A suspension control method, apparatus, electronic device, and storage medium

Abstract

A suspension control method and device, electronic equipment and storage medium, through the body key point position information of the target character in the target character image, the reference position reference point of the vehicle suspension is determined, the influence of different individual body shapes on the reference position reference point is fully considered, the suspension can more accurately understand the interaction intention of the target character, and adaptively moves with the posture change of the target character, which improves the interaction effect and user experience, and effectively improves the response stability of the suspension, avoids the problem that the response stability of the suspension is insufficient or does not match the interaction intention of the user due to the difference in the body shape of the user, such as being too tall or too short; in addition, at least two reference position reference points are used to independently control the movement of at least two vehicle suspensions, so that the movement modes of the vehicle suspensions can be different, and the individualized needs of users for control of different vehicle suspensions are met.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to a suspension control method, device, electronic device, and storage medium. Background Technology

[0002] The vehicle chassis suspension is an important component of the vehicle chassis, used to connect the wheels and the body and support the weight of the vehicle. The vehicle chassis suspension consists of elastic elements, shock absorbers, guiding mechanisms and anti-roll bars. Its main functions are to absorb the impact caused by uneven road surfaces, improve the handling and comfort of the vehicle, and ensure stable contact between the wheels and the ground.

[0003] Currently, vehicle chassis suspension adjustment methods are too simplistic and lack support for diverse user needs. Therefore, it is necessary to explore a new human-vehicle interaction method that enables the vehicle chassis to dynamically adjust the suspension according to the user's intentions. Summary of the Invention

[0004] Based on this, a suspension control method, device, electronic device, and storage medium are provided to solve the above-mentioned technical problems.

[0005] Firstly, a suspension control method is provided, including:

[0006] In response to receiving an interactive command, acquire an image of the target person;

[0007] Determine the location information of key human body points of the target person in the target person image;

[0008] Based on the human body key point location information, determine the human body interaction reference point of the target person, the first reference position reference point of the first vehicle suspension, and the second reference position reference point of the second vehicle suspension from the target person image;

[0009] Based on the relative positional relationship between the human interaction reference point and the first reference position reference point, the movement of the first vehicle suspension is controlled, and based on the relative positional relationship between the human interaction reference point and the second reference position reference point, the movement of the second vehicle suspension is controlled.

[0010] In the above method, the corresponding reference points are determined by using the key point location information of the target person's body in the target person image. The influence of different individual body shapes on the reference point position is fully considered, enabling the suspension to more accurately understand the target person's interaction intention and adapt to the target person's posture changes. While improving the interaction effect and user experience, it also effectively improves the suspension's response stability. In addition, the movement of at least two vehicle suspensions is controlled relatively independently based on at least two reference points, so that the movement mode of each vehicle suspension can be different, meeting the user's personalized needs for the control of different vehicle suspensions.

[0011] In one embodiment, acquiring the image of the target person includes:

[0012] Acquire the original video images; the original video images include N frames of original images, where N is an integer greater than or equal to 2;

[0013] The target person is identified from the original video image;

[0014] The image region corresponding to the target person in the original image is determined as the target person image.

[0015] In the above method, by determining the corresponding target person for each frame of the original video image, the suspension can move according to the position information of the key points of the target person's body in multiple frames of images, achieving the effect of people and vehicles dancing together through video images, thus enhancing the user's interactive experience.

[0016] In one embodiment, the interaction command is an external vehicle interaction command or an in-vehicle interaction command; acquiring the original video image includes:

[0017] When the interaction command is an external interaction command, the vehicle's image acquisition device acquires images of the external area to obtain a video image, which is the original video image.

[0018] or,

[0019] When the interaction command is an in-vehicle interaction command, a dance video image played through the vehicle's display device is acquired, and the dance video image is the original video image.

[0020] In the above method, in response to receiving an external interaction command, the suspension movement is controlled according to the key point position information of the target person outside the vehicle to meet the usage requirements of the external scene; in response to receiving an internal interaction command, the suspension movement is controlled according to the key point position information of the target person in the dance video image played in the vehicle to meet the usage requirements of the internal scene and enhance the immersive experience of dancing together with the vehicle inside the vehicle.

[0021] In one embodiment, determining the target person from the original video image includes:

[0022] Determine the target detection box from the original image;

[0023] In response to the presence of a target scene image region in the original image, and the number of target detection boxes in the target scene image region being greater than 1, the person in the target detection box closest to the center point of the target scene image region is determined to be the target person; or,

[0024] In response to the number of target detection boxes being greater than 1, the person in the target detection box with the largest area is determined to be the target person, or the person in the target detection box closest to the center point of the original image is determined to be the target person.

[0025] When a user intends to interact with a vehicle, the user usually tends to be near the center of the target scene or near a location that is convenient for the vehicle's image acquisition device to capture images, such as being directly in front of the image acquisition device or being in the closest position to the image acquisition device. In the above method, by taking the person in the target detection box closest to the center point of the target scene image area as the target person, or taking the person in the target detection box with the largest area as the target person, or taking the person in the target detection box closest to the center point of the original image as the target person, the identified target person is the person who intends to interact with the vehicle, thus improving the accuracy of target person identification.

[0026] In one embodiment, when the interaction command is the external vehicle interaction command, determining the target person from the original video image includes:

[0027] The motion of each person in the original video image is detected to obtain motion detection results;

[0028] Based on the action detection results, the person who first performs the preset target action is identified as the target person.

[0029] In the above method, the actions of each character are detected, and the character who first performs the preset target action is identified as the target character, which further improves the accuracy of target character identification.

[0030] In one embodiment, the human interaction reference point includes a first human interaction reference point and a second human interaction reference point; controlling the movement of the first vehicle suspension based on the relative positional relationship between the human interaction reference point and the first reference position reference point includes:

[0031] Determine the first difference between the ordinate of the first reference position reference point and the ordinate of the first human interaction reference point;

[0032] In response to the first difference being less than a preset first threshold, the first vehicle suspension is controlled to move to a first position of the first reference position; or, in response to the first difference being greater than the first threshold, the first vehicle suspension is controlled to move to a second position of the first reference position; wherein the first position and the second position are opposite.

[0033] The step of controlling the movement of the second vehicle suspension based on the relative positional relationship between the human interaction reference point and the second reference position reference point includes:

[0034] Determine the second difference between the ordinate of the second reference position reference point and the ordinate of the second human body interaction reference point;

[0035] In response to the second difference being less than a preset second threshold, the second vehicle suspension is controlled to move to a third position of the second reference position; or, in response to the second difference being greater than the second threshold, the second vehicle suspension is controlled to move to a fourth position of the second reference position; wherein the third position and the fourth position are opposite.

[0036] In the above method, the suspension movement direction is controlled based on the relative positional relationship between the human interaction reference point and the reference position reference point. Since the reference position reference point is obtained based on the key point position information of the target person's body, and the suspension movement direction is obtained based on the reference position reference point, the target person's body shape is fully considered in determining the suspension movement direction. This effectively avoids the problem of insufficient stability of the suspension movement direction response or mismatch with the target person's interaction intention due to the target person's height being too tall or too short (e.g., children). In addition, different vehicle suspensions are independently controlled based on different human interaction reference points, making the control methods of each vehicle suspension completely independent, better meeting the user's personalized needs for the control of different vehicle suspensions.

[0037] In one embodiment, controlling the movement of the first vehicle suspension based on the relative positional relationship between the human interaction reference point and the first reference position reference point includes:

[0038] Determine the first distance between the first human interaction reference point and the first reference position reference point;

[0039] The second distance between the first target position of the first vehicle suspension and the first reference position is determined according to D2 = D1 × k1; where D2 is the second distance, D1 is the first distance, and k1 is a preset amplification factor.

[0040] Based on the second distance, the first vehicle suspension is controlled to move to the first target position.

[0041] In the above method, since the first reference position is obtained based on the key point position information of the target person's body, and the movement distance of the first vehicle suspension is obtained based on the first reference position, the target person's body shape is fully considered in determining the movement distance of the first vehicle suspension. This effectively avoids the problem that the stability of the movement distance response of the first vehicle suspension is insufficient or does not match the target person's interaction intention due to the target person's height being too tall or too short (e.g., a child). In addition, during the interaction, some key parts of the user's body may not be able to make large movements. In the above method, the amplification factor is used to amplify the amplitude of small changes, so that the first vehicle suspension can be controlled to move a large range with small movements.

[0042] In one embodiment, before determining a second distance between a first target position of the first vehicle suspension and a first reference position, the method includes:

[0043] The first distance is determined to be greater than or equal to a preset third threshold.

[0044] Since the positions of key points on a user's body may change when the user is in a natural state, the corresponding key point position information may also change. Natural changes in the user's posture may cause changes in the relative distance between the human interaction reference point and the reference position reference point. To avoid triggering the suspension to respond based on this change when the user's posture changes naturally, the above method controls the movement of the first vehicle suspension only after determining that the first distance between the first human interaction reference point and the first reference position reference point is greater than or equal to the third threshold. This prevents the first vehicle suspension from responding without needing to respond, allowing the first vehicle suspension to move precisely according to the user's needs and improving the accuracy of the first vehicle suspension response.

[0045] In one embodiment, controlling the first vehicle suspension to move to the first target position based on the second distance includes:

[0046] Obtain the first current position information of the first vehicle suspension;

[0047] First target location information is generated based on the comparison result between the first difference and the first threshold, the second distance, and the first reference position;

[0048] The first direction of movement and the first distance of movement of the first vehicle suspension are determined based on the first current location information and the first target location information.

[0049] Control the first vehicle suspension to move to the first target position according to the first moving direction and the first moving distance.

[0050] In the above method, the first direction of movement and the first distance of movement of the first vehicle suspension are determined by the first current position information and the first target position information, so that the movement path of the first vehicle suspension is more in line with the user's needs.

[0051] In one embodiment, controlling the movement of the second vehicle suspension based on the relative positional relationship between the human interaction reference point and the second reference position reference point includes:

[0052] Determine the interaction limit reference point corresponding to the second human body interaction reference point;

[0053] Determine the third distance between the interaction limit reference point and the second reference position reference point;

[0054] Determine the fourth distance between the second human interaction reference point and the second reference position reference point;

[0055] Based on the ratio between the fourth distance and the third distance, and the reference height of the second vehicle suspension, a fifth distance is determined between the second target position of the second vehicle suspension and the second reference position;

[0056] Based on the fifth distance, the second vehicle suspension is controlled to move to the second target position.

[0057] In the above method, the motion of the second human interaction reference relative to the second reference position reference point is mapped to the motion of the second vehicle suspension relative to the second reference position through the ratio relationship. This enables adaptive control based on users of different heights, so as to accurately understand the user's interaction intention and avoid the problem of unstable response of the second vehicle suspension caused by the second reference position reference point being too high or too low when the second vehicle suspension moves with the user's posture due to different user height differences.

[0058] In one embodiment, controlling the movement of the second vehicle suspension to the second target position based on the fifth distance includes:

[0059] Obtain the second current position information of the second vehicle suspension;

[0060] The second target location information is generated based on the comparison result between the second difference and the second threshold, the fifth distance, and the second reference position.

[0061] The second direction of movement and the second distance of movement of the second vehicle suspension are determined based on the second current position information and the second target position information.

[0062] Control the second vehicle suspension to move to the second target position according to the second direction of movement and the second distance of movement.

[0063] In the above method, the second direction of movement and the second distance of movement of the second vehicle suspension are determined by the second current position information and the second target position information, so that the movement path of the second vehicle suspension is more in line with the user's needs.

[0064] In one embodiment, the human body key point location information includes first human body key point location information, second human body key point location information, and third human body key point location information; the method for determining the first reference position reference point includes:

[0065] The reference point of the first reference position is determined based on the location information of the first human body key point and the location information of the second human body key point;

[0066] The methods for determining the reference point of the second reference position include:

[0067] The second reference position reference point is determined based on the second human body key point location information and the third human body key point location information.

[0068] In the above method, the reference point is determined based on the location information of two human body key points. Compared with the reference point determined based on the location information of a single human body key point, the accuracy and stability of the reference point determination can be improved because more human body key points are considered.

[0069] In one embodiment, determining the first reference position reference point based on the first human body key point location information and the second human body key point location information includes:

[0070] Determine the first vertical height between the position indicated by the first human body key point position information and the position indicated by the second human body key point position information;

[0071] Based on at least one of the positions indicated by the first human body key point position information and the positions indicated by the second human body key point position information, and the first height, the first reference position reference point is determined;

[0072] The step of determining the second reference position reference point based on the second human body key point location information and the third human body key point location information includes:

[0073] Determine the second vertical height between the position indicated by the second human body key point position information and the position indicated by the third human body key point position information;

[0074] The second reference position reference point is determined based on at least one of the positions indicated by the second human body key point position information and the positions indicated by the third human body key point position information, and the second height.

[0075] During the interaction, to avoid inaccuracies and instabilities in the confirmation of reference points caused by subtle changes in the position information of key human body points, the above method eliminates the influence of subtle changes in the position of a single key human body point by using the positions of two key human body points. This is because the changes in the position of key human body points during the interaction are mostly synchronous. After the positions of two key human body points change synchronously, the height between the positions of these two key human body points tends to be stable. In this way, the influence of subtle changes in the position of a single key human body point can be eliminated, thereby improving the accuracy and stability of the confirmation of reference points.

[0076] Secondly, this application provides a suspension control device, the device comprising:

[0077] The acquisition module is used to acquire the image of the target person in response to received interactive instructions;

[0078] The first determining module is used to determine the location information of key human body points of the target person in the target person image;

[0079] The second determining module is used to determine the human body interaction reference point of the target person, the first reference position reference point of the first vehicle suspension, and the second reference position reference point of the second vehicle suspension from the target person image based on the human body key point position information.

[0080] The control module is used to control the movement of the first vehicle suspension based on the relative positional relationship between the human interaction reference point and the first reference position reference point, and to control the movement of the second vehicle suspension based on the relative positional relationship between the human interaction reference point and the second reference position reference point.

[0081] Thirdly, this application provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program to implement the suspension control method of the first aspect described above.

[0082] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the suspension control method of the first aspect described above.

[0083] The suspension control method, device, electronic equipment, and storage medium provided in this application, in response to receiving an interactive command, acquire an image of a target person, determine the position information of key human body points of the target person in the image, determine the human body interactive reference point of the target person, a first reference position reference point of the first vehicle suspension, and a second reference position reference point of the second vehicle suspension from the image based on the position information of the key human body points, control the movement of the first vehicle suspension based on the relative positional relationship between the human body interactive reference point and the first reference position reference point, and control the movement of the second vehicle suspension based on the relative positional relationship between the human body interactive reference point and the second reference position reference point, thereby controlling the movement of the target person's human body in the image. By identifying key point location information and determining the reference points for the vehicle suspension, this method fully considers the impact of different individual body shapes on the reference points. This enables the suspension to more accurately understand the user's interaction intentions and adapt to changes in the user's posture. This approach not only improves the interaction effect and user experience but also effectively enhances the suspension's response stability, avoiding issues caused by user body shape differences, such as excessively tall or short individuals, leading to insufficient suspension response stability or a mismatch with the user's interaction intentions. Furthermore, by independently controlling the movement of at least two vehicle suspensions based on at least two reference points, the movement patterns of each vehicle suspension can differ, meeting the personalized needs of users for controlling the suspensions of different vehicles.

[0084] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing the application. The purposes and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not intended to limit this disclosure. Attached Figure Description

[0085] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0086] Figure 1 This is a flowchart illustrating a suspension control method in one embodiment;

[0087] Figure 2 This is a schematic diagram of the process of obtaining an image of a target person in one embodiment;

[0088] Figure 3 This is a schematic diagram of the reference point of the second reference position in one embodiment;

[0089] Figure 4 This is a schematic diagram of the reference point of the first reference position in one embodiment;

[0090] Figure 5 This is a flowchart illustrating the process of determining the first direction of movement and the first distance of movement of the first vehicle suspension in one embodiment.

[0091] Figure 6 This is a flowchart illustrating the process of determining the second direction of movement and the second distance of movement of the second vehicle suspension in one embodiment.

[0092] Figure 7 This is a schematic diagram illustrating the positional relationship between the second human interaction reference point and the second reference position reference point in one embodiment;

[0093] Figure 8 This is a flowchart illustrating a suspension control method in an external vehicle interaction scenario, as shown in one embodiment.

[0094] Figure 9 This is a schematic diagram of the suspension control device in one embodiment;

[0095] Figure 10 This is a diagram of the internal structure of an electronic device in one embodiment. Detailed Implementation

[0096] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0097] Example 1:

[0098] This application provides a suspension control method; please refer to [link / reference]. Figure 1 As shown, it includes:

[0099] S11: In response to receiving an interactive command, acquire the image of the target person.

[0100] S12: Determine the location information of key points of the target person in the image.

[0101] S13: Determine the human body interaction reference point of the target person, the first reference position reference point of the first vehicle suspension, and the second reference position reference point of the second vehicle suspension from the target person image based on the human body key point position information.

[0102] S14: Based on the relative positional relationship between the human interaction reference point and the first reference position reference point, control the movement of the first vehicle suspension, and based on the relative positional relationship between the human interaction reference point and the second reference position reference point, control the movement of the second vehicle suspension.

[0103] Specifically, the representation of the above-mentioned key human body location information includes, but is not limited to, at least one of two-dimensional coordinates, three-dimensional coordinates, polar coordinates, and latitude and longitude coordinates.

[0104] To facilitate understanding, the relevant terms mentioned in the embodiments of this application will be introduced first.

[0105] The movement of a vehicle suspension can drive the movement of the vehicle body. Any point on the suspension can be taken as a target point, and the process of the suspension moving up and down is also the process of that target point moving up and down. For example, the point on the vehicle suspension that connects to the vehicle body can be taken as the target point, and the target point moves between its upper and lower height limits. In the embodiments of this application, the height and position of the suspension can be the height and position of the target point, and any height position between the upper and lower height limits of the target point can be used as the reference position of the suspension.

[0106] Understandably, reference positions can be preset for each suspension of the vehicle. Specifically, reference positions can be set for target points of each suspension. The height of the reference positions for each suspension can be the same or different, and the reference positions for each suspension can be flexibly set by developers or can be customized by users.

[0107] The suspension reset position refers to the height position of the suspension in its default state. Typically, the suspension reset position is the midline between its upper and lower height limits. For example, the suspension reset position can be used as the suspension reference position.

[0108] In this embodiment of the application, for the vehicle suspension, a mapping between a reference position and a reference position reference point is essentially established. The reference position reference point represents the mapping point of the reference position of the vehicle suspension in the target person image, and the human interaction reference point represents the mapping point of the human key points used to interact with the vehicle in the target person image.

[0109] By controlling the direction and / or distance of the human interaction reference point relative to the reference position reference point, the direction and / or distance of the corresponding vehicle suspension relative to the reference position is controlled.

[0110] When the actual position of the vehicle suspension is higher than the reference position of the vehicle suspension, it indicates that the vehicle suspension is above the reference position. When the actual position of the vehicle suspension is lower than the reference position of the vehicle suspension, it indicates that the vehicle suspension is below the reference position.

[0111] In the above steps, for at least two vehicle suspensions, reference points corresponding to each are determined based on the key human body position information, namely the first reference point and the second reference point mentioned above, thereby realizing independent control of the motion mode of at least two vehicle suspensions.

[0112] The following is a detailed explanation of each of the above steps.

[0113] In the first example, the number of target person images obtained in step S11 can be 1, that is, it can be a single image, thus enabling control of the suspension through a single image.

[0114] In the second example, the number of target person images obtained in step S11 can be greater than or equal to 2. In this case, each target person image carries its corresponding time stamp, and according to the time stamp, the target person images form a target person image sequence.

[0115] In this example, for each frame of the target person image sequence, the location information of the key points of the target person's body is determined. Then, based on the location information of the key points, the human interaction reference point of the target person and the reference position reference point of the vehicle suspension are determined. Based on the relative positional relationship between the human interaction reference point and the reference position reference point, the motion parameters of the vehicle suspension are determined. Then, based on the motion parameters corresponding to each target person image in the target person image sequence, the vehicle suspension is controlled sequentially in time order to achieve the effect of the vehicle suspension continuously moving with the posture of the person.

[0116] For example, at the moment corresponding to the target person image in the i-th frame, the vehicle suspension is controlled according to the motion parameters corresponding to the target person image in the i-th frame, and at the moment corresponding to the target person image in the (i+1)-th frame, the vehicle suspension is controlled according to the motion parameters corresponding to the target person image in the (i+1)-th frame, to achieve the effect of people and vehicles dancing together.

[0117] The process of obtaining the target person image in the second example above is described below. Please refer to [link / reference]. Figure 2 As shown, the specific steps may include the following:

[0118] S111: Obtain the original video images; the original video images include N frames of original images, where N is an integer greater than or equal to 2;

[0119] S112: Identify the target person from the original video images.

[0120] S113: Determine the image region corresponding to the target person in the original image as the target person image.

[0121] It should be noted that the interactive commands in the embodiments of this application can be either external or internal vehicle interactive commands.

[0122] Regarding step S111 above, when the interaction command is an external interaction command, the external area can be captured using the vehicle's image acquisition device to obtain a captured video image, which is then the original video image. Alternatively, when the interaction command is an internal interaction command, a dance video image played through the vehicle's display device can be acquired, which is then the original video image. Of course, in some embodiments, when the interaction command is an internal interaction command, the internal area can also be captured, and the acquired internal video image can be used as the original video image.

[0123] In the above implementation, in response to receiving an external interaction command, the vehicle suspension is controlled to move according to the key point position information of the target person outside the vehicle to meet the usage requirements of the external scene; in response to receiving an internal interaction command, the vehicle suspension is controlled to move according to the key point position information of the target person in the dance video image played in the vehicle or the video image inside the vehicle to meet the usage requirements of the internal scene and enhance the immersive experience of dancing together between people and the vehicle inside the vehicle.

[0124] It is understood that the dance video played in the vehicle can be a user-uploaded video or a video of a game character dancing in game mode, in which case the game character can be identified as the target character. The dance video can be played via at least one of the following methods: vehicle infotainment screen, projection screen, and ceiling-mounted screen.

[0125] To further enhance the immersive experience of human-vehicle interaction, for external vehicle scenes, in response to external interaction commands, the vehicle is controlled to project onto a target area outside the vehicle, and an image acquisition device is controlled to acquire images of that target area outside the vehicle to obtain the acquired video images.

[0126] Specifically, virtual imaging technology can be used to project onto a target area outside the vehicle, such as projecting a virtual stage. Alternatively, the vehicle lights can be controlled to project onto the target area outside the vehicle according to preset projection parameters, thereby controlling the projection of a stage with preset lighting effects onto the target area outside the vehicle.

[0127] It should be noted that the interactive commands in this application embodiment can be issued directly to the vehicle by the user through the in-vehicle input device or through the APP (Application) of the mobile terminal. For example, the user can issue external interactive commands through the "External Dance Mode" button on the in-vehicle input device or the APP of the mobile terminal, and issue in-vehicle interactive commands through the "In-vehicle Dance Mode" button on the in-vehicle input device or the APP of the mobile terminal.

[0128] The methods for issuing external and internal interaction commands can also be other. For example, users can issue external interaction commands by gesturing the first target action in the area outside the vehicle, and issue internal interaction commands by gesturing the second target action in the area inside the vehicle.

[0129] In this example, the specific actions of the first and second target actions can be flexibly set by the developers or customized by the users. For example, the first target action can be a fist gesture and the second target action can be an OK gesture.

[0130] It is understandable that users may make various body movements due to natural changes in posture during actual operation. To avoid accidentally triggering the vehicle suspension control, the first and second target actions can be a group of gestures composed of multiple individual gestures. For example, the first target action can be a group of gestures composed of a fist gesture and an OK gesture. When the vehicle detects that the target user sequentially performs the fist gesture and then the OK gesture in the area outside the vehicle, it then performs the operation of acquiring the target person's image. In this embodiment, interactive commands are issued through the user's body movements, which is more convenient for users to operate in scenarios where people and vehicles interact, freeing up the user's hands.

[0131] For step S112 above, the target person can be determined from the original video image in the following way:

[0132] Method 1: Determine the target detection box from the original image. In response to the existence of a target scene image region in the original image and the number of target detection boxes in the target scene image region being greater than 1, determine the person in the target detection box closest to the center point of the target scene image region as the target person.

[0133] It is understandable that when the number of target detection boxes in the target scene image region is 1, the person in the target detection box can be directly identified as the target person.

[0134] The center point of the target scene image region refers to the point located at the center of the target scene image region. However, it should be noted that the target scene image region is not an absolutely regular image region, and the center point of the target scene image region is not the absolute center of the image region. For example, when the target scene image region is the image region corresponding to a stage, the center point of the stage can be taken as the center point of the target scene image region.

[0135] In this embodiment, the target detection box can be determined by the target box detection model. It should be noted that the target box detection model in this embodiment is used to generate target detection boxes that can cover the corresponding person's image for each person in the original image. The structure of the target box detection model in this embodiment may include, but is not limited to, at least one of FCOS (Fully Convolutional One-Stage Object Detection), R-CNN (Region-based Convolutional Neural Networks), YOLO (YouOnly Look Once), SSD (Single Shot MultiBox Detector), and deformable convolutional networks.

[0136] In this embodiment, the presence of a target scene image region in the original image can be detected by a target scene detection model. The target scene image region refers to the region in the image where the target scene exists, and the target scene refers to a scene that meets the preset scene conditions. The preset scene conditions can be flexibly set by the developers.

[0137] For example, the target scene here can be a stage scene, such as the virtual stage scene projected by virtual imaging technology mentioned above, or the stage scene that meets the preset lighting effects mentioned above.

[0138] It is understandable that when a user intends to interact with a vehicle, the user will usually tend to be close to the center of the target scene. Therefore, in this embodiment, the person in the target detection box that is closest to the center of the target scene image area is taken as the target person, so that the identified target person is exactly the person who needs to interact with the vehicle, thus improving the accuracy of target person identification.

[0139] Method 2: Determine the target detection box from the original image. In response to the fact that the number of target detection boxes in the original image is greater than 1, determine the person in the target detection box closest to the center point of the original image as the target person.

[0140] In practical applications, when a user intends to interact with a vehicle, the user usually tends to move closer to the front of the image acquisition device. Therefore, in this embodiment, the person in the target detection box closest to the center point of the original image is taken as the target person to improve the accuracy of target person identification.

[0141] Method 3: Determine the target detection box from the original image. In response to the number of target detection boxes being greater than 1, determine the person in the target detection box with the largest area as the target person.

[0142] The largest target detection bounding box means that the target is close enough to the image acquisition device to identify the target as a person who intends to interact with the vehicle.

[0143] Understandably, when the number of target detection boxes determined from the original image is 1, the person in that target detection box can be directly regarded as the target person.

[0144] It should be noted that the above three methods for identifying target individuals from original video images are applicable to both in-vehicle and out-of-vehicle interaction scenarios.

[0145] In one implementation, when determining the target person from the original video images, the target person can be determined for each frame of the original video images. Specifically, the target person can be determined for each frame of the original video images using the method described above. For example, determining the target person for each frame of the original video images using the method described above is equivalent to confirming the target person for each frame of the original video images, thereby ensuring that the target person in each confirmed frame is someone who has the intention to interact with the vehicle.

[0146] To improve the accuracy and quality of the target person image, after identifying the target person in the nth frame of the original image, the nth frame of the original image can be corrected using historical original images. In this embodiment, the historical original image refers to the image frame in the original video image that precedes the nth frame of the original image.

[0147] Specifically, in the first example of this embodiment, after the target person in the nth frame original image is determined by the above method, if it is determined that the target person is occluded, the image corresponding to the target person in the nth frame original image can be corrected by using the image information corresponding to the target person in the historical original image, so as to restore the complete image of the target person in the nth frame original image, and ensure that the human body interaction reference point and reference position reference point can be accurately determined in the future.

[0148] For example, when target person A interacts with the vehicle in the area outside the vehicle, if pedestrian B obscures part of target person A's body while walking, causing target person A to be obscured in the nth frame of the original video image, the image information corresponding to target person A in the historical original images can be used to correct the image corresponding to target person A in the nth frame of the original image, so as to restore the complete body image of target person A.

[0149] Understandably, in this example, multiple historical original images can be used to correct the current nth original image.

[0150] In the second example of this embodiment, after determining the target person in the nth frame of the original image using the above method, if the target detection box corresponding to the target person changes relative to the target detection boxes corresponding to the target person in the m consecutive historical original images, then the target detection box corresponding to the target person in the nth frame of the original image is corrected based on the position of the target detection box corresponding to the target person in the historical original images, thereby achieving the purpose of re-determining the target person in the nth frame of the original image. It should be noted that, in this example, to ensure the accuracy of the correction, the target detection boxes corresponding to each target person in the m historical original images are positioned close to each other in each historical original image, for example, all located in the center of the image.

[0151] In another implementation, after identifying the target person from the original video image, the target person is locked and used as the object of interaction with the vehicle until the current interaction process ends.

[0152] In other words, in this embodiment, it is not necessary to confirm the target person for each frame of the original image. Instead, once the target person is identified, the target person is directly locked. Since it is not necessary to confirm the target person for each frame of the original image, the control efficiency is improved.

[0153] In the first example of this embodiment, for the first frame of the original video image, the target person can be identified in the manner described above. After the target person is identified, the target person is directly locked. For the original images after the first frame, the image area corresponding to the target person can be directly used as the target person image.

[0154] In real-world applications, when a user interacts with a vehicle and controls the vehicle's suspension, the user's position relative to the vehicle usually does not change, or if it does change, the change is very small. Throughout the interactive control process, the user controls the vehicle's suspension primarily by changing their own posture.

[0155] Therefore, in this example, the position of the target detection box corresponding to the target person in the first frame of the original image can be locked to locate the target person. For example, when a target detection box is determined from the first frame of the original image, and the person in the target detection box is determined to be the target person, the detection box information of the target detection box is obtained. The detection box information includes the first coordinate information and the first size information of the target detection box in the original image.

[0156] It should be noted that the target detection box can be uniquely located from the original image using the first coordinate information and the first size information. Therefore, for the original images after the first frame, the target detection box containing the target person can be directly located from the original images after the first frame based on the detection box information, thereby locating the target person from the target detection box.

[0157] In this example, it is not necessary to detect the target bounding boxes in each frame of the original image using a target bounding box detection model, which greatly improves control efficiency.

[0158] In the second example of this implementation, for an external vehicle interaction scenario, the target person can also be determined from the original image in the following way:

[0159] When the interaction command is an external interaction command, the actions of each person in the original video image are detected to obtain the action detection results; based on the action detection results, the person who first performs the preset target action is determined as the target person.

[0160] This example demonstrates how to detect the actions of individuals in an original video image using an action detection model. The structure of the action detection model can include, but is not limited to, at least one of CNN (Convolutional Neural Network), Transformer (a deep neural network model based on attention mechanisms), LSTM (Long Short-Term Memory networks), and ResNet (Residual Network).

[0161] The actions mentioned in this example can be hand gestures or body movements made with body parts other than the hand area. The preset target action can be flexibly set by the developers, and may include, but is not limited to, at least one of the following: raising hands, making a heart shape with both hands raised above the head.

[0162] It is understandable that after identifying the target person from the original video image according to the method provided in this example, a bounding box for the target person can be generated. It should be noted that the bounding box can be generated by the target box detection model mentioned above. In this case, the bounding box is essentially equivalent to the target detection box mentioned above. Of course, the bounding box can also be generated by other methods, as long as it can be guaranteed that a corresponding bounding box can be generated for the target person.

[0163] When capturing an image of a target person outside a vehicle using an image acquisition device, the different distances between the image acquisition device and the target person will result in different sizes of the image area corresponding to the target person in the captured image. Therefore, the person's bounding box can be generated in the original image based on the distance of the target person relative to the image acquisition device and the position of the target person in the original image.

[0164] After generating the person's bounding box, the bounding box information of the person's bounding box is obtained. The bounding box information includes the second coordinate information and the second size information of the person's bounding box in the original image.

[0165] It should be noted that the second coordinate information and the second size information can be used to uniquely locate the person's bounding box in the original image. If the target person is determined based on the first k frames of the original video image, the bounding box of the person used to cover the target person in the k frames of the original image is obtained, and the bounding box information of the person's bounding box is obtained. For the original images after the k frames of the original image, the target person can be directly located from each original image based on the bounding box information.

[0166] The method provided in this example allows for the direct locking of a target person who needs to interact with the vehicle after identifying their actions. This eliminates the need to confirm the target person frame by frame for subsequent raw image captures, thus improving control efficiency.

[0167] Since there may be multiple people in the original image, in order to improve the efficiency of subsequent human body key point recognition, the object of human body key point recognition is focused on the target person. In this embodiment of the application, the corresponding target person image can be determined from each original image. Then, human body key point recognition can be performed only on the target person in the target person image to obtain the human body key point location information of each human body key point.

[0168] For step S113 above, the target person image can be determined based on the target detection box or person coverage box where the target person is located.

[0169] For example, the image within the target detection box containing the target person can be directly used as the target person image. Since the specific positions of a user's limbs may change during interaction with the vehicle, to further ensure the quality of the target person image and that all parts of the target person's body are complete in the obtained image, the target detection box containing the target person can be enlarged by a preset factor to obtain an enlarged target detection box. The image within the enlarged target detection box is then determined as the target person image. This preset factor can be flexibly set by the developers, for example, it can be 1.5 times.

[0170] In some embodiments, the identity of the target person can be identified before step S113. After the identity of the target person is determined to be legitimate, step S113 is then executed.

[0171] Specifically, it can obtain the facial information of the target person, match the facial information with preset legitimate facial information, and when the match is successful, determine that the target person's identity is legitimate.

[0172] For example, the system acquires the first facial information of the target person, compresses it to obtain the second facial information, and sends the second facial information to the cloud. It then receives the third facial information from the cloud, which includes an enhanced image of the target person's facial region. This enhanced image is compared with a pre-stored list of legitimate facial images to determine the legitimacy of the target person's identity. In this example, image enhancement is performed in the cloud, solving the problem of limited local computing power, improving the efficiency of person identification, and thus improving control efficiency.

[0173] For example, the target detection box or person coverage box containing the target person can be further detected to determine the face coverage box, which is located within the target detection box or the person coverage box. When obtaining the first face information of the target person, the image within the face coverage box is extracted and used as the first face information.

[0174] After obtaining the image of the target person, the key points of the target person's body in the image can be identified to obtain the location information of the key points.

[0175] For example, key points of the human body include, but are not limited to, at least one of the following: eyes, ears, nose, mouth, shoulders, waist, knees, hips, wrists, elbows, and palms.

[0176] In this embodiment, at least two vehicle suspensions are controlled to move independently through at least one human interaction reference point and at least two reference position reference points.

[0177] It is understood that the number of human interaction reference points and the number of reference position reference points in the embodiments of this application can be flexibly set by the developers. For example, the number of human interaction reference points can be 2, 3 or 4; the number of reference position reference points can be 3 or 4.

[0178] In one embodiment, the number of human interaction reference points is 1. The movement of at least one suspension in the front / rear suspension of the vehicle is controlled according to the relative positional relationship between the human interaction reference point and the first reference position reference point. The movement of at least one suspension in the rear / front suspension of the vehicle is controlled according to the relative positional relationship between the human interaction reference point and the second reference position reference point.

[0179] In one embodiment, the number of human interaction reference points is 2, and the relative positional relationship between the 2 human interaction reference points and the 2 reference position reference points controls the movement of at least 2 vehicle suspensions.

[0180] For example, the human interaction reference points include a first human interaction reference point and a second human interaction reference point; based on the relative positional relationship between the first human interaction reference point and the first reference position reference point, the movement of at least one suspension in the rear / front suspension of the vehicle is controlled, and based on the relative positional relationship between the second human interaction reference point and the second reference position reference point, the movement of at least one suspension in the front / rear suspension of the vehicle is controlled.

[0181] In the above method, the relative positional relationship between two sets of human body interaction reference points and reference position reference points is used to control the movement of the first vehicle suspension and the second vehicle suspension respectively, so that the control mode of each vehicle suspension is relatively independent, making it easier for the target person to independently control the suspension of each vehicle according to the posture of each part of the body.

[0182] In one embodiment, the movement of the four vehicle suspensions is controlled by the relative positional relationship between four human interaction reference points and two reference position reference points.

[0183] Specifically, the human interaction reference points include the first human interaction reference point, the second human interaction reference point, the third human interaction reference point, and the fourth human interaction reference point.

[0184] For example, the movement of the first vehicle suspension can be controlled based on the relative positional relationship between the first human interaction reference point and the first reference position reference point; the movement of the second vehicle suspension can be controlled based on the relative positional relationship between the second human interaction reference point and the second reference position reference point; the movement of the third vehicle suspension can be controlled based on the relative positional relationship between the third human interaction reference point and the first reference position reference point; and the movement of the fourth vehicle suspension can be controlled based on the relative positional relationship between the fourth human interaction reference point and the second reference position reference point.

[0185] For example, in this embodiment of the application, the first vehicle suspension is the left front vehicle suspension, the second vehicle suspension is the left rear vehicle suspension, the third vehicle suspension is the right front vehicle suspension, and the fourth vehicle suspension is the right rear vehicle suspension.

[0186] In this embodiment, the movement of the two vehicle suspensions can be controlled based on the first reference position reference point. That is, the reference positions of the two vehicle suspensions correspond to the same reference position reference point. Under the premise of minimizing the number of reference position reference points, the movement mode of the vehicle suspension is matched with the movement of the target person. Under the premise of ensuring algorithm efficiency, the linkage between the target person's dancing and the movement of the vehicle suspension is better realized, and the interactive experience of the person and the vehicle dancing together is improved.

[0187] In one embodiment, the movement of the four vehicle suspensions is controlled by the relative positional relationships between four human interaction reference points and three reference position reference points.

[0188] Specifically, the human interaction reference points include a first human interaction reference point, a second human interaction reference point, a third human interaction reference point, and a fourth human interaction reference point. The reference position reference points include the first reference position reference point, the second reference position reference point, and the third reference position reference point.

[0189] In this embodiment, the movement of the first vehicle suspension can be controlled based on the relative positional relationship between the first human interaction reference point and the first reference position reference point; the movement of the second vehicle suspension can be controlled based on the relative positional relationship between the second human interaction reference point and the second reference position reference point; the movement of the third vehicle suspension can be controlled based on the relative positional relationship between the third human interaction reference point and the third reference position reference point; and the movement of the fourth vehicle suspension can be controlled based on the relative positional relationship between the fourth human interaction reference point and the second reference position reference point.

[0190] Since the reference position is preset, the reference position of the vehicle suspension remains unchanged during a user interaction with the vehicle. Therefore, during user interaction, it is necessary to keep the position of the vehicle suspension interaction reference point mapped to the target person image constant to improve the stability of the vehicle suspension response. Thus, in this embodiment, the reference position can be determined based on the position information of the human key points corresponding to rigid human key points. Rigid human key points refer to human key points whose positions do not easily change during interaction, including but not limited to at least one of the following: ear key points, nose key points, mouth key points, waist key points, and shoulder key points.

[0191] In one embodiment, the positions of the human key points corresponding to the two rigid human key points can be directly used as the first reference position reference point and the second reference position reference point.

[0192] In one embodiment, a reference point can be determined based on the location information of two human body key points. Compared with determining the reference point by the coordinates of a pre-specified human body key point, the accuracy of the reference point confirmation can be improved because more human body key points are considered.

[0193] For example, the identified human body key points include a first human body key point, a second human body key point, and a third human body key point, and the human body key point location information includes the first human body key point location information, the second human body key point location information, and the third human body key point location information corresponding to each human body key point.

[0194] At this point, the first reference position can be determined based on the location information of the first and second human body key points, and the second reference position can be determined based on the location information of the second and third human body key points.

[0195] For example, the first, second, and third human body key points mentioned above are rigid human body key points.

[0196] It is understandable that the position of rigid human body key points is not absolutely unchanging. During the interaction, their positions may change slightly. To avoid the inaccuracy and instability of the reference position confirmation caused by such slight changes, in the above embodiment, the influence of slight changes in the position of a single human body key point is eliminated by using the position information of two human body key points. The reason is that the changes in the position of human body key points during the interaction are mostly synchronous. After the positions of two human body key points change synchronously, the height between the positions of the two human body key points tends to be stable. In this way, the influence of slight changes in the position of a single human body key point can be eliminated, thereby improving the accuracy and stability of the reference position confirmation.

[0197] First, the process of determining the second reference point based on the location information of the second and third human body key points will be described in detail.

[0198] In one embodiment, the midpoint between the location indicated by the second human body key point location information and the location indicated by the third human body key point location information is directly used as the second reference location reference point.

[0199] In one embodiment, a second height in the vertical direction is determined between the position indicated by the second human body key point location information and the position indicated by the third human body key point location information; a second reference position reference point is determined based on at least one of the position indicated by the second human body key point location information and the position indicated by the third human body key point location information and the second height.

[0200] For example, when the second human body key point location information is waist coordinates and the third human body key point location information is shoulder coordinates, please refer to... Figure 3 As shown, the first reference point is located above the waist coordinate and at a vertical distance of d2×f1 from the waist coordinate. The second reference point is located below the waist coordinate and at a vertical distance of d2×f2 from the waist coordinate. The midpoint between the first and second reference points is determined as the second reference position reference point. d2 is the vertical height of the waist coordinate and shoulder coordinate, which is also the second height. f1 and f2 are preset scaling factors. Generally speaking, f1>1 and 0<f2<1.

[0201] In this example, the ordinate of the first reference point represents the highest height the user's hand can reach in a standing posture. The ordinate of the second reference point represents the lowest height the user's hand can reach when the arm falls naturally in a standing posture.

[0202] Let the coordinates of the first reference point be (x1, y1) and the coordinates of the second reference point be (x2, y2). Then the coordinates of the reference point of the second reference position can be determined as follows:

[0203] The process of determining the first reference point based on the location information of the first and second human body key points is described in detail below.

[0204] Similarly, in one embodiment, the midpoint between the location indicated by the first human body key point location information and the location indicated by the second human body key point location information is directly used as the first reference location reference point.

[0205] In one embodiment, a first height in the vertical direction is determined between the position indicated by the first human body key point location information and the position indicated by the second human body key point location information; a first reference position reference point is determined based on at least one of the position indicated by the first human body key point location information and the position indicated by the second human body key point location information and the first height.

[0206] For example, when the location information of the second human body key point is the waist coordinate and the location information of the first human body key point is the nose coordinate, please refer to Figure 4 As shown, the first reference position is a point located below the nose coordinates and at a vertical distance of d1×f3 from the nose coordinates, where d1 is the vertical height of the nose coordinates and waist coordinates, i.e., the first height, and f3 is a preset scaling factor.

[0207] The above content introduced the methods for determining the reference points of the first and second reference positions. The following section introduces the methods for determining the human interaction reference points.

[0208] In order to ensure the flexibility and timeliness of the response, simplify the algorithm process, and improve control efficiency during the interaction process, in one embodiment, the identified human body key points can be directly used as the human body interaction reference points.

[0209] To further improve the timeliness and flexibility of responding to user interaction commands, the human keypoints corresponding to the aforementioned human interaction reference points can be flexible human keypoints. Flexible human keypoints refer to human keypoints whose positions are easily changed during interaction. In this embodiment, flexible human keypoints may include, but are not limited to, at least one of wrist keypoints, elbow keypoints, palm keypoints, and knee keypoints.

[0210] To enhance the independence of suspension control for the four vehicles, the identified human key points can include a fourth, fifth, sixth, and seventh human key point, with corresponding location information for each. The location indicated by the fourth human key point can then be designated as the first human interaction reference point, the location indicated by the fifth human key point as the second human interaction reference point, the location indicated by the sixth human key point as the third human interaction reference point, and the location indicated by the seventh human key point as the fourth human interaction reference point. These four human interaction reference points allow for independent control of the suspensions of the four vehicles.

[0211] For example, the fourth key point of the human body is the left wrist key point, the fifth key point of the human body is the left shoulder key point, the sixth key point of the human body is the right wrist key point, and the seventh key point of the human body is the right shoulder key point.

[0212] It should also be noted that, in the embodiments of this application, a trained key point detection model can be used to detect human key points. This key point detection model can be a model trained based on CPM (Convolutional Pose Machines) and / or YOLO-Pose (You Only Look Once Pose, YOLO human pose estimation algorithm).

[0213] In step S14, the human interaction reference points include a first human interaction reference point and a second human interaction reference point. Based on the relative positional relationship between the first human interaction reference point and the first reference position reference point, the movement direction of the first vehicle suspension is controlled. Based on the relative positional relationship between the second human interaction reference point and the second reference position reference point, the movement direction of the second vehicle suspension is controlled.

[0214] The process of controlling the movement direction of the first vehicle suspension based on the relative positional relationship between the first human interaction reference point and the first reference position reference point will be introduced below.

[0215] In one embodiment, a first difference is determined between the ordinate of a first reference position reference point and the ordinate of a first human interaction reference point; in response to the first difference being less than a preset first threshold, the first vehicle suspension is controlled to move to a first orientation of the first reference position of the first vehicle suspension; or, in response to the first difference being greater than the first threshold, the first vehicle suspension is controlled to move to a second orientation of the first reference position; wherein the first orientation and the second orientation are opposite. The first threshold may, for example, be 0.

[0216] The first reference position is a height position pre-set for the suspension of the first vehicle. The movement of the first vehicle suspension can be reflected by the movement of a target point on the suspension. Therefore, the height position here can be a height position set for the target point of the suspension. For example, the first position is above the first reference position, and the second position is below the first reference position. When the first difference is less than the first threshold, the target point is controlled to move above the first reference position, which is equivalent to controlling the suspension of the first vehicle to move above the first reference position. When the first difference is greater than the first threshold, the target point is controlled to move below the first reference position, which is equivalent to controlling the suspension of the first vehicle to move below the first reference position. Alternatively, the first position is below the first reference position, and the second position is above the first reference position.

[0217] In one embodiment, in response to a first difference between the ordinate of the first reference position reference point and the ordinate of the first human interaction reference point being less than a preset first threshold, the first vehicle suspension is controlled to move in a first direction; or in response to a first difference being greater than the first threshold, the first vehicle suspension is controlled to move in a second direction; wherein the first direction and the second direction are opposite.

[0218] For example, the first direction is upward and the second direction is downward; or, the first direction is downward and the second direction is upward.

[0219] In one embodiment, in response to a first difference between the ordinate of the first reference position reference point and the ordinate of the first human interaction reference point being less than a preset first threshold, the first vehicle suspension is moved to a first preset target position above the first reference position; in response to the first difference being greater than the first threshold, the first vehicle suspension is moved to a second preset target position below the first reference position.

[0220] The first and second preset target positions are pre-set locations, and their specific locations can be flexibly set by the developers or customized by the users.

[0221] The following describes the process of controlling the movement direction of the second vehicle suspension based on the relative positional relationship between the second human interaction reference point and the second reference position reference point.

[0222] In one embodiment, a second difference is determined between the ordinate of the second reference position reference point and the ordinate of the second human interaction reference point; in response to the second difference being less than a preset second threshold, the second vehicle suspension is controlled to move to a third position of the second reference position; or, in response to the second difference being greater than the second threshold, the second vehicle suspension is controlled to move to a fourth position of the second reference position; wherein the third position is opposite to the fourth position, and the second threshold may be, for example, 0.

[0223] Similarly, in this embodiment, the movement of the target point on the second vehicle suspension can reflect the movement of the second vehicle suspension. For example, a corresponding height position is pre-set for the target point on the second vehicle suspension, which is the second reference position. When the second difference is less than the second threshold, the target point is controlled to move to a third position of the second reference position, which is equivalent to controlling the second vehicle suspension to move to a third position of the second reference position. When the second difference is greater than the second threshold, the target point is controlled to move to a fourth position of the second reference position, which is equivalent to controlling the second vehicle suspension to move to a fourth position of the second reference position.

[0224] Other methods for controlling the movement direction of the second vehicle suspension can refer to the methods for controlling the movement direction of the first vehicle suspension described above, and will not be repeated here.

[0225] In order to match the movement distance of the vehicle suspension with the movement distance of the human interaction reference point, in one embodiment, the movement distance and direction of the vehicle suspension can be controlled based on the relative positional relationship between the human interaction reference point and the reference position reference point.

[0226] Below, we will first give a detailed introduction to the process of determining the first moving distance and the first moving direction of the first vehicle suspension based on the relative positional relationship between the first human interaction reference point and the first reference position reference point.

[0227] Specifically, it may include the following steps:

[0228] Step 1: Determine the first distance between the first human interaction reference point and the first reference position reference point.

[0229] Step 2: Determine the second distance between the first target position and the first reference position of the first vehicle suspension according to D2 = D1 × k1; where D2 is the second distance, D1 is the first distance, and k1 is the preset amplification factor.

[0230] Step 3: Based on the second distance, control the first vehicle suspension to move to the first target position.

[0231] The first target position is the position that the first vehicle suspension is expected to reach during the interaction process. Therefore, the second distance between the first target position and the first reference position essentially represents the distance between the final movement position of the first vehicle suspension and the first reference position. Specifically, the first target position here can be the final movement position of the target point on the first vehicle suspension. That is, in step three above, the target point on the first vehicle suspension can be controlled to move to the first target position based on the second distance.

[0232] The control method for controlling the movement of the first vehicle suspension in this embodiment is particularly suitable for scenarios where the change range of the first human interaction reference point is small, such as when the first human interaction reference point is a point on the shoulder. Whether the user is tall or short, the difference in the range of shoulder vibration is minimal. To improve computational efficiency, the product of the first distance and a preset amplification factor is directly used as the second distance.

[0233] Since the positions of key points on a user's body may change when the user is in a natural state, that is, the corresponding key point position information may change. The natural change of the user's posture may cause the relative distance between the first human body interaction reference point and the first reference position reference point to change. In order to avoid triggering the first vehicle suspension to respond based on the change when the user's posture changes naturally, before determining the second distance, it is necessary to first determine whether the first distance is greater than the preset third threshold. If so, the step of determining the second distance is executed. If not, no response is required.

[0234] The third threshold in this application embodiment can be flexibly set by the developer; for example, it can be 4 pixels in length.

[0235] In the above method, after determining that the first distance between the first human interaction reference point and the first reference position reference point is greater than or equal to the third threshold, the first vehicle suspension is then controlled to move. This avoids the first vehicle suspension responding without needing to respond, allowing the first vehicle suspension to move precisely according to the user's needs, thus improving the accuracy of the first vehicle suspension response.

[0236] In one embodiment of step three above, the first direction of movement of the first vehicle suspension is determined directly based on the comparison result between the first difference and the first threshold, and the first vehicle suspension is directly controlled to move according to the second distance and the first direction of movement.

[0237] Through the above implementation method, in the control process in which the first human interaction reference point is always located above the first reference position reference point, regardless of whether the first human interaction reference point moves up or down, it will cause the first vehicle suspension to move up or down continuously. The first vehicle suspension cannot adapt and adjust its movement direction according to the up and down movement of the first human interaction reference point.

[0238] Therefore, to adapt to user needs, in another embodiment, please refer to [link / reference needed]. Figure 5 As shown, step three includes the following steps:

[0239] S51: Obtain the first current position information of the first vehicle suspension.

[0240] S52: Generate first target location information based on the comparison result between the first difference and the first threshold, the second distance, and the first reference position.

[0241] S53: Determine the first direction of movement and the first distance of movement of the first vehicle suspension based on the first current position information and the first target position information.

[0242] S54: Control the first vehicle suspension to move to the first target position according to the first moving direction and the first moving distance.

[0243] It should be noted that step S52 can determine the first target position of the first vehicle suspension based on the first reference position, the second distance, and the first relative direction of the first vehicle suspension.

[0244] The relative direction refers to the direction of the first human interaction reference point relative to the first reference position reference point. As mentioned above, if the first difference between the ordinate of the first reference position reference point and the ordinate of the first human interaction reference point is less than a preset first threshold, then the first relative direction is upward, indicating that the first vehicle suspension needs to be moved above the first reference position. If the first difference between the ordinate of the first reference position reference point and the ordinate of the first human interaction reference point is greater than the first threshold, then the first relative direction is downward, indicating that the first vehicle suspension needs to be moved below the first reference position.

[0245] If the current position of the first vehicle suspension coincides with the first reference position, for example, if the current position of the target point on the first vehicle suspension coincides with the first reference position, then the target point on the first vehicle suspension can be moved directly according to the second distance and the first relative direction to reach the first target position.

[0246] The following section provides a detailed explanation of steps S52 to S54 using specific examples.

[0247] If the first reference position of the first vehicle suspension is at a height of D8 above the ground and the first relative direction is upward, then the position at a height of D8+D2 above the ground is determined as the first target position of the first vehicle suspension. If the current position of the first vehicle suspension is at a height of D9 above the ground and D8+D2>D9, then the first vehicle suspension is controlled to move upward by D8+D2-D9. If D8+D2<D9, then the first vehicle suspension is controlled to move downward by D9-(D8+D2).

[0248] Correspondingly, if the first relative direction is downward, then the position at a height of D8-D2 above the ground is determined as the first target position of the first vehicle suspension. If the current position of the first vehicle suspension is at a height of D9 above the ground, and D8-D2>D9, then the first vehicle suspension is controlled to move upward by D8-D2-D9. If D8-D2<D9, then the first vehicle suspension is controlled to move downward by D9-(D8-D2).

[0249] The following section details the process of determining the second moving distance and the second moving direction of the second vehicle suspension based on the relative positional relationship between the second human interaction reference point and the second reference position reference point.

[0250] Specifically, it may include the following steps:

[0251] Step 1: Determine the interaction limit reference point corresponding to the second human interaction reference point.

[0252] Step 2: Determine the third distance between the interactive limit reference point and the second reference position reference point.

[0253] Step 3: Determine the fourth distance between the second human interaction reference point and the second reference position reference point.

[0254] Step 4: Based on the ratio between the fourth distance and the third distance, and the reference height of the second vehicle suspension, determine the fifth distance between the second target position and the second reference position of the second vehicle suspension.

[0255] Step 5: Based on the fifth distance, control the second vehicle suspension to move to the second target position.

[0256] The second target position is the position that the second vehicle suspension is expected to reach during the interaction process. Therefore, the fifth distance between the second target position and the second reference position essentially represents the distance between the final movement position of the second vehicle suspension and the second reference position. Specifically, the second target position here can be the final movement position of the target point on the second vehicle suspension. That is, in step five above, the target point on the second vehicle suspension can be controlled to move to the second target position based on the fifth distance.

[0257] For step four above, for example, it can be based on... Calculate the fifth distance, where h0 is the reference height of the second vehicle suspension, D5 is the fifth distance, D4 ​​is the fourth distance, D3 is the third distance, and k2 is the control coefficient of the second vehicle suspension.

[0258] For example, the reference height is the height of the second reference position, or the initial height of the second vehicle suspension at the beginning of this interaction, or the current height of the second vehicle suspension, or the extreme height of the second vehicle suspension.

[0259] An interactive limit reference point refers to the point corresponding to the extreme position that the second human interactive reference point can reach during the interaction process. It includes a first interactive limit reference point used to indicate the highest position that the second human interactive reference point can reach, and a second interactive limit reference point used to indicate the lowest position that the second human interactive reference point can reach.

[0260] For example, when the second human interaction reference point is located above the second reference position reference point, the distance between the first interaction limit reference point and the second reference position reference point is determined as the third distance; when the second human interaction reference point is located above the second reference position reference point, the distance between the second interaction limit reference point and the second reference position reference point is determined as the third distance.

[0261] For example, Where D max The distance between the first interactive limit reference point and the second interactive limit reference point.

[0262] The method for confirming the interactive limit reference point can refer to the method for confirming the first reference point and the second reference point described above, and will not be repeated here.

[0263] It is understandable that the control method for controlling the movement of the second vehicle suspension in this embodiment is particularly suitable for scenarios where the second human interaction reference point changes significantly. For example, in scenarios where the second human interaction reference point is a point on the hand, the range of motion of the hand varies greatly for users of different heights. Therefore, it is necessary to normalize the data using the ratio in the above formula to achieve adaptive control based on users of different heights. This is to accurately understand the user's interaction intention and avoid the problem of unstable vehicle suspension response caused by the reference point being too high or too low when the second vehicle suspension moves with the user's posture due to height differences.

[0264] Similarly, for step five above, in one embodiment, the second movement direction of the second vehicle suspension is directly determined based on the comparison result between the second difference and the second threshold, and the second vehicle suspension is directly controlled to move according to the fifth distance and the second movement direction.

[0265] To accommodate user needs, please refer to another embodiment. Figure 6 As shown, step five above may include the following steps:

[0266] S61: Obtain the second current position information of the second vehicle suspension.

[0267] S62: Generate second target location information based on the comparison result between the second difference and the second threshold, the fifth distance, and the second reference position.

[0268] S63: Determine the second direction of movement and the second distance of movement of the second vehicle suspension based on the second current position information and the second target position information.

[0269] S64: Control the second vehicle suspension to move to the second target position in the second direction of movement and the second distance of movement.

[0270] Please see Figure 7 As shown, Figure 7 The second human interaction reference point is located above the second reference position reference point. Taking the target point on the second vehicle suspension as the point where the second vehicle suspension connects to the vehicle body as an example, controlling this point to move it above the second reference position means controlling the height of the second vehicle suspension to be higher than the height corresponding to the second reference position. When the second human interaction reference point is located below the second reference position reference point, controlling this point to move it below the second reference position means controlling the height of the second vehicle suspension to be lower than the height corresponding to the second reference position.

[0271] The specific process for determining the second moving distance and the second moving direction can refer to the specific process for determining the first moving distance and the first moving direction, and will not be repeated here.

[0272] Finally, it should be noted that the distances mentioned above, such as the second difference or the first distance, can be distances in the vertical direction, or actual distances in two-dimensional coordinates or other coordinate systems.

[0273] For example, if the coordinates of the first human interaction reference point are (x3, y3) and the coordinates of the first reference position reference point are (x4, y4), then... This serves as the first distance between the first human interaction reference point and the first reference position reference point.

[0274] The suspension control method provided in this application, in response to receiving an interactive command, acquires an image of a target person, determines the position information of key human body points of the target person in the image, determines the interactive reference point of the target person, a first reference position reference point of the first vehicle suspension, and a second reference position reference point of the second vehicle suspension from the image based on the position information of the key human body points, controls the movement of the first vehicle suspension based on the relative positional relationship between the interactive reference point and the first reference position reference point, and controls the movement of the second vehicle suspension based on the relative positional relationship between the interactive reference point and the second reference position reference point. This method utilizes the position information of key human body points of the target person in the image to... This method determines the reference points for the vehicle suspension based on information, fully considering the impact of different individual body shapes on the reference points. This enables the suspension to more accurately understand the target user's interaction intentions and adapt to changes in the target user's posture. While improving the interaction effect and user experience, this method also effectively improves the suspension's response stability and avoids problems caused by differences in user body shape, such as excessively tall or short users, leading to insufficient suspension response stability or a mismatch with the user's interaction intentions. In addition, by independently controlling the movement of at least two vehicle suspensions based on at least two reference points, the movement modes of each vehicle suspension can be different, meeting the personalized needs of users for controlling the suspensions of different vehicles.

[0275] Example 2:

[0276] For ease of understanding, this application provides a detailed description of the suspension control method using an external vehicle interaction scenario as an example.

[0277] Please see Figure 8 As shown, it includes the following steps:

[0278] S801: In response to receiving an external interaction command, the vehicle's image acquisition device acquires images of the external area to obtain a video image, and determines that the acquired video image is the original video image.

[0279] The original video image includes multiple original frames.

[0280] S802: Determine the target detection box from each original image.

[0281] Specifically, the target detection box can be determined using the target detection model mentioned in the above embodiments, which will not be repeated in this embodiment.

[0282] S803: For each original image, in response to the number of target detection boxes being greater than 1, determine the person in the target detection box with the largest area as the target person.

[0283] S804: For each original image, determine the image region corresponding to the target person as the target person image.

[0284] Using the above method, target person images corresponding to each original image are obtained, and the target person images are arranged in the time order of the original images to form a target person image sequence.

[0285] S805: Determine the location information of key points of the target person's body in each target person's image.

[0286] S806: For each target person image, determine the human body interaction reference point and the vehicle suspension reference point from the target person image based on the human body key point position information.

[0287] S807: For each target human image, determine the motion parameters of the corresponding vehicle suspension based on the relative positional relationship between the human interaction reference point and the reference position reference point.

[0288] The motion parameters here include the direction of movement and / or the distance of movement.

[0289] S808: Controls the vehicle suspension movement according to the motion parameters corresponding to each target person's image.

[0290] It should be noted that in step S808, the vehicle suspension needs to be controlled sequentially according to the motion parameters corresponding to each target person image in the target person image sequence, so that the vehicle suspension can follow the posture of the target person.

[0291] The following is a detailed description of steps S805 to S808.

[0292] In this embodiment of the application, the key points of the target person in the image include the key points of the left wrist, right wrist, left shoulder, right shoulder, nose, left waist, and right waist.

[0293] In step S805, the coordinates of the key points of the human body can be used as the corresponding key point location information of the human body.

[0294] In this embodiment of the application, the key points of the left wrist, right wrist, left shoulder, and right shoulder can be used as human body interaction reference points.

[0295] The reference point for the front left suspension of the vehicle is determined based on the coordinates of the left shoulder key point and the left waist key point. For example, the vertical height h1 between the left shoulder key point and the left waist key point can be determined. The highest position when the left hand is raised is at a distance k1·h1 above the left waist key point, and the lowest position when the left hand is placed is at a distance k2·h1 below the left waist key point. The position of the midpoint between the highest and lowest positions is determined as the reference point for the front left suspension of the vehicle, where k1 and k2 are preset scaling factors.

[0296] Similarly, the reference point for the front right suspension of the vehicle can be determined based on the coordinates of the key points on the right shoulder and the right waist. The method for determining the reference point for the front right suspension of the vehicle can be the same as the method for determining the reference point for the front left suspension of the vehicle, and will not be repeated here.

[0297] It is understandable that, since the body is symmetrical, the reference point of the front right suspension of the vehicle can be obtained by using the reference point of the front left suspension of the vehicle, which is symmetrical to the vertical center line of the target person's body.

[0298] In some embodiments, to simplify the algorithm, the reference point for the reference position of the front left suspension and the reference point for the reference position of the front right suspension can be the same point.

[0299] By moving the left wrist, the relative distance and direction between the key point of the left wrist and the reference point of the front left suspension of the vehicle change, thereby controlling the movement of the front left suspension; similarly, by moving the right wrist, the relative distance and direction between the key point of the right wrist and the reference point of the front right suspension of the vehicle change, thereby controlling the movement of the front right suspension.

[0300] In this embodiment, the position of the center point between the two shoulders of a human body in a natural standing state can be used as the reference point of the rear suspension. By shaking the left and right shoulders, the relative distance and direction between the left and right shoulders and the reference point of the rear suspension change. The relative distance can be the vertical distance, thereby controlling the movement of the left and right rear suspensions.

[0301] The position of the center point between the two shoulders when the human body is in a natural standing position can be determined in the following way:

[0302] Because the left and right shoulders support each other, and the left and right waists are symmetrical, the reference point for the rear suspension can be determined based on the coordinates of the left and right shoulders, the left and right waists, and the key point of the nose.

[0303] For example, the vertical height h2 between the key points of the nose and the left waist can be determined based on their coordinates. The position below the key point of the nose, at a distance of k3·h2 from the key point of the nose, can be used as the reference point for the rear suspension, where k3 is a preset scaling factor.

[0304] It should be understood that although the steps in the flowchart above are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart above may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0305] Example 3:

[0306] Based on the same inventive concept, please refer to Figure 9 As shown, this application embodiment provides a suspension control device, including:

[0307] The acquisition module 901 is used to acquire the image of the target person in response to receiving an interactive command;

[0308] The first determining module 902 is used to determine the location information of key human body points of the target person in the target person image;

[0309] The second determining module 903 is used to determine the human body interaction reference point of the target person, the first reference position reference point of the first vehicle suspension, and the second reference position reference point of the second vehicle suspension from the target person image based on the human body key point position information.

[0310] The control module 904 is used to control the movement of the first vehicle suspension based on the relative positional relationship between the human interaction reference point and the first reference position reference point, and to control the movement of the second vehicle suspension based on the relative positional relationship between the human interaction reference point and the second reference position reference point.

[0311] In one embodiment, the acquisition module 901 is used to acquire original video images; the original video images include N frames of original images, where N is an integer greater than or equal to 2; the target person is determined from the original video images; the image region corresponding to the target person in the original images is determined as the target person image.

[0312] In one embodiment, the interaction command is an external interaction command or an internal interaction command; the acquisition module 901 is used to acquire a video image of the external area of ​​the vehicle through the vehicle's image acquisition device when the interaction command is an external interaction command, and the acquired video image is the original video image; or, when the interaction command is an internal interaction command, to acquire a dance video image played through the vehicle's display device, and the dance video image is the original video image.

[0313] In one embodiment, the acquisition module 901 is configured to determine target detection boxes from the original image; in response to the existence of a target scene image region in the original image and the number of target detection boxes in the target scene image region being greater than 1, the person in the target detection box closest to the center point of the target scene image region is determined to be the target person; or, in response to the number of target detection boxes being greater than 1, the person in the target detection box with the largest area is determined to be the target person, or the person in the target detection box closest to the center point of the original image is determined to be the target person.

[0314] In one embodiment, when the interaction command is the external interaction command, the acquisition module 901 is used to detect the actions of each person in the original video image and obtain the action detection result; based on the action detection result, the person who first performs the preset target action is determined as the target person.

[0315] In one embodiment, the human interaction reference point includes a first human interaction reference point and a second human interaction reference point; the control module 904 is used to determine a first difference between the ordinate of the first reference position reference point and the ordinate of the first human interaction reference point.

[0316] In response to the first difference being less than a preset first threshold, the first vehicle suspension is controlled to move to a first position of the first reference position; or, in response to the first difference being greater than the first threshold, the first vehicle suspension is controlled to move to a second position of the first reference position; wherein the first position and the second position are opposite.

[0317] The control module 904 is further configured to determine a second difference between the ordinate of the reference point of the second reference position and the ordinate of the second human interaction reference point; in response to the second difference being less than a preset second threshold, control the second vehicle suspension to move to a third position of the second reference position; or, in response to the second difference being greater than the second threshold, control the second vehicle suspension to move to a fourth position of the second reference position; wherein the third position and the fourth position are opposite.

[0318] In one embodiment, the control module 904 is used to determine a first distance between the first human interaction reference point and the first reference position reference point; determine a second distance between the first target position of the first vehicle suspension and the first reference position according to D2 = D1 × k1; wherein, D2 is the second distance, D1 is the first distance, and k1 is a preset amplification factor; and control the first vehicle suspension to move to the first target position based on the second distance.

[0319] In one embodiment, the control module 904 is configured to determine that the first distance is greater than or equal to a preset third threshold before determining the second distance between the first target position of the first vehicle suspension and the first reference position.

[0320] In one embodiment, the control module 904 is configured to acquire first current position information of the first vehicle suspension; generate first target position information based on the comparison result between the first difference and the first threshold, the second distance and the first reference position; determine a first moving direction and a first moving distance of the first vehicle suspension according to the first current position information and the first target position information; and control the first vehicle suspension to move to the first target position according to the first moving direction and the first moving distance.

[0321] In one embodiment, the control module 904 is used to determine an interaction limit reference point corresponding to the second human interaction reference point; determine a third distance between the interaction limit reference point and the second reference position reference point; determine a fourth distance between the second human interaction reference point and the second reference position reference point; determine a fifth distance between the second target position of the second vehicle suspension and the second reference position based on the ratio between the fourth distance and the third distance and the reference height of the second vehicle suspension; and control the second vehicle suspension to move to the second target position based on the fifth distance.

[0322] In one embodiment, the control module 904 is used to acquire the second current position information of the second vehicle suspension; generate the second target position information based on the comparison result between the second difference and the second threshold, the fifth distance and the second reference position; determine the second moving direction and the second moving distance of the second vehicle suspension according to the second current position information and the second target position information; and control the second vehicle suspension to move to the second target position according to the second moving direction and the second moving distance.

[0323] In one embodiment, the human body key point location information includes first human body key point location information, second human body key point location information, and third human body key point location information; the second determining module 903 is used to determine the first reference position reference point based on the first human body key point location information and the second human body key point location information; and to determine the second reference position reference point based on the second human body key point location information and the third human body key point location information.

[0324] In one embodiment, the second determining module 903 is configured to determine a first vertical height between the position indicated by the first human key point location information and the position indicated by the second human key point location information; determine a first reference position reference point based on at least one of the positions indicated by the first and second human key point location information and the first height; determine a second vertical height between the position indicated by the second and third human key point location information and the position indicated by the third human key point location information; and determine a second reference position reference point based on at least one of the positions indicated by the second and third human key point location information and the second height.

[0325] In one embodiment, the control module 904 is used to control the movement of the four vehicle suspensions respectively by means of the relative positional relationship between four human interaction reference points and two reference position reference points.

[0326] Specifically, the human interaction reference points include the first human interaction reference point, the second human interaction reference point, the third human interaction reference point, and the fourth human interaction reference point.

[0327] For example, the control module 904 is used to control the movement of the first vehicle suspension based on the relative positional relationship between the first human interaction reference point and the first reference position reference point, control the movement of the second vehicle suspension based on the relative positional relationship between the second human interaction reference point and the second reference position reference point, control the movement of the third vehicle suspension based on the relative positional relationship between the third human interaction reference point and the first reference position reference point, and control the movement of the fourth vehicle suspension based on the relative positional relationship between the fourth human interaction reference point and the second reference position reference point.

[0328] It should be understood that, for the sake of brevity, some of the content described in the previous embodiments will not be repeated in this embodiment.

[0329] Example 4:

[0330] Please see Figure 10 As shown, this application embodiment provides an electronic device, including a processor 1001 and a memory 1002. The memory 1002 stores a computer program, and the processor 1001 executes the computer program to implement the steps of the method described above, which will not be repeated here.

[0331] The processor 1001 can be an integrated circuit chip with signal processing capabilities. The processor 1001 can be a general-purpose processor, including a CPU (Central Processing Unit), an NP (Network Processor), etc.; it can also be a DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor.

[0332] The memory 1002 may include, but is not limited to, RAM (Random Access Memory), ROM (Read Only Memory), PROM (Programmable Read Only Memory), EPROM (Erasable Programmable Read-Only Memory), and EEPROM (Electrically Erasable Programmable Read Only Memory).

[0333] Those skilled in the art will understand that Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the application of the present application. Specific electronic devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0334] Based on the same inventive concept, embodiments of this application also provide a computer-readable storage medium, such as a floppy disk, optical disk, hard disk, flash memory, USB flash drive, SD (Secure Digital) card, MMC (Multi-Media Card), etc., in which one or more programs implementing the above steps are stored. These one or more programs can be executed by one or more processors to implement the steps of the methods in the above embodiments, which will not be repeated here.

[0335] Based on the same inventive concept, embodiments of this application also provide a computer program product, including a computer program that, when executed by a processor, implements any of the methods described above.

[0336] The program code for executing the computer program product of this application can be written in any combination of one or more programming languages. The program code can be executed entirely on the user device, partially on the user device, as a standalone software package, partially on the user device and partially on a remote device, or entirely on a remote device.

[0337] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, etc.) containing computer-usable program code.

[0338] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer-readable storage media according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0339] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0340] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of user-operated steps to be executed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0341] It should be noted that the illustrations provided in this embodiment are only schematic representations of the basic concept of this application. Therefore, the drawings only show components relevant to this application and are not drawn according to the actual number, shape, and size of components in implementation. In actual implementation, the form, quantity, and proportion of each component can be arbitrarily changed, and the component layout may also be more complex. The structures, proportions, sizes, etc., shown in the accompanying drawings are only used to complement the content disclosed in the specification for those skilled in the art to understand and read, and are not intended to limit the implementation conditions of this application. Therefore, they have no substantial technical significance. Any modification to the structure, change in the proportional relationship, or adjustment of the size, without affecting the effect and purpose that this application can produce, should still fall within the scope of the technical content disclosed in this application. At the same time, the terms such as "upper," "lower," "left," "right," "middle," and "one" used in this specification are only for clarity of description and are not intended to limit the scope of implementation of this application. Changes or adjustments in their relative relationships, without substantially changing the technical content, should also be considered within the scope of implementation of this application.

[0342] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the document does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0343] As illustrated herein, unless the context clearly indicates otherwise, the words “a,” “an,” “an,” and / or “the” do not specifically refer to the singular and may also include the plural. Generally speaking, the terms “comprising” and “including” only indicate the inclusion of explicitly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0344] The definitions used herein, such as the terms “having,” “may have,” “comprising,” or “may include,” indicate the presence of the corresponding function, operation, element, etc., and do not limit the presence of one or more other functions, operations, elements, etc. Furthermore, it should be understood that the terms “comprising” or “having” as used herein indicate the presence of the features, figures, steps, operations, elements, components, or combinations thereof described in the specification, without excluding the presence or addition of one or more other features, figures, steps, operations, elements, components, or combinations thereof.

[0345] The prefixes such as "first" and "second" used in this application embodiment are merely for distinguishing different descriptive objects and do not limit the position, order, priority, quantity, or content of the described objects. The use of ordinal numbers and other prefixes used to distinguish descriptive objects in this application embodiment does not constitute a limitation on the described objects. For statements regarding the described objects, please refer to the claims or the context of the embodiments. The use of such prefixes should not constitute unnecessary limitations. Furthermore, in the description of this embodiment, unless otherwise stated, "multiple" means two or more.

[0346] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0347] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A suspension control method characterized by, The method comprises: in response to receiving an interaction instruction, obtaining a target person image; determining human body key point position information of a target person in the target person image; determining a human body interaction reference point of the target person, a first reference position reference point of a first vehicle suspension, and a second reference position reference point of a second vehicle suspension from the target person image according to the human body key point position information; controlling the first vehicle suspension to move based on the relative positional relationship between the human body interaction reference point and the first reference position reference point, and controlling the second vehicle suspension to move based on the relative positional relationship between the human body interaction reference point and the second reference position reference point.

2. The suspension control method according to claim 1, characterized by, The method comprises: obtaining an original video image; the original video image comprises N original images, N being an integer greater than or equal to 2; determining the target person from the original video image; determining the image region corresponding to the target person in the original image as the target person image.

3. The suspension control method according to claim 2, characterized by, The interaction instruction is an out-of-vehicle interaction instruction or an in-vehicle interaction instruction; the method comprises: when the interaction instruction is an out-of-vehicle interaction instruction, obtaining a captured video image by capturing an out-of-vehicle region through an image capturing device of the vehicle, the captured video image being the original video image; or, when the interaction instruction is an in-vehicle interaction instruction, obtaining a dance video image played through a display device of the vehicle, the dance video image being the original video image.

4. The suspension control method according to claim 2, characterized by, The method comprises: determining a target detection frame from the original image; in response to the presence of a target scene image region in the original image and the number of target detection frames in the target scene image region being greater than 1, determining the person in the target detection frame closest to the center point of the target scene image region as the target person; or in response to the number of target detection frames being greater than 1, determining the person in the target detection frame with the largest area as the target person, or determining the person in the target detection frame closest to the center point of the original image as the target person.

5. The suspension control method according to claim 3, characterized by, When the interaction instruction is the out-of-vehicle interaction instruction, the method comprises: detecting the actions of each person in the original video image to obtain an action detection result; determining the person who first performs a preset target action as the target person according to the action detection result.

6. The suspension control method according to any one of claims 1 to 5, characterized by, The human body interaction reference point comprises a first human body interaction reference point and a second human body interaction reference point; the method comprises: determining a first difference between the longitudinal coordinate of the first reference position reference point and the longitudinal coordinate of the first human body interaction reference point; in response to the first difference being less than a preset first threshold, controlling the first vehicle suspension to move to a first orientation of the first reference position; or, in response to the first difference being greater than the first threshold, controlling the first vehicle suspension to move to a second orientation of the first reference position; wherein the first orientation and the second orientation are opposite; controlling the second vehicle suspension to move based on a relative position relationship between the human body interaction reference point and the second reference position reference point, comprises: determining a second difference between a longitudinal coordinate of the second reference position reference point and a longitudinal coordinate of the second human body interaction reference point; in response to the second difference being less than a preset second threshold, controlling the second vehicle suspension to move to a third orientation of the second reference position; or, in response to the second difference being greater than the second threshold, controlling the second vehicle suspension to move to a fourth orientation of the second reference position; wherein the third orientation and the fourth orientation are opposite.

7. The suspension control method according to claim 6, characterized by, controlling the first vehicle suspension to move based on a relative position relationship between the human body interaction reference point and the first reference position reference point, comprises: determining a first distance between the first human body interaction reference point and the first reference position reference point; determining a second distance between a first target position of the first vehicle suspension and the first reference position according to D2=D1×k1; wherein D2 is the second distance, D1 is the first distance, and k1 is a preset amplification coefficient; controlling the first vehicle suspension to move to the first target position based on the second distance.

8. The suspension control method according to claim 7, characterized by, Before determining the second distance between the first target position of the first vehicle suspension and the first reference position, the method comprises: determining that the first distance is greater than or equal to a preset third threshold.

9. The suspension control method according to claim 7, characterized by, controlling the first vehicle suspension to move to the first target position based on the second distance, comprises: obtaining first current position information of the first vehicle suspension; generating first target position information based on a comparison result between the first difference and the first threshold, the second distance, and the first reference position; determining a first moving direction and a first moving distance of the first vehicle suspension according to the first current position information and the first target position information; controlling the first vehicle suspension to move to the first target position according to the first moving direction and the first moving distance.

10. The suspension control method according to claim 6, characterized by, controlling the second vehicle suspension to move based on a relative position relationship between the human body interaction reference point and the second reference position reference point, comprises: determining an interaction limit reference point corresponding to the second human body interaction reference point; determining a third distance between the interaction limit reference point and the second reference position reference point; determining a fourth distance between the second human body interaction reference point and the second reference position reference point; determining a fifth distance between a second target position of the second vehicle suspension and the second reference position according to a ratio between the fourth distance and the third distance, and a reference height of the second vehicle suspension; Controlling the second vehicle suspension to move to the second target position based on the fifth distance.

11. The suspension control method according to claim 10, characterized by, The controlling the second vehicle suspension to move to the second target position based on the fifth distance comprises: Obtaining second current position information of the second vehicle suspension; Generating second target position information based on a comparison result between the second difference and the second threshold, the fifth distance and the second reference position; Determining a second moving direction and a second moving distance of the second vehicle suspension according to the second current position information and the second target position information; Controlling the second vehicle suspension to move to the second target position according to the second moving direction and the second moving distance.

12. The suspension control method according to any one of claims 1 to 5, characterized by, The human body key point position information comprises first human body key point position information, second human body key point position information and third human body key point position information. The manner of determining the first reference position reference point comprises: Determining the first reference position reference point according to the first human body key point position information and the second human body key point position information; The manner of determining the second reference position reference point comprises: Determining the second reference position reference point according to the second human body key point position information and the third human body key point position information.

13. The suspension control method according to claim 12, characterized by, The determining the first reference position reference point according to the first human body key point position information and the second human body key point position information comprises: Determining a first height of positions indicated by the first human body key point position information and the second human body key point position information in a vertical direction; Determining the first reference position reference point based on at least one of the positions indicated by the first human body key point position information and the second human body key point position information and the first height; The determining the second reference position reference point according to the second human body key point position information and the third human body key point position information comprises: Determining a second height of positions indicated by the second human body key point position information and the third human body key point position information in a vertical direction; Determining the second reference position reference point based on at least one of the positions indicated by the second human body key point position information and the third human body key point position information and the second height.

14. A suspension control device characterized by comprising: The apparatus comprises: An obtaining module configured to obtain a target character image in response to receiving an interaction instruction; A first determining module configured to determine human body key point position information of a target character in the target character image; A second determining module configured to determine, from the target character image, a human body interaction reference point of the target character, a first reference position reference point of a first vehicle suspension and a second reference position reference point of a second vehicle suspension according to the human body key point position information; A control module configured to control movement of the first vehicle suspension based on a relative position relationship between the human body interaction reference point and the first reference position reference point, and control movement of the second vehicle suspension based on a relative position relationship between the human body interaction reference point and the second reference position reference point.

15. An electronic device, comprising: A computer program product comprising a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code configured such that, on execution by at least one processor, the computer readable program code causes the at least one processor to perform the method of any one of claims 1-13.

16. A computer readable storage medium characterized by: The computer readable storage medium stores a computer program which, when executed by at least one processor, implements the method of any one of claims 1-13.

Images