure 2 As shown, the method includes the following steps S110 to S180.

[0069] S110: When the vehicle is parked, obtain the rear-seat audio and video.

[0070] In this embodiment, the wheel speed sensor is first used to detect whether the vehicle is in a parked state. Specifically, when the wheel speed detected by the wheel speed sensor is zero, it indicates that the current vehicle is in a parked state. Next, the in-car camera and the rear microphone are used to obtain the rear-seat audio and video in the car to determine whether the rear-seat passengers intend to open the door; specifically, the in-car camera can be used to capture the corresponding audio and video.

[0071] S120, detecting whether the rear-seat passenger intends to open the door based on the rear-seat audio and video in the vehicle.

[0072] In this embodiment, optical flow analysis is used to analyze the movements of the rear passengers based on the rear audio and video in the vehicle, and / or sound is used to detect keywords in the rear audio and video in the vehicle to determine whether there is an intention to open the door.

[0073] Specifically, the optical flow analysis technology is combined with the images in the audio and video to judge the rear passenger's intention to open the door. The overall process includes: first, extracting two consecutive frames of images from the audio and video. These images are used to capture the temporal motion changes and provide basic data for subsequent analysis; then, the image is preprocessed, including denoising and grayscale processing, to improve the analysis accuracy. Specifically, filtering technology (such as Gaussian filtering) is applied to reduce the noise in the image to improve the accuracy of optical flow calculation, and the color image is converted into a grayscale image to reduce data complexity and enhance the algorithm processing efficiency, because the optical flow algorithm usually processes grayscale images. The algorithm compares the pixels of the two frames to generate a motion vector (optical flow) for each pixel, which indicates the movement of the pixel in time. Thirdly, the movement trajectory of each pixel is tracked according to the direction and size of the optical flow vector. These trajectories reveal the movement mode and direction of the object or occupant. Finally, the calculated movement trajectory is analyzed to determine whether there is an intention to open the door. By identifying specific movement patterns (such as the obvious deviation of the rear passengers toward the door), it can be determined whether the door is ready to be opened.

[0074] Optical flow analysis can accurately capture subtle motion changes, improve recognition accuracy, achieve efficient real-time processing, and respond to occupant actions in a timely manner; denoising and grayscale processing reduce interference factors in image data and improve system stability and reliability.

[0075] In addition, the in-car camera can be used to monitor the movements of rear passengers, such as whether their body is leaning to one side or whether they are reaching out toward the door. The rear microphone can also be used to identify keywords of rear passengers, such as "bye," "goodbye," or "get off," to determine whether they intend to open the door.

[0076] S130. If the rear passenger intends to open the door, image technology is used to determine the body size of the rear passenger.

[0077] In this embodiment, the body shape of the rear-seat passenger refers to the body shape characteristics of the rear-seat passenger.

[0078] In one embodiment, see Figure 3 , the above-mentioned step S130 may include steps S131 to S133.

[0079] S131, acquiring facial images and sitting posture images of rear seat passengers.

[0080] In this embodiment, the facial image and sitting posture image of the rear passenger are obtained from the audio and video, and the body shape of the rear passenger is determined from the dimensions of the facial features and sitting posture, so as to determine the minimum angle at which the door needs to be opened according to the body shape. The sitting posture image refers to an image including the entire body of the rear passenger.

[0081] S132: Analyze the sitting posture image using image processing technology to preliminarily determine the body shape.

[0082] In this embodiment, the Canny algorithm is used to detect the edges in the occupant image. The algorithm identifies edge information in the sitting image through multiple steps such as Gaussian smoothing, gradient calculation, non-maximum suppression, double thresholding, etc. The edge information helps to clarify the outline of the occupant, so as to accurately identify the body outline of the occupant in the sitting image; then, the relative position relationship between the occupant and the seat is identified from the edge information extracted by the Canny algorithm. For example, by analyzing the relative position of the occupant's outline and the seat, the occupant's body shape can be preliminarily determined. For example, whether the occupant's body outline is completely within the seat, or exceeds the seat boundary, etc.; combined with the sitting image, the occupant's sitting state and body shape characteristics are analyzed. These features include the body outline, body width and height, etc., so as to judge its body shape, thereby preliminarily determining the body shape.

[0083] S133: Analyze the facial image of the rear passenger to determine facial features, and combine the facial features with the initially determined body shape to determine the body shape of the rear passenger.

[0084] In this embodiment, the key facial feature points (such as the tip of the nose, the edge of the eyes, the edge of the face, etc.) of the rear passenger's facial image are identified. The distance and relative position of these feature points can be used to further analyze the body type. The distance between the feature points is calculated. For example, the distance from the tip of the nose to the edge of the face is measured. This measurement can provide information about facial dimensions and help with body type classification.

[0085] In addition, in this embodiment, through machine learning, the distance from the nose tip to the cheek edge is used as the key feature of the training model to classify facial features, thereby assigning different facial features to different body shape categories.

[0086] Next, body type classification is performed based on facial features and the preliminarily determined body type using a pre-calibrated weight ratio, which is based on actual data and calibrated criteria, including a comprehensive judgment of facial dimensions and the preliminarily determined body type.

[0087] The classification standards for the size of rear passengers include: small, medium and large.

[0088] Small body type: For example, the distance from the tip of the nose to the edge of the face is short, and the body outline is relatively compact.

[0089] Medium body shape: For example, the distance from the tip of the nose to the edge of the face is in the medium range, and the body shape is medium.

[0090] Large body shape: For example, the distance from the tip of the nose to the edge of the face is long, and the body shape is wider.

[0091] By processing and analyzing facial images and sitting posture images, combined with Canny edge detection and facial feature measurement technology, the body shape of the occupants can be accurately determined.

[0092] Of course, in other embodiments, the passenger's body shape can also be determined by a seat pressure sensor, and the passenger's weight can be detected by the seat pressure sensor and converted into the body shape according to a set correspondence between weight and body shape.

[0093] S140: Obtain the door opening side video and project it into the vehicle.

[0094] In this embodiment, when the rear passenger intends to open the door, the projector rotation mechanism rotates the projector to the corresponding window and closes the window at the same time, projecting the side view camera of the door opening side captured by the external camera onto the window.

[0095] Specifically, the side view camera on the door opening side collects video and transmits it to the cockpit domain control, and projects it onto the car window through a projector. If there are vehicles or pedestrians passing quickly in the video, the video border will flash red to warn the rear passengers.

[0096] If the rear corner radar fails, passengers can be prompted through in-car projection and audio to alert them to potential collision objects. Specifically, the in-car camera is used to capture the video stream on the door opening side. Even if the radar fails, the camera can still provide visual information about the environment outside the door. The real-time video or image captured by the camera is projected onto the window through the projection equipment in the car. The projection content should include potential collision objects and safety prompts to ensure that passengers can clearly see possible dangers. Before the door is about to open, the projection device can display warning signs such as "Watch out for obstacles" or "Please check the outside of the door" to attract the attention of passengers.

[0097] When the system detects a radar failure, it can automatically start a preset warning sound or voice prompt, such as "Rear corner radar failure, please pay attention to obstacles outside the door". Make sure the audio prompt has sufficient volume and frequency so that passengers can hear it when the door is opened. At the same time, the audio prompt should not conflict with other sounds in the car to ensure the warning effect.

[0098] S150: Acquire rear corner radar data.

[0099] In this embodiment, the rear corner radar data includes the distance, speed, and direction between an object on the door opening side and the rear corner radar disposed at the rear corner of the vehicle.

[0100] S160, calculating the lateral distance and longitudinal distance of each object on the door opening side according to the door opening side video and the rear corner radar data, and determining the collision object and the corresponding lateral distance and longitudinal distance.

[0101] In this embodiment, the lateral distance and longitudinal distance of each object on the door opening side refer to the lateral distance and longitudinal distance between each object on the door opening side and the vehicle door, respectively.

[0102] In one embodiment, see Figure 4 , the above-mentioned step S160 may include steps S161 to S164.

[0103] S161. Calculate the lateral distance, angle, and longitudinal distance between the vehicle door and each object on the door opening side according to the rear corner radar data to obtain first data.

[0104] In this embodiment, the first data refers to the lateral distance, angle, and longitudinal distance between the vehicle door and each object on the door opening side, wherein the lateral distance refers to the lateral distance between the vehicle door and each object on the door opening side. The angle refers to the angle between the vehicle door and each object on the door opening side. The longitudinal distance refers to the longitudinal distance between the vehicle door and each object on the door opening side.

[0105] The rear-angle radar calculates the lateral distance by the time difference between the transmitted wave and the reflected wave, calculates the straight-line distance, calculates the angle between the target and the vehicle based on the phase difference between the transmitted wave and the reflected wave, and calculates the lateral distance and longitudinal distance based on trigonometric functions.

[0106] The rear corner radar has high accuracy in detecting the distance and angle of objects, and can provide accurate information about the area near the door. It helps to understand the environmental conditions in the door opening area and identify potential collision objects.

[0107] S162. Calculate the lateral distance and longitudinal distance between the vehicle door and each object on the door opening side according to the door opening side video to obtain second data.

[0108] In this embodiment, the second data refers to the lateral distance and longitudinal distance between the vehicle door and various objects on the door opening side calculated based on the door opening side video.

[0109] The horizontal distance refers to the horizontal distance between the vehicle door and each object on the door opening side in the door opening side video. The vertical distance refers to the vertical distance between the vehicle door and each object on the door opening side in the door opening side video.

[0110] Specifically, the horizontal and vertical distances of the target object are calculated based on the relative coordinates of the target objects (i.e., the objects on the door opening side) in the two frames before and after the door opening side video at a fixed position on the vehicle body in the image.

[0111] Video data can provide real-time visual information, which helps to supplement and verify radar data. It can capture the dynamic changes of objects and obtain real-time spatial information.

[0112] S163. Determine the final lateral distance and longitudinal distance of each object on the door opening side according to the first data and the second data.

[0113] In this embodiment, the minimum value of the lateral distance and longitudinal distance of each object on the door opening side in the first data and the second data is taken to obtain the final lateral distance and longitudinal distance of each object on the door opening side. In this way, the information of the object closest to the door is obtained. This method can improve the accuracy of collision detection and ensure that the object that is most likely to collide is identified first when the door is opened, thereby providing a more reliable safety warning.

[0114] S164. Determine that the object with the smallest lateral distance among the objects on the door opening side is the collision object, and obtain the corresponding lateral distance and longitudinal distance.

[0115] In this embodiment, the object closest to the vehicle door is found from the final lateral distance data and is determined to be a potential collision object.

[0116] Finding the objects closest to the door can prioritize these objects as potential targets for collision, improving the effectiveness of safety warnings. Focusing on the most dangerous objects helps to take timely action.

[0117] S170, determining a speed of a collision object according to the rear angle radar data, determining an acceleration in combination with the collision object and a corresponding longitudinal distance, and determining a collision time according to the acceleration, speed, and longitudinal distance.

[0118] Determine that the object with the smallest lateral distance among the objects on the final door opening side is the collision object, and obtain the corresponding lateral distance and longitudinal distance. In this embodiment, the velocity and acceleration of the collision object are calculated based on its lateral distance and longitudinal distance; the predicted collision time is calculated in combination with the longitudinal distance, velocity and acceleration.

[0119] Specifically, Sy=Vt+0.5at is adopted 2Calculate the predicted collision time, where Sy is the longitudinal distance, V is the velocity, a is the acceleration, and t is the predicted collision time.

[0120] S180: Control the door opening angle according to the collision time, the lateral distance, the door size, and the body size of the rear passenger.

[0121] In one embodiment, see Figure 5 , the above-mentioned step S180 may include steps S181 to S183.

[0122] S181: Determine whether the collision time is less than a set duration.

[0123] In this embodiment, when the collision time is less than the door opening time, that is, when the door is opened, the collision object has left the door opening area, the door opening time can be set to about 3s. This value can be set according to actual conditions. If the door is opened normally, otherwise it will be judged based on the lateral distance.

[0124] S182: If the collision time is less than the set time, the vehicle door is opened normally.

[0125] Specifically, when the collision time is less than the set time, the door can be opened normally; when the collision time is not less than the set time, the door opening angle needs to be controlled.

[0126] Normal door opening means that the door can be fully opened without controlling the opening angle of the door.

[0127] S183: If the collision time is not less than the set time, the door opening angle is controlled according to the lateral distance, door size and rear passenger body size.

[0128] In one embodiment, see Figure 6 , the above-mentioned step S183 may include steps S1831 to S1834.

[0129] S1831. Calculate the maximum angle at which the door can be safely opened based on the lateral distance and the door size.

[0130] In this embodiment, the maximum angle at which the door can be safely opened refers to the angle at which the door will not collide with a collision object when opened.

[0131] Specifically, the maximum angle θ at which the door can be safely opened is max =arcsin(Sx / W), where W is the door length and Sx is the lateral distance.

[0132] S1832. Determine whether the maximum angle is greater than the door opening angle threshold corresponding to the passenger's body size.

[0133] In this embodiment, the door opening angle threshold corresponding to the passenger body type refers to a pre-set door opening angle corresponding to different body types that satisfies the requirements for passengers to get off the vehicle.

[0134] Calculate based on the door opening size. The door opening width for a small person is set to 35cm, the door opening width for a medium person is set to 50cm, and the door opening width for a large person is set to 65cm. All values ​​can be calibrated. The door opening width is converted into the door opening angle threshold corresponding to the passenger's body size using trigonometric functions.

[0135] S1833. If the maximum angle is greater than the door opening angle threshold corresponding to the passenger's body size, control the door opening angle to be the maximum angle.

[0136] In this embodiment, when the maximum angle is greater than the door opening angle threshold corresponding to the passenger's body size, the door opening angle is adjusted to the maximum angle to ensure that there will be no collision with collision objects during the opening process while meeting the passenger's door opening needs.

[0137] S1834. If the maximum angle is not greater than the door opening angle threshold corresponding to the passenger's body size, the door opening angle is controlled to be zero.

[0138] In this embodiment, if the maximum angle is not greater than the door opening angle threshold corresponding to the passenger's body size, that is, the door cannot be safely opened to meet the passenger's body size requirements. In this case, the door will be locked to avoid accidental collision or unsafe opening, that is, the door opening angle is controlled to zero, and the door is locked at this time.

[0139] If the rear passenger has no intention to open the door, proceed to the end step.

[0140] The method of this embodiment can project the video captured by the side-view camera of the car onto the side window of the door through the in-cabin projection technology, and directly warn the rear passengers by marking a red border or projecting a warning sign. By introducing the DOW (Door Open Warning) function, it is ensured that the occupants in each area of ​​the car can clearly receive the warning information. This function avoids safety hazards caused by failure to detect obstacles or vehicles in time when the door is opened by improving the visibility and coverage of the warning; not only the head in the car is used for entertainment functions, but also as a tool for door opening warning and information display. This extension uses the versatility of the projection equipment to provide additional security and convenience for car owners, such as projecting the video captured by the side-view camera of the car or other important information onto the car window; integrating the equipment in the cockpit with the intelligent driving system to achieve intelligent control and functional linkage. This linkage can improve the overall intelligence level of the vehicle, making the vehicle more adaptable and intelligent in various driving scenarios, thereby enhancing the competitiveness of the product; the minimum door opening angle is calculated according to the body shape of different passengers to ensure that the door can meet the actual needs of the occupants when it is opened. In actual operation, the door can be opened only partially to accommodate the needs of occupants of different sizes, which improves the practicality and flexibility of the system and significantly improves the practicality of the system.

[0141] The above-mentioned vehicle door opening warning method obtains rear-seat audio and video through the in-vehicle camera, detects the passenger's intention to open the door, analyzes the passenger's facial and sitting image to determine his or her body shape, obtains the video of the door opening side and the rear corner radar data, calculates the distance, speed and acceleration of the object, identifies potential collision objects, and evaluates whether the door can be opened safely based on the detection data and calculation results. If there is a risk of collision, the most suitable door opening angle is calculated based on the lateral distance, door size and rear passenger body shape to ensure that the passengers can get off the vehicle safely without causing accidents; it can achieve efficient and direct prompts to the rear passengers to prevent accidents, and at the same time avoid any door opening warning in the vehicle when the corner radar fails, and the door opening angle can be controlled to meet the needs of passengers getting off the vehicle and preventing collisions, thereby enhancing practicality.

[0142] Figure 7 FIG. 3 is a schematic block diagram of a vehicle door opening warning device 300 provided in an embodiment of the present invention. Figure 7 As shown, corresponding to the above vehicle door opening warning method, the present invention also provides a vehicle door opening warning device 300. The vehicle door opening warning device 300 includes a unit for executing the above vehicle door opening warning method, and the device can be configured in a server. Figure 7The vehicle door opening warning device 300 includes an audio and video acquisition unit 301, an intention detection unit 302, a body shape determination unit 303, a projection unit 304, a radar data acquisition unit 305, a distance determination unit 306, a collision time determination unit 307 and an angle control unit 308.

[0143] The audio and video acquisition unit 301 is used to acquire the audio and video of the rear seats in the vehicle when the vehicle is in a parked state; the intention detection unit 302 is used to detect whether the rear passengers have the intention to open the door based on the audio and video of the rear seats in the vehicle; the body shape determination unit 303 is used to determine the body shape of the rear passengers using image technology; the projection unit 304 is used to acquire the video of the door opening side and project it into the vehicle; the radar data acquisition unit 305 is used to acquire the rear corner radar data; the distance determination unit 306 is used to calculate the lateral distance and longitudinal distance of each object on the door opening side based on the video of the door opening side and the rear corner radar data, and determine the collision object and the corresponding lateral distance and longitudinal distance; the collision time determination unit 307 is used to determine the speed of the collision object based on the rear corner radar data, determine the acceleration in combination with the collision object and the corresponding longitudinal distance, and determine the collision time based on the acceleration, speed and longitudinal distance; the angle control unit 308 is used to control the door opening angle based on the collision time, the lateral distance, the door size and the body shape of the rear passengers.

[0144] In one embodiment, the intention detection unit 302 is used to perform action analysis of rear-seat passengers based on the rear-seat audio and video in the vehicle using optical flow analysis, and / or to detect keywords in the rear-seat audio and video in the vehicle using sound to determine whether there is an intention to open the door.

[0145] In one embodiment, if Figure 8 As shown, the body shape determination unit 303 includes an image acquisition subunit 3031 , a sitting posture analysis subunit 3032 and a facial analysis subunit 3033 .

[0146] The image acquisition subunit 3031 is used to acquire the facial image and sitting posture image of the rear passenger. The sitting posture analysis subunit 3033 is used to analyze the sitting posture image using image processing technology to preliminarily determine the body type; the facial analysis subunit 3033 is used to analyze the facial image of the rear passenger to determine the facial features, and combine the preliminarily determined body type to determine the body type of the rear passenger.

[0147] In one embodiment, if Fig. 9 As shown, the distance determination unit 306 includes a first calculation subunit 3061 , a second calculation subunit 3062 , a final determination subunit 3063 and a collision object determination subunit 3064 .

[0148] The first calculation subunit 3061 is used to calculate the lateral distance, angle and longitudinal distance between the vehicle door and each object on the door opening side according to the rear angle radar data to obtain the first data; the second calculation subunit 3062 is used to calculate the lateral distance and longitudinal distance between the vehicle door and each object on the door opening side according to the door opening side video to obtain the second data; the final determination subunit 3063 is used to determine the final lateral distance and longitudinal distance of each object on the door opening side according to the first data and the second data; the collision object determination subunit 3064 is used to determine that the object with the smallest lateral distance among the final objects on the door opening side is the collision object, and obtain the corresponding lateral distance and longitudinal distance.

[0149] In one embodiment, the final determination subunit 3063 is used to take the minimum value of the lateral distance and the longitudinal distance of each object on the door opening side in the first data and the second data to obtain the final lateral distance and longitudinal distance of each object on the door opening side.

[0150] In one embodiment, if Fig.10 As shown, the angle control unit 308 includes a judgment subunit 3081 , a normal opening subunit 3082 , and a safety control subunit 3083 .

[0151] The judgment subunit 3081 is used to judge whether the collision time is less than the set time; the normal opening subunit 3082 is used to open the door normally if the collision time is less than the set time; the safety control subunit 3083 is used to control the door opening angle according to the lateral distance, door size and rear passenger body shape if the collision time is not less than the set time.

[0152] In one embodiment, if Fig.11 As shown, the safety control subunit 3083 includes a maximum angle calculation subunit 30831 , an angle judgment subunit 30832 , an opening angle control subunit 30833 and a locking subunit 30834 .

[0153] The maximum angle calculation subunit 30831 is used to calculate the maximum angle at which the door can be safely opened based on the lateral distance and the door size; the angle judgment subunit 30832 is used to judge whether the maximum angle is greater than the door opening angle threshold corresponding to the passenger size; the opening angle control subunit 30833 is used to control the door opening angle to the maximum angle if the maximum angle is greater than the door opening angle threshold corresponding to the passenger size; the locking subunit 30834 is used to control the door opening angle to zero if the maximum angle is not greater than the door opening angle threshold corresponding to the passenger size.

[0154] It should be noted that technicians in the relevant field can clearly understand that the specific implementation process of the above-mentioned vehicle door opening warning device 300 and each unit can refer to the corresponding description in the aforementioned method embodiment, and for the convenience and brevity of description, it will not be repeated here.

[0155] The vehicle door opening warning device 300 can be implemented in the form of a computer program. The computer program can be implemented in the form of a computer program. Fig.12 Runs on the computer device shown.

[0156] See also Fig.12 , Fig.12 5 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device 500 may be a server, wherein the server may be an independent server or a server cluster composed of multiple servers.

[0157] See also Fig.12 The computer device 500 includes a processor 502 , a memory and a network interface 505 connected via a system bus 501 , wherein the memory may include a non-volatile storage medium 503 and an internal memory 504 .

[0158] The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions, and when the program instructions are executed, the processor 502 can execute a vehicle door opening warning method.

[0159] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

[0160] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute a vehicle door opening warning method.

[0161] The network interface 505 is used to communicate with other devices over the network. Fig.10 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device 500 to which the solution of the present application is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0162] The processor 502 is used to run the computer program 5032 stored in the memory to implement the following steps:

[0163] When the vehicle is parked, obtain the rear-seat audio and video in the vehicle; detect whether the rear-seat passenger has the intention to open the door based on the rear-seat audio and video in the vehicle; if the rear-seat passenger has the intention to open the door, use image technology to determine the size of the rear-seat passenger; obtain the door-opening side video and project it into the vehicle; obtain the rear-corner radar data; calculate the lateral distance and longitudinal distance of each object on the door-opening side based on the door-opening side video and the rear-corner radar data, and determine the collision object and the corresponding lateral distance and longitudinal distance; determine the speed of the collision object based on the rear-corner radar data, determine the acceleration in combination with the collision object and the corresponding longitudinal distance, and determine the collision time based on the acceleration, speed and longitudinal distance; control the door opening angle based on the collision time, the lateral distance, the door size and the size of the rear-seat passenger.

[0164] In one embodiment, when the processor 502 implements the step of detecting whether the rear-seat passenger has the intention to open the door according to the rear-seat audio and video in the vehicle, the processor 502 specifically implements the following steps:

[0165] Optical flow analysis is used to analyze the movements of rear passengers based on the rear audio and video in the vehicle, and / or sound is used to detect keywords in the rear audio and video in the vehicle to determine whether there is an intention to open the door.

[0166] In one embodiment, when the processor 502 implements the step of using image technology to determine the body size of the rear passenger, the processor 502 specifically implements the following steps:

[0167] Acquire a facial image and a sitting image of a rear-seat passenger; use image processing technology to analyze the sitting image to preliminarily determine the body type; analyze the facial image of the rear-seat passenger to determine facial features, and combine the preliminarily determined body type to determine the body type of the rear-seat passenger.

[0168] In one embodiment, when the processor 502 implements the step of calculating the lateral distance and longitudinal distance of each object on the door opening side according to the door opening side video and the rear corner radar data, and determining the collision object and the corresponding lateral distance and longitudinal distance, the following steps are specifically implemented:

[0169] The lateral distance, angle and longitudinal distance between the vehicle door and each object on the door opening side are calculated according to the rear corner radar data to obtain the first data; the lateral distance and longitudinal distance between the vehicle door and each object on the door opening side are calculated according to the door opening side video to obtain the second data; the final lateral distance and longitudinal distance of each object on the door opening side are determined according to the first data and the second data; the object with the smallest lateral distance among the final objects on the door opening side is determined to be the collision object, and the corresponding lateral distance and longitudinal distance are obtained.

[0170] In one embodiment, when the processor 502 implements the step of determining the final lateral distance and longitudinal distance of each object on the door opening side according to the first data and the second data, the processor 502 specifically implements the following steps:

[0171] The minimum value of the lateral distance and the longitudinal distance of each object on the door opening side in the first data and the second data is taken to obtain the final lateral distance and longitudinal distance of each object on the door opening side. In one embodiment, when the processor 502 implements the step of controlling the door opening angle according to the collision time, the lateral distance, the door size and the body type of the rear passenger, the following steps are specifically implemented:

[0172] Determine whether the collision time is less than the set time; if the collision time is less than the set time, open the door normally; if the collision time is not less than the set time, control the door opening angle according to the lateral distance, door size and rear passenger body shape.

[0173] In one embodiment, when the processor 502 implements the step of controlling the door opening angle according to the lateral distance, the door size, and the size of the rear passenger, the processor 502 specifically implements the following steps:

[0174] The maximum angle at which the door can be safely opened is calculated based on the lateral distance and the door size; whether the maximum angle is greater than the door opening angle threshold corresponding to the passenger body size is determined; if the maximum angle is greater than the door opening angle threshold corresponding to the passenger body size, the door opening angle is controlled to be the maximum angle; if the maximum angle is not greater than the door opening angle threshold corresponding to the passenger body size, the door opening angle is controlled to be zero.

[0175] It should be understood that in the embodiment of the present application, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be 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. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0176] It can be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0177] Therefore, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein when the computer program is executed by a processor, the processor executes the following steps:

[0178] When the vehicle is parked, obtain the rear-seat audio and video in the vehicle; detect whether the rear-seat passenger has the intention to open the door based on the rear-seat audio and video in the vehicle; if the rear-seat passenger has the intention to open the door, use image technology to determine the size of the rear-seat passenger; obtain the door-opening side video and project it into the vehicle; obtain the rear-corner radar data; calculate the lateral distance and longitudinal distance of each object on the door-opening side based on the door-opening side video and the rear-corner radar data, and determine the collision object and the corresponding lateral distance and longitudinal distance; determine the speed of the collision object based on the rear-corner radar data, determine the acceleration in combination with the collision object and the corresponding longitudinal distance, and determine the collision time based on the acceleration, speed and longitudinal distance; control the door opening angle based on the collision time, the lateral distance, the door size and the size of the rear-seat passenger.

[0179] In one embodiment, when the processor executes the computer program to implement the step of detecting whether the rear-seat passenger has the intention to open the door according to the rear-seat audio and video in the vehicle, the processor specifically implements the following steps:

[0180] Optical flow analysis is used to analyze the movements of rear passengers based on the rear audio and video in the vehicle, and / or sound is used to detect keywords in the rear audio and video in the vehicle to determine whether there is an intention to open the door.

[0181] In one embodiment, when the processor executes the computer program to implement the step of using image technology to determine the body size of the rear passenger, the processor specifically implements the following steps:

[0182] Acquire a facial image and a sitting image of a rear-seat passenger; use image processing technology to analyze the sitting image to preliminarily determine the body type; analyze the facial image of the rear-seat passenger to determine facial features, and combine the preliminarily determined body type to determine the body type of the rear-seat passenger.

[0183] In one embodiment, when the processor executes the computer program to implement the step of calculating the lateral distance and longitudinal distance of each object on the door opening side according to the door opening side video and the rear corner radar data, and determining the collision object and the corresponding lateral distance and longitudinal distance, the following steps are specifically implemented:

[0184] The lateral distance, angle and longitudinal distance between the vehicle door and each object on the door opening side are calculated according to the rear corner radar data to obtain the first data; the lateral distance and longitudinal distance between the vehicle door and each object on the door opening side are calculated according to the door opening side video to obtain the second data; the final lateral distance and longitudinal distance of each object on the door opening side are determined according to the first data and the second data; the object with the smallest lateral distance among the final objects on the door opening side is determined to be the collision object, and the corresponding lateral distance and longitudinal distance are obtained.

[0185] In one embodiment, when the processor executes the computer program to implement the step of determining the final lateral distance and longitudinal distance of each object on the door opening side according to the first data and the second data, the processor specifically implements the following steps:

[0186] The minimum value of the lateral distance and the longitudinal distance of each object on the door opening side in the first data and the second data is taken to obtain the final lateral distance and longitudinal distance of each object on the door opening side.

[0187] In one embodiment, when the processor executes the computer program to implement the step of controlling the door opening angle according to the collision time, the lateral distance, the door size, and the size of the rear passenger, the processor specifically implements the following steps:

[0188] Determine whether the collision time is less than the set time; if the collision time is less than the set time, open the door normally; if the collision time is not less than the set time, control the door opening angle according to the lateral distance, door size and rear passenger body shape.

[0189] In one embodiment, when the processor executes the computer program to implement the step of controlling the door opening angle according to the lateral distance, the door size, and the size of the rear passenger, the processor specifically implements the following steps:

[0190] The maximum angle at which the door can be safely opened is calculated based on the lateral distance and the door size; whether the maximum angle is greater than the door opening angle threshold corresponding to the passenger body size is determined; if the maximum angle is greater than the door opening angle threshold corresponding to the passenger body size, the door opening angle is controlled to be the maximum angle; if the maximum angle is not greater than the door opening angle threshold corresponding to the passenger body size, the door opening angle is controlled to be zero.

[0191] The storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which are computer-readable storage media that can store program codes.

[0192] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0193] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0194] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present invention 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.

[0195] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0196] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. Vehicle door opening warning method, It is characterized in that include: When the vehicle is parked, obtain the rear audio and video in the vehicle; Detecting whether a rear passenger intends to open the door based on the rear audio and video in the vehicle; If the rear passenger intends to open the door, image technology is used to determine the rear passenger's body shape; Get the door opening side video and project it inside the car; Get rear corner radar data; Calculate the lateral distance and longitudinal distance of each object on the door opening side according to the door opening side video and the rear corner radar data, and determine the collision object and the corresponding lateral distance and longitudinal distance; determining a velocity of a collision object based on the rear angle radar data, determining an acceleration in combination with the collision object and a corresponding longitudinal distance, and determining a collision time based on the acceleration, velocity, and longitudinal distance; The door opening angle is controlled according to the collision time, the lateral distance, the door size and the body size of the rear passengers.

2. The vehicle door opening warning method according to claim 1, It is characterized in that The detecting whether the rear-seat passenger intends to open the door according to the rear-seat audio and video in the vehicle includes: Optical flow analysis is used to analyze the movements of rear passengers based on the rear audio and video in the vehicle, and / or sound is used to detect keywords in the rear audio and video in the vehicle to determine whether there is an intention to open the door.

3. The vehicle door opening warning method according to claim 1, It is characterized in that The method of using image technology to determine the body size of the rear seat passengers includes: Acquire facial images and sitting posture images of rear passengers; Analyzing the sitting posture image using image processing technology to preliminarily determine the body shape; The facial image of the rear passenger is analyzed to determine facial features, and combined with the initially determined body shape to determine the body shape of the rear passenger.

4. The vehicle door opening warning method according to claim 1, It is characterized in that The calculating the lateral distance and longitudinal distance of each object on the door opening side according to the door opening side video and the rear corner radar data, and determining the collision object and the corresponding lateral distance and longitudinal distance, includes: Calculating the lateral distance, angle and longitudinal distance between the door and each object on the door opening side according to the rear corner radar data to obtain first data; Calculating the lateral distance and longitudinal distance between the vehicle door and each object on the door opening side according to the door opening side video to obtain second data; Determine the final horizontal distance and vertical distance of each object on the door opening side according to the first data and the second data; The object with the smallest lateral distance among the objects on the final door opening side is determined to be the collision object, and the corresponding lateral distance and longitudinal distance are obtained.

5. The vehicle door opening warning method according to claim 4, It is characterized in that The final determination of the horizontal distance and the vertical distance of each object on the door opening side according to the first data and the second data includes: The minimum value of the lateral distance and the longitudinal distance of each object on the door opening side in the first data and the second data is taken to obtain the final lateral distance and longitudinal distance of each object on the door opening side.

6. The vehicle door opening warning method according to claim 1, It is characterized in that The controlling of the door opening angle according to the collision time, the lateral distance, the door size and the body size of the rear passenger includes: Determine whether the collision time is less than a set time; If the collision time is less than the set time, the door is opened normally; If the collision time is not less than the set time, the door opening angle is controlled according to the lateral distance, door size and rear passenger body size.

7. The vehicle door opening warning method according to claim 6, It is characterized in that The controlling of the door opening angle according to the lateral distance, the door size and the body size of the rear passenger comprises: Calculating the maximum angle at which the door can be safely opened based on the lateral distance and the door size; Determining whether the maximum angle is greater than a door opening angle threshold corresponding to the passenger's body size; If the maximum angle is greater than the door opening angle threshold corresponding to the passenger's body size, the door opening angle is controlled to be the maximum angle; If the maximum angle is not greater than the door opening angle threshold corresponding to the passenger's body size, the door opening angle is controlled to be zero.

8. Vehicle door opening warning device, It is characterized in that include: An audio and video acquisition unit, used to acquire rear-seat audio and video in the vehicle when the vehicle is in a parked state; An intention detection unit, used to detect whether a rear passenger intends to open the door based on the rear audio and video in the vehicle; A body size determination unit, used to determine the body size of rear passengers using image technology; A projection unit, used to obtain the door opening side video and project it inside the car; A radar data acquisition unit, used for acquiring rear angle radar data; A distance determination unit, used to calculate the lateral distance and longitudinal distance of each object on the door opening side according to the door opening side video and the rear corner radar data, and determine the collision object and the corresponding lateral distance and longitudinal distance; a collision time determination unit, configured to determine a speed of a collision object according to the rear angle radar data, determine an acceleration in combination with the collision object and a corresponding longitudinal distance, and determine a collision time according to the acceleration, speed and longitudinal distance; An angle control unit is used to control the door opening angle according to the collision time, the lateral distance, the door size and the body size of the rear passengers.

9. A computer device, It is characterized in that The computer device comprises a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

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

Images